feat: promote qpi cases and consolidate review bundle

.gitignore

@@ -0,0 +1,2 @@
+__pycache__/
+*.py[cod]

ccra_review_bundle/round-03_2026-06-17_contract-hardening-selector-calibration/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF.md

@@ -1,4 +1,4 @@
-# CCRA Review Brief: Round 03 Contract Hardening and Selector Calibration
+# CCRA / GPT Review Brief: Round 03 Consolidated Review Package
 
 Date: 2026-06-17
 
@@ -6,7 +6,16 @@ Repository: `C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-t
 
 Phase: `model_library_mvp`
 
-## 1. Default Conclusion
+## 1. Why This Is The Official Round 03 Package
+
+Round 03 had two sequential work streams:
+
+1. framework hardening: model contract, QPI contextual routing rules, selector executable rules, no-call gates, and validation;
+2. owner-supplied QPI case processing: draft `.cases.md` files, owner review, case digest promotion, selector calibration inputs, and selected regression cases.
+
+The earlier Round 03 review bundle was created after step 1 and before owner data processing. It was correct at the time, but incomplete for formal third-round review. This consolidated package keeps the original Round 03 directory and updates it into the single official third-round review package.
+
+## 2. Default Conclusion
 
 This round does not upgrade model lifecycle state.
 
@@ -17,7 +26,7 @@ Current model states remain:
 | `qpi` | draft | B | pending |
 | `intellectual_archaeology` | draft | B | pending |
 
-Allowed review conclusion: `draft-callable` as report-level language only.
+Allowed review language: `draft-callable` at report level only.
 
 Not allowed:
 
@@ -27,24 +36,29 @@ Not allowed:
 - LLM selector;
 - database, vector database, full RAG, frontend, backend service, or user account system.
 
-## 2. What Changed
+## 3. What Changed In This Consolidated Round
 
-Round 03 hardened second-round risks:
+Framework and contract hardening:
 
-- `ccra_review_bundle/` is now a per-round archive root.
+- `ccra_review_bundle/` uses per-round review archives.
-- QPI source structure now includes the 2025 contextual article as a live source, not an obsolete predecessor.
+- QPI source structure includes the 2025 contextual article as a live source.
-- QPI definition and runtime output contract now reflect subject, context, expectation-reality gap, dynamic stage, multi-perspective divergence, and governance load.
+- QPI is represented as subject-context-dynamic routing, not flat text classification.
-- `schemas/model_card.schema.json` now allows `structured_output_contract` without making model-specific fields globally required.
+- `structured_output_contract` is allowed by schema and enforced by model-specific validation.
-- `scripts/validate_model_library.py` now enforces model-specific structured output contract fields for QPI and Intellectual Archaeology.
+- `selector/selector_rules.json` is the executable runtime source for selector signals, weights, thresholds, and hard no-call gates.
-- `selector/selector_rules.json` is now the runtime source for selector scoring, no-call gates, signal lists, and weights.
+- `scripts/run_selector_demo.py` reads selector rules at runtime instead of owning hard-coded primary rules.
-- `scripts/run_selector_demo.py` no longer owns hard-coded primary selector rules.
+- QPI and Intellectual Archaeology remain `draft / B / pending`.
-- hard no-call signals now block fact lookup, rewrite, translation, and direct execution unless the user explicitly asks for deeper analysis.
-- `selector/selector_calibration_inputs.json` adds 20 draft calibration inputs.
-- QPI and IA rule docs were added.
 
-## 3. QPI Scope Boundary
+Owner-reviewed QPI case promotion:
 
-QPI is now treated as a subject-context-dynamic routing model:
+- 8 owner-reviewed QPI `.cases.md` files are complete.
+- 62 QPI case digests were promoted into `selector/qpi_case_digests.json`.
+- 83 selector calibration inputs now include owner-reviewed QPI case examples.
+- 46 QPI regression cases exist in `tests/qpi.regression.json`.
+- 23 organizational year-end-review QPI regression cases were selected from the owner-reviewed batch.
+
+## 4. QPI Scope Boundary
+
+QPI is treated as a routing model:
 
 ```text
 某个认知主体
@@ -54,40 +68,26 @@ QPI is now treated as a subject-context-dynamic routing model:
 框定成 Q / P / I / mixed / no-call
 ```
 
-Owner raw QPI cases have not yet been processed. The calibration file is a draft selector calibration set, not a replacement for owner-provided raw case materials.
+The owner-reviewed cases should be evaluated as auditable routing examples and regression traps. They are not intended to solve the underlying organizational, personnel, legal, tax, or operational problems.
 
-## 4. Verification Summary
+## 5. What Is Complete Before Review
 
-Fresh checks run in this round:
+The pre-review work is complete for the formal third-round review:
 
-```powershell
+- framework hardening files are updated;
-python scripts\rebuild_indexes.py --check
+- selector hard no-call behavior is executable and regression-checked;
-python -m unittest discover -s tests -p "test*.py" -v
+- all 8 owner-reviewed QPI draft groups have been processed;
-python scripts\check_card_contract.py
+- no Round 01 QPI draft review files remain unprocessed;
-python scripts\validate_model_library.py
+- digest, calibration, and regression assets have been updated;
-python scripts\run_selector_demo.py
+- validation commands were run after the final QPI case promotion.
-python scripts\run_selector_regression.py
-python scripts\check_model_card_sync.py
-```
 
-Results:
+## 6. Suggested Reading Order
 
-- Index check: PASS
+1. `00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF.md`
-- Unit tests: PASS, 15 tests
+2. `01_GUIDANCE_PACK_AND_COMPLIANCE_MATRIX.md`
-- Card contract: PASS
+3. `02_CURRENT_ASSET_PACK.md`
-- Model library validation: PASS
+4. `03_REPORTS_DIFF_AND_COMMAND_LOG.md`
-- Selector demo: PASS; selected `qpi`, rejected `intellectual_archaeology`
+5. `04_QPI_CASE_PROMOTION_SUMMARY_AND_REVIEW_GUIDE.md`
-- Selector regression: PASS
+6. `05_REVIEW_QUESTIONS_FOR_GPT.md`
-- Model/card sync: PASS
+7. `optional_raw_changed_files.zip` only if exact changed files are needed
-
-## 5. Review Focus
-
-CCRA / Owner should review:
-
-- Whether QPI v0.3 contextual routing fields are the right required runtime output layer.
-- Whether `classification_scope`, `is_provisional`, `context_sufficiency`, and `missing_context` sufficiently prevent false high-confidence QPI classification.
-- Whether `intra_frame_mixed` and `inter_viewpoint_divergence` are correctly separated.
-- Whether the Issue-as-governance-load rule is accepted.
-- Whether selector hard no-call signals are too broad or too narrow.
-- Whether owner raw case preprocessing should later be routed to `skills-vault` as a reusable Skill.
 

ccra_review_bundle/round-03_2026-06-17_contract-hardening-selector-calibration/01_GUIDANCE_PACK_AND_COMPLIANCE_MATRIX.md

@@ -1,26 +1,28 @@
-# Guidance Pack and Compliance Matrix
+# Guidance Pack And Compliance Matrix
 
 ## 1. Input Guidance
 
-Round 03 implements the Owner/GPT instruction:
+Round 03 implements two connected Owner/GPT requirements:
+
+1. harden the model-library framework without expanding product scope;
+2. after owner-provided QPI case data became available, process those cases into auditable QPI digest, calibration, and regression assets.
+
+The same non-goals apply across both parts:
 
 - do not add a third model;
 - do not upgrade stable;
 - do not build a full answer system;
 - do not introduce an LLM selector;
-- harden model-specific output contracts;
+- do not introduce database, vector database, RAG, frontend, backend service, user accounts, or platform features.
-- make selector rules executable, not documentary;
-- upgrade QPI from text classification to subject-context-dynamic routing;
-- defer owner raw case preprocessing until materials are available.
 
 ## 2. Compliance Matrix
 
 | Requirement | Status | Evidence |
 | --- | --- | --- |
 | Per-round CCRA bundle directory | Done | `ccra_review_bundle/round-02_...`, `round-03_...` |
-| Preserve second-round bundle | Done | Existing flat files moved under `round-02_2026-06-16_second-audit/` |
+| Preserve second-round bundle | Done | Existing second-round files live under `round-02_2026-06-16_second-audit/` |
 | Add `structured_output_contract` to schema properties | Done | `schemas/model_card.schema.json` |
-| Do not make QPI/IA fields global top-level required | Done | schema allows object; validator does model-specific checks |
+| Do not make QPI/IA fields global top-level required | Done | Schema allows object; validator performs model-specific checks |
 | QPI required runtime fields | Done | `models/qpi.model.json`, `scripts/validate_model_library.py` |
 | IA required runtime fields | Done | `models/intellectual_archaeology.model.json`, `scripts/validate_model_library.py` |
 | Fix QPI report missing `classification` | Done | `reports/content_review_report_v0.2.md` |
@@ -28,9 +30,12 @@ Round 03 implements the Owner/GPT instruction:
 | Add IA depth gate rules | Done | `docs/INTELLECTUAL_ARCHAEOLOGY_DEPTH_GATE.md` |
 | Make selector rules executable source | Done | `selector/selector_rules.json`, `scripts/run_selector_demo.py` |
 | Hard no-call gate | Done | `selector/selector_rules.json`, `scripts/run_selector_demo.py` |
-| Add selector calibration inputs | Done | `selector/selector_calibration_inputs.json` |
 | Keep models `draft / B / pending` | Done | `models/model_index.json` |
-| Defer owner raw sample processing | Done | documented in QPI rules and calibration notes |
+| Process owner-reviewed QPI case drafts | Done | `reports/model_case_preprocessing/qpi/round-01/*.cases.md` |
+| Promote case digests | Done | `selector/qpi_case_digests.json`, 62 cases |
+| Promote selector calibration inputs | Done | `selector/selector_calibration_inputs.json`, 83 inputs |
+| Promote selected regression cases | Done | `tests/qpi.regression.json`, 46 total QPI regression cases |
+| Keep APTC as context note, not a model | Done | International-college case guidance and no third-model policy |
 
 ## 3. QPI Contract Delta
 
@@ -83,14 +88,25 @@ Required runtime fields enforced by validator:
 - QPI gate signals;
 - IA heavy-depth signals;
 - scoring weights;
-- per-model base score and trigger lists.
+- per-model base scores and trigger lists.
 
 `scripts/run_selector_demo.py` reads that file at runtime.
 
-## 5. Known Limits
+## 5. QPI Case Promotion Delta
 
-- Calibration inputs are draft and not owner-supplied real cases.
+The owner-reviewed QPI case layer adds a second kind of evidence for review:
-- QPI raw case preprocessing is deferred until owner materials arrive.
+
-- `frame_shift_risk` is represented through `misclassification_risk`; it can become a separate required field later if Owner/CCRA wants a stricter contract.
+- Markdown case files preserve owner review decisions and human-readable reasoning;
-- Selector calibration is still rule-based and local; it is not evidence of stable selector behavior in the wild.
+- `selector/qpi_case_digests.json` stores compact auditable case summaries;
+- `selector/selector_calibration_inputs.json` gives the rule-based selector concrete QPI examples and no-call traps;
+- `tests/qpi.regression.json` stores selected high-value regression cases for boundary, misuse, and false-positive prevention.
+
+Not every owner-reviewed case was promoted into regression. Regression was reserved for cases that protect model boundaries, selector behavior, or high-risk Q/P/I/mixed/no-call distinctions.
+
+## 6. Known Limits
+
+- QPI and Intellectual Archaeology remain draft assets.
+- The selector is still rule-based and local; passing regression is not evidence of stable behavior in the wild.
+- Case digests are owner-reviewed processing artifacts, not raw legal, personnel, financial, or operational findings.
+- `frame_shift_risk` can become a separate required field later if Owner/CCRA wants a stricter contract, but this round keeps it under `misclassification_risk`.
 

ccra_review_bundle/round-03_2026-06-17_contract-hardening-selector-calibration/02_CURRENT_ASSET_PACK.md

@@ -9,7 +9,7 @@
 - `models/model_index.json`
 - `cards/card_index.md`
 
-## 2. Contract and Rule Assets
+## 2. Contract And Rule Assets
 
 - `schemas/model_card.schema.json`
 - `docs/DATA_CONTRACT.md`
@@ -18,7 +18,7 @@
 - `docs/DECISIONS.md`
 - `knowledge_assets/08_CCRA模型库MVP质量门与交接协议.md`
 
-## 3. Source and Evidence Assets
+## 3. Source And Evidence Assets
 
 - `sources/source_articles.json`
 - `sources/source_excerpts.json`
@@ -34,27 +34,64 @@ New QPI evidence excerpts:
 - `excerpt_qpi_contextual_gap_001`
 - `excerpt_qpi_contextual_dynamic_001`
 
-## 4. Selector Assets
+## 4. Owner-Reviewed QPI Case Assets
+
+Owner-reviewed Markdown cases:
+
+- `reports/model_case_preprocessing/qpi/round-01/disappointment-emotional-isolation.cases.md`
+- `reports/model_case_preprocessing/qpi/round-01/flow-redesign.cases.md`
+- `reports/model_case_preprocessing/qpi/round-01/year-end-review-development-office.cases.md`
+- `reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md`
+- `reports/model_case_preprocessing/qpi/round-01/year-end-review-employment-entrepreneurship.cases.md`
+- `reports/model_case_preprocessing/qpi/round-01/year-end-review-engineering-center.cases.md`
+- `reports/model_case_preprocessing/qpi/round-01/year-end-review-international-college.cases.md`
+- `reports/model_case_preprocessing/qpi/round-01/year-end-review-research-office.cases.md`
+
+Process and handoff docs:
+
+- `reports/model_case_preprocessing/qpi/round-01/README.md`
+- `reports/GPT讨论上下文_QPI草稿案例审阅_2026-06-17.md`
+- `reports/Codex新会话交接文档_QPI案例草稿审阅与第三轮后续_2026-06-17.md`
+
+## 5. Structured Case And Selector Assets
 
 - `selector/selector_rules.json`
 - `selector/selector_examples.json`
 - `selector/selector_calibration_inputs.json`
+- `selector/qpi_case_digests.json`
 - `scripts/run_selector_demo.py`
 - `scripts/run_selector_regression.py`
 
-## 5. Validation Assets
+Current counts:
+
+| Artifact | Count |
+| --- | ---: |
+| `selector/qpi_case_digests.json` cases | 62 |
+| `selector/selector_calibration_inputs.json` inputs | 83 |
+| `tests/qpi.regression.json` regression cases | 46 |
+| New organizational year-end-review QPI regression cases | 23 |
+
+## 6. Validation Assets
 
 - `scripts/validate_model_library.py`
 - `scripts/check_card_contract.py`
 - `scripts/check_model_card_sync.py`
 - `scripts/rebuild_indexes.py`
 - `tests/test_validate_model_library.py`
+- `tests/qpi.regression.json`
+- `tests/regression_cases.json`
 - `reports/validation_report.md`
 - `reports/index_rebuild_report.md`
 - `reports/model_card_sync_report_v0.2.md`
 - `reports/selector_regression_report_v0.2.md`
 
-## 6. Deferred Owner Input
+## 7. Deliberately Out Of Scope
 
-Owner raw QPI case materials are not yet included. The expected future raw-case format is documented in `docs/QPI_CONTEXTUAL_ROUTING_RULES.md`.
+- no third model;
+- no APTC model registration;
+- no stable upgrade;
+- no LLM selector;
+- no full QA system;
+- no RAG/vector database;
+- no frontend or backend platform.
 

ccra_review_bundle/round-03_2026-06-17_contract-hardening-selector-calibration/03_REPORTS_DIFF_AND_COMMAND_LOG.md

@@ -1,6 +1,8 @@
-# Reports Diff and Command Log
+# Reports Diff And Command Log
 
-## 1. Fresh Verification Commands
+## 1. Framework-Hardening Verification Commands
+
+These checks were run after the contract and selector hardening work:
 
 ```powershell
 python scripts\rebuild_indexes.py --check
@@ -12,15 +14,47 @@ python scripts\run_selector_regression.py
 python scripts\check_model_card_sync.py
 ```
 
-## 2. Results
+Results:
 
-- `python scripts\rebuild_indexes.py --check`: PASS
+- Index check: PASS.
-- `python -m unittest discover -s tests -p "test*.py" -v`: PASS, 15 tests
+- Unit tests: PASS, 15 tests.
-- `python scripts\check_card_contract.py`: PASS
+- Card contract: PASS.
-- `python scripts\validate_model_library.py`: PASS
+- Model library validation: PASS.
-- `python scripts\run_selector_demo.py`: PASS; selected `qpi`, rejected `intellectual_archaeology`
+- Selector demo: PASS; selected `qpi`, rejected `intellectual_archaeology`.
-- `python scripts\run_selector_regression.py`: PASS
+- Selector regression: PASS.
-- `python scripts\check_model_card_sync.py`: PASS
+- Model/card sync: PASS.
+
+## 2. Case-Promotion Verification Commands
+
+These checks were run after the final `year-end-review-research-office.cases.md` promotion:
+
+```powershell
+python -c "import json; paths=['selector/qpi_case_digests.json','selector/selector_calibration_inputs.json','tests/qpi.regression.json','tests/regression_cases.json']; exec('for p in paths:\n    json.load(open(p, encoding=\'utf-8\'))\n    print(\'json_ok\\t\' + p)')"
+
+python -c "import json; d=json.load(open('selector/qpi_case_digests.json', encoding='utf-8')); c=json.load(open('selector/selector_calibration_inputs.json', encoding='utf-8')); r=json.load(open('tests/qpi.regression.json', encoding='utf-8')); a=json.load(open('tests/regression_cases.json', encoding='utf-8')); print('digest research', sum(x['case_id'].startswith('qpi-year-end-research-office-') for x in d['cases'])); print('calibration research', sum(x['case_id'].startswith('selector_calibration_qpi_research_') for x in c['inputs'])); print('qpi regression research', sum(x['case_id'].startswith('case_qpi_research_') for x in r['regression_cases'])); print('all regression research', sum(x['case_id'].startswith('case_qpi_research_') for x in a['regression_cases']))"
+
+python scripts\rebuild_indexes.py --write
+python scripts\rebuild_indexes.py --check
+python -m unittest discover -s tests -p "test*.py" -v
+python scripts\check_card_contract.py
+python scripts\validate_model_library.py
+python scripts\run_selector_demo.py
+python scripts\run_selector_regression.py
+python scripts\check_model_card_sync.py
+```
+
+Results:
+
+- JSON load check: PASS for all 4 relevant JSON files.
+- Research-office count check: PASS, 8 digest / 8 calibration / 4 QPI regression / 4 all regression.
+- Index rebuild `--write`: PASS.
+- Index rebuild `--check`: PASS.
+- Unit tests: PASS, 15 tests.
+- Card contract: PASS.
+- Model library validation: PASS.
+- Selector demo: PASS; selected `qpi`, rejected `intellectual_archaeology`.
+- Selector regression: PASS.
+- Model/card sync: PASS.
 
 ## 3. Important Implementation Notes
 
@@ -66,8 +100,16 @@ Selector:
 
 - `selector/selector_rules.json`
 - `selector/selector_calibration_inputs.json`
+- `selector/qpi_case_digests.json`
 - `scripts/run_selector_demo.py`
 
+Owner-reviewed QPI cases:
+
+- `reports/model_case_preprocessing/qpi/round-01/*.cases.md`
+- `reports/model_case_preprocessing/qpi/round-01/README.md`
+- `tests/qpi.regression.json`
+- `tests/regression_cases.json`
+
 Reports and docs:
 
 - `reports/content_review_report_v0.2.md`
@@ -75,11 +117,20 @@ Reports and docs:
 - `reports/index_rebuild_report.md`
 - `reports/model_card_sync_report_v0.2.md`
 - `reports/selector_regression_report_v0.2.md`
+- `reports/GPT讨论上下文_QPI草稿案例审阅_2026-06-17.md`
+- `reports/Codex新会话交接文档_QPI案例草稿审阅与第三轮后续_2026-06-17.md`
 - `README.md`
 - `docs/DECISIONS.md`
 - `knowledge_assets/08_CCRA模型库MVP质量门与交接协议.md`
 
-## 5. Git Status Caveat
+## 5. Working Tree Caveat
 
-This workspace already contains many untracked second-round files. `git diff --name-only` only reports tracked file diffs, so it is not a complete changed-file list for this MVP worktree. Use `BUNDLE_FILE_MANIFEST.md` and `optional_raw_changed_files.zip` for the round-03 review set.
+The workspace has not been staged or committed. There are intentionally untracked artifacts such as:
+
+- `selector/qpi_case_digests.json`
+- `reports/GPT讨论上下文_QPI草稿案例审阅_2026-06-17.md`
+- `scripts/__pycache__/`
+- `tests/__pycache__/`
+
+For GPT review, use this consolidated Round 03 bundle and `optional_raw_changed_files.zip`, not `git diff` alone.
 

ccra_review_bundle/round-03_2026-06-17_contract-hardening-selector-calibration/04_QPI_CASE_PROMOTION_SUMMARY_AND_REVIEW_GUIDE.md

@@ -0,0 +1,83 @@
+# QPI Case Promotion Summary And Review Guide
+
+## 1. Promotion Scope
+
+This round promotes 62 owner-reviewed QPI draft cases into reusable review assets:
+
+| Source group | Digest count | Calibration count | Regression count |
+| --- | ---: | ---: | ---: |
+| `disappointment-emotional-isolation.cases.md` | 8 | 8 | carried from prior work |
+| `flow-redesign.cases.md` | 6 | 6 | carried from prior work |
+| `year-end-review-development-office.cases.md` | 8 | 8 | 3 |
+| `year-end-review-academic-affairs.cases.md` | 8 | 8 | 4 |
+| `year-end-review-employment-entrepreneurship.cases.md` | 8 | 8 | 4 |
+| `year-end-review-engineering-center.cases.md` | 8 | 8 | 4 |
+| `year-end-review-international-college.cases.md` | 8 | 9 | 4 |
+| `year-end-review-research-office.cases.md` | 8 | 8 | 4 |
+
+International-college has 9 calibration inputs because it includes one paired no-call trap for simple logistics.
+
+## 2. Key Modeling Decisions To Review
+
+### Development Office
+
+- Hard resource gaps must not be disguised as document polishing or compliance packaging.
+- Credential continuity, incentive backlash, untrusted source data, and cross-unit resource conflicts were promoted into QPI assets.
+- 3 high-priority regression cases were added.
+
+### Academic Affairs
+
+- Cases focus on evidence legitimacy, staffing deadlocks, policy memory, quality assurance gaps, digital governance, and bottom-line control.
+- `dominant_scarcity: consensus_order` is intentionally common because the owner review emphasized governance and legitimacy over local execution.
+- 4 high-priority regression cases were added.
+
+### Employment Entrepreneurship
+
+- This group tests employment outcomes as organizational survival proof.
+- Key patterns include reverse accountability, credential compliance exposure, reported-metric legitimacy, overpromising, metric credibility, and transactional education.
+- 4 high-priority regression cases were added.
+
+### Engineering Center
+
+- This group tests target authenticity, equipment-led solutionism, shortcut debt, credential integrity, production without market closure, decision-rights fatigue, inherited asset liability, and personnel transition governance.
+- Case 005 was changed away from `question` framing because production without market closure is a business-purpose mismatch for the organizational subject.
+- 4 high-priority regression cases were added.
+
+### International College
+
+- Case 001 was promoted from `mixed` to `issue` because compliance boundary dominates retention tactics.
+- Case 002 keeps `dominant_scarcity: path_resource` but remains `mixed` because cross-unit conflict and capacity governance are visible.
+- Case 004 is the clearest `inter_viewpoint_divergence` sample with `classification_by_viewpoint`.
+- Case 006 was promoted from `problem` to `issue` because high-ticket education pricing deadlock is a trust-system failure.
+- APTC appears only as an owner-provided context note, not as a new model.
+- 4 high-priority regression cases were added.
+
+### Research Office
+
+- Case 001 is the umbrella case: research identity simulation.
+- Case 002 was changed from `inter_viewpoint_divergence` to `intra_frame_mixed`.
+- Case 003 is retained as a subcase/evidence case under 001.
+- Case 006 is classified as `problem` with governance risk, per owner review.
+- Case 008 is kept independent as `punishment_state_vs_integrity_state`.
+- 4 high-priority regression cases were added.
+
+## 3. Regression Selection Principle
+
+Not all owner-reviewed cases enter regression. Regression was reserved for cases that are:
+
+- reusable false-positive / false-negative traps;
+- boundary cases where QPI is likely to misclassify Q/P/I/mixed;
+- high-value misuse cases involving violent reduction, malicious inflation, tool solutionism, or untrusted data;
+- selector-critical cases that protect QPI-before-IA and no-call behavior.
+
+Other cases remain in digest and calibration.
+
+## 4. Current Review Question
+
+The main question is not whether these cases solve the organizational problems. QPI is not a solution model.
+
+The review question is:
+
+```text
+Do these owner-reviewed cases now give QPI enough auditable, evidence-linked, misuse-resistant routing examples for draft-callable selector calibration and regression hardening?
+```

ccra_review_bundle/round-03_2026-06-17_contract-hardening-selector-calibration/05_REVIEW_QUESTIONS_FOR_GPT.md

@@ -0,0 +1,64 @@
+# Review Questions For GPT
+
+## 1. Round-Level Judgment
+
+Please return:
+
+1. pass / revise / block judgment;
+2. required corrections, grouped by file;
+3. any regression cases that should be added, removed, or downgraded to calibration;
+4. any schema, naming, or bundle-structure risk;
+5. confirmation that QPI remains a routing model and not a full solution system.
+
+## 2. Framework And Contract Questions
+
+1. Are the QPI v0.3 contextual routing fields the right required runtime output layer?
+2. Do `classification_scope`, `is_provisional`, `context_sufficiency`, and `missing_context` sufficiently prevent false high-confidence QPI classification?
+3. Are `intra_frame_mixed` and `inter_viewpoint_divergence` separated correctly?
+4. Is the Issue-as-governance-load rule acceptable?
+5. Are selector hard no-call signals too broad or too narrow?
+6. Does the IA heavy-depth gate sufficiently prevent IA from being selected for ordinary QPI cases?
+
+## 3. Case Promotion Questions
+
+1. Are the 62 owner-reviewed QPI case digests faithful to the owner/GPT review decisions?
+2. Are the selected 23 new organizational QPI regression cases the right subset, or are there missing high-value regression traps?
+3. Are any cases over-promoted into regression when digest/calibration would be enough?
+4. Are `classification` and `dominant_scarcity` decisions coherent across similar patterns?
+5. Are `intra_frame_mixed` and `inter_viewpoint_divergence` separated consistently in the promoted case layer?
+6. Do umbrella / synthesis / subcase / boundary-case markers help reviewability, or do they overcomplicate the QPI case layer?
+7. Does the no-call calibration remain narrow and safe?
+
+## 4. Specific High-Risk Decisions To Audit
+
+- `year-end-review-international-college` case 002:
+  - `classification: mixed`
+  - `dominant_scarcity: path_resource`
+  - includes a paired simple-logistics no-call trap.
+
+- `year-end-review-research-office` case 006:
+  - `classification: problem`
+  - `dominant_scarcity: path_resource`
+  - `governance_risk: medium`
+  - intentionally lower than similar international-college capacity governance case.
+
+- `year-end-review-research-office` case 002:
+  - changed from `inter_viewpoint_divergence` to `intra_frame_mixed`.
+
+- `year-end-review-international-college` case 006:
+  - promoted from pricing Problem to trust-system Issue.
+  - APTC remains only an owner note, not a new model.
+
+- `year-end-review-research-office` case 001:
+  - marked as umbrella case for research identity simulation.
+
+## 5. Required Non-Goal Check
+
+Confirm that the updated framework and case layer still do not imply:
+
+- a third model;
+- stable upgrade;
+- LLM selector;
+- full answer system;
+- legal/tax/personnel decision engine;
+- RAG / vector database / frontend / backend platform.

ccra_review_bundle/round-03_2026-06-17_contract-hardening-selector-calibration/BUNDLE_FILE_MANIFEST.md

@@ -1,15 +1,18 @@
 # Bundle File Manifest
 
-## Required Review Files
+## Recommended Upload Order
 
-- `00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF.md`
+1. `00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF.md`
-- `01_GUIDANCE_PACK_AND_COMPLIANCE_MATRIX.md`
+2. `01_GUIDANCE_PACK_AND_COMPLIANCE_MATRIX.md`
-- `02_CURRENT_ASSET_PACK.md`
+3. `02_CURRENT_ASSET_PACK.md`
-- `03_REPORTS_DIFF_AND_COMMAND_LOG.md`
+4. `03_REPORTS_DIFF_AND_COMMAND_LOG.md`
-- `BUNDLE_FILE_MANIFEST.md`
+5. `04_QPI_CASE_PROMOTION_SUMMARY_AND_REVIEW_GUIDE.md`
-- `optional_raw_changed_files.zip`
+6. `05_REVIEW_QUESTIONS_FOR_GPT.md`
+7. `optional_raw_changed_files.zip` only if exact changed files are needed
 
-## Raw Changed Files Included In Zip
+## Included In `optional_raw_changed_files.zip`
+
+Framework hardening files:
 
 - `README.md`
 - `docs/DATA_CONTRACT.md`
@@ -25,7 +28,6 @@
 - `sources/source_articles.json`
 - `sources/source_excerpts.json`
 - `selector/selector_rules.json`
-- `selector/selector_calibration_inputs.json`
 - `scripts/run_selector_demo.py`
 - `scripts/validate_model_library.py`
 - `tests/test_validate_model_library.py`
@@ -36,3 +38,17 @@
 - `reports/selector_regression_report_v0.2.md`
 - `docs/superpowers/plans/2026-06-17-contract-hardening-selector-calibration.md`
 
+Owner-reviewed QPI case promotion files:
+
+- `reports/model_case_preprocessing/qpi/round-01/*.cases.md`
+- `reports/model_case_preprocessing/qpi/round-01/README.md`
+- `reports/GPT讨论上下文_QPI草稿案例审阅_2026-06-17.md`
+- `reports/Codex新会话交接文档_QPI案例草稿审阅与第三轮后续_2026-06-17.md`
+- `selector/qpi_case_digests.json`
+- `selector/selector_calibration_inputs.json`
+- `tests/qpi.regression.json`
+- `tests/regression_cases.json`
+
+## Bundle Policy
+
+This directory is the official third-round review package. It contains both the framework-hardening work and the owner-reviewed QPI case-promotion work without requiring a separate supplemental review directory.

models/model_index.json

@@ -26,7 +26,7 @@
       "card_file": "cards/qpi.md",
       "source_article_count": 3,
       "source_evidence_count": 10,
-      "regression_case_count": 17,
+      "regression_case_count": 46,
       "stability_level": "B",
       "regression_status": "pending",
       "status": "draft",

reports/Codex新会话交接文档_QPI案例草稿审阅与第三轮后续_2026-06-17.md

@@ -61,6 +61,16 @@ reports/model_case_preprocessing/qpi/round-01/
 - `reports/model_case_preprocessing/qpi/round-01/flow-redesign.cases.md`
 - `reports/model_case_preprocessing/qpi/round-01/disappointment-emotional-isolation.cases.md`
 - `reports/model_case_preprocessing/qpi/round-01/year-end-review-development-office.cases.md`
+- `reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md`
+- `reports/model_case_preprocessing/qpi/round-01/year-end-review-employment-entrepreneurship.cases.md`
+- `reports/model_case_preprocessing/qpi/round-01/year-end-review-engineering-center.cases.md`
+- `reports/model_case_preprocessing/qpi/round-01/year-end-review-international-college.cases.md`
+- `reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md`
+- `reports/model_case_preprocessing/qpi/round-01/year-end-review-employment-entrepreneurship.cases.md`
+- `reports/model_case_preprocessing/qpi/round-01/year-end-review-engineering-center.cases.md`
+- `reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md`
+- `reports/model_case_preprocessing/qpi/round-01/year-end-review-employment-entrepreneurship.cases.md`
+- `reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md`
 - `reports/model_case_preprocessing/qpi/round-01/year-end-review-engineering-center.cases.md`
 - `reports/model_case_preprocessing/qpi/round-01/year-end-review-international-college.cases.md`
 - `reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md`
@@ -205,6 +215,165 @@ python scripts\check_model_card_sync.py
 
 案例草稿抽取后没有再改 selector / regression / model JSON，因此无需因为草稿本身重跑全量验证。等 digest/calibration/regression 被写入后，必须重跑完整验证链。
 
+## 8.1 2026-06-17 增量处理进度
+
+已按 owner + GPT 审核意见完成八组 draft 的 owner-reviewed 处理和后续加工：
+
+- `reports/model_case_preprocessing/qpi/round-01/flow-redesign.cases.md`
+- `reports/model_case_preprocessing/qpi/round-01/disappointment-emotional-isolation.cases.md`
+- `reports/model_case_preprocessing/qpi/round-01/year-end-review-development-office.cases.md`
+- `reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md`
+- `reports/model_case_preprocessing/qpi/round-01/year-end-review-employment-entrepreneurship.cases.md`
+- `reports/model_case_preprocessing/qpi/round-01/year-end-review-engineering-center.cases.md`
+- `reports/model_case_preprocessing/qpi/round-01/year-end-review-international-college.cases.md`
+- `reports/model_case_preprocessing/qpi/round-01/year-end-review-research-office.cases.md`
+
+本次 `year-end-review-development-office.cases.md` 处理结果：
+
+- 8 个 case 全部保留并标记 `owner_reviewed` / `owner_approved_for_digest: true`。
+- 已写入 `selector/qpi_case_digests.json`：
+  - 001 硬资源缺口伪装成文书/合规包装问题。
+  - 002 资质指标修复损害运营连续性。
+  - 003 激励反噬被误读为个人不努力。
+  - 004 战略职能被治理成指标包装单位。
+  - 005 低成本雄心制造物理规律矛盾，作为 pattern-level Issue。
+  - 006 数据完整性不等于真实性 / 可审计性。
+  - 007 执行中层把不可能指令翻译成变通动作。
+  - 008 低投入指标生存吞噬真实能力，作为 umbrella organization-level Issue。
+- 已追加 8 条 selector calibration input。
+- 已选择 3 条进入 regression：
+  - `case_qpi_org_hard_resource_documentation_001`
+  - `case_qpi_org_credential_continuity_001`
+  - `case_qpi_org_untrusted_data_001`
+- 005、008 只作为 digest / calibration，不进入首轮 regression。
+
+本次 `year-end-review-academic-affairs.cases.md` 处理结果：
+
+- 8 个 case 全部保留并标记 `owner_reviewed` / `owner_approved_for_digest: true`。
+- 已写入 `selector/qpi_case_digests.json`：
+  - 001 AI / 工具请求转为证据合法性与工具边界问题。
+  - 002 外部政策触发的资质指标与师资吸纳死锁。
+  - 003 政策清理背后的 policy memory、trust debt 与诚信反噬。
+  - 004 短期可申报 / 可包装性替代长期战略规划。
+  - 005 跨边界资源复用失败，不与 002 合并。
+  - 006 结果下滑被生源质量解释掩盖，需质量保障与管理杠杆审计。
+  - 007 平台 / 本地 AI 选择掩盖数字化治理边界。
+  - 008 大型活动安全合规事故暴露底线控制失败。
+- 已追加 8 条 selector calibration input。
+- 已选择 4 条进入 regression：
+  - `case_qpi_academic_ai_evidence_boundary_001`
+  - `case_qpi_academic_policy_memory_001`
+  - `case_qpi_academic_outcome_quality_assurance_001`
+  - `case_qpi_academic_bottom_line_control_001`
+- 002、004、007 主要作为 selector calibration；005 作为配对支持样本保留，不与人员配比死锁案例合并。
+
+本次处理后的验证链已通过：
+
+```powershell
+python scripts\rebuild_indexes.py --write
+python scripts\rebuild_indexes.py --check
+python -m unittest discover -s tests -p "test*.py" -v
+python scripts\check_card_contract.py
+python scripts\validate_model_library.py
+python scripts\run_selector_demo.py
+python scripts\run_selector_regression.py
+python scripts\check_model_card_sync.py
+```
+
+结果：
+
+- Index rebuild/write: PASS
+- Index check: PASS
+- Unit tests: PASS, 15 tests
+- Card contract: PASS
+- Model library validation: PASS
+- Selector demo: PASS
+- Selector regression: PASS
+- Model/card sync: PASS
+
+
+本次 `year-end-review-employment-entrepreneurship.cases.md` 处理结果：
+
+- 8 个 case 全部保留并标记 `owner_reviewed` / `owner_approved_for_digest: true`。
+- 已写入 `selector/qpi_case_digests.json`：
+  - 001 就业指标压力转为反向问责权与教学权威重构。
+  - 002 资质指标修补造成 compliance exposure，与教务组 002 cross-link 不合并。
+  - 003 述职指标口径错配暴露 performance legitimacy 问题。
+  - 004 就业结果承诺扭曲招生 / 学生 pipeline。
+  - 005 高指标值掩盖指标可信度和数据生产机制风险。
+  - 006 真实雇主资产未整合进学习系统，作为边界型 mixed。
+  - 007 局部资产认可被膨胀为系统级 authority transfer。
+  - 008 生存策略把教育重构为交易化输出，作为本组 Issue anchor。
+- 已写入 `selector/selector_calibration_inputs.json`：8 条 employment-entrepreneurship calibration inputs。
+- 已写入 `tests/qpi.regression.json` 与 `tests/regression_cases.json`：4 条高优先级 regression：
+  - `case_qpi_employment_credential_compliance_exposure_001`
+  - `case_qpi_employment_reported_metric_legitimacy_001`
+  - `case_qpi_employment_overpromising_pipeline_001`
+  - `case_qpi_employment_metric_credibility_001`
+- 001、006、007、008 只作为 digest / calibration，不进入首轮 regression。
+
+本次 `year-end-review-engineering-center.cases.md` 处理结果：
+
+- 8 个 case 全部保留并标记 `owner_reviewed` / `owner_approved_for_digest: true`。
+- 已写入 `selector/qpi_case_digests.json`：
+  - 001 目标真实性缺口：高目标与能力—市场—资源—验证桥梁断裂。
+  - 002 设备主导方案主义：资产采购替代需求、操作者、安全和经济模型验证。
+  - 003 P 式短路长期处理 I，最终撞上硬边界，作为 Issue anchor。
+  - 004 资质完整性不能被“能不能临时用”覆盖，路由到制度审查而非人员 verdict。
+  - 005 生产能力不等于商业闭环，经营主体忽略市场是第一性错位。
+  - 006 执行疲劳可能是决策权结构问题，不只是动力问题。
+  - 007 继承项目可能是资产，也可能是隐性负债。
+  - 008 人员能力升级需要合法、预算化、能力化转型路径，作为人员转型治理 Issue anchor。
+- 已写入 `selector/selector_calibration_inputs.json`：8 条 engineering-center calibration inputs。
+- 已写入 `tests/qpi.regression.json` 与 `tests/regression_cases.json`：4 条高优先级 regression：
+  - `case_qpi_engineering_target_authenticity_001`
+  - `case_qpi_engineering_equipment_solutionism_001`
+  - `case_qpi_engineering_credential_integrity_policy_001`
+  - `case_qpi_engineering_market_closure_001`
+- 003、006、007、008 只作为 digest / calibration，不进入首轮 regression。
+
+本次 `year-end-review-international-college.cases.md` 处理结果：
+
+- 8 个 case 全部保留并标记 `owner_reviewed` / `owner_approved_for_digest: true`。
+- 已写入 `selector/qpi_case_digests.json`：
+  - 001 招生留存动作越过合规边界，从 mixed 上调为 Issue。
+  - 002 物理容量硬缺口引发跨单元冲突，保留 `dominant_scarcity: path_resource`。
+  - 003 业绩背书型权威膨胀。
+  - 004 战略链条坍缩为前端销售，作为 inter-viewpoint divergence 样例。
+  - 005 资质指标事实核验嵌入治理扭曲，从 Question 上调为 Issue。
+  - 006 定价僵局背后的高客单价信任体系，从 Problem 上调为 Issue。
+  - 007 高绩效能力未制度化，替代“组织能力被私有化”表述。
+  - 008 真实外部资产被当作未就绪内部扩张许可证，作为 synthesis case。
+- 已写入 `selector/selector_calibration_inputs.json`：9 条 international-college calibration inputs，其中包含 1 条 simple logistics no-call trap。
+- 已写入 `tests/qpi.regression.json` 与 `tests/regression_cases.json`：4 条高优先级 regression：
+  - `case_qpi_international_compliance_retention_001`
+  - `case_qpi_international_capacity_governance_001`
+  - `case_qpi_international_metric_governance_001`
+  - `case_qpi_international_pricing_trust_system_001`
+- 003、004、007、008 只作为 digest / calibration，不进入首轮 regression。
+- APTC 仅作为 owner 补充分析框架记录在 006，不注册为本仓库第三模型。
+
+本次 `year-end-review-research-office.cases.md` 处理结果：
+
+- 8 个 case 全部保留并标记 `owner_reviewed` / `owner_approved_for_digest: true`。
+- 已写入 `selector/qpi_case_digests.json`：
+  - 001 研究身份模拟，作为本组 umbrella case。
+  - 002 研究能力被暴力降维成会计/表格类别。
+  - 003 交易性研究资产作为 001 的 subcase / evidence case。
+  - 004 排名焦虑将研究价值压缩成可购买、可填报、可冲刺的指标输入。
+  - 005 高端人才作为展示资产，独立保留并链接 001。
+  - 006 设施容量是 hard-capacity Problem，保留 governance risk。
+  - 007 看似“谁负责”的 Q，实为安全问责体系 Issue。
+  - 008 惩罚状态框架 vs 诚信状态框架，独立保留并链接 001。
+- 已写入 `selector/selector_calibration_inputs.json`：8 条 research-office calibration inputs。
+- 已写入 `tests/qpi.regression.json` 与 `tests/regression_cases.json`：4 条高优先级 regression：
+  - `case_qpi_research_identity_simulation_001`
+  - `case_qpi_research_data_truthfulness_001`
+  - `case_qpi_research_ranking_reduction_001`
+  - `case_qpi_research_penalty_integrity_001`
+- 003、005、006、007 只作为 digest / calibration，不进入首轮 regression。
+- round-01 的年终述职会 draft 处理已全部完成。
+
 ## 9. 后续建议计划
 
 ### Step 1: 用户审阅草稿
@@ -271,4 +440,3 @@ tests/qpi.regression.json
 qpi: draft / B / pending
 intellectual_archaeology: draft / B / pending
 ```
-

reports/GPT讨论上下文_QPI草稿案例审阅_2026-06-17.md

@@ -0,0 +1,283 @@
+# GPT 讨论上下文：QPI 草稿案例审阅
+
+date: 2026-06-17
+
+repo: `C:\Users\wangq\Documents\Codex\work-projects\the-mindscape-of-bro-tsong`
+
+purpose: 给 ChatGPT / CCRA / Owner 讨论 QPI draft cases 使用
+
+## 1. 我们在做什么
+
+我们正在为 `the-mindscape-of-bro-tsong` 的 `model_library_mvp` 阶段，稳定 QPI 模型。
+
+QPI 当前不是“问题文本分类器”，而是：
+
+```text
+用于判断某个认知主体在特定上下文中，
+如何将期望—现实落差框定为 Question、Problem、Issue、mixed 或 no-call，
+并识别其中的上下文缺口、动态演化和误框定风险。
+```
+
+因此，QPI 判断的对象不是一句话本身，而是：
+
+```text
+某个主体
+在某个场景
+基于知识结构、责任位置、目标、资源、时间压力
+把某个期望—现实落差
+框定成 Q / P / I / mixed / no-call 的过程
+```
+
+## 2. 当前状态
+
+Codex 已经从 8 份原始素材中加工出：
+
+```text
+62 个 QPI draft cases
+```
+
+这些案例状态都是：
+
+```text
+draft_owner_review_needed
+```
+
+它们还不是：
+
+- selector calibration JSON
+- regression cases
+- CCRA 审定案例
+- QPI stable 证据
+
+它们只是供 Owner / GPT / CCRA 审阅和修正的 Markdown 草稿。
+
+## 3. 讨论方式
+
+每次讨论只处理一份原始素材和它对应的一份 `.cases.md`。
+
+推荐上传：
+
+1. 本上下文文档。
+2. 一份原始素材。
+3. Codex 对应加工出的 `.cases.md` 草稿。
+
+不要一次上传 62 个 cases。
+
+## 4. GPT 本轮任务
+
+GPT 需要帮助 Owner 判断：
+
+1. Codex 抽出的 case 是否成立。
+2. 是否有 case 应该删除。
+3. 是否有 case 应该合并。
+4. 是否有遗漏的重要 case。
+5. 每个 case 的 QPI 判断是否合理：
+   - `classification_scope`
+   - `is_provisional`
+   - `classification`
+   - `dominant_scarcity`
+   - `classification_confidence`
+   - `recommended_next_step`
+6. 是否误把 `inter_viewpoint_divergence` 写成 `intra_frame_mixed`。
+7. 是否误把组织级 Issue 降维成 Problem。
+8. 是否把具体可执行 Problem 恶意升维成 Issue。
+9. 是否存在脱敏不足或敏感信息残留。
+10. 哪些案例值得进入后续 digest / calibration / regression。
+
+## 5. QPI 判断规则摘要
+
+### 5.1 Question
+
+核心匮乏物是信息、事实、定义、位置、证据或标准答案。
+
+适合：
+
+- 查询
+- 检索
+- 补充事实
+- 明确概念
+
+### 5.2 Problem
+
+目标相对明确，但缺路径、方法、资源、分解、工程实现或执行闭环。
+
+适合：
+
+- 拆解
+- 求解
+- 工程化
+- 制定方案
+
+### 5.3 Issue
+
+不是只看“有没有多人组织”。只要存在持续治理负荷，就可能是 Issue。
+
+Issue 典型信号：
+
+- 成功标准不唯一。
+- 多个合理目标长期冲突。
+- 不能一次性解决，只能持续治理。
+- 解决动作会改变后续问题结构。
+- 涉及权责、激励、秩序、合规、审计、真实性、共识、长期副作用。
+- 局部真实可能冒充整体结构。
+- 需要人工确认、权威来源或边界协议。
+
+### 5.4 mixed
+
+`mixed` 只用于同一主体、同一场景、同一阶段内多类匮乏物并存。
+
+例如：
+
+```text
+同一组织在同一合规场景中，同时存在资源硬缺口和秩序/合规风险。
+```
+
+### 5.5 multi-perspective
+
+同一句输入在不同主体、责任位置、时间尺度下会被框定为不同 QPI 类型。
+
+这不是 mixed。
+
+例如：
+
+```text
+如何提高流量？
+```
+
+对学生可能是 Question。
+
+对营销经理可能是 Problem。
+
+对集团营销总监可能是 Issue。
+
+## 6. 需要特别关注的误判
+
+### 6.1 暴力降维
+
+把系统性 Issue 压成个人执行 Problem。
+
+例如：
+
+```text
+激励结构失灵 -> 被说成某些人不努力。
+```
+
+### 6.2 恶意升维
+
+把职责范围内可执行 Problem 放大成不可触碰的宏大 Issue。
+
+例如：
+
+```text
+具体执行路径缺失 -> 被说成时代问题、文化问题、战略问题。
+```
+
+### 6.3 工具解法主义
+
+把主体-上下文-治理问题误判为工具不熟。
+
+### 6.4 过早定性
+
+缺少主体、场景、责任范围、成功标准、资源约束、时间尺度时，仍然高置信判定 Q/P/I。
+
+## 7. 审阅输出格式
+
+GPT 最好按下面格式给出结果。
+
+```md
+# QPI Case Review Result
+
+## 1. 总体判断
+
+这份素材适合 / 不适合进入 QPI 案例库。
+
+## 2. 建议保留的 cases
+
+- Case XXX：保留。理由：...
+
+## 3. 建议删除的 cases
+
+- Case XXX：删除。理由：...
+
+## 4. 建议合并的 cases
+
+- Case XXX + Case YYY：建议合并。理由：...
+
+## 5. 建议改判的 cases
+
+- Case XXX：
+  - 原判断：
+  - 建议判断：
+  - 理由：
+
+## 6. 遗漏案例
+
+- 建议新增 case：...
+
+## 7. 脱敏问题
+
+- 是否有敏感信息残留：
+- 建议替换：
+
+## 8. 最值得进入 digest/calibration/regression 的案例
+
+- digest:
+- selector calibration:
+- regression:
+
+## 9. 需要 Owner 判断的问题
+
+- ...
+```
+
+## 8. Codex 后续会怎么做
+
+Owner 和 GPT 完成审阅后，Codex 会：
+
+1. 根据审阅意见修改 `.cases.md`。
+2. 标记 owner-reviewed 状态。
+3. 把确认案例转成 case digest。
+4. 把适合 selector 的案例合并进 `selector/selector_calibration_inputs.json`。
+5. 把少量关键边界案例加入 regression。
+6. 重跑完整验证链。
+7. 生成 CCRA 审核补充资料。
+
+Codex 不会：
+
+- 把未确认草稿直接转 JSON。
+- 把 62 个案例全部塞进 regression。
+- 因案例数量增加就升级 stable。
+- 扩展第三模型。
+- 引入 LLM selector。
+- 接完整问题回答系统。
+
+## 9. 当前相关本地文件
+
+QPI 规则：
+
+- `docs/QPI_CONTEXTUAL_ROUTING_RULES.md`
+- `docs/model_case_preprocessing/qpi/CASE_PREPROCESSING_WORKFLOW.md`
+
+草稿目录：
+
+- `reports/model_case_preprocessing/qpi/round-01/`
+
+交接文档：
+
+- `reports/Codex新会话交接文档_QPI案例草稿审阅与第三轮后续_2026-06-17.md`
+
+第三轮审核包：
+
+- `ccra_review_bundle/round-03_2026-06-17_contract-hardening-selector-calibration/00_OPEN_THIS_FIRST_CCRA_REVIEW_BRIEF.md`
+- `ccra_review_bundle/round-03_2026-06-17_contract-hardening-selector-calibration/01_GUIDANCE_PACK_AND_COMPLIANCE_MATRIX.md`
+
+## 10. 当前模型状态
+
+继续保持：
+
+```text
+qpi: draft / B / pending
+intellectual_archaeology: draft / B / pending
+```
+
+本轮审阅的目标不是升级 stable，而是筛出可以进入 digest / calibration / regression 的高质量真实案例。

reports/model_case_preprocessing/qpi/round-01/README.md

@@ -1,13 +1,31 @@
 # QPI Case Preprocessing Round 01
 
-status: draft_owner_review_needed
+status: owner_review_in_progress
 
 This round preprocesses owner-provided raw QPI materials into Markdown case drafts.
 
-Raw source files currently assigned:
+Owner-reviewed and promoted so far:
 
-- `C:\Users\wangq\Documents\Codex\knowledge-vault\work\internal\强哥的思想宇宙\QPI案例分析\流程改造.md`
+- `flow-redesign.cases.md`
-- `C:\Users\wangq\Documents\Codex\knowledge-vault\work\internal\强哥的思想宇宙\QPI案例分析\失望性情感隔离心理分析.md`
+- `disappointment-emotional-isolation.cases.md`
+- `year-end-review-development-office.cases.md`
+- `year-end-review-academic-affairs.cases.md`
+- `year-end-review-employment-entrepreneurship.cases.md`
+- `year-end-review-engineering-center.cases.md`
+- `year-end-review-international-college.cases.md`
+- `year-end-review-research-office.cases.md`
 
-Output files should remain Markdown drafts until owner review.
+Remaining draft review files:
 
+No remaining draft review files in this round.
+Promotion rule:
+
+```text
+draft .cases.md
+-> owner-reviewed .cases.md
+-> selector/qpi_case_digests.json
+-> selector/selector_calibration_inputs.json
+-> selected regression cases only
+```
+
+Do not promote unreviewed draft cases into digest, calibration, or regression.

reports/model_case_preprocessing/qpi/round-01/disappointment-emotional-isolation.cases.md

@@ -1,6 +1,10 @@
 # QPI Case Drafts: Disappointment Emotional Isolation
 
-status: draft_owner_review_needed
+status: owner_reviewed
+
+owner_review_source: `C:\Users\wangq\Documents\Codex\knowledge-vault\work\internal\强哥的思想宇宙\QPI案例审阅\QPI提炼审核\disappointment-emotional-isolation.cases-GPT.md`
+
+owner_review_note: Owner review completed for all eight draft cases. This file is ready for incremental digest / calibration / selected regression processing. QPI remains a front routing and misframing-diagnostic model, not a psychological intervention model.
 
 source_path: `C:\Users\wangq\Documents\Codex\knowledge-vault\work\internal\强哥的思想宇宙\QPI案例分析\失望性情感隔离心理分析.md`
 
@@ -8,7 +12,11 @@ source_note: Owner-provided raw material. These drafts paraphrase and restructur
 
 ## Case qpi-draft-001: Same Surface Term, Different Mechanisms
 
-status: draft_owner_review_needed
+status: owner_reviewed
+
+owner_approved_for_digest: true
+
+digest_role: selector_calibration_multi_perspective_mechanism_ambiguity
 
 source_path: `C:\Users\wangq\Documents\Codex\knowledge-vault\work\internal\强哥的思想宇宙\QPI案例分析\失望性情感隔离心理分析.md`
 
@@ -76,9 +84,26 @@ The governance load is medium to high when the label affects boundaries, help-se
 - Should the QPI output require a mechanism distinction before any route recommendation?
 - Is "passive numbness vs active withdrawal" a required preprocessing distinction for future psychological-relational cases?
 
+### 13. Owner Review Decision
+
+- Treat primarily as `multi_perspective / inter_viewpoint_divergence`, not `intra_frame_mixed`.
+  - The same surface term can route differently depending on subject position, goal, and responsibility scope.
+  - In the source context, the owner is analyzing an external psychological-content frame and its misframing risks, not simply asking for a neutral definition.
+- Require mechanism distinction before route recommendation when a surface label compresses different mechanisms.
+  - Mechanism distinction means identifying whether the label points to passive numbness, active cognitive withdrawal, both, or insufficient context.
+  - QPI should not make a clinical diagnosis or intervention plan.
+- Do not make "passive numbness vs active withdrawal" a universal required field for all psychological-relational cases.
+  - Use the broader rule: if a surface label may compress different mechanisms, mark `mechanism_ambiguity` before routing.
+
 ## Case qpi-draft-002: I Domain Misread As a Label Question
 
-status: draft_owner_review_needed
+status: owner_reviewed
+
+owner_approved_for_digest: true
+
+digest_role: label_question_false_positive_trap
+
+regression_candidate: high_priority
 
 source_path: `C:\Users\wangq\Documents\Codex\knowledge-vault\work\internal\强哥的思想宇宙\QPI案例分析\失望性情感隔离心理分析.md`
 
@@ -116,9 +141,9 @@ The case starts as Q: "What is this?" It shifts to I when the label becomes part
 
 ### 8. Mixed Or Multi-Perspective
 
-`intra_frame_mixed`
+`not_mixed`
 
-Within the same subject frame, there is both knowledge scarcity and governance scarcity. The label may help, but routing only to Q risks missing the recurring system.
+The question may include a Q-shaped label component, but once the label organizes identity, relationship boundaries, help-seeking, and future action, the QPI classification is primarily an Issue. Treat this as `issue_with_Q_component` in prose, not as a separate enum value.
 
 ### 9. Governance Load
 
@@ -135,7 +160,7 @@ High. The subject must manage the cost and benefit of the explanatory label, pre
 
 - classification_scope: subject_contextual
 - is_provisional: true
-- classification: mixed
+- classification: issue
 - dominant_scarcity: consensus_order
 - classification_confidence: medium
 - recommended_next_step: Treat the label as a provisional map, then ask what pattern is recurring, what it protects, what it costs, and what context is needed before choosing an intervention route.
@@ -146,9 +171,30 @@ High. The subject must manage the cost and benefit of the explanatory label, pre
 - What minimum context would distinguish a pure Q concept lookup from an I-domain self-framing case?
 - Should this become a selector false-positive trap for "what is X" questions that are actually identity/governance cases?
 
+### 13. Owner Review Decision
+
+- If the label is already organizing identity, self-explanation, relationship boundaries, and future action, the dominant route should be `issue`.
+  - The label has a Q component, but Q is no longer the dominant scarcity.
+  - Use prose note `issue_with_Q_component`.
+- Minimum context needed to distinguish pure Q lookup from I-domain self-framing:
+  - problem_owner;
+  - label_use;
+  - decision_stake;
+  - recurrence;
+  - desired_output.
+- Use as a conditional "what is X" false-positive trap.
+  - Not every concept or label question is P or I.
+  - Escalate only when the label affects identity, relationship decisions, self-pathologizing, or long-term governance.
+
 ## Case qpi-draft-003: Single-Cause Attribution Compresses a System
 
-status: draft_owner_review_needed
+status: owner_reviewed
+
+owner_approved_for_digest: true
+
+digest_role: single_factor_totalization_regression_case
+
+regression_candidate: high_priority
 
 source_path: `C:\Users\wangq\Documents\Codex\knowledge-vault\work\internal\强哥的思想宇宙\QPI案例分析\失望性情感隔离心理分析.md`
 
@@ -197,7 +243,7 @@ High. The subject must avoid blame compression, preserve explanatory plurality,
 ### 10. Misframing Risks
 
 - violent_reduction
-- single-cause_reduction
+- single_factor_totalization
 - over_pathologizing
 - premature_classification
 
@@ -216,9 +262,30 @@ High. The subject must avoid blame compression, preserve explanatory plurality,
 - Should this case be used to test that QPI does not output a single definitive cause when the source provides coupled mechanisms?
 - What owner-approved language should be used to distinguish explanatory usefulness from causal finality?
 
+### 13. Owner Review Decision
+
+- Keep the case, but avoid the overbroad rule "all single-cause attribution is wrong."
+  - Rename the risk to `single_factor_totalization` or `single_cause_totalization`.
+  - QPI should prevent a single factor from being treated as the complete causal closure when the source already shows coupled mechanisms.
+  - In bounded P cases, a single high-weight factor can still be a valid current lever.
+- Use as a regression case with this target:
+  - Do not forbid high-weight factor identification.
+  - Prevent QPI from outputting a single definitive root cause when coupled mechanisms are already present.
+  - Require distinction between trigger, maintaining condition, high-weight factor, current action lever, and causal totality.
+- Owner-approved language:
+  - "This factor has explanatory usefulness, but it is not causal finality."
+  - "It may be a high-weight factor or current lever, not the complete cause."
+  - "It can be prioritized in this context, but it cannot replace the system maintenance map."
+
 ## Case qpi-draft-004: Intervention Framed as a One-Time Solution
 
-status: draft_owner_review_needed
+status: owner_reviewed
+
+owner_approved_for_digest: true
+
+digest_role: one_time_solution_misroute_regression_case
+
+regression_candidate: high_priority
 
 source_path: `C:\Users\wangq\Documents\Codex\knowledge-vault\work\internal\强哥的思想宇宙\QPI案例分析\失望性情感隔离心理分析.md`
 
@@ -256,9 +323,9 @@ The frame shifts from P to I. It begins as a path problem but becomes an Issue b
 
 ### 8. Mixed Or Multi-Perspective
 
-`intra_frame_mixed`
+`not_mixed`
 
-The subject needs both action paths and governance rules. A pure P route would overpromise a one-time fix.
+The subject may later extract bounded local P tasks, but the QPI classification itself is centered on ongoing governance rather than a one-time fix.
 
 ### 9. Governance Load
 
@@ -275,10 +342,10 @@ High. The subject must continuously calibrate when isolation is protective, when
 
 - classification_scope: subject_contextual
 - is_provisional: true
-- classification: mixed
+- classification: issue
 - dominant_scarcity: consensus_order
-- classification_confidence: medium
+- classification_confidence: high
-- recommended_next_step: Route as P/I mixed: identify one immediate boundary or experiment, while also defining ongoing governance variables and review conditions.
+- recommended_next_step: Route as Issue. Do not design psychological intervention; first decide whether a bounded local P subtask has enough actor, object, local goal, risk boundary, feedback, reversibility, and non-terminal framing.
 
 ### 12. Owner Review Questions
 
@@ -286,9 +353,22 @@ High. The subject must continuously calibrate when isolation is protective, when
 - Should this case become a regression sample for preventing QPI from over-routing psychological-relational questions to Problem?
 - What minimum actionability is required before recommending a P step inside an I-domain case?
 
+### 13. Owner Review Decision
+
+- "Cannot be solved once, can be governed over time" is a standard Issue signal when paired with other signals such as unstable success criteria, feedback loops, relationship effects, and multiple reasonable goals.
+- Use as a regression sample to prevent QPI from over-routing psychological-relational Issues to Problem.
+  - The failure mode is outputting one-time fixes, three-step cures, or single intervention scripts.
+- QPI does not design psychological intervention.
+  - It may only decide whether enough context exists to split out a bounded local P subtask.
+  - Minimum conditions: actor, object, local_goal, risk_boundary, feedback_signal, reversibility, and non_terminal framing.
+
 ## Case qpi-draft-005: External Help as Method Teaching vs Calibration Environment
 
-status: draft_owner_review_needed
+status: owner_reviewed
+
+owner_approved_for_digest: true
+
+digest_role: supporting_external_authority_boundary_issue_case
 
 source_path: `C:\Users\wangq\Documents\Codex\knowledge-vault\work\internal\强哥的思想宇宙\QPI案例分析\失望性情感隔离心理分析.md`
 
@@ -326,9 +406,9 @@ The frame shifts from binary Q/P to Issue. The relevant judgment depends on role
 
 ### 8. Mixed Or Multi-Perspective
 
-`intra_frame_mixed`
+`not_mixed`
 
-The same subject needs to decide both what to do and how to govern agency, trust, expertise, and external calibration boundaries.
+This is primarily an Issue case about role boundaries, agency, trust, expertise, and external calibration. Method choice is secondary.
 
 ### 9. Governance Load
 
@@ -347,7 +427,7 @@ High. The case requires role boundary management, risk control, authority calibr
 - is_provisional: true
 - classification: issue
 - dominant_scarcity: consensus_order
-- classification_confidence: medium
+- classification_confidence: high
 - recommended_next_step: Reframe from "external help works or does not work" to "what external role, under what boundaries, helps the subject build a stronger self-governance system."
 
 ### 12. Owner Review Questions
@@ -356,9 +436,23 @@ High. The case requires role boundary management, risk control, authority calibr
 - Should QPI include "external authority boundary" as a governance-load signal?
 - Should selector calibration treat "does therapy work" style inputs as low-confidence until context is known?
 
+### 13. Owner Review Decision
+
+- Keep this case; do not delete it as an intervention case.
+  - The core is not whether psychological consultation works, but the role boundary of external help in a self-governance system.
+- Add `external_authority_boundary` as a governance-load signal in prose.
+  - This is not psychological advice.
+  - It marks authority, dependency, calibration environment, and subject agency risks.
+- Treat "does therapy work" style inputs as low-confidence until context is known.
+  - They may be Q, P, or I depending on whether the user asks for evidence, logistics, or long-term self-governance.
+
 ## Case qpi-draft-006: Time Scale Changes the QPI Classification
 
-status: draft_owner_review_needed
+status: owner_reviewed
+
+owner_approved_for_digest: true
+
+digest_role: selector_calibration_time_scale_scope_case
 
 source_path: `C:\Users\wangq\Documents\Codex\knowledge-vault\work\internal\强哥的思想宇宙\QPI案例分析\失望性情感隔离心理分析.md`
 
@@ -426,9 +520,24 @@ High when the subject must choose the right scale before acting. Mis-scaling can
 - Should "same phenomenon, different time scale" be treated as inter-viewpoint divergence or a separate dynamic-scope category?
 - Should selector calibration include short inputs that are no-call or Q at one scale but QPI/Issue at another?
 
+### 13. Owner Review Decision
+
+- Keep `time_scale` and `classification_scope`.
+  - QPI is a slice-at-a-time front routing model, not a full dynamic simulation.
+  - It must record the time slice and scope so that a local Q/P/I judgment is not mistaken for a global judgment.
+- Treat "same phenomenon, different time scale" as `inter_viewpoint_divergence` for now.
+  - Do not introduce a new dynamic-scope enum in this round.
+- Add selector calibration for short inputs that are no-call or Q at one scale but QPI/Issue at another.
+
 ## Case qpi-draft-007: QPI Mismatch Table for Psychological-Relational Material
 
-status: draft_owner_review_needed
+status: owner_reviewed
+
+owner_approved_for_digest: true
+
+digest_role: qpi_mismatch_diagnostics_regression_case
+
+regression_candidate: high_priority
 
 source_path: `C:\Users\wangq\Documents\Codex\knowledge-vault\work\internal\强哥的思想宇宙\QPI案例分析\失望性情感隔离心理分析.md`
 
@@ -498,9 +607,30 @@ High for the model library. The rule must prevent future selector and regression
 - Should mismatch detection become part of QPI regression rather than selector calibration only?
 - Which mismatch labels should be canonical in v0.3?
 
+### 13. Owner Review Decision
+
+- Keep this case as a QPI guardrail case.
+- Add explicit `wrong_route_to_avoid` in case digest.
+- Use mismatch detection in QPI regression, not selector calibration only.
+- Canonical mismatch labels for this round:
+  - `I_as_Q`
+  - `I_as_P`
+  - `P_as_I`
+  - `over_pathologizing`
+  - `moral_judgment_substitution`
+  - `single_factor_totalization`
+
 ## Case qpi-draft-008: Isolation as Protective Boundary or Overgeneralized Defense
 
-status: draft_owner_review_needed
+status: owner_reviewed
+
+owner_approved_for_digest: true
+
+digest_role: canonical_one_person_self_governance_issue_anchor
+
+regression_candidate: high_priority
+
+selector_calibration_candidate: high_priority
 
 source_path: `C:\Users\wangq\Documents\Codex\knowledge-vault\work\internal\强哥的思想宇宙\QPI案例分析\失望性情感隔离心理分析.md`
 
@@ -538,9 +668,9 @@ The frame shifts from Q to I. It may start as "Is this normal?" but becomes an o
 
 ### 8. Mixed Or Multi-Perspective
 
-`intra_frame_mixed`
+`not_mixed`
 
-The same subject must integrate evidence, action paths, and governance tradeoffs. A one-label answer is inadequate.
+The same subject may later extract bounded local P tasks, but the core classification is Issue: ongoing calibration of a protective strategy across target, intensity, duration, benefit, cost, environment, energy state, feedback, and reversibility.
 
 ### 9. Governance Load
 
@@ -556,14 +686,40 @@ High. The subject must repeatedly judge when withdrawal is protective, when it i
 ### 11. Candidate QPI Judgment
 
 - classification_scope: subject_contextual
-- is_provisional: true
+- is_provisional: false
 - classification: issue
 - dominant_scarcity: consensus_order
-- classification_confidence: medium
+- classification_confidence: high
-- recommended_next_step: Replace binary judgment with a governance review: target, strength, duration, benefit, cost, and evidence for whether the strategy still fits the current context.
+- classification_note: issue_with_local_P_candidates
+- recommended_next_step: Replace binary judgment with a governance review: target, intensity, duration, benefit, cost, generalization, current environment, energy state, feedback, and reversibility. First run value assessment to decide whether this case needs full Issue governance or only a bounded local Problem step.
 
 ### 12. Owner Review Questions
 
 - Should this be classified as Issue rather than P/I mixed because the core task is ongoing calibration?
 - What evidence would justify routing part of the case to Problem, such as a concrete boundary conversation?
 - Should this case become a canonical example of "Issue does not require many people; one-person self-governance can still be Issue"?
+
+### 13. Owner Review Decision
+
+- Do not merge this case into qpi-draft-004.
+  - qpi-draft-004 prevents psychological-relational Issue from being misrouted as one-time Problem.
+  - qpi-draft-008 is the positive anchor for one-person self-governance as Issue.
+- Classify as `issue`, not P/I mixed.
+  - Local P tasks can exist only as bounded subtasks inside the Issue.
+  - Use prose note `issue_with_local_P_candidates`.
+- Problem routing requires value assessment plus a bounded action unit:
+  - actor;
+  - object;
+  - local_goal;
+  - risk_boundary;
+  - time_window;
+  - feedback_signal;
+  - reversibility;
+  - non_terminal framing.
+- Make this a canonical example:
+  - `Issue does not require multiple people; one-person self-governance can still be Issue.`
+  - Issue depends on sustained governance load, not the presence of multiple human participants.
+- Owner model notes:
+  - A single self-governing subject can have energy, recovery, attribution, protective cutoff, and long feedback loops.
+  - Related owner models may be recorded as notes: Dual-Engine & Regenerator, Cognitive Regenerator, Attribution Oscilloscope, Metacognitive Monitoring & BMS, and Value Assessment Gate.
+  - Do not add these as new QPI classification categories in this round.

reports/model_case_preprocessing/qpi/round-01/flow-redesign.cases.md

@@ -1,6 +1,10 @@
 # QPI Case Drafts: Flow Redesign
 
-status: draft_owner_review_needed
+status: owner_reviewed
+
+owner_review_source: `C:\Users\wangq\Documents\Codex\knowledge-vault\work\internal\强哥的思想宇宙\QPI案例审阅\QPI提炼审核\flow-redesing.cases-GPT.md`
+
+owner_review_note: Owner review completed for all six draft cases. This file is now ready for later digest / calibration / regression selection, but no selector JSON or regression JSON has been written from it yet.
 
 source_path: `C:\Users\wangq\Documents\Codex\knowledge-vault\work\internal\强哥的思想宇宙\QPI案例分析\流程改造.md`
 
@@ -8,7 +12,11 @@ source_note: Raw source remains outside this repository. These are reviewable QP
 
 ## Case qpi-draft-001: Outline Review Was Not The Real Entry Point
 
-status: draft_owner_review_needed
+status: owner_reviewed
+
+owner_approved_for_digest: true
+
+digest_role: supporting_evidence_for_context_engineering_entry_point_case
 
 source_path: `C:\Users\wangq\Documents\Codex\knowledge-vault\work\internal\强哥的思想宇宙\QPI案例分析\流程改造.md`
 
@@ -75,9 +83,26 @@ High. The case requires deciding stage boundaries, ownership of context engineer
 - Is "outline review was the wrong entry point" the core case, or should it be folded into a larger context-engineering case?
 - Should this case become a selector calibration example for "workflow automation that looks like P but becomes P/I mixed"?
 
+### 13. Owner Review Decision
+
+- Keep `dominant_scarcity: consensus_order`.
+  - `path_resource` is high because the workflow lacked the correct processing path.
+  - The deeper issue is stage authority, context sufficiency, confirmation gates, and externalizing owner judgment.
+- Fold this case into a larger context-engineering / entry-point governance case.
+  - If retained as a standalone case, keep it provisional.
+  - Use it as an evidence fragment rather than the strongest independent case.
+- This can support selector calibration for workflow automation that looks like P but becomes P/I mixed.
+  - Calibration focus: the wrong automation entry point exposes missing context engineering and stage authority.
+
 ## Case qpi-draft-002: Dispatch Pack Was Mistaken For Real Invocation
 
-status: draft_owner_review_needed
+status: owner_reviewed
+
+owner_approved_for_digest: true
+
+digest_role: no_simulation_calibration_candidate
+
+regression_candidate: high_priority
 
 source_path: `C:\Users\wangq\Documents\Codex\knowledge-vault\work\internal\强哥的思想宇宙\QPI案例分析\流程改造.md`
 
@@ -115,9 +140,9 @@ P -> I. At first the issue looked like a missing file-format or dispatch-design
 
 ### 8. Mixed Or Multi-Perspective
 
-`intra_frame_mixed`
+`not_mixed`
 
-The owner is in one frame, but the problem includes both a path gap (how to package invocation) and an order gap (what counts as formal output).
+The invocation packet has downstream implementation work, but the QPI classification itself is centered on execution authenticity, role boundaries, formal-output legitimacy, and the no-simulation rule.
 
 ### 9. Governance Load
 
@@ -144,9 +169,29 @@ High. This case depends on audit authenticity, role boundary management, formal-
 - Should "formal_output: false" and "simulation-only" be named as expected downstream routing notes in the case digest?
 - Should this case be used as a no-simulation calibration example across other models, not only QPI?
 
+### 13. Owner Review Decision
+
+- Keep `classification: issue`; do not change to `mixed`.
+  - Invocation packet implementation is a downstream P task.
+  - The core scarcity is execution authenticity, formal-output legitimacy, role boundary, and no-simulation governance.
+  - Keep `path_or_resource_scarcity: medium` as a secondary scarcity.
+- Add expected downstream routing notes for later digest:
+  - `simulation_only: true`
+  - `formal_output: false`
+  - `excluded_from_synthesis: true`
+  - `blocked_until_real_invocation: true`
+- Use this as a cross-model no-simulation calibration example.
+  - It is not QPI-only.
+  - The rule also applies to writing-workbench, CCPE canonical agents, selector regression, and case preprocessing.
+  - Orchestrators must not present role-play or simulated reports as canonical agent output.
+
 ## Case qpi-draft-003: Chunk-First Distillation Produced Local Truth But Global Misread
 
-status: draft_owner_review_needed
+status: owner_reviewed
+
+owner_approved_for_digest: true
+
+digest_role: local_truth_global_structure_misframing_case
 
 source_path: `C:\Users\wangq\Documents\Codex\knowledge-vault\work\internal\强哥的思想宇宙\QPI案例分析\流程改造.md`
 
@@ -214,9 +259,23 @@ High. The case requires managing source fidelity, whole/part authority, human co
 - Is `dominant_scarcity=consensus_order` correct, or should the dominant scarcity be `path_resource` because the workflow lacked the right processing path?
 - Should "local truth impersonating global structure" become a named misframing risk in QPI?
 
+### 13. Owner Review Decision
+
+- Do not split this case.
+  - Chunk-first failure and whole-source gestalt remedy are one dynamic shift.
+- Keep `dominant_scarcity: consensus_order`.
+  - `path_resource` remains high, but the main issue is which layer has structural interpretation authority: whole-source gestalt, chunks, topic map, or human confirmation.
+- Add "local truth impersonating global structure" as a named QPI misframing risk.
+  - Chinese label: `局部真实冒充全局结构`.
+  - Treat it as a subtype under `violent_reduction` / `premature_classification`.
+
 ## Case qpi-draft-004: Material Distillation Needed Stop Gates, Not More Automation
 
-status: draft_owner_review_needed
+status: owner_reviewed
+
+owner_approved_for_digest: true
+
+digest_role: stop_gate_and_downstream_boundary_case
 
 source_path: `C:\Users\wangq\Documents\Codex\knowledge-vault\work\internal\强哥的思想宇宙\QPI案例分析\流程改造.md`
 
@@ -254,9 +313,9 @@ P -> I. The processing pipeline can be engineered, but deciding when not to cont
 
 ### 8. Mixed Or Multi-Perspective
 
-`intra_frame_mixed`
+`not_mixed`
 
-The same source-processing frame combines a solvable pipeline problem with an authority and stop-boundary problem.
+This case can generate downstream P implementation tasks, but the QPI classification itself is centered on stop rules, owner authorization, and downstream boundary control. Treat it as `issue_with_downstream_P_tasks` in prose, not as a separate enum value.
 
 ### 9. Governance Load
 
@@ -283,9 +342,33 @@ High. The case involves owner confirmation, downstream dependency control, preve
 - Should "do not automatically create writing project / model-mining" become an expected routing note?
 - Which owner confirmation gates should be represented in the eventual case digest?
 
+### 13. Owner Review Decision
+
+- Keep `classification: issue`; do not change to `mixed`.
+  - Pipeline implementation is downstream P work.
+  - The case is primarily about stop rules, owner authorization, and downstream boundary control.
+- Add expected routing notes for later digest:
+  - `do_not_auto_create_writing_project: true`
+  - `do_not_auto_start_model_mining: true`
+  - `requires_owner_authorization_for_downstream_transition: true`
+- Represent these owner confirmation gates in the eventual digest:
+  - whole-source gestalt confirmation;
+  - topic map canonicalization;
+  - material routing confirmation;
+  - topic docs generation boundary;
+  - writing-workbench transition gate;
+  - model-mining authorization gate;
+  - source-of-truth promotion gate.
+
 ## Case qpi-draft-005: Personal Workflow Redesign Looked Like P But Became P/I
 
-status: draft_owner_review_needed
+status: owner_reviewed
+
+owner_approved_for_digest: true
+
+digest_role: intra_frame_mixed_anchor_candidate
+
+selector_calibration_candidate: high_priority
 
 source_path: `C:\Users\wangq\Documents\Codex\knowledge-vault\work\internal\强哥的思想宇宙\QPI案例分析\流程改造.md`
 
@@ -352,9 +435,23 @@ Very high. The workflow has proxy stakeholders: present owner, future owner, fut
 - Should this become the anchor case for `intra_frame_mixed` in QPI contextual routing rules?
 - Should the eventual digest preserve "code has a compiler; process has no compiler" as a concise rationale, or is that too interpretive?
 
+### 13. Owner Review Decision
+
+- This case accurately captures the QPI update: Issue is sustained governance load, not only multi-person conflict.
+- Use this as an anchor candidate for `intra_frame_mixed` in QPI contextual routing rules.
+- Preserve the compiler/process rationale in revised form:
+  - A compiler provides relatively hard feedback for form, syntax, and some runtime constraints.
+  - A compiler does not guarantee that the system solves the real business problem.
+  - Cognitive workflow validation depends on owner judgment, audit, counterexamples, and calibration.
+  - Recommended digest wording: "Code at least has relatively hard formal feedback; cognitive workflows do not have an equivalent compiler."
+
 ## Case qpi-draft-006: Complexity Placement Gate
 
-status: draft_owner_review_needed
+status: owner_reviewed
+
+owner_approved_for_digest: true
+
+digest_role: complexity_placement_gate_case
 
 source_path: `C:\Users\wangq\Documents\Codex\knowledge-vault\work\internal\强哥的思想宇宙\QPI案例分析\流程改造.md`
 
@@ -421,3 +518,15 @@ High. The decision must be re-applied across future workflows, source types, wor
 - Should Complexity Placement Gate be represented as a QPI case, a separate model candidate, or both?
 - Should this case remain under QPI calibration, or should it later become evidence for another model in the library?
 - Are the listed value categories complete enough for an owner-reviewed case digest?
+
+### 13. Owner Review Decision
+
+- Represent Complexity Placement Gate as a QPI case in the current MVP phase.
+  - It may later become future model candidate evidence.
+  - Do not introduce a third model in this round.
+- Keep this case under QPI calibration for now.
+  - If a future process-complexity governance model or anti-overengineering model is created, this case can be reused as evidence.
+- The value categories are sufficient for owner-reviewed digest work, with three additions:
+  - stoppability / blocking value: when true execution is unavailable, the system can stop as blocked rather than produce fake artifacts;
+  - adjudicability / clear authority: when errors occur, the system can identify who has interpretation authority, confirmation authority, and veto authority;
+  - cost reasonableness / ROI: the purchased value must justify token, time, maintenance, and cognitive cost.

reports/model_case_preprocessing/qpi/round-01/year-end-review-academic-affairs.cases.md

@@ -1,6 +1,10 @@
 # QPI Case Drafts: Year-End Review Academic Affairs Function
 
-status: draft_owner_review_needed
+status: owner_reviewed
+
+owner_review_source: `C:\Users\wangq\Documents\Codex\knowledge-vault\work\internal\强哥的思想宇宙\QPI案例审阅\QPI提炼审核\year-end-review-academic-affairs.cases-GPT.md`
+
+owner_review_note: Owner review completed for all eight draft cases. The owner confirmed current anonymization is sufficient. The group-level center is that academic affairs treats compliance indicators, teaching outcomes, staffing ratios, academic output, digital tools, and safety controls as reportable artifacts rather than operating realities, causing multiple local Problems to accumulate into a system-level Issue.
 
 source_path: `[redacted external source path: owner-provided organizational CT slice]`
 
@@ -10,8 +14,16 @@ anonymization_note: People are represented as generic roles such as `decision_ma
 
 ## Case qpi-draft-001: Compliance Reporting Becomes Performative Evidence Construction
 
-status: draft_owner_review_needed
+status: owner_reviewed
 
+
+owner_approved_for_digest: true
+
+digest_role: ai_tool_evidence_legitimacy_regression_case
+
+regression_candidate: high_priority
+
+selector_calibration_candidate: high_priority
 source_path: `[redacted external source path: owner-provided organizational CT slice]`
 
 ### 1. Surface Problem
@@ -70,18 +82,34 @@ High. The case requires managing audit authenticity, review exposure, data linea
 - classification: mixed
 - dominant_scarcity: consensus_order
 - classification_confidence: medium
-- recommended_next_step: Separate legitimate evidence organization from fabricated evidence construction, then require a traceable evidence inventory before any tool-assisted material drafting.
+- recommended_next_step: Separate legitimate evidence organization from fabricated evidence construction, require a traceable evidence inventory before tool-assisted material drafting, and keep tool use inside evidence-boundary governance.
 
 ### 12. Owner Review Questions
 
-- Should this case emphasize `consensus_order` because it is about evidence legitimacy, or `data` because the triggering gap is missing reliable proof?
+- Should this case emphasize `consensus_order` because it is about evidence legitimacy, or `data` because the triggering gap is missing reliable proof? [answered: keep `consensus_order`; missing reliable proof is the trigger]
-- Should it become a selector calibration case for "AI or tool request that should not be treated as a simple execution task"?
+- Should it become a selector calibration case for "AI or tool request that should not be treated as a simple execution task"? [answered: yes]
-- Is the anonymization level sufficient, or should the external review context be generalized further?
+- Is the anonymization level sufficient, or should the external review context be generalized further? [answered: sufficient; no further generalization needed]
+
+### 13. Owner Review Decision
+
+- Keep `dominant_scarcity: consensus_order`.
+  - `data_scarcity` remains high because reliable evidence is missing.
+  - The core QPI issue is evidence legitimacy, audit authenticity, and tool boundary governance.
+- Keep `classification: mixed` because the same case contains data scarcity and governance scarcity.
+- Use as selector calibration and high-priority regression for AI/tool requests that must not be treated as simple execution.
+- Owner-approved wording: "AI can organize evidence, but must not manufacture the evidentiary relationship."
+- Current anonymization is sufficient.
 
 ## Case qpi-draft-002: Credential Metric Repair Creates Staffing Ratio Deadlock
 
-status: draft_owner_review_needed
+status: owner_reviewed
 
+
+owner_approved_for_digest: true
+
+digest_role: credential_metric_staffing_ratio_deadlock_calibration_case
+
+selector_calibration_candidate: high_priority
 source_path: `[redacted external source path: owner-provided organizational CT slice]`
 
 ### 1. Surface Problem
@@ -140,18 +168,34 @@ High. This requires ongoing management of staffing legitimacy, workload distribu
 - classification: mixed
 - dominant_scarcity: consensus_order
 - classification_confidence: medium
-- recommended_next_step: Treat the staffing metric as a P/I mixed case, model real workload absorption before further recruitment or reclassification, and identify which compliance path is legitimate rather than merely cosmetic.
+- recommended_next_step: Treat the staffing metric as a P/I mixed case triggered by external policy pressure, then test whether the organization is creating a staffing-ratio deadlock by prioritizing compliance value over real teaching-use value.
 
 ### 12. Owner Review Questions
 
-- Should the dominant scarcity be `path_resource` because the immediate blocker is role absorption, or `consensus_order` because the deeper risk is zero-sum governance?
+- Should the dominant scarcity be `path_resource` because the immediate blocker is role absorption, or `consensus_order` because the deeper risk is zero-sum governance? [answered: keep `consensus_order`; policy pressure is the trigger, path/resource absorption is direct blocker]
-- Should this case be merged with other staffing-ratio cases, or kept separate as an academic-affairs-specific example?
+- Should this case be merged with other staffing-ratio cases, or kept separate as an academic-affairs-specific example? [answered: keep separate and link to related staffing-ratio cases]
-- Does the phrase "credential metric" sufficiently anonymize the original compliance indicator?
+- Does the phrase "credential metric" sufficiently anonymize the original compliance indicator? [answered: yes]
+
+### 13. Owner Review Decision
+
+- Keep `classification: mixed` and `dominant_scarcity: consensus_order`.
+  - External policy adjustment is the trigger.
+  - Direct blockage is path/resource: staff are counted but courses, roles, workload, and capability models cannot absorb them.
+  - The deeper issue is governance/order: compliance value is substituted for real use value, producing staffing-ratio deadlock.
+- Do not merge with other staffing cases.
+  - Link it to related staffing-ratio cases, but keep it as an academic-affairs-specific resource-deadlock sample.
+- Current anonymization is sufficient.
 
 ## Case qpi-draft-003: Academic Output Incentive Becomes Integrity Backlash
 
-status: draft_owner_review_needed
+status: owner_reviewed
 
+
+owner_approved_for_digest: true
+
+digest_role: policy_memory_integrity_backlash_regression_case
+
+regression_candidate: high_priority
 source_path: `[redacted external source path: owner-provided organizational CT slice]`
 
 ### 1. Surface Problem
@@ -209,18 +253,34 @@ High. The organization must manage academic integrity, incentive transition, ret
 - classification: issue
 - dominant_scarcity: consensus_order
 - classification_confidence: medium
-- recommended_next_step: Frame this as incentive and trust repair, not only as policy cancellation. Separate future integrity rules from transitional handling of people affected by prior incentives.
+- recommended_next_step: Frame this as incentive integrity and trust repair, not policy cleanup. Separate future integrity rules from transitional handling of policy memory, trust debt, and people affected by prior incentives.
 
 ### 12. Owner Review Questions
 
-- Should this be classified as `issue` rather than `mixed`, given that the path to correction exists but legitimacy remains contested?
+- Should this be classified as `issue` rather than `mixed`, given that the path to correction exists but legitimacy remains contested? [answered: yes]
-- Should the draft explicitly include "policy memory" as a proxy stakeholder?
+- Should the draft explicitly include "policy memory" as a proxy stakeholder? [answered: yes; policy memory means historical commitments, sunk costs, trust debt, and behavioral inertia left by prior policy]
-- Is this case useful as a false-negative trap where a selector might under-call QPI because the surface request sounds like policy cleanup?
+- Is this case useful as a false-negative trap where a selector might under-call QPI because the surface request sounds like policy cleanup? [answered: yes]
+
+### 13. Owner Review Decision
+
+- Classify as `issue`, not ordinary `mixed`.
+  - A correction path exists, but the core scarcity is not how to cancel a policy.
+  - The old incentive created integrity risk, trust debt, historical commitments, and behavioral inertia.
+- Add `policy_memory` as a proxy stakeholder.
+  - It is not a person; it is the old policy's commitments, sunk cost, trust debt, and habits continuing to shape the system.
+- Use as a false-negative trap: surface policy cleanup should still call QPI when the real issue is incentive integrity and trust repair.
+- Recommended field: `classification_note: policy_repair_with_policy_memory_and_trust_debt`.
 
 ## Case qpi-draft-004: Strategic Alignment Is Replaced By Easier Program Packaging
 
-status: draft_owner_review_needed
+status: owner_reviewed
 
+
+owner_approved_for_digest: true
+
+digest_role: short_term_packaging_vs_long_term_strategy_calibration_case
+
+selector_calibration_candidate: high_priority
 source_path: `[redacted external source path: owner-provided organizational CT slice]`
 
 ### 1. Surface Problem
@@ -278,18 +338,35 @@ High. The case requires aligning strategy, incentives, execution capacity, exter
 - classification: issue
 - dominant_scarcity: consensus_order
 - classification_confidence: medium
-- recommended_next_step: Ask whose frame is being used. If the owner frame is strategic governance, treat as Issue; if the local execution frame is selected, first verify whether the easier path still satisfies strategic alignment.
+- recommended_next_step: Ask whose frame is active. Keep the role divergence visible, then test whether a resource-feasible compromise is being checked against long-term positioning or becoming short-term strategic myopia.
 
 ### 12. Owner Review Questions
 
-- Should this case be labeled `inter_viewpoint_divergence` because the same choice differs by role, or `intra_frame_mixed` because one organization contains both frames?
+- Should this case be labeled `inter_viewpoint_divergence` because the same choice differs by role, or `intra_frame_mixed` because one organization contains both frames? [answered: keep `inter_viewpoint_divergence` for QPI calibration strength]
-- Should the owner-expected judgment emphasize "strategic evasion" or "resource-feasible compromise"?
+- Should the owner-expected judgment emphasize "strategic evasion" or "resource-feasible compromise"? [answered: resource-feasible compromise can become strategic myopia if not tested against long-term positioning]
-- Is this a good calibration case for distinguishing local feasibility from organizational strategy?
+- Is this a good calibration case for distinguishing local feasibility from organizational strategy? [answered: calibrate short-term reportability/packaging versus long-term strategic planning, not generic local feasibility]
+
+### 13. Owner Review Decision
+
+- Keep `inter_viewpoint_divergence`.
+  - Decision layer sees strategic alignment.
+  - Execution layer sees reportability and application feasibility.
+  - Market-facing frame sees communication and enrollment value.
+  - Long-term organization frame sees strategic myopia risk.
+- Keep `classification: issue` and `dominant_scarcity: consensus_order`.
+- Owner-approved wording: "A resource-feasible compromise becomes strategic myopia if it is not tested against long-term positioning."
+- Use as calibration for short-term reportability or packaging substituting for long-term strategic planning.
 
 ## Case qpi-draft-005: Resource Reuse Proposal Collides With Operational Reality
 
-status: draft_owner_review_needed
+status: owner_reviewed
 
+
+owner_approved_for_digest: true
+
+digest_role: cross_boundary_resource_reuse_issue_case
+
+selector_calibration_candidate: supporting
 source_path: `[redacted external source path: owner-provided organizational CT slice]`
 
 ### 1. Surface Problem
@@ -344,21 +421,38 @@ High. Sustainable reuse requires role compatibility, scheduling authority, quali
 
 - classification_scope: multi_perspective
 - is_provisional: true
-- classification: mixed
+- classification: issue
-- dominant_scarcity: mixed
+- dominant_scarcity: consensus_order
 - classification_confidence: medium
-- recommended_next_step: Build a role-fit and schedule-fit test before treating surplus capacity as redeployable. If fit fails, do not classify the resistance as mere execution unwillingness.
+- recommended_next_step: Treat cross-boundary resource reuse as a role-boundary governance issue unless role fit, learner fit, schedule fit, quality standard, willingness, retraining cost, compensation, and pilot feedback are all evidenced.
 
 ### 12. Owner Review Questions
 
-- Should the classification be `mixed` or `issue`?
+- Should the classification be `mixed` or `issue`? [answered: issue; the decision-layer resource Problem is a violent reduction]
-- Should this be paired with the staffing ratio deadlock case, or does it represent a distinct resource reuse pattern?
+- Should this be paired with the staffing ratio deadlock case, or does it represent a distinct resource reuse pattern? [answered: pair but do not merge; this is cross-boundary resource reuse failure]
-- What minimum evidence would make redeployment a legitimate Problem rather than an Issue?
+- What minimum evidence would make redeployment a legitimate Problem rather than an Issue? [answered: role_fit, learner_fit, schedule_fit, quality_standard, willingness, retraining_cost, compensation, and pilot_feedback]
+
+### 13. Owner Review Decision
+
+- Classify as `issue`, not ordinary `mixed`.
+  - From the decision layer it looks like a resource reuse Problem.
+  - That is the violent reduction: different teaching objects, capability models, time structures, and quality responsibilities are compressed into "available capacity can be reused."
+- Pair with qpi-draft-002, but do not merge.
+  - qpi-draft-002 is staffing-ratio deadlock.
+  - qpi-draft-005 is cross-boundary resource reuse failure.
+- Redeployment can become a legitimate Problem only when evidence exists for role fit, learner fit, schedule fit, quality standard, willingness, retraining cost, compensation, and pilot feedback.
+- Owner note: university teachers may be considered for low-risk interest classes, but direct core-course redeployment is not valid without retraining and compensation.
 
 ## Case qpi-draft-006: Student Outcome Decline Is Reframed As Input Quality Excuse
 
-status: draft_owner_review_needed
+status: owner_reviewed
 
+
+owner_approved_for_digest: true
+
+digest_role: outcome_decline_quality_assurance_gap_regression_case
+
+regression_candidate: high_priority
 source_path: `[redacted external source path: owner-provided organizational CT slice]`
 
 ### 1. Surface Problem
@@ -416,18 +510,38 @@ High. The organization must manage outcome evidence, learner voice, quality assu
 - classification: mixed
 - dominant_scarcity: consensus_order
 - classification_confidence: medium
-- recommended_next_step: Separate input-condition analysis from management-lever analysis, then require a quality assurance map that links complaints, outcomes, process controls, and owner accountability.
+- recommended_next_step: Separate input-condition analysis from management-lever audit, then require a quality assurance map linking complaints, outcomes, process controls, owner accountability, and the limits of isolated achievements.
 
 ### 12. Owner Review Questions
 
-- Should this case be classified as `mixed` because data, path, and responsibility are all contested?
+- Should this case be classified as `mixed` because data, path, and responsibility are all contested? [answered: yes, with `consensus_order` as dominant scarcity]
-- Should isolated achievements be treated as evidence of latent capability or as masking signals?
+- Should isolated achievements be treated as evidence of latent capability or as masking signals? [answered: prioritize as masking signal; they may indicate local capability but cannot offset systemic decline]
-- What owner-approved wording should be used to avoid over-claiming causal responsibility?
+- What owner-approved wording should be used to avoid over-claiming causal responsibility? [answered: input conditions may affect outcomes but cannot replace audit of management levers]
+
+### 13. Owner Review Decision
+
+- Keep `classification: mixed` and `dominant_scarcity: consensus_order`.
+  - Data, path, and responsibility are all contested.
+  - The leading issue is whether learning quality is institutionally supported or whether academic affairs is treated as cost, revenue, or reporting function.
+- Treat isolated achievements primarily as masking signals.
+  - They may indicate local capability, but they cannot offset systemic outcome decline.
+- Owner-approved wording:
+  - "Input conditions may affect outcomes, but cannot replace audit of management levers."
+  - "Learner quality can explain part of the difficulty, but it cannot automatically exempt quality-assurance responsibility."
+  - "Isolated achievements can be local capability signals, but cannot offset systemic decline."
+  - "Current evidence indicates a quality assurance gap, but is insufficient to assign all causal responsibility to one function."
+- Recommended field: `classification_note: outcome_decline_with_contested_input_conditions_and_quality_assurance_gap`.
 
 ## Case qpi-draft-007: Digital Platform And Local AI Choice Becomes Governance Boundary Problem
 
-status: draft_owner_review_needed
+status: owner_reviewed
 
+
+owner_approved_for_digest: true
+
+digest_role: digital_governance_boundary_calibration_case
+
+selector_calibration_candidate: high_priority
 source_path: `[redacted external source path: owner-provided organizational CT slice]`
 
 ### 1. Surface Problem
@@ -485,18 +599,34 @@ High. The organization must maintain platform standards, data boundaries, lifecy
 - classification: issue
 - dominant_scarcity: consensus_order
 - classification_confidence: medium
-- recommended_next_step: Define decision criteria and authority before selecting tools. Treat the deployment choice as governance-bound technical strategy, not a simple platform preference.
+- recommended_next_step: Define digital governance criteria, authority, data boundaries, lifecycle responsibility, user adoption standards, and migration responsibility before comparing platform or AI deployment options.
 
 ### 12. Owner Review Questions
 
-- Should this case remain in QPI calibration, or does it overlap too much with generic technology strategy examples?
+- Should this case remain in QPI calibration, or does it overlap too much with generic technology strategy examples? [answered: keep in QPI calibration; tool choice is masking digital governance]
-- Should the dominant scarcity be `consensus_order` because criteria are contested, or `path_resource` because implementation cost is material?
+- Should the dominant scarcity be `consensus_order` because criteria are contested, or `path_resource` because implementation cost is material? [answered: `consensus_order`]
-- Is the local-vs-cloud distinction too specific and should it be further generalized?
+- Is the local-vs-cloud distinction too specific and should it be further generalized? [answered: no; keep it, but emphasize governance criteria rather than which option is better]
+
+### 13. Owner Review Decision
+
+- Keep in QPI calibration.
+  - This is not a generic technology preference case.
+  - Tool selection is masking missing management standards, data boundaries, lifecycle responsibility, adoption incentives, and digital governance level.
+- Keep `dominant_scarcity: consensus_order`.
+  - Path/resource cost exists, but the missing object is shared governance criteria and authority.
+- Local versus cloud detail can remain.
+- Owner-approved wording: "Define digital governance criteria before platform selection."
 
 ## Case qpi-draft-008: Public Safety Compliance Gap Reveals Bottom-Line Control Failure
 
-status: draft_owner_review_needed
+status: owner_reviewed
 
+
+owner_approved_for_digest: true
+
+digest_role: bottom_line_control_failure_regression_case
+
+regression_candidate: high_priority
 source_path: `[redacted external source path: owner-provided organizational CT slice]`
 
 ### 1. Surface Problem
@@ -554,10 +684,20 @@ High. The case requires defining approval authority, event risk classification,
 - classification: mixed
 - dominant_scarcity: consensus_order
 - classification_confidence: medium
-- recommended_next_step: Treat the event as a bottom-line control signal, not only a process mistake. Build a hard-gate event approval workflow and assign risk ownership before allowing similar activities.
+- recommended_next_step: Treat the event as a bottom-line control signal and a local P/system I mixed case. Build hard-gate approval, reporting, risk ownership, participant safety controls, and stop rules before allowing similar activities.
 
 ### 12. Owner Review Questions
 
-- Should this case be classified as `mixed` or direct `issue`?
+- Should this case be classified as `mixed` or direct `issue`? [answered: mixed, with `consensus_order` dominant]
-- Should it be included in QPI calibration even though it is less cognitively subtle and more operationally concrete?
+- Should it be included in QPI calibration even though it is less cognitively subtle and more operationally concrete? [answered: yes; concrete operational accidents can reveal bottom-line control failure]
-- What level of detail should remain after anonymization so the safety risk is still meaningful?
+- What level of detail should remain after anonymization so the safety risk is still meaningful? [answered: keep large activity, missing approval/reporting, external enforcement risk, participant safety risk, and bottom-line control failure]
+
+### 13. Owner Review Decision
+
+- This case refers to a large activity / event that lacked proper reporting, approval, and safety compliance controls.
+- Keep `classification: mixed` and `dominant_scarcity: consensus_order`.
+  - Local layer is P: missing approval, reporting, risk checklist, accountable owner, and hard stop rule.
+  - System layer is I: whether public safety, learner rights, and external compliance are treated as hard boundaries.
+- Include in QPI calibration and high-priority regression.
+  - Its value is testing whether QPI can identify a concrete operating accident as a bottom-line control failure rather than only a missing checklist.
+- Current anonymization is sufficient; preserve only large activity, missing approval/reporting, external enforcement risk, participant safety risk, and bottom-line control failure.

reports/model_case_preprocessing/qpi/round-01/year-end-review-development-office.cases.md

@@ -1,6 +1,10 @@
 # QPI Case Drafts: Year-End Review Planning Function
 
-status: draft_owner_review_needed
+status: owner_reviewed
+
+owner_review_source: `C:\Users\wangq\Documents\Codex\knowledge-vault\work\internal\强哥的思想宇宙\QPI案例审阅\QPI提炼审核\year-end-review-development-office.cases-GPT.md`
+
+owner_review_note: Owner review completed for all eight draft cases. Personal or cultural CT diagnosis notes are translated into QPI routing fields such as governance failure, target-resource inconsistency, compliance authenticity risk, role-authority mismatch, incentive credibility collapse, and low-cost indicator survival. This file is ready for incremental digest / calibration / selected regression processing.
 
 source_path: `[redacted external source path: owner-provided organizational CT slice]`
 
@@ -8,10 +12,16 @@ source_note: Owner-provided raw organizational material. These drafts are anonym
 
 anonymization_note: People are represented as roles such as `decision_maker`, `execution_lead`, `strategy_staff`, `functional_department`, and `frontline_staff`. The organization is represented as `the organization`; the department is represented as `planning function`. Sensitive details are generalized as `facility metric gap`, `staffing credential metric gap`, `compliance workaround risk`, `incentive backlash`, and `operational continuity risk`.
 
-## Case qpi-draft-001: Compliance Goal Becomes Compliance Workaround Risk
+## Case qpi-draft-001: Hard Resource Gap Disguised As Compliance Documentation
 
-status: draft_owner_review_needed
+status: owner_reviewed
 
+
+owner_approved_for_digest: true
+
+digest_role: hard_resource_gap_disguised_as_documentation_calibration_case
+
+regression_candidate: high_priority
 source_path: `[redacted external source path: owner-provided organizational CT slice]`
 
 ### 1. Surface Problem
@@ -70,18 +80,36 @@ High. The case requires managing audit authenticity, regulatory exposure, intern
 - classification: mixed
 - dominant_scarcity: consensus_order
 - classification_confidence: medium
-- recommended_next_step: Treat the facility metric gap as a P/I mixed case, separate legitimate remediation paths from compliance workaround risk, and ask the owner whether the intended QPI label should emphasize resource scarcity or governance failure.
+- classification_note: path_resource_trigger_with_compliance_governance_failure
+- recommended_next_step: Treat the facility metric gap as a P/I mixed case, separate legitimate remediation paths from compliance workaround risk, and keep dominant scarcity on governance/order rather than the triggering physical shortage.
 
 ### 12. Owner Review Questions
 
-- Should the dominant scarcity be `consensus_order` because of compliance workaround risk, or `path_resource` because the physical gap is the triggering constraint?
+- Should the dominant scarcity be `consensus_order` because of compliance workaround risk, or `path_resource` because the physical gap is the triggering constraint? [answered: keep `consensus_order`; physical shortage is the trigger, governance failure is the QPI scarcity]
-- Should this case become a selector calibration input for "hard resource gap disguised as documentation problem"?
+- Should this case become a selector calibration input for "hard resource gap disguised as documentation problem"? [answered: yes]
-- Is the draft sufficiently anonymized, or should the source relation to an external compliance milestone be further generalized?
+- Is the draft sufficiently anonymized, or should the source relation to an external compliance milestone be further generalized? [answered: sufficient for internal model-library review; future public use should generalize the qualification gate further]
+
+### 13. Owner Review Decision
+
+- Keep `dominant_scarcity: consensus_order`; do not change it to `path_resource`.
+  - Physical shortage is the trigger and keeps `path_or_resource_scarcity: high`.
+  - The QPI case centers on governance/order scarcity: the organization converts a hard resource gap into documentation and compliance packaging risk.
+- Translate upstream CT diagnosis into QPI routing language.
+  - Personal pathology or organizational culture notes are not QPI classification fields.
+  - QPI digest wording should use governance failure, compliance authenticity risk, and auditability risk.
+- Use as selector calibration for `hard_resource_gap_disguised_as_documentation_problem`.
+- Keep current anonymization for internal review. For external publication, generalize the external qualification gate and remove any remaining concrete source anchors.
 
 ## Case qpi-draft-002: Credential Metric Repair Creates Operational Continuity Risk
 
-status: draft_owner_review_needed
+status: owner_reviewed
 
+
+owner_approved_for_digest: true
+
+digest_role: credential_metric_operational_continuity_regression_case
+
+regression_candidate: high_priority
 source_path: `[redacted external source path: owner-provided organizational CT slice]`
 
 ### 1. Surface Problem
@@ -136,21 +164,36 @@ High. This case requires balancing compliance metrics, role-function fit, morale
 
 - classification_scope: subject_contextual
 - is_provisional: true
-- classification: mixed
+- classification: issue
 - dominant_scarcity: consensus_order
 - classification_confidence: medium
-- recommended_next_step: Frame the case as a staffing-governance Issue with a path/resource trigger, and ask whether the QPI output should explicitly mark `violent_reduction` when role-function fit is collapsed into credential count.
+- classification_note: credential_metric_problem_escalated_into_staffing_governance_issue
+- recommended_next_step: Frame operational continuity as the summary focus while preserving role mismatch, morale risk, labor risk, and credential-count reduction as the mechanism.
 
 ### 12. Owner Review Questions
 
-- Should this be treated as the clearest example of `violent_reduction` in this source?
+- Should this be treated as the clearest example of `violent_reduction` in this source? [answered: yes, one of the clearest examples]
-- Should the QPI case emphasize role mismatch, morale damage, compliance optics, or operational continuity?
+- Should the QPI case emphasize role mismatch, morale damage, compliance optics, or operational continuity? [answered: operational continuity as summary focus; role mismatch and morale/labor risk as mechanism]
-- Is `classification: issue` more appropriate than `classification: mixed` once the staffing path is chosen?
+- Is `classification: issue` more appropriate than `classification: mixed` once the staffing path is chosen? [answered: yes]
+
+### 13. Owner Review Decision
+
+- Keep this as one of the clearest `violent_reduction` examples from the source.
+- Promote `operational_continuity` as the summary focus.
+  - Preserve role mismatch, morale/labor risk, and credential-count reduction as the causal mechanism.
+- Change QPI judgment to `classification: issue`.
+  - The credential metric gap is a P trigger.
+  - The selected staffing path creates governance, role-boundary, continuity, and legitimacy risk.
+- Use as high-priority regression.
 
 ## Case qpi-draft-003: Incentive Backlash Misread As Lack of Effort
 
-status: draft_owner_review_needed
+status: owner_reviewed
 
+
+owner_approved_for_digest: true
+
+digest_role: performance_decline_incentive_backlash_calibration_case
 source_path: `[redacted external source path: owner-provided organizational CT slice]`
 
 ### 1. Surface Problem
@@ -189,7 +232,7 @@ I misread as P. The decision frame treats the issue as a manageable execution pr
 
 `inter_viewpoint_divergence`
 
-Different roles classify the same decline differently. `decision_maker` sees a Problem of mobilization; `frontline_staff` experience an Issue of unfair incentive structure; `planning function` sees a system loop.
+Different roles classify the same decline differently. `decision_maker` sees a Problem of mobilization; `frontline_staff` experience an Issue of unfair incentive structure; `planning function` sees a system loop. Owner review notes that an organization-level rewrite could also be `intra_frame_mixed`; this draft keeps the multi-perspective form because that is the stronger selector calibration value.
 
 ### 9. Governance Load
 
@@ -212,14 +255,25 @@ High. The case requires redesigning incentive credibility, cost coverage, trust,
 
 ### 12. Owner Review Questions
 
-- Should this be classified as `inter_viewpoint_divergence` because roles see different problems, or `intra_frame_mixed` because the organization has simultaneous incentive and path gaps?
+- Should this be classified as `inter_viewpoint_divergence` because roles see different problems, or `intra_frame_mixed` because the organization has simultaneous incentive and path gaps? [answered: organization-level rewrite could be `intra_frame_mixed`; keep current multi-role case as `inter_viewpoint_divergence` for calibration strength]
-- Is the main misframing `violent_reduction` from incentive structure to personal effort?
+- Is the main misframing `violent_reduction` from incentive structure to personal effort? [answered: yes; rooted in organizational culture and institutional design]
-- Should this be a strong selector calibration example for "performance decline with incentive backlash"?
+- Should this be a strong selector calibration example for "performance decline with incentive backlash"? [answered: yes]
+
+### 13. Owner Review Decision
+
+- Keep the current multi-role form as `inter_viewpoint_divergence` for selector calibration.
+  - Owner notes that an organization-level rewrite could be `intra_frame_mixed`, but the strongest calibration value here is that different roles see the same decline differently.
+- Mark the main misframing as `violent_reduction`: incentive structure and institutional design are reduced to individual effort.
+- Use as strong selector calibration for `performance_decline_with_incentive_backlash`.
 
 ## Case qpi-draft-004: Strategic Planning Function Reduced To Indicator Packaging
 
-status: draft_owner_review_needed
+status: owner_reviewed
 
+
+owner_approved_for_digest: true
+
+digest_role: strategic_function_role_authority_mismatch_case
 source_path: `[redacted external source path: owner-provided organizational CT slice]`
 
 ### 1. Surface Problem
@@ -274,21 +328,36 @@ High. The organization must decide whether the planning function has real strate
 
 - classification_scope: multi_perspective
 - is_provisional: true
-- classification: mixed
+- classification: issue
 - dominant_scarcity: consensus_order
 - classification_confidence: medium
-- recommended_next_step: Ask the owner to confirm whether this should become a QPI sample for role-authority mismatch: the function is blamed for strategy while governed as a packaging unit.
+- classification_note: strategic_role_without_strategic_operating_conditions
+- recommended_next_step: Use this as a QPI sample for role-authority mismatch: the function is blamed for strategy while governed as a packaging unit. Keep middle-management capability as a local P component, not the main classification.
 
 ### 12. Owner Review Questions
 
-- Should this be classified as `issue` rather than `mixed` because the role contradiction dominates?
+- Should this be classified as `issue` rather than `mixed` because the role contradiction dominates? [answered: yes; organizational culture/order problem dominates, with local P components around middle-leadership capability]
-- Does the case need a separate viewpoint table for `decision_maker`, `strategy_staff`, and `execution_lead`?
+- Does the case need a separate viewpoint table for `decision_maker`, `strategy_staff`, and `execution_lead`? [answered: no; preserve brief role contrast only]
-- Should the anonymized role `planning function` be made even broader for future publication safety?
+- Should the anonymized role `planning function` be made even broader for future publication safety? [answered: internal review can keep it; future public use may generalize to `strategic support function` or `functional planning unit`]
+
+### 13. Owner Review Decision
+
+- Change classification to `issue`.
+  - Middle-leadership capability can remain a local P component.
+  - The dominant scarcity is role-authority mismatch: the organization demands strategic output while denying strategic operating conditions.
+- Do not add a full role-viewpoint table.
+  - Preserve only concise role contrast needed for QPI routing.
+  - Person-level diagnosis belongs outside this QPI case.
+- Keep `planning function` for internal review. For public use, generalize to `strategic support function` or `functional planning unit`.
 
 ## Case qpi-draft-005: Low-Cost Ambition Creates Physical-Law Contradictions
 
-status: draft_owner_review_needed
+status: owner_reviewed
 
+
+owner_approved_for_digest: true
+
+digest_role: low_cost_ambition_pattern_level_issue_case
 source_path: `[redacted external source path: owner-provided organizational CT slice]`
 
 ### 1. Surface Problem
@@ -347,18 +416,37 @@ High. This requires confronting target-resource consistency, investment boundari
 - classification: issue
 - dominant_scarcity: consensus_order
 - classification_confidence: medium
-- recommended_next_step: Treat the pattern as an Issue about target-resource governance, not as a list of independent execution blockers.
+- case_level: pattern_level
+- subcases: qpi-draft-001, qpi-draft-002, qpi-draft-003, qpi-draft-004
+- not_first_wave_regression: true
+- recommended_next_step: Treat the pattern as an Issue about target-resource governance, not as a list of independent execution blockers. Use as digest / calibration rather than first-wave regression.
 
 ### 12. Owner Review Questions
 
-- Is this case too broad, or is it useful as a meta-case for the whole organizational slice?
+- Is this case too broad, or is it useful as a meta-case for the whole organizational slice? [answered: useful as whole-slice meta-case]
-- Should QPI allow a "pattern-level Issue" extracted from multiple surface Problems in one source?
+- Should QPI allow a "pattern-level Issue" extracted from multiple surface Problems in one source? [answered: yes, when the surface problems share the same generating mechanism]
-- Should this case be merged with the compliance workaround and staffing credential cases, or kept as a higher-level calibration sample?
+- Should this case be merged with the compliance workaround and staffing credential cases, or kept as a higher-level calibration sample? [answered: keep as higher-level digest / calibration sample; do not merge into narrow regression cases]
+
+### 13. Owner Review Decision
+
+- Retain as a whole-slice meta-case / `pattern-level Issue`.
+- QPI may extract a pattern-level Issue from multiple surface problems when they share a generating mechanism.
+  - Here the mechanism is `low-cost ambition / target-resource inconsistency / downstream contradiction absorption`.
+- Do not merge this into qpi-draft-001 or qpi-draft-002.
+  - Narrow cases are better regression candidates.
+  - This case is better suited to digest and calibration.
+- Mark as `not_first_wave_regression: true`.
 
 ## Case qpi-draft-006: Data Completeness Masks Truthfulness Gap
 
-status: draft_owner_review_needed
+status: owner_reviewed
 
+
+owner_approved_for_digest: true
+
+digest_role: data_completeness_truthfulness_gap_regression_case
+
+regression_candidate: high_priority
 source_path: `[redacted external source path: owner-provided organizational CT slice]`
 
 ### 1. Surface Problem
@@ -389,7 +477,7 @@ Q/P -> I. It begins as a data or documentation question: "What information is mi
 
 ### 7. Scarcity Profile
 
-- data_scarcity: medium
+- data_scarcity: low
 - path_or_resource_scarcity: medium
 - consensus_or_order_scarcity: high
 
@@ -416,18 +504,34 @@ High. The organization needs audit authenticity, evidence discipline, internal t
 - classification: issue
 - dominant_scarcity: consensus_order
 - classification_confidence: medium
-- recommended_next_step: Mark this as an Issue where evidence traceability and audit authenticity dominate; request owner confirmation before converting it into selector calibration.
+- evidence_integrity_gap: high
+- audit_authenticity_risk: high
+- truthfulness_gap: high
+- recommended_next_step: Run evidence authenticity audit before treating the case as a resource-planning problem.
 
 ### 12. Owner Review Questions
 
-- Should this case be used to test QPI's ability to distinguish "missing data" from "untrusted data"?
+- Should this case be used to test QPI's ability to distinguish "missing data" from "untrusted data"? [answered: yes]
-- Should the recommended next step be evidence audit rather than resource planning?
+- Should the recommended next step be evidence audit rather than resource planning? [answered: yes; resource planning may follow, but authenticity audit comes first]
-- Is `data_scarcity: medium` correct, or should it be `low` because the facts are known but politically inconvenient?
+- Is `data_scarcity: medium` correct, or should it be `low` because the facts are known but politically inconvenient? [answered: change to `low`; the gap is evidence integrity/truthfulness, not missing facts]
+
+### 13. Owner Review Decision
+
+- Use this as a strong regression case for distinguishing `missing data` from `untrusted data`.
+- Change `data_scarcity` to `low`.
+  - The core facts are mostly known but politically or organizationally inconvenient.
+  - The scarcity is evidence integrity, truthfulness, and audit authenticity.
+- Recommended next step is evidence authenticity audit before resource planning.
+- Add digest signals: `evidence_integrity_gap: high`, `audit_authenticity_risk: high`, and `truthfulness_gap: high`.
 
 ## Case qpi-draft-007: Execution Lead As Translator Of Impossible Commands
 
-status: draft_owner_review_needed
+status: owner_reviewed
 
+
+owner_approved_for_digest: true
+
+digest_role: role_boundary_workaround_normalization_supporting_case
 source_path: `[redacted external source path: owner-provided organizational CT slice]`
 
 ### 1. Surface Problem
@@ -464,9 +568,9 @@ P -> I. It begins as a Problem of execution under constraints. It becomes an Iss
 
 ### 8. Mixed Or Multi-Perspective
 
-`inter_viewpoint_divergence`
+`not_mixed`
 
-From `decision_maker`, the execution lead may look effective. From `frontline_staff`, the role may look coercive. From QPI, the same behavior reveals governance scarcity: the system lacks a legitimate channel for refusing impossible commands.
+With the subject fixed as `execution_lead`, the case is primarily a role-boundary governance issue. It may still serve as an auxiliary multi-viewpoint sample because different roles evaluate the same behavior differently, but its strongest use is not `inter_viewpoint_divergence`.
 
 ### 9. Governance Load
 
@@ -480,23 +584,40 @@ High. The case requires boundary rules for escalation, refusal, risk documentati
 
 ### 11. Candidate QPI Judgment
 
-- classification_scope: multi_perspective
+- classification_scope: role_contextual
+- evidence_status: owner_confirmed_from_interviews
 - is_provisional: true
 - classification: issue
 - dominant_scarcity: consensus_order
 - classification_confidence: medium
-- recommended_next_step: Use this case to test whether QPI can identify governance scarcity when a competent executor is converting impossible directives into risky action.
+- primary_risk: normalization_of_workaround / complicity_in_workaround
+- secondary_condition: lack_of_escalation_channel
+- recommended_next_step: Use this case to test whether QPI can identify governance scarcity when a competent executor converts impossible directives into normalized workaround action.
 
 ### 12. Owner Review Questions
 
-- Should this role-level case be kept, or is it too interpretive without more owner confirmation?
+- Should this role-level case be kept, or is it too interpretive without more owner confirmation? [answered: keep; owner has cross-checked through multiple participant conversations]
-- Is the main risk "complicity in workaround" or "lack of escalation channel"?
+- Is the main risk "complicity in workaround" or "lack of escalation channel"? [answered: complicity/normalization of workaround; lack of escalation channel is a condition]
-- Should this become a calibration sample for `inter_viewpoint_divergence`?
+- Should this become a calibration sample for `inter_viewpoint_divergence`? [answered: auxiliary only; stronger use is role-boundary governance with fixed execution-lead subject]
 
-## Case qpi-draft-008: External Review Pressure Turns Mission Into Indicator Survival
+### 13. Owner Review Decision
 
-status: draft_owner_review_needed
+- Keep the role-level case.
+  - Owner has cross-checked the pattern through multiple participant conversations.
+  - Mark `evidence_status: owner_confirmed_from_interviews`.
+- Main risk is `normalization_of_workaround / complicity_in_workaround`.
+  - Lack of escalation channel is a condition, not the primary risk.
+- Use as role-boundary governance support.
+  - It can support `inter_viewpoint_divergence`, but the stronger fixed-subject classification is `role_contextual / issue / consensus_order / not_mixed`.
 
+## Case qpi-draft-008: Low-Cost Indicator Survival Cannibalizes Real Capability
+
+status: owner_reviewed
+
+
+owner_approved_for_digest: true
+
+digest_role: umbrella_low_cost_indicator_survival_issue_case
 source_path: `[redacted external source path: owner-provided organizational CT slice]`
 
 ### 1. Surface Problem
@@ -514,8 +635,8 @@ The slice shows the organization treating the external review milestone as an ov
 ### 4. Expectation-Reality Gap
 
 - Expected: Passing the external milestone should validate organizational development.
-- Reality: The effort to pass the milestone may be destroying the real capabilities the milestone is supposed to measure.
+- Reality: The effort to pass the milestone exposes and amplifies internal low-investment governance failures that damage real operating capability.
-- Gap summary: The metric becomes detached from the mission and begins to cannibalize the system it was meant to improve.
+- Gap summary: External indicator pressure is a trigger, not the root cause; low-cost indicator survival cannibalizes real capability.
 
 ### 5. Attempted Paths
 
@@ -555,10 +676,23 @@ Very high. The case requires deciding how to balance survival pressure, truthful
 - classification: issue
 - dominant_scarcity: consensus_order
 - classification_confidence: medium
-- recommended_next_step: Treat this as the umbrella organization-level Issue and use the narrower cases as subcases. Owner should confirm whether this should be a calibration input or only a source-level summary case.
+- future_ct_relevance: true
+- current_scope: QPI case library only
+- recommended_next_step: Treat this as the umbrella organization-level Issue and use the narrower cases as subcases. Do not route to future CT work in this round.
 
 ### 12. Owner Review Questions
 
-- Should this umbrella case be retained, or should only the narrower pathology cases be promoted later?
+- Should this umbrella case be retained, or should only the narrower pathology cases be promoted later? [answered: retain as umbrella organization-level Issue / digest anchor]
-- Is "indicator survival cannibalizes mission capability" the correct anonymized abstraction?
+- Is "indicator survival cannibalizes mission capability" the correct anonymized abstraction? [answered: directionally correct, but revise to `low-cost indicator survival cannibalizes real capability`; external pressure exposes and amplifies internal low-investment governance failures]
-- Should this case be linked to future CT diagnosis model work rather than only QPI?
+- Should this case be linked to future CT diagnosis model work rather than only QPI? [answered: not in this round; mark only as future relevance while keeping current scope QPI]
+
+### 13. Owner Review Decision
+
+- Retain as an umbrella organization-level Issue and digest anchor.
+  - Do not let it replace narrower regression cases such as 001, 002, 003, and 006.
+- Revise abstraction from external-pressure causality to internal-governance causality.
+  - External review pressure is a trigger and accelerator.
+  - Internal low-investment, high-pressure, formalistic governance is the generating mechanism.
+  - Preferred abstraction: `low-cost indicator survival cannibalizes real capability`.
+- Do not route into future CT work in this round.
+  - Mark `future_ct_relevance: true` only as a note; current scope remains QPI.

reports/model_case_preprocessing/qpi/round-01/year-end-review-employment-entrepreneurship.cases.md

@@ -1,16 +1,20 @@
 # QPI Case Drafts: Year-End Review Employment Function
 
-status: draft_owner_review_needed
+status: owner_reviewed
 
 source_path: `[redacted external source path: owner-provided organizational CT slice]`
 
 source_note: Owner-provided raw organizational material. These drafts are anonymized and generalized for QPI review. Real or potentially identifying people, departments, institutions, timestamps, places, titles, exact numbers, and sensitive operational details have been removed or generalized. Ancient-style cognitive anchors from the source are intentionally omitted. These drafts are not selector JSON, regression cases, or owner-approved calibration data.
 
+owner_review_source: `C:/Users/wangq/Documents/Codex/knowledge-vault/work/internal/强哥的思想宇宙/QPI案例审阅/QPI提炼审核/year-end-review-employment-entrepreneurship.cases-GPT.md`
+
+owner_review_note: Owner/GPT review approved all eight cases for digest promotion. No additional anonymization required. Core pattern: employment outcomes as organizational survival proof can shift the employment function from service support into authority redesign; data credibility, delivery capacity, teaching legitimacy, and education value definition must be governed together.
+
 anonymization_note: People are represented as roles such as `decision_maker`, `execution_lead`, `employment_function`, `teaching_function`, `finance_function`, and `frontline_staff`. The organization is represented as `the organization`. Sensitive details are generalized as `outcome metric pressure`, `student pipeline`, `employer coordination risk`, `credential metric workaround`, `internal accounting mismatch`, `reverse accountability power`, and `compliance exposure`.
 
 ## Case qpi-draft-001: Outcome Metric Pressure Becomes Reverse Accountability Power
 
-status: draft_owner_review_needed
+status: owner_reviewed
 
 source_path: `[redacted external source path: owner-provided organizational CT slice]`
 
@@ -70,7 +74,7 @@ High. The case requires ongoing tradeoff among student outcomes, teaching author
 - classification: mixed
 - dominant_scarcity: consensus_order
 - classification_confidence: medium
-- recommended_next_step: Treat this as a P/I mixed case. Separate the operational question of how to improve outcomes from the governance question of who may legitimately evaluate and direct teaching work.
+- recommended_next_step: Separate outcome-improvement design from authority redesign. Define who may evaluate teaching, what evidence counts, and what checks limit reverse accountability power.
 
 ### 12. Owner Review Questions
 
@@ -78,9 +82,24 @@ High. The case requires ongoing tradeoff among student outcomes, teaching author
 - Does `reverse accountability power` capture the source pathology without exposing sensitive organizational details?
 - Should this become a selector calibration trap for cases where a hard metric hides authority redesign?
 
+### 13. Owner Review Decision
+
+- owner_review_status: owner_reviewed
+- owner_approved_for_digest: true
+- digest_role: hard_outcome_metric_authority_redesign_calibration_case
+- selector_calibration_candidate: high_priority
+- classification: mixed
+- dominant_scarcity: consensus_order
+- classification_note: outcome_improvement_problem_with_authority_redesign
+- owner_decision: 保留 mixed。既有教学内容、教师状态、课程与就业断裂等 Problem，也有就业办获得反向考核权后的组织权威重构。
+- owner_approved_terms:
+  - reverse accountability power
+  - hard outcome metric hiding authority redesign
+- processing_note: 进入 digest 和 selector calibration；用于测试硬就业指标是否掩盖 authority redesign。
+
 ## Case qpi-draft-002: Credential Metric Repair Becomes Compliance Exposure
 
-status: draft_owner_review_needed
+status: owner_reviewed
 
 source_path: `[redacted external source path: owner-provided organizational CT slice]`
 
@@ -140,7 +159,7 @@ High. The case requires managing external audit exposure, internal incentive dis
 - classification: mixed
 - dominant_scarcity: consensus_order
 - classification_confidence: medium
-- recommended_next_step: Identify which credential gaps are substantive capability gaps and which proposed repairs are compliance exposure. Do not classify the case as a simple procurement or staffing problem.
+- recommended_next_step: Treat credential repair as a compliance-legitimacy risk unless substantive integration into teaching, research, or student development is evidenced.
 
 ### 12. Owner Review Questions
 
@@ -148,9 +167,26 @@ High. The case requires managing external audit exposure, internal incentive dis
 - Are the generalized terms `credential metric workaround` and `compliance exposure` sufficiently anonymized?
 - Should future calibration require QPI to ask for evidence of substantive integration before accepting metric repair as a valid path?
 
+### 13. Owner Review Decision
+
+- owner_review_status: owner_reviewed
+- owner_approved_for_digest: true
+- digest_role: credential_metric_compliance_exposure_regression_case
+- regression_candidate: high_priority
+- classification: mixed
+- dominant_scarcity: consensus_order
+- classification_note: credential_gap_with_compliance_exposure
+- owner_decision: 保留 mixed。credential gap 是真实 path/resource gap，但通过挂靠、贸易化、外部标签化修补指标会制造 compliance exposure。
+- cross_link: academic_affairs_qpi_draft_002_staffing_ratio_deadlock
+- evidence_gap:
+  - substantive_integration_not_proven
+  - credential_holder_role_in_teaching_or_research_unknown
+  - compliance_review_boundary_unclear
+- processing_note: 与教务组师资比例僵局 cross-link，不合并；进入 digest、calibration 和 regression。
+
 ## Case qpi-draft-003: Internal Accounting Mismatch Inflates Functional Performance
 
-status: draft_owner_review_needed
+status: owner_reviewed
 
 source_path: `[redacted external source path: owner-provided organizational CT slice]`
 
@@ -208,9 +244,9 @@ High. The case requires financial standard alignment, credibility management, pe
 - classification_scope: subject_contextual
 - is_provisional: true
 - classification: mixed
-- dominant_scarcity: data
+- dominant_scarcity: consensus_order
 - classification_confidence: medium
-- recommended_next_step: First reconcile recognized financial data, then separately evaluate whether the function's claimed strategic importance is justified.
+- recommended_next_step: Reconcile financial recognition standards and reported metric lineage before using the figure as evidence of strategic value or authority expansion.
 
 ### 12. Owner Review Questions
 
@@ -218,9 +254,25 @@ High. The case requires financial standard alignment, credibility management, pe
 - Should this case be used to test QPI's ability to avoid accepting reported metrics at face value?
 - Does the anonymized phrasing remove enough source specificity?
 
+### 13. Owner Review Decision
+
+- owner_review_status: owner_reviewed
+- owner_approved_for_digest: true
+- digest_role: reported_metric_legitimacy_regression_case
+- regression_candidate: high_priority
+- classification: mixed
+- dominant_scarcity: consensus_order
+- classification_note: reported_metric_lineage_problem_as_performance_legitimacy_issue
+- owner_decision: 现场实质是为了述职会构造更好看的绩效数据；数据口径问题只是入口，核心是 performance legitimacy。
+- evidence_gap:
+  - recognized_financial_standard_unknown
+  - reported_metric_lineage_unverified
+  - department_accounting_basis_conflicts_with_group_standard
+- processing_note: 进入 digest、calibration 和 regression；测试 QPI 是否照单全收 reported metrics。
+
 ## Case qpi-draft-004: Outcome Promise Creates Student Pipeline Distortion
 
-status: draft_owner_review_needed
+status: owner_reviewed
 
 source_path: `[redacted external source path: owner-provided organizational CT slice]`
 
@@ -280,7 +332,7 @@ High. The case requires balancing recruitment pressure, student expectations, em
 - classification: mixed
 - dominant_scarcity: consensus_order
 - classification_confidence: medium
-- recommended_next_step: Require evidence that the promised outcome can be delivered before treating the issue as a recruitment or messaging problem.
+- recommended_next_step: Require delivery capacity, promise boundaries, outcome verification, and student-rights handling before treating outcome promises as legitimate recruitment strategy.
 
 ### 12. Owner Review Questions
 
@@ -288,9 +340,30 @@ High. The case requires balancing recruitment pressure, student expectations, em
 - Does the source imply a stronger `issue` judgment because the student promise changes institutional identity?
 - What context would be needed to distinguish legitimate outcome orientation from overpromising?
 
+### 13. Owner Review Decision
+
+- owner_review_status: owner_reviewed
+- owner_approved_for_digest: true
+- digest_role: overpromising_student_pipeline_regression_case
+- regression_candidate: high_priority
+- classification: mixed
+- dominant_scarcity: consensus_order
+- classification_note: external_promise_and_student_pipeline_distortion
+- owner_decision: 独立成案，不并入 Case 001。001 是内部权力倒置，004 是外部学生承诺和招生 pipeline 扭曲。
+- boundary_tests:
+  - delivery_capacity
+  - historical_outcome
+  - employer_commitment
+  - student_fit
+  - risk_disclosure
+  - verification
+  - complaint_or_refund_boundary
+- owner_approved_sentence: 结果导向只有在交付能力真实、承诺边界清楚时才是正当的。
+- processing_note: 进入 digest、calibration 和 regression；测试 outcome promise 与 overpromising 的边界。
+
 ## Case qpi-draft-005: High Outcome Data Masks Data Quality Risk
 
-status: draft_owner_review_needed
+status: owner_reviewed
 
 source_path: `[redacted external source path: owner-provided organizational CT slice]`
 
@@ -348,9 +421,9 @@ High. The case requires audit design, anti-gaming controls, student trust protec
 - classification_scope: subject_contextual
 - is_provisional: true
 - classification: mixed
-- dominant_scarcity: data
+- dominant_scarcity: consensus_order
 - classification_confidence: medium
-- recommended_next_step: Verify the production mechanism behind the outcome data before using it as evidence of institutional health or as a basis for stronger internal pressure.
+- recommended_next_step: Audit the production mechanism behind outcome data before using high metric values as evidence of institutional health.
 
 ### 12. Owner Review Questions
 
@@ -358,9 +431,31 @@ High. The case requires audit design, anti-gaming controls, student trust protec
 - Is this primarily a data scarcity case or an incentive governance case?
 - Should future calibration distinguish high metric value from high metric credibility?
 
+### 13. Owner Review Decision
+
+- owner_review_status: owner_reviewed
+- owner_approved_for_digest: true
+- digest_role: high_metric_value_low_credibility_regression_case
+- regression_candidate: high_priority
+- classification: mixed
+- dominant_scarcity: consensus_order
+- classification_note: outcome_metric_production_governance_problem
+- owner_decision: 主导稀缺不是普通 data scarcity，而是数据生产、加工、解释和使用机制的治理问题。
+- evidence_gap:
+  - outcome_data_production_mechanism
+  - student_level_verification
+  - employer_verification
+  - coercion_or_compliance_behavior_risk
+  - metric_use_in_authority_expansion
+- calibration_distinction:
+  - high_metric_value
+  - high_metric_credibility
+- owner_note: 在 I 域，高压 KPI 往往会制造其想要看到的数据；数据越被用于问责、招生、合规和权力扩张，越需要审计其生产机制。
+- processing_note: 进入 digest、calibration 和 regression。
+
 ## Case qpi-draft-006: Employer Coordination Asset Remains Isolated From Teaching
 
-status: draft_owner_review_needed
+status: owner_reviewed
 
 source_path: `[redacted external source path: owner-provided organizational CT slice]`
 
@@ -388,23 +483,23 @@ The apparent path is to list the external asset as proof of employment-oriented
 
 ### 6. Dynamic Shift
 
-P. It is mainly a Problem because the asset appears real and the key gap is an integration path. It may become an Issue if authority conflict between functions blocks integration.
+P -> mixed. It begins as a Problem because the asset appears real and the key gap is an integration path. It may become an Issue if authority conflict between functions blocks integration.
 
 ### 7. Scarcity Profile
 
 - data_scarcity: medium
 - path_or_resource_scarcity: high
-- consensus_or_order_scarcity: medium
+- consensus_or_order_scarcity: high
 
 ### 8. Mixed Or Multi-Perspective
 
-`not_mixed`
+`intra_frame_mixed`
 
-The primary scarcity is path/resource scarcity: how to connect employer assets to teaching and student capability. Governance risk exists, but it is not necessarily dominant unless internal authority conflict blocks integration.
+The primary scarcity remains path/resource scarcity: how to connect employer assets to teaching and student capability. It becomes mixed when the asset is used as proof material, internship credential, or authority asset rather than learning capability.
 
 ### 9. Governance Load
 
-Medium. The case requires coordination between functions, but the source suggests the asset itself may be healthy if connected to the learning system.
+Medium-high. The case requires coordination between functions and value-order judgment about whether the asset is used for capability building or merely for proof, display, and authority.
 
 ### 10. Misframing Risks
 
@@ -415,10 +510,10 @@ Medium. The case requires coordination between functions, but the source suggest
 
 - classification_scope: subject_contextual
 - is_provisional: true
-- classification: problem
+- classification: mixed
 - dominant_scarcity: path_resource
 - classification_confidence: medium
-- recommended_next_step: Ask for the operational bridge from employer asset to curriculum, student project, assessment, and outcome verification.
+- recommended_next_step: Ask for the operational bridge from employer asset to curriculum, projects, assessment, portfolio evidence, and verified learning outcomes.
 
 ### 12. Owner Review Questions
 
@@ -426,9 +521,31 @@ Medium. The case requires coordination between functions, but the source suggest
 - Is it useful as a positive contrast case where QPI should not over-escalate to Issue?
 - What minimum evidence would prove that the employer asset is truly integrated?
 
+### 13. Owner Review Decision
+
+- owner_review_status: owner_reviewed
+- owner_approved_for_digest: true
+- digest_role: real_external_asset_integration_boundary_case
+- selector_calibration_candidate: boundary_case
+- classification: mixed
+- dominant_scarcity: path_resource
+- classification_note: real_external_asset_with_unproven_learning_integration_and_governance_risk
+- owner_decision: 从 problem 改为边界型 mixed。若资源真实且只缺课程桥接是 Problem；但本来源中资源可能被用作展示资产、实习证明或述职材料，而非学生能力建设系统。
+- minimum_integration_evidence:
+  - curriculum_mapping
+  - student_project
+  - assessment_rubric
+  - mentor_input
+  - teacher_integration
+  - portfolio_evidence
+  - employer_feedback
+  - outcome_verification
+  - incentive_alignment
+- processing_note: 进入 digest 和 calibration；不作为纯正面对照，不进入首轮 regression。
+
 ## Case qpi-draft-007: Functional Performance Gains Justify Power Expansion Too Quickly
 
-status: draft_owner_review_needed
+status: owner_reviewed
 
 source_path: `[redacted external source path: owner-provided organizational CT slice]`
 
@@ -487,7 +604,7 @@ High. The case requires designing authority scope, checks and balances, conflict
 - classification: mixed
 - dominant_scarcity: consensus_order
 - classification_confidence: medium
-- recommended_next_step: Do not infer from functional performance that the function should own system-wide authority. Define scope, checks, and evidence standards before expanding control.
+- recommended_next_step: Do not infer authority transfer from asset recognition. Define scope, checks, and evidence standards before expanding control.
 
 ### 12. Owner Review Questions
 
@@ -495,9 +612,24 @@ High. The case requires designing authority scope, checks and balances, conflict
 - Does `malicious_inflation` apply, or is this better described as crisis-driven overextension?
 - Should QPI distinguish "asset recognition" from "authority transfer" as a recurring pattern?
 
+### 13. Owner Review Decision
+
+- owner_review_status: owner_reviewed
+- owner_approved_for_digest: true
+- digest_role: asset_recognition_to_authority_transfer_calibration_case
+- selector_calibration_candidate: high_priority
+- classification: mixed
+- dominant_scarcity: consensus_order
+- risk_tag: asset_recognition_to_authority_transfer
+- owner_decision: 独立保留，不与 Case 001 合并。malicious_inflation 适用：局部职能绩效被膨胀成系统级权威。
+- qpi_distinction:
+  - asset_recognition
+  - authority_transfer
+- processing_note: 进入 digest 和 selector calibration；用于区分承认资源成果与转移教学评价权/组织控制权。
+
 ## Case qpi-draft-008: Survival Strategy Reframes Education As Transactional Output
 
-status: draft_owner_review_needed
+status: owner_reviewed
 
 source_path: `[redacted external source path: owner-provided organizational CT slice]`
 
@@ -557,10 +689,26 @@ Very high. The case requires continuous governance of identity, incentives, comp
 - classification: issue
 - dominant_scarcity: consensus_order
 - classification_confidence: medium
-- recommended_next_step: Treat this as an Issue-level strategic governance case. Identify which survival tactics are reversible experiments and which would permanently alter institutional identity and trust.
+- recommended_next_step: Treat this as an Issue-level strategic governance case. Identify which survival tactics preserve education capability and which replace education value with transactional output metrics.
 
 ### 12. Owner Review Questions
 
 - Is this case too broad for calibration, or useful as an Issue anchor?
 - Should it be decomposed into several narrower P/I mixed cases?
 - What owner-approved wording should be used for the anonymized identity-shift risk?
+
+### 13. Owner Review Decision
+
+- owner_review_status: owner_reviewed
+- owner_approved_for_digest: true
+- digest_role: transactional_education_issue_anchor
+- selector_calibration_candidate: issue_anchor
+- classification: issue
+- dominant_scarcity: consensus_order
+- case_level: umbrella_issue
+- owner_decision: 保留为 Issue anchor，不拆。组织价值观在市场/营销第一与质量/产品服务第一之间的界定，本身是治理和协调过程。
+- owner_approved_wording:
+  - 组织在生存压力下，正在从教育能力建设滑向交易化输出逻辑。
+  - 就业、创收和合规指标可以是生存信号，但不能替代教育产品的真实质量。
+  - 风险不是重视就业本身，而是用就业/创收/合规指标接管教育价值定义。
+- processing_note: 进入 digest 和 calibration，作为本组 Issue anchor；不拆分为更窄 case。

reports/model_case_preprocessing/qpi/round-01/year-end-review-engineering-center.cases.md

@@ -1,14 +1,18 @@
 # QPI Case Drafts: Year-End Review Technical Function
 
-status: draft_owner_review_needed
+status: owner_reviewed
 
 source_path: `<owner-provided QPI raw source path; redacted for anonymization>`
 
+owner_review_source: `C:/Users/wangq/Documents/Codex/knowledge-vault/work/internal/强哥的思想宇宙/QPI案例审阅/QPI提炼审核/year-end-review-engineering-center.cases-GPT.md`
+
+owner_review_note: Owner/GPT review approved all eight cases for digest promotion. No additional anonymization required. Core pattern: a support-oriented technical unit is forced into industrialized revenue-center logic without validated demand, operator capability, lawful staffing paths, or target authenticity.
+
 anonymization_note: Real names, ancient-style cognitive-anchor names, organization names, places, timestamps, titles, exact figures, and sensitive operational details have been generalized. This draft preserves only the QPI-relevant structure of the organizational pathology.
 
 ## Case qpi-draft-eng-001: Strategic Target Exceeds Operating Reality
 
-status: draft_owner_review_needed
+status: owner_reviewed
 
 source_path: `<owner-provided QPI raw source path; redacted for anonymization>`
 
@@ -68,16 +72,34 @@ High. The case requires ongoing target governance, metric authenticity checks, p
 - classification: mixed
 - dominant_scarcity: consensus_order
 - classification_confidence: medium
-- recommended_next_step: Reframe the target as a staged capability-and-market validation problem before accepting it as an execution target.
+- recommended_next_step: Reframe the target as staged capability, market, resource, and validation bridge-building before accepting it as an execution target.
 
 ### 12. Owner Review Questions
 
 - Should this case be judged as `issue` rather than `mixed` because the dominant risk is target governance?
 - Should the target-authenticity problem become a reusable QPI calibration pattern?
 
+### 13. Owner Review Decision
+
+- owner_review_status: owner_reviewed
+- owner_approved_for_digest: true
+- digest_role: target_authenticity_gap_regression_case
+- regression_candidate: high_priority
+- classification: mixed
+- dominant_scarcity: consensus_order
+- classification_note: capability_and_market_gap_under_inauthentic_target_pressure
+- reusable_pattern: target_authenticity_gap
+- owner_decision: 保留 mixed，不升为纯 issue。这里确实有能力、市场、设备、人员、工艺、交付路径等真实 P，但主导风险是目标治理。
+- owner_approved_distinction:
+  - milestone_target
+  - terminal_target
+  - bridge_evidence
+- owner_approved_wording: 高目标不是问题；没有能力—市场—资源—验证桥梁的高目标，才会变成组织造假压力。
+- processing_note: 进入 digest、calibration 和 regression；用于测试目标真实性缺口。
+
 ## Case qpi-draft-eng-002: Equipment-Led Solutionism Without Market Closure
 
-status: draft_owner_review_needed
+status: owner_reviewed
 
 source_path: `<owner-provided QPI raw source path; redacted for anonymization>`
 
@@ -136,16 +158,38 @@ High. The case requires procurement gates, demand validation, safety boundaries,
 - classification: mixed
 - dominant_scarcity: consensus_order
 - classification_confidence: medium
-- recommended_next_step: Require demand proof, operator readiness, and safety validation before asset purchase.
+- recommended_next_step: Treat equipment purchase as gated by demand proof, operator readiness, safety validation, unit economics, and pilot results.
 
 ### 12. Owner Review Questions
 
 - Is `tool_solutionism` the primary misframing risk here?
 - Should QPI recommend a hard no-go gate when demand and operator readiness are both absent?
 
+### 13. Owner Review Decision
+
+- owner_review_status: owner_reviewed
+- owner_approved_for_digest: true
+- digest_role: equipment_led_solutionism_regression_case
+- regression_candidate: high_priority
+- classification: mixed
+- dominant_scarcity: consensus_order
+- risk_tags:
+  - equipment_led_solutionism
+  - asset_first_solutionism
+- owner_decision: 提炼成立。核心不是设备选型，而是组织把设备购买当成市场、能力、流程和安全体系的替代品。
+- routing_note: QPI 不替 owner 做采购否决，但可输出 `do_not_treat_as_execution_problem_until_gates_passed`。
+- gate_conditions:
+  - demand_proof
+  - operator_readiness
+  - safety_validation
+  - unit_economics
+  - pilot_result
+- owner_approved_wording: 先验证需求和操作者，再谈设备；否则设备不是能力，而是沉没成本制造机。
+- processing_note: 进入 digest、calibration 和 regression。
+
 ## Case qpi-draft-eng-003: Compliance Shortcut Becomes Structural Constraint
 
-status: draft_owner_review_needed
+status: owner_reviewed
 
 source_path: `<owner-provided QPI raw source path; redacted for anonymization>`
 
@@ -204,16 +248,32 @@ High. The organization needs stable staffing policy, compliance review, budget r
 - classification: issue
 - dominant_scarcity: consensus_order
 - classification_confidence: medium
-- recommended_next_step: Treat staffing as a compliance-governance constraint, not as a simple headcount patch.
+- recommended_next_step: Treat this as shortcut debt meeting a hard boundary, not as a simple headcount or compliance patch.
 
 ### 12. Owner Review Questions
 
 - Should this be a canonical example of `issue` caused by compliance boundary hardening?
 - Should QPI require a separate compliance-risk field for cases like this?
 
+### 13. Owner Review Decision
+
+- owner_review_status: owner_reviewed
+- owner_approved_for_digest: true
+- digest_role: shortcut_debt_hard_boundary_issue_anchor
+- selector_calibration_candidate: issue_anchor
+- classification: issue
+- dominant_scarcity: consensus_order
+- classification_note: shortcut_debt_meets_hard_boundary
+- owner_decision: 保留 issue，但不命名为 compliance boundary hardening 的典型案例。更准确是长期用 P 式短路方法处理 I，最后撞上监管、事故、审计或组织信任硬边界。
+- optional_risk_flags:
+  - compliance_legitimacy_risk: high
+  - audit_exposure: high
+  - shortcut_debt: high
+- processing_note: 进入 digest 和 calibration；作为 Issue anchor，不新增 QPI 通用必填字段。
+
 ## Case qpi-draft-eng-004: Credential Integrity Treated As Mere Usability
 
-status: draft_owner_review_needed
+status: owner_reviewed
 
 source_path: `<owner-provided QPI raw source path; redacted for anonymization>`
 
@@ -272,16 +332,35 @@ High. The case requires a durable rule for credential verification, exception ha
 - classification: issue
 - dominant_scarcity: consensus_order
 - classification_confidence: medium
-- recommended_next_step: Convert the incident into a screening and exception-policy review before making a convenience-based staffing decision.
+- recommended_next_step: Convert the incident into a screening, exception-policy, and risk-ownership review without making a specific personnel verdict.
 
 ### 12. Owner Review Questions
 
 - Should this case be linked to QPI's no-call boundary against making specific personnel judgments?
 - Is the key QPI lesson about evidence integrity, compliance order, or both?
 
+### 13. Owner Review Decision
+
+- owner_review_status: owner_reviewed
+- owner_approved_for_digest: true
+- digest_role: credential_integrity_policy_regression_case
+- regression_candidate: high_priority
+- classification: issue
+- dominant_scarcity: consensus_order
+- risk_tag: credential_integrity_treated_as_usability
+- no_personnel_verdict: true
+- route_to_policy_review_not_person_judgment: true
+- owner_decision: 保留，但必须与 QPI 的 no-call/personnel-verdict 边界谨慎关联。QPI 不判断具体人员是否可用、是否造假或是否应辞退，只判断组织如何处理资质异常、例外规则和风险归属。
+- evidence_gap:
+  - credential_verification_lineage
+  - exception_policy_unknown
+  - risk_owner_unknown
+- owner_approved_wording: 资质异常不是“这个人还能不能临时用”的问题，而是组织筛查系统是否还能被信任的问题。
+- processing_note: 进入 digest、calibration 和 regression。
+
 ## Case qpi-draft-eng-005: Production Capability Without Acquisition Channel
 
-status: draft_owner_review_needed
+status: owner_reviewed
 
 source_path: `<owner-provided QPI raw source path; redacted for anonymization>`
 
@@ -315,7 +394,7 @@ This begins as a Question: where do orders come from? It becomes a Problem when
 
 - data_scarcity: high
 - path_or_resource_scarcity: high
-- consensus_or_order_scarcity: medium
+- consensus_or_order_scarcity: high
 
 ### 8. Mixed Or Multi-Perspective
 
@@ -338,18 +417,39 @@ Medium. Governance load rises if the organization continues to impose revenue ta
 - classification_scope: subject_contextual
 - is_provisional: true
 - classification: mixed
-- dominant_scarcity: data
+- dominant_scarcity: consensus_order
 - classification_confidence: medium
-- recommended_next_step: Validate demand source and acquisition channel before committing to revenue targets or equipment expansion.
+- recommended_next_step: Clarify subject purpose, customer segment, demand signal, acquisition channel, delivery fit, and unit economics before treating production capability as business viability.
 
 ### 12. Owner Review Questions
 
 - Should this be classified as `question` first because the missing demand source blocks all later action?
 - What minimal evidence would move this from Q to P?
 
+### 13. Owner Review Decision
+
+- owner_review_status: owner_reviewed
+- owner_approved_for_digest: true
+- digest_role: production_without_market_closure_regression_case
+- regression_candidate: high_priority
+- classification: mixed
+- dominant_scarcity: consensus_order
+- classification_note: market_source_unknown_because_business_purpose_is_misframed_as_production_capacity
+- owner_decision: 不建议首先分类为 question。对学生或研究者，订单来源可以是 Q；但对集团经营主体，生产能力没有消费/市场/盈利闭环，是组织第一性错位。
+- minimum_q_to_p_evidence:
+  - problem_owner
+  - primary_purpose
+  - customer_segment
+  - demand_signal
+  - acquisition_channel
+  - delivery_fit
+  - unit_economics
+- owner_note: 作为研究，可以先忽略市场做投入；作为集团经营目标，忽略市场而只谈生产，就是本末倒置。
+- processing_note: 进入 digest、calibration 和 regression；测试生产能力不等于商业闭环。
+
 ## Case qpi-draft-eng-006: Micro-Intervention Creates Execution Fatigue
 
-status: draft_owner_review_needed
+status: owner_reviewed
 
 source_path: `<owner-provided QPI raw source path; redacted for anonymization>`
 
@@ -408,16 +508,41 @@ High. The organization needs explicit decision lanes, escalation rules, and prot
 - classification: issue
 - dominant_scarcity: consensus_order
 - classification_confidence: medium
-- recommended_next_step: Diagnose decision-rights architecture before blaming execution motivation.
+- recommended_next_step: Diagnose decision-rights architecture and distinguish healthy hands-on leadership from destructive micro-control before blaming execution motivation.
 
 ### 12. Owner Review Questions
 
 - Should this case be used as a violent-reduction example: "people are unmotivated" masking authority-design failure?
 - What evidence would distinguish healthy hands-on leadership from destructive micro-control?
 
+### 13. Owner Review Decision
+
+- owner_review_status: owner_reviewed
+- owner_approved_for_digest: true
+- digest_role: execution_fatigue_decision_rights_calibration_case
+- selector_calibration_candidate: high_priority
+- classification: issue
+- dominant_scarcity: consensus_order
+- misclassification_pattern: violent_reduction
+- owner_decision: 可作为 violent_reduction 示例，但必须区分健康亲自下场与破坏性微操。错误降维是把执行疲劳解释成“人没有动力/不主动”，却忽略决策权设计和权威干预造成的系统性疲劳。
+- distinction:
+  - outsider_leading_experts
+  - expert_strong_leader_with_system_view
+- evidence_to_distinguish:
+  - domain_competence
+  - decision_accuracy
+  - autonomy_preservation
+  - feedback_loop
+  - bottleneck_effect
+  - learning_effect
+  - error_ownership
+  - business_fit
+- owner_approved_wording: 健康下场会增加系统判断力；破坏性微操会吞掉执行者的判断权。
+- processing_note: 进入 digest 和 calibration；不进入首轮 regression。
+
 ## Case qpi-draft-eng-007: Inherited Project May Be Hidden Liability
 
-status: draft_owner_review_needed
+status: owner_reviewed
 
 source_path: `<owner-provided QPI raw source path; redacted for anonymization>`
 
@@ -476,16 +601,33 @@ Medium. The organization needs transfer due diligence, cost accounting, and resp
 - classification: mixed
 - dominant_scarcity: data
 - classification_confidence: medium
-- recommended_next_step: Investigate transfer history, operating cost, and realistic value before treating the project as a confirmed asset.
+- recommended_next_step: Investigate transfer history, cost structure, responsibility boundary, and prior owner exit reason before treating the project as a confirmed asset.
 
 ### 12. Owner Review Questions
 
 - Should this be a QPI calibration sample for "asset or liability" ambiguity?
 - Is the main lesson adverse selection, missing data, or organizational dumping?
 
+### 13. Owner Review Decision
+
+- owner_review_status: owner_reviewed
+- owner_approved_for_digest: true
+- digest_role: inherited_asset_liability_calibration_case
+- selector_calibration_candidate: high_priority
+- classification: mixed
+- dominant_scarcity: data
+- classification_note: inherited_asset_may_hide_operating_liability
+- reusable_pattern: asset_or_liability_ambiguity
+- owner_decision: 作为资产/负债歧义校准样本保留。Owner 的理解是缺乏专业人员指导贸然进入新领域会踩坑；Codex 的 missing data / adverse selection / organizational dumping 可保留并翻译。
+- translated_risk_chain:
+  - missing_data: 不知道转移历史、成本收益和责任边界。
+  - adverse_selection: 强势部门放弃本身就是风险信号。
+  - organizational_dumping: 强势部门可能把低收益、高维护、难执行的项目甩给弱势部门。
+- processing_note: 进入 digest 和 calibration；不进入首轮 regression。
+
 ## Case qpi-draft-eng-008: Personnel Redeployment Without Legitimate Path
 
-status: draft_owner_review_needed
+status: owner_reviewed
 
 source_path: `<owner-provided QPI raw source path; redacted for anonymization>`
 
@@ -544,9 +686,36 @@ High. The case requires legal review, budget planning, role transition design, a
 - classification: issue
 - dominant_scarcity: consensus_order
 - classification_confidence: medium
-- recommended_next_step: Define lawful redeployment and hiring boundaries before treating staff mismatch as an execution-only problem.
+- recommended_next_step: Define lawful, budgeted, and capability-oriented personnel transition paths before treating staff mismatch as an execution-only problem.
 
 ### 12. Owner Review Questions
 
 - Should this case be merged with the compliance staffing case or kept separate as a personnel-transition governance case?
 - What minimum context is needed to avoid overclaiming legal or labor-risk conclusions?
+
+### 13. Owner Review Decision
+
+- owner_review_status: owner_reviewed
+- owner_approved_for_digest: true
+- digest_role: personnel_transition_governance_issue_anchor
+- selector_calibration_candidate: issue_anchor
+- classification: issue
+- dominant_scarcity: consensus_order
+- classification_note: capability_upgrade_requires_legitimate_personnel_transition_path
+- owner_decision: 单独保留，不与合规人员配置案例合并。本案例关注技术方向变化后旧人员如何合法、有效、有预算地过渡。
+- owner_note: 类似传统软件公司转型 AI 开发公司；旧工程师转型不是换工具，而是认知框架、技术栈、开发方法、工具链和评价方式的整体迁移。
+- legal_boundary_note:
+  - requires_legal_review
+  - legal_labor_risk_context_needed
+- minimum_context:
+  - employment_status
+  - contract_terms
+  - performance_record
+  - redeployment_option
+  - training_offer
+  - compensation_budget
+  - consultation_process
+  - compliance_review
+  - operational_need
+  - dignity_and_trust_cost
+- processing_note: 进入 digest 和 calibration；作为人员转型治理 Issue anchor。

reports/model_case_preprocessing/qpi/round-01/year-end-review-international-college.cases.md

@@ -1,14 +1,18 @@
 # QPI Case Drafts: Year-End Review, Cross-Border Education Function
 
-status: draft_owner_review_needed
+status: owner_reviewed
 
 source_path: `[redacted owner-provided raw source path: organization CT slice]`
 
+owner_review_source: `C:/Users/wangq/Documents/Codex/knowledge-vault/work/internal/强哥的思想宇宙/QPI案例审阅/QPI提炼审核/year-end-review-international-college.cases-GPT.md`
+
+owner_review_note: Owner/GPT review approved all eight cases for digest promotion. No additional anonymization required. Core pattern: a fast-growing international function turns enrollment, external channels, pricing, capacity, credentials, and titles into growth proof before compliance, trust, delivery capacity, and authority boundaries are fully governed.
+
 anonymization_note: Real names, ancient-style cognitive-anchor names, organization names, places, timestamps, titles, exact numbers, and sensitive operational details have been generalized. These drafts are for owner review only and must not be promoted to JSON, selector calibration, or regression assets before owner confirmation.
 
 ## Case qpi-draft-intl-001: Compliance Risk Packaged As Enrollment Retention
 
-status: draft_owner_review_needed
+status: owner_reviewed
 
 source_path: `[redacted owner-provided raw source path: organization CT slice]`
 
@@ -65,10 +69,10 @@ High. The case requires risk containment, role boundary clarification, audit aut
 
 - classification_scope: subject_contextual
 - is_provisional: true
-- classification: mixed
+- classification: issue
 - dominant_scarcity: consensus_order
 - classification_confidence: medium
-- recommended_next_step: Separate retention problem-solving from compliance judgment; confirm hard red lines before designing any replacement pathway.
+- recommended_next_step: Separate retention pressure from compliance judgment; confirm hard red lines before designing any replacement pathway.
 
 ### 12. Owner Review Questions
 
@@ -76,9 +80,28 @@ High. The case requires risk containment, role boundary clarification, audit aut
 - Should this be treated as Issue rather than mixed because the compliance boundary dominates?
 - Which details, if any, are safe enough to retain in a future owner-approved case digest?
 
+### 13. Owner Review Decision
+
+- owner_review_status: owner_reviewed
+- owner_approved_for_digest: true
+- digest_role: compliance_boundary_retention_issue_regression_case
+- regression_candidate: high_priority
+- classification: issue
+- dominant_scarcity: consensus_order
+- classification_note: retention_workaround_crosses_compliance_boundary
+- owner_decision: 从 mixed 上调为 issue。路径/资源缺口存在，但招生留存手段一旦改变机构合规姿态，就不再是普通招生 Problem。
+- safe_digest_details:
+  - enrollment_retention_pressure
+  - pathway_adjustment_mechanism
+  - compliance_red_line
+  - credential_trust
+  - future_complaint_or_audit_risk
+- owner_approved_wording: 招生留存不是不能做；问题是留存手段一旦改变机构的合规姿态，就不再是普通招生 Problem，而是 Issue。
+- processing_note: 进入 digest、calibration 和 regression。
+
 ## Case qpi-draft-intl-002: Physical Capacity Treated As Negotiable Resource
 
-status: draft_owner_review_needed
+status: owner_reviewed
 
 source_path: `[redacted owner-provided raw source path: organization CT slice]`
 
@@ -137,7 +160,7 @@ High. The case requires a hard capacity gate, cross-functional arbitration, comm
 - classification: mixed
 - dominant_scarcity: path_resource
 - classification_confidence: medium
-- recommended_next_step: Establish a verified delivery-capacity gate before allowing further promises, then decide whether resource conflict requires governance escalation.
+- recommended_next_step: Establish a verified hard capacity gate and cross-unit arbitration rule before allowing further enrollment promises.
 
 ### 12. Owner Review Questions
 
@@ -145,9 +168,27 @@ High. The case requires a hard capacity gate, cross-functional arbitration, comm
 - Is the key failure over-promising, cross-unit conflict, or the absence of a hard capacity gate?
 - Should this case be paired with a no-call selector trap about simple logistics requests?
 
+### 13. Owner Review Decision
+
+- owner_review_status: owner_reviewed
+- owner_approved_for_digest: true
+- digest_role: capacity_gate_cross_unit_conflict_regression_case
+- regression_candidate: high_priority
+- classification: mixed
+- dominant_scarcity: path_resource
+- classification_note: cross_unit_conflict_under_missing_hard_capacity_gate
+- owner_decision: 主导稀缺保留 path_resource。硬约束是物理容量、宿舍、床位、配套服务和交付能力；但挤占其他单元资源会形成 P/I mixed。
+- key_failure_chain:
+  - hard_capacity_gap
+  - cross_unit_conflict
+  - missing_hard_capacity_gate
+  - over_promising_and_delivery_risk
+- selector_pairing_note: 可配对 no-call trap，区分简单排床位执行与容量治理问题。
+- processing_note: 进入 digest、calibration 和 regression。
+
 ## Case qpi-draft-intl-003: Performance-Backed Role Inflation
 
-status: draft_owner_review_needed
+status: owner_reviewed
 
 source_path: `[redacted owner-provided raw source path: organization CT slice]`
 
@@ -206,7 +247,7 @@ High. The organization must manage role boundaries, incentive legitimacy, succes
 - classification: issue
 - dominant_scarcity: consensus_order
 - classification_confidence: medium
-- recommended_next_step: Define a rule-based authority and accountability package before granting status; avoid converting personal leverage directly into structural power.
+- recommended_next_step: Define a rule-based authority and accountability package before converting performance leverage into structural power.
 
 ### 12. Owner Review Questions
 
@@ -214,9 +255,27 @@ High. The organization must manage role boundaries, incentive legitimacy, succes
 - Should this case include proxy stakeholders such as future management, adjacent units, and external partners?
 - Is the classification too confidently Issue without more context from the organization owner?
 
+### 13. Owner Review Decision
+
+- owner_review_status: owner_reviewed
+- owner_approved_for_digest: true
+- digest_role: performance_backed_role_inflation_calibration_case
+- selector_calibration_candidate: high_priority
+- classification: issue
+- dominant_scarcity: consensus_order
+- classification_confidence: medium
+- abstraction: performance_backed_role_inflation
+- owner_decision: “以业绩为背书的角色膨胀”是正确抽象；“有权力、无问责”可作为风险后果，但不是最佳标题。涉及权力、头衔、资源分配、组织身份和对外代表权，分类为 Issue 不算过于自信。
+- affected_stakeholders:
+  - future_management
+  - adjacent_units
+  - external_partners
+- owner_approved_wording: 业绩可以获得认可，但不能直接兑换成不受规则约束的结构性权力。
+- processing_note: 进入 digest 和 calibration。
+
 ## Case qpi-draft-intl-004: Strategic Chain Collapsed Into Front-End Sales
 
-status: draft_owner_review_needed
+status: owner_reviewed
 
 source_path: `[redacted owner-provided raw source path: organization CT slice]`
 
@@ -275,7 +334,7 @@ High. The organization must decide what business it is actually in, what outcome
 - classification: issue
 - dominant_scarcity: consensus_order
 - classification_confidence: medium
-- recommended_next_step: Explicitly separate the decision-layer strategic frame from the execution-layer sales frame, then define which frame governs resource allocation.
+- recommended_next_step: Output classification by viewpoint: execution-layer enrollment Problem versus decision-layer full-chain Issue, then define which frame governs resources.
 
 ### 12. Owner Review Questions
 
@@ -283,9 +342,35 @@ High. The organization must decide what business it is actually in, what outcome
 - Should the execution-layer frame be classified as Problem while the decision-layer frame is Issue?
 - Does this case need a paired expected output showing `classification_by_viewpoint`?
 
+### 13. Owner Review Decision
+
+- owner_review_status: owner_reviewed
+- owner_approved_for_digest: true
+- digest_role: inter_viewpoint_chain_vs_sales_calibration_case
+- selector_calibration_candidate: high_priority
+- classification: issue
+- dominant_scarcity: consensus_order
+- mixed_or_multi_perspective: inter_viewpoint_divergence
+- owner_decision: 本案例是本资料中最清晰的 inter_viewpoint_divergence。执行层框架是 Problem，决策层框架是 Issue。
+- classification_by_viewpoint:
+  execution_layer:
+    classification: problem
+    dominant_scarcity: path_resource
+    frame: lead_generation_and_conversion
+  decision_layer:
+    classification: issue
+    dominant_scarcity: consensus_order
+    frame: full_chain_strategy_and_outcome_accountability
+  organization_level:
+    classification: issue
+    dominant_scarcity: consensus_order
+    frame: strategic_object_and_operational_object_are_misaligned
+- owner_approved_wording: 执行层卖的是前端转化，决策层要的是完整链条；这不是同一个问题。
+- processing_note: 进入 digest 和 calibration；用于训练 classification_by_viewpoint。
+
 ## Case qpi-draft-intl-005: Inflated Credential Metrics As Fact Scarcity
 
-status: draft_owner_review_needed
+status: owner_reviewed
 
 source_path: `[redacted owner-provided raw source path: organization CT slice]`
 
@@ -319,7 +404,7 @@ The case begins as Q because the first scarcity is factual: what is the reported
 
 - data_scarcity: high
 - path_or_resource_scarcity: medium
-- consensus_or_order_scarcity: medium
+- consensus_or_order_scarcity: high
 
 ### 8. Mixed Or Multi-Perspective
 
@@ -341,10 +426,10 @@ Medium to high. If the metric is false or misleading, the organization must repa
 
 - classification_scope: subject_contextual
 - is_provisional: true
-- classification: question
+- classification: issue
-- dominant_scarcity: data
+- dominant_scarcity: consensus_order
 - classification_confidence: medium
-- recommended_next_step: Verify whether the indicator maps to real delivery capacity before treating it as an asset or a compliance risk.
+- recommended_next_step: Audit whether the metric links long-term goals, real capability, multi-party value, and traceable evidence before treating it as an asset.
 
 ### 12. Owner Review Questions
 
@@ -352,9 +437,31 @@ Medium to high. If the metric is false or misleading, the organization must repa
 - What level of evidence would let this case move from fact verification into governance remediation?
 - Should the future digest keep the credential category abstract to avoid compliance sensitivity?
 
+### 13. Owner Review Decision
+
+- owner_review_status: owner_reviewed
+- owner_approved_for_digest: true
+- digest_role: metric_distortion_governance_regression_case
+- regression_candidate: high_priority
+- classification: issue
+- dominant_scarcity: consensus_order
+- classification_note: metric_fact_verification_embedded_in_governance_distortion
+- data_scarcity: high
+- owner_decision: 不保持 question-first。若只是查某个指标真假，可以是 Q；但本来源中资质指标已进入“执行层提出—决策层质疑急功近利—评估压力”的治理语境。
+- governance_remediation_evidence:
+  - metric_used_for_assessment_reporting_compliance_or_resource_competition
+  - metric_decoupled_from_real_delivery_capacity
+  - metric_incentivizes_short_term_number_assembly
+  - metric_benefits_one_unit_while_other_units_absorb_cost
+  - metric_fails_multi_win_alignment
+  - traceable_evidence_chain_missing
+  - metric_fails_to_reflect_student_value_teaching_value_or_org_capability
+- owner_approved_wording: 好的 KPI 不只是好看，而是能把长期目标、真实能力、多方收益和可审计证据连起来。
+- processing_note: 进入 digest、calibration 和 regression。
+
 ## Case qpi-draft-intl-006: Pricing Deadlock Misread As Simple Market Weakness
 
-status: draft_owner_review_needed
+status: owner_reviewed
 
 source_path: `[redacted owner-provided raw source path: organization CT slice]`
 
@@ -388,7 +495,7 @@ The case begins as P: find a viable pricing and enrollment path. It can become I
 
 - data_scarcity: low
 - path_or_resource_scarcity: high
-- consensus_or_order_scarcity: medium
+- consensus_or_order_scarcity: high
 
 ### 8. Mixed Or Multi-Perspective
 
@@ -410,10 +517,10 @@ Medium. The organization needs a transition rule, risk budget, and communication
 
 - classification_scope: subject_contextual
 - is_provisional: true
-- classification: problem
+- classification: issue
-- dominant_scarcity: path_resource
+- dominant_scarcity: consensus_order
 - classification_confidence: medium
-- recommended_next_step: Model the transition options and their fairness costs before using workaround enrollment tactics.
+- recommended_next_step: Reframe the pricing deadlock as high-ticket trust-system construction before adjusting price or using workaround enrollment tactics.
 
 ### 12. Owner Review Questions
 
@@ -421,9 +528,29 @@ Medium. The organization needs a transition rule, risk budget, and communication
 - Does the owner want this retained as a distinct case if similar pricing deadlocks appear in other department slices?
 - What anonymized wording best captures the inherited-pricing constraint?
 
+### 13. Owner Review Decision
+
+- owner_review_status: owner_reviewed
+- owner_approved_for_digest: true
+- digest_role: high_ticket_trust_system_regression_case
+- regression_candidate: high_priority
+- classification: issue
+- dominant_scarcity: consensus_order
+- classification_note: pricing_deadlock_as_trust_system_failure_in_high_ticket_education_sales
+- owner_decision: 从 problem 上调为 issue。定价僵局是表象，高客单价教育产品的信任建设才是本质，需要组织多部门共同建立可信承诺、可验证结果和交付体系。
+- related_owner_model:
+  - APTC_trust_conversion_funnel
+- owner_model_note: APTC 作为 owner 补充分析框架记录，不注册为本仓库第三模型。
+- inherited_pricing_terms:
+  - legacy_price_value_mismatch
+  - inherited_pricing_constraint
+  - historical_price_anchor_with_fairness_debt
+- owner_approved_wording: 价格不是孤立变量；在高客单价教育产品中，价格必须由可信承诺、可验证结果和组织交付共同支撑。
+- processing_note: 进入 digest、calibration 和 regression。
+
 ## Case qpi-draft-intl-007: High-Quality Asset At Risk Of Privatization
 
-status: draft_owner_review_needed
+status: owner_reviewed
 
 source_path: `[redacted owner-provided raw source path: organization CT slice]`
 
@@ -482,7 +609,7 @@ High. The organization must balance retention, incentives, knowledge transfer, r
 - classification: issue
 - dominant_scarcity: consensus_order
 - classification_confidence: medium
-- recommended_next_step: Design an institutionalization path that preserves execution energy while separating team capability from personal bargaining monopoly.
+- recommended_next_step: Institutionalize the high-performing capability through process capture, succession, data transparency, and incentive design without killing execution energy.
 
 ### 12. Owner Review Questions
 
@@ -490,9 +617,31 @@ High. The organization must balance retention, incentives, knowledge transfer, r
 - Should this case be connected with the role-inflation case or kept separate?
 - What owner-approved signal distinguishes healthy recognition from dangerous private capture?
 
+### 13. Owner Review Decision
+
+- owner_review_status: owner_reviewed
+- owner_approved_for_digest: true
+- digest_role: non_institutionalized_capability_calibration_case
+- selector_calibration_candidate: supporting_governance_case
+- classification: issue
+- dominant_scarcity: consensus_order
+- classification_note: high_performing_capability_not_yet_institutionalized
+- revised_abstraction:
+  - non_institutionalized_high_performing_capability
+  - key_person_dependent_capability_risk
+  - capability_not_institutionalized
+- owner_decision: “组织能力被私有化”不够准确。问题是组织级能力尚未建立，关键能力停留在个人/小团队身上，存在流失和不可复制风险。
+- linked_case: qpi-draft-intl-003
+- do_not_merge: true
+- risk_tags:
+  - key_person_dependency
+  - capability_not_institutionalized
+  - continuity_risk
+- processing_note: 进入 digest 和 calibration；与 003 关联但保持独立。
+
 ## Case qpi-draft-intl-008: Strong External Channel Used To Justify Risky Internal Expansion
 
-status: draft_owner_review_needed
+status: owner_reviewed
 
 source_path: `[redacted owner-provided raw source path: organization CT slice]`
 
@@ -551,7 +700,7 @@ High. The organization needs rules for asset protection, partner trust, quality
 - classification: issue
 - dominant_scarcity: consensus_order
 - classification_confidence: medium
-- recommended_next_step: Treat the external channel as a protected strategic asset; define what internal uses are prohibited before scaling.
+- recommended_next_step: Treat the external channel as a protected strategic asset and define prohibited internal uses before scaling.
 
 ### 12. Owner Review Questions
 
@@ -559,3 +708,26 @@ High. The organization needs rules for asset protection, partner trust, quality
 - Is the key misframing "real asset implies safe expansion"?
 - What minimum evidence should be kept in a future digest without identifying the partner or program category?
 
+### 13. Owner Review Decision
+
+- owner_review_status: owner_reviewed
+- owner_approved_for_digest: true
+- digest_role: real_asset_unready_expansion_synthesis_case
+- selector_calibration_candidate: issue_anchor
+- classification: issue
+- dominant_scarcity: consensus_order
+- classification_note: real_external_asset_used_as_license_for_unready_internal_expansion
+- case_level: synthesis_case
+- do_not_merge: true
+- linked_cases:
+  - qpi-draft-intl-001
+  - qpi-draft-intl-002
+  - qpi-draft-intl-006
+  - qpi-draft-intl-007
+- risk_tags:
+  - real_asset_implies_safe_expansion
+  - asset_contamination_risk
+  - channel_trust_degradation
+- owner_decision: 保持独立，但标记为 higher-level synthesis case。独特价值是：真实外部资产如何被内部冒险扩张污染。
+- owner_approved_wording: 外部渠道真实，不代表内部扩张安全；真实资产如果挂接到低质量交付上，会被组织自己污染。
+- processing_note: 进入 digest 和 calibration。

reports/model_case_preprocessing/qpi/round-01/year-end-review-research-office.cases.md

@@ -1,16 +1,20 @@
 # QPI Case Drafts: Year-End Review Research Function
 
-status: draft_owner_review_needed
+status: owner_reviewed
 
 source_path: `[redacted external source path: owner-provided organizational CT slice]`
 
 source_note: Owner-provided raw organizational material. These drafts are anonymized and generalized for QPI review. Real or potentially identifying people, departments, institutions, timestamps, locations, titles, ancient-style cognitive anchors, exact numeric details, and sensitive operational details have been removed or generalized. These drafts are not selector JSON, regression cases, or owner-approved calibration data.
 
+owner_review_source: `C:/Users/wangq/Documents/Codex/knowledge-vault/work/internal/强哥的思想宇宙/QPI案例审阅/QPI提炼审核/year-end-review-research-office.cases-GPT.md`
+
+owner_review_note: Owner/GPT review approved all eight cases for digest promotion. No additional anonymization required. Core pattern: the research function is distorted from real research capability building into tax planning, ranking metric production, compliance material production, and display-talent containment.
+
 anonymization_note: People are represented as roles such as `decision_maker`, `execution_lead`, `research_staff`, `compliance_staff`, and `frontline_staff`. The organization is represented as `the organization`; the department is represented as `research_function`. Sensitive details are generalized as `tax-preference metric pressure`, `research identity simulation`, `paper-and-patent metric pressure`, `talent-role mismatch`, `resource allocation bottleneck`, `facility capacity risk`, and `compliance red-line risk`.
 
 ## Case qpi-draft-001: Tax-Preference Goal Becomes Research Identity Simulation
 
-status: draft_owner_review_needed
+status: owner_reviewed
 
 source_path: `[redacted external source path: owner-provided organizational CT slice]`
 
@@ -70,7 +74,7 @@ Very high. The case requires managing audit authenticity, compliance boundaries,
 - classification: issue
 - dominant_scarcity: consensus_order
 - classification_confidence: medium
-- recommended_next_step: Treat the case as a governance Issue with a path/resource trigger; separate legitimate capability-building paths from evidence simulation and compliance red-line risk.
+- recommended_next_step: Treat this as the umbrella research identity simulation Issue; separate real capability building from evidence packaging, transactional assets, and compliance red-line risk.
 
 ### 12. Owner Review Questions
 
@@ -78,9 +82,30 @@ Very high. The case requires managing audit authenticity, compliance boundaries,
 - Should `classification` be `issue` or `mixed` given the strong path/resource shortage behind the governance failure?
 - Is the anonymized phrase `research identity simulation` acceptable, or should it be softened further?
 
+### 13. Owner Review Decision
+
+- owner_review_status: owner_reviewed
+- owner_approved_for_digest: true
+- digest_role: research_identity_simulation_umbrella_regression_case
+- regression_candidate: high_priority
+- case_level: umbrella_case
+- classification: issue
+- dominant_scarcity: consensus_order
+- classification_note: research_identity_simulation_under_tax_preference_pressure
+- linked_cases:
+  - qpi-draft-002
+  - qpi-draft-003
+  - qpi-draft-004
+  - qpi-draft-005
+  - qpi-draft-008
+- owner_decision: 作为本来源 umbrella QPI case。它不只是窄的认证风险样本，而是“研究身份模拟”的总案例。
+- owner_approved_term: research identity simulation
+- owner_approved_wording: 税收优惠目标本身不是问题；问题是组织没有真实科研能力，却试图用人员、费用、专利和论文来模拟科研身份。
+- processing_note: 进入 digest、calibration 和 regression。
+
 ## Case qpi-draft-002: Research Staff Count Treated As Movable Accounting Data
 
-status: draft_owner_review_needed
+status: owner_reviewed
 
 source_path: `[redacted external source path: owner-provided organizational CT slice]`
 
@@ -118,7 +143,7 @@ Q/P -> I. It may first appear as a Question about what the metric requires or a
 
 ### 8. Mixed Or Multi-Perspective
 
-`inter_viewpoint_divergence`
+`intra_frame_mixed`
 
 From `decision_maker`, the case may look like an execution Problem: adjust the table. From a compliance or research-quality viewpoint, it is an Issue about role truthfulness and institutional integrity.
 
@@ -140,17 +165,39 @@ High. The organization needs rules for role classification, evidence authenticit
 - classification: issue
 - dominant_scarcity: consensus_order
 - classification_confidence: medium
-- recommended_next_step: Use this as a QPI sample for distinguishing missing data from falsified or untrusted data; ask the owner whether the case should explicitly mark "data completeness is not truthfulness."
+- recommended_next_step: Distinguish data completeness from data truthfulness and evidence legitimacy; require compliance review before legal or tax conclusions.
 
 ### 12. Owner Review Questions
 
-- Should this case be classified as `inter_viewpoint_divergence` because different roles see different frames, or `intra_frame_mixed` because both resource and governance scarcities exist?
+- Should this case be classified as `intra_frame_mixed` because different roles see different frames, or `intra_frame_mixed` because both resource and governance scarcities exist?
 - Is the main misframing `violent_reduction` from research capability to spreadsheet category?
 - Should this sample later test QPI's ability to reject high-confidence classification when compliance details are not owner-verified?
 
+### 13. Owner Review Decision
+
+- owner_review_status: owner_reviewed
+- owner_approved_for_digest: true
+- digest_role: research_capacity_accounting_reduction_regression_case
+- regression_candidate: high_priority
+- classification: issue
+- dominant_scarcity: consensus_order
+- mixed_or_multi_perspective: intra_frame_mixed
+- classification_confidence: medium
+- requires_compliance_review: true
+- risk_tags:
+  - research_capacity_reduced_to_accounting_category
+  - data_completeness_is_not_truthfulness
+  - evidence_legitimacy
+- evidence_gap:
+  - actual_research_role_evidence
+  - payroll_category_validity
+  - research_contribution_trace
+- owner_decision: 改为 intra_frame_mixed，不是 inter_viewpoint_divergence。主要误框是 violent_reduction：把企业治理和真实科研能力建设暴力降维成科技处可操作的指标填报任务。
+- processing_note: 进入 digest、calibration 和 regression；不输出高置信法律/税务结论。
+
 ## Case qpi-draft-003: Transactional Research Assets Create Audit Fragility
 
-status: draft_owner_review_needed
+status: owner_reviewed
 
 source_path: `[redacted external source path: owner-provided organizational CT slice]`
 
@@ -209,7 +256,7 @@ Very high. The case requires deciding what counts as authentic evidence, what tr
 - classification: mixed
 - dominant_scarcity: consensus_order
 - classification_confidence: medium
-- recommended_next_step: Treat the case as a P/I mixed sample where the immediate path gap is dominated by evidence authenticity and compliance governance.
+- recommended_next_step: Keep as a subcase of research identity simulation and test whether transactional evidence is being substituted for real capability.
 
 ### 12. Owner Review Questions
 
@@ -217,9 +264,24 @@ Very high. The case requires deciding what counts as authentic evidence, what tr
 - Should the dominant scarcity be `path_resource` because the organization lacks real assets, or `consensus_order` because the chosen route is illegitimate?
 - Is this anonymized enough, or should all references to transactional research assets be further abstracted?
 
+### 13. Owner Review Decision
+
+- owner_review_status: owner_reviewed
+- owner_approved_for_digest: true
+- digest_role: transactional_research_asset_subcase
+- selector_calibration_candidate: evidence_case
+- case_status: keep_as_subcase
+- parent_case: qpi-draft-001
+- classification: mixed
+- dominant_scarcity: consensus_order
+- classification_note: transactional_research_assets_as_research_identity_simulation_mechanism
+- owner_decision: 可并入 Case 001 作为 research identity simulation 的子案例，但不完全删除；保留为 subcase / evidence case。
+- owner_approved_wording: 研究资产可以被转让，但研究能力不能靠交易痕迹模拟出来。
+- processing_note: 进入 digest 和 calibration，不进入首轮 regression。
+
 ## Case qpi-draft-004: Ranking Anxiety Converts Research Into Purchasable Metrics
 
-status: draft_owner_review_needed
+status: owner_reviewed
 
 source_path: `[redacted external source path: owner-provided organizational CT slice]`
 
@@ -279,7 +341,7 @@ High. The case requires ongoing tradeoffs among ranking pressure, research authe
 - classification: issue
 - dominant_scarcity: consensus_order
 - classification_confidence: medium
-- recommended_next_step: Use this as a QPI sample for "metric improvement is not the same as capability improvement"; ask the owner whether later calibration should route this to governance review rather than execution planning.
+- recommended_next_step: Route ranking-improvement pressure to governance review when it reduces research value to purchasable or sprintable metric inputs.
 
 ### 12. Owner Review Questions
 
@@ -287,9 +349,26 @@ High. The case requires ongoing tradeoffs among ranking pressure, research authe
 - Or is the stronger risk `violent_reduction`, where research value is reduced to ranking inputs?
 - Should this case later connect to selector traps around "how to improve ranking quickly"?
 
+### 13. Owner Review Decision
+
+- owner_review_status: owner_reviewed
+- owner_approved_for_digest: true
+- digest_role: ranking_metric_reduction_regression_case
+- regression_candidate: high_priority
+- classification: issue
+- dominant_scarcity: consensus_order
+- primary_risk: violent_reduction
+- secondary_risk: malicious_inflation
+- selector_trap:
+  - how_to_improve_ranking_quickly
+  - metric_improvement_without_capability_improvement
+- owner_decision: 本案例是 violent_reduction 强样本。核心误框是把研究价值、学术文化、人才培养和知识生产压缩成可购买、可填报、可冲刺的排名输入。
+- owner_approved_wording: 排名可以作为反馈信号，但不能反过来接管研究价值的定义。
+- processing_note: 进入 digest、calibration 和 regression。
+
 ## Case qpi-draft-005: High-Level Talent Becomes Role-Mismatched Display Asset
 
-status: draft_owner_review_needed
+status: owner_reviewed
 
 source_path: `[redacted external source path: owner-provided organizational CT slice]`
 
@@ -348,7 +427,7 @@ High. The case requires balancing credential needs, real capability use, task de
 - classification: mixed
 - dominant_scarcity: consensus_order
 - classification_confidence: medium
-- recommended_next_step: Frame the case as a role-governance Issue with a work-design Problem inside it; ask whether the QPI output should explicitly mark talent-as-indicator reduction.
+- recommended_next_step: Treat this as a role-governance Issue with a work-design Problem inside it; include high-level talent as a proxy stakeholder.
 
 ### 12. Owner Review Questions
 
@@ -356,9 +435,31 @@ High. The case requires balancing credential needs, real capability use, task de
 - Is `dominant_scarcity: consensus_order` correct, or should `path_resource` dominate because the immediate blocker is work design?
 - Should future case digest include proxy stakeholder `high_level_talent`?
 
+### 13. Owner Review Decision
+
+- owner_review_status: owner_reviewed
+- owner_approved_for_digest: true
+- digest_role: high_level_talent_role_governance_calibration_case
+- selector_calibration_candidate: high_priority
+- case_status: keep_independent
+- linked_to: qpi-draft-001
+- classification: mixed
+- dominant_scarcity: consensus_order
+- classification_note: role_governance_issue_with_work_design_problem_inside
+- proxy_stakeholders:
+  - high_level_talent
+- risk_tags:
+  - talent_as_indicator_reduction
+  - role_mismatch
+  - capability_underutilization
+  - retention_risk
+- owner_decision: 独立保留，不只作为指标驱动研究身份的子案例。独特价值是识别“人才作为能力”与“人才作为展示资产”的冲突。
+- owner_approved_wording: 高端人才不是可摆放的指标资产；如果组织没有平台、任务和角色设计，人才引进会从能力建设变成展示消耗。
+- processing_note: 进入 digest 和 calibration。
+
 ## Case qpi-draft-006: Facility Capacity Risk Misread As Expansion Logistics
 
-status: draft_owner_review_needed
+status: owner_reviewed
 
 source_path: `[redacted external source path: owner-provided organizational CT slice]`
 
@@ -386,7 +487,7 @@ The attempted path is to squeeze or repurpose existing space rather than slow ex
 
 ### 6. Dynamic Shift
 
-P -> I. It begins as a Problem of finding enough physical space. It becomes an Issue when growth promises, resource allocation, user rights, staff disruption, and reputational risk collide.
+P. It is primarily a Problem of finding enough physical space. It becomes an Issue when growth promises, resource allocation, user rights, staff disruption, and reputational risk collide.
 
 ### 7. Scarcity Profile
 
@@ -396,7 +497,7 @@ P -> I. It begins as a Problem of finding enough physical space. It becomes an I
 
 ### 8. Mixed Or Multi-Perspective
 
-`intra_frame_mixed`
+`not_mixed`
 
 The same organizational frame contains a hard resource shortage and a governance burden. The path scarcity is dominant, but the way the shortage is handled creates order and legitimacy risks.
 
@@ -414,10 +515,10 @@ High. The case requires capacity governance, expansion pacing, risk communicatio
 
 - classification_scope: subject_contextual
 - is_provisional: true
-- classification: mixed
+- classification: problem
 - dominant_scarcity: path_resource
 - classification_confidence: medium
-- recommended_next_step: Treat as a P/I mixed case; first verify physical capacity and committed obligations, then decide whether expansion should be capped, delayed, or redesigned.
+- recommended_next_step: Verify hard physical capacity and obligations first; solve through investment, cap, delay, redesign, or lower commitments rather than administrative command.
 
 ### 12. Owner Review Questions
 
@@ -425,9 +526,23 @@ High. The case requires capacity governance, expansion pacing, risk communicatio
 - Should it be used as a calibration sample for "hard constraint cannot be solved by administrative command"?
 - Is the growth context anonymized enough, or should all references to external-facing activity be made more generic?
 
+### 13. Owner Review Decision
+
+- owner_review_status: owner_reviewed
+- owner_approved_for_digest: true
+- digest_role: hard_capacity_constraint_calibration_case
+- selector_calibration_candidate: boundary_case
+- classification: problem
+- dominant_scarcity: path_resource
+- governance_risk: medium
+- classification_note: hard_capacity_problem_with_visible_downstream_governance_risk
+- owner_decision: 优先判为 problem，因为物理容量、床位、设施、空间是硬约束；但保留 governance risk note，若扩张承诺、挤占其他单元、安全和信任风险显现，可升级为 P/I mixed。
+- owner_approved_wording: 硬容量不能靠行政命令解决；最多只能靠投资、限流、延期、改造或降低承诺解决。
+- processing_note: 进入 digest 和 calibration；用于“硬约束无法靠行政命令解决”校准。
+
 ## Case qpi-draft-007: Safety Responsibility Vacuum Covered By Emergency Command
 
-status: draft_owner_review_needed
+status: owner_reviewed
 
 source_path: `[redacted external source path: owner-provided organizational CT slice]`
 
@@ -486,7 +601,7 @@ High. The case requires responsibility mapping, documented ownership, escalation
 - classification: issue
 - dominant_scarcity: consensus_order
 - classification_confidence: medium
-- recommended_next_step: Route as an Issue: identify the missing responsibility chain before treating it as an isolated task execution problem.
+- recommended_next_step: Identify the missing responsibility chain, process owner, evidence trail, and escalation rule before treating this as task assignment.
 
 ### 12. Owner Review Questions
 
@@ -494,9 +609,26 @@ High. The case requires responsibility mapping, documented ownership, escalation
 - Is this a useful QPI sample for "Q-like responsibility question that is actually an accountability Issue"?
 - Should safety details be further generalized for publication safety?
 
+### 13. Owner Review Decision
+
+- owner_review_status: owner_reviewed
+- owner_approved_for_digest: true
+- digest_role: accountability_vacuum_q_as_i_calibration_case
+- selector_calibration_candidate: high_priority
+- classification: issue
+- dominant_scarcity: consensus_order
+- classification_note: responsibility_question_reveals_accountability_architecture_gap
+- risk_tags:
+  - command_substitution_for_process
+  - safety_accountability_vacuum
+  - Q_as_I_trap
+- owner_decision: 纳入。它虽然是较小切片，但适合作为“看似 Q 的责任归属问题，实为问责 Issue”的样本。
+- owner_approved_wording: 安全事项不能靠临时抓人补位；如果必须靠最高层临时指派，说明责任架构已经失效。
+- processing_note: 进入 digest 和 calibration。
+
 ## Case qpi-draft-008: Compliance Risk Defined Only By Immediate Penalty
 
-status: draft_owner_review_needed
+status: owner_reviewed
 
 source_path: `[redacted external source path: owner-provided organizational CT slice]`
 
@@ -555,7 +687,7 @@ High. The case requires redefining compliance beyond immediate punishment, creat
 - classification: issue
 - dominant_scarcity: consensus_order
 - classification_confidence: medium
-- recommended_next_step: Treat as an Issue about compliance-risk framing; request owner confirmation before using it as a calibration sample because legal interpretation must remain generalized.
+- recommended_next_step: Separate penalty-status inquiry from integrity-status review; absence of immediate punishment is not evidence of legitimacy.
 
 ### 12. Owner Review Questions
 
@@ -563,3 +695,22 @@ High. The case requires redefining compliance beyond immediate punishment, creat
 - Should the candidate judgment emphasize `inter_viewpoint_divergence` between penalty-status and integrity-status frames?
 - Is the legal-risk language sufficiently generalized?
 
+### 13. Owner Review Decision
+
+- owner_review_status: owner_reviewed
+- owner_approved_for_digest: true
+- digest_role: punishment_state_vs_integrity_state_regression_case
+- regression_candidate: high_priority
+- case_status: keep_independent
+- linked_to: qpi-draft-001
+- classification: issue
+- dominant_scarcity: consensus_order
+- mixed_or_multi_perspective: inter_viewpoint_divergence
+- abstraction: punishment_state_vs_integrity_state
+- risk_tags:
+  - punishment_state_frame
+  - absence_of_penalty_is_not_legitimacy
+  - compliance_minimum_game
+- owner_decision: 独立保留并链接到 Case 001。它不是研究身份模拟本身，而是合规风险认知框架错误。
+- owner_approved_wording: 没有被罚不是合规，只是尚未被惩罚；合规应以行为正当性和可审计性为边界，而不是以是否立刻受罚为边界。
+- processing_note: 进入 digest、calibration 和 regression。

reports/selector_regression_report_v0.2.md

@@ -2,7 +2,7 @@
 
 Status: `PASS`
 
-Cases checked: 9
+Cases checked: 10
 Failures: 0
 
 ## Cases
@@ -16,3 +16,4 @@ Failures: 0
 - `case_qpi_no_call_direct_edit_001`: PASS; selected=[]; no_call=True
 - `case_qpi_selector_gate_fact_001`: PASS; selected=[]; no_call=True
 - `case_qpi_pipeline_before_ia_001`: PASS; selected=['qpi']; no_call=False
+- `case_qpi_disappointment_mismatch_diagnostics_001`: PASS; selected=['qpi']; no_call=False

selector/README.md

@@ -19,9 +19,13 @@ Current files:
 
 - `selector_rules.json`
 - `selector_examples.json`
+- `selector_calibration_inputs.json`
+- `qpi_case_digests.json`
 
 The selector does not call an LLM.
 
 The executable demo is `scripts/run_selector_demo.py`.
 
 Selector regression is `scripts/run_selector_regression.py`.
+
+`qpi_case_digests.json` stores owner-reviewed QPI case digests that can feed selector calibration or later regression selection. It is not a model status upgrade and should not include unreviewed draft cases.

selector/selector_calibration_inputs.json

@@ -142,6 +142,447 @@
       "input": "QPI 已判断不是事实查询，而是系统性课题；下一步检查它是否值得沉淀成可复用模型。",
       "expected_selector_behavior": "select_intellectual_archaeology",
       "expected_notes": "QPI has completed the front gate."
+    },
+    {
+      "case_id": "selector_calibration_qpi_flow_entry_point_001",
+      "category": "qpi_owner_reviewed_flow_redesign",
+      "input": "我们本来想自动化大纲审阅，但发现真正卡住的是原始材料压缩、前置上下文、主笔框定和 owner 确认，review 只是很晚才暴露问题。",
+      "expected_selector_behavior": "select_qpi",
+      "expected_notes": "Owner-reviewed flow-redesign case 001: wrong automation entry point reveals context engineering and stage authority scarcity."
+    },
+    {
+      "case_id": "selector_calibration_qpi_no_simulation_001",
+      "category": "qpi_owner_reviewed_flow_redesign",
+      "input": "这个多代理评审包看起来有完整报告，但其实只是主会话模拟，没有真实独立 agent 调用记录；我需要判断它能不能作为正式输出。",
+      "expected_selector_behavior": "select_qpi",
+      "expected_notes": "Owner-reviewed flow-redesign case 002: no-simulation and formal-output legitimacy should route to QPI issue framing."
+    },
+    {
+      "case_id": "selector_calibration_qpi_local_truth_global_structure_001",
+      "category": "qpi_owner_reviewed_flow_redesign",
+      "input": "分块提炼都局部正确，但整体主轴、主题结构和模型演化线被误读了；我怀疑局部真实冒充了全局结构。",
+      "expected_selector_behavior": "select_qpi",
+      "expected_notes": "Owner-reviewed flow-redesign case 003: local truth impersonating global structure is a QPI misframing risk."
+    },
+    {
+      "case_id": "selector_calibration_qpi_stop_gate_001",
+      "category": "qpi_owner_reviewed_flow_redesign",
+      "input": "素材提炼完成后，不应该自动创建写作项目或自动进入模型挖掘；下一步必须先经过 owner 授权和 source-of-truth 确认。",
+      "expected_selector_behavior": "select_qpi",
+      "expected_notes": "Owner-reviewed flow-redesign case 004: stop gates and downstream transition authority are QPI issue signals."
+    },
+    {
+      "case_id": "selector_calibration_qpi_intra_frame_mixed_flow_001",
+      "category": "qpi_owner_reviewed_flow_redesign",
+      "input": "这只是我个人的流程改造，但它涉及真实调用、上下文裁剪、审计边界、token 成本、后续复用和未来 owner 的维护责任。",
+      "expected_selector_behavior": "select_qpi",
+      "expected_notes": "Owner-reviewed flow-redesign case 005: one-owner workflow can be intra_frame_mixed when governance load is sustained."
+    },
+    {
+      "case_id": "selector_calibration_qpi_complexity_placement_001",
+      "category": "qpi_owner_reviewed_flow_redesign",
+      "input": "我不想简单判断这个流程是不是过度工程，而是要判断这些复杂度分别买到了真实性、保真性、可追溯性、可停止性和 ROI 吗。",
+      "expected_selector_behavior": "select_qpi",
+      "expected_notes": "Owner-reviewed flow-redesign case 006: complexity placement gate is QPI issue calibration, not a third model."
+    },
+    {
+      "case_id": "selector_calibration_qpi_psych_mechanism_ambiguity_001",
+      "category": "qpi_owner_reviewed_disappointment_isolation",
+      "input": "同一个“失望性情感隔离”标签，可能是被动麻木，也可能是主动认知抽离；我需要先区分机制再判断这是什么问题。",
+      "expected_selector_behavior": "select_qpi",
+      "expected_notes": "Owner-reviewed disappointment case 001: mechanism ambiguity and multi-perspective routing should select QPI."
+    },
+    {
+      "case_id": "selector_calibration_qpi_label_as_identity_001",
+      "category": "qpi_owner_reviewed_disappointment_isolation",
+      "input": "我不是只想查这个心理标签是什么意思，它已经影响我怎么理解自己、怎么设关系边界和要不要寻求帮助。",
+      "expected_selector_behavior": "select_qpi",
+      "expected_notes": "Owner-reviewed disappointment case 002: a label used for identity and relationship governance is not pure Q lookup."
+    },
+    {
+      "case_id": "selector_calibration_qpi_single_factor_totalization_001",
+      "category": "qpi_owner_reviewed_disappointment_isolation",
+      "input": "我不想把情感隔离全部归因于童年或某一个人，我需要判断哪些是触发、维持条件、高权重要素和当前行动杠杆。",
+      "expected_selector_behavior": "select_qpi",
+      "expected_notes": "Owner-reviewed disappointment case 003: single-factor totalization is a QPI misframing risk."
+    },
+    {
+      "case_id": "selector_calibration_qpi_one_time_fix_trap_001",
+      "category": "qpi_owner_reviewed_disappointment_isolation",
+      "input": "这个心理关系问题不能靠三步修复或一次干预解决，我需要判断它是不是只能阶段性重构和长期治理。",
+      "expected_selector_behavior": "select_qpi",
+      "expected_notes": "Owner-reviewed disappointment case 004: one-time solution framing should route to QPI issue diagnosis."
+    },
+    {
+      "case_id": "selector_calibration_qpi_external_authority_boundary_001",
+      "category": "qpi_owner_reviewed_disappointment_isolation",
+      "input": "我想判断外部帮助是在替我给答案，还是帮我建立自我治理和校准环境，这涉及权威边界和依赖风险。",
+      "expected_selector_behavior": "select_qpi",
+      "expected_notes": "Owner-reviewed disappointment case 005: external authority boundary is a governance-load signal."
+    },
+    {
+      "case_id": "selector_calibration_qpi_time_scale_scope_001",
+      "category": "qpi_owner_reviewed_disappointment_isolation",
+      "input": "同一个关系现象，在概念层像 Q，在一次行动上像 P，在长期生命模式上又像 I；我需要先确定时间尺度和分类范围。",
+      "expected_selector_behavior": "select_qpi",
+      "expected_notes": "Owner-reviewed disappointment case 006: time scale and classification scope determine QPI routing."
+    },
+    {
+      "case_id": "selector_calibration_qpi_mismatch_diagnostics_001",
+      "category": "qpi_owner_reviewed_disappointment_isolation",
+      "input": "我需要检查这个心理关系材料有没有被误路由：把 I 当 Q、把 I 当 P、把 P 过度升维成 I，或者把保护性边界病理化。",
+      "expected_selector_behavior": "select_qpi",
+      "expected_notes": "Owner-reviewed disappointment case 007: QPI mismatch diagnostics should select QPI."
+    },
+    {
+      "case_id": "selector_calibration_qpi_one_person_issue_001",
+      "category": "qpi_owner_reviewed_disappointment_isolation",
+      "input": "只有我一个人在做自我治理，但我要长期校准隔离什么时候是保护，什么时候是过度泛化防御，这是不是仍然可以是 Issue？",
+      "expected_selector_behavior": "select_qpi",
+      "expected_notes": "Owner-reviewed disappointment case 008: one-person self-governance can still be Issue."
+    },
+    {
+      "case_id": "selector_calibration_qpi_org_hard_resource_documentation_001",
+      "category": "qpi_owner_reviewed_year_end_development_office",
+      "input": "组织面对硬性资源缺口，没有真实补资源，而是想通过重命名、材料包装和合规口径让指标看起来达标。",
+      "expected_selector_behavior": "select_qpi",
+      "expected_notes": "Owner-reviewed development-office case 001: hard resource gap disguised as documentation problem should route to QPI as governance/order scarcity with path/resource trigger."
+    },
+    {
+      "case_id": "selector_calibration_qpi_org_credential_continuity_001",
+      "category": "qpi_owner_reviewed_year_end_development_office",
+      "input": "为了修复人员资质指标，组织准备替换或重分类一批岗位，但这些人承担运营记忆、角色连续性和信任关系。",
+      "expected_selector_behavior": "select_qpi",
+      "expected_notes": "Owner-reviewed development-office case 002: credential metric repair damaging operational continuity is QPI issue / violent reduction."
+    },
+    {
+      "case_id": "selector_calibration_qpi_org_incentive_backlash_001",
+      "category": "qpi_owner_reviewed_year_end_development_office",
+      "input": "管理层把绩效下滑解释成员工不努力，但一线实际是在负激励和成本转嫁下理性减少投入。",
+      "expected_selector_behavior": "select_qpi",
+      "expected_notes": "Owner-reviewed development-office case 003: performance decline with incentive backlash should not be reduced to effort problem."
+    },
+    {
+      "case_id": "selector_calibration_qpi_org_role_authority_mismatch_001",
+      "category": "qpi_owner_reviewed_year_end_development_office",
+      "input": "一个战略支持职能被要求拿出战略增长和外部合作，却没有资源、授权、信任和可执行空间，最后只能做指标包装。",
+      "expected_selector_behavior": "select_qpi",
+      "expected_notes": "Owner-reviewed development-office case 004: strategic role without strategic operating conditions is QPI role-authority mismatch."
+    },
+    {
+      "case_id": "selector_calibration_qpi_org_pattern_level_issue_001",
+      "category": "qpi_owner_reviewed_year_end_development_office",
+      "input": "同一组织反复要求高目标低投入：要合作但不给交换，要产出但不给激励，要容量但不扩资源，下游只能吸收矛盾。",
+      "expected_selector_behavior": "select_qpi",
+      "expected_notes": "Owner-reviewed development-office case 005: pattern-level Issue from shared low-cost ambition / target-resource inconsistency mechanism."
+    },
+    {
+      "case_id": "selector_calibration_qpi_org_untrusted_data_001",
+      "category": "qpi_owner_reviewed_year_end_development_office",
+      "input": "材料和台账都很完整，但它们对应的真实运营并不稳定，也经不起审计核查；这不是缺数据，而是数据不可信。",
+      "expected_selector_behavior": "select_qpi",
+      "expected_notes": "Owner-reviewed development-office case 006: data completeness versus truthfulness gap should route to QPI evidence authenticity issue."
+    },
+    {
+      "case_id": "selector_calibration_qpi_org_workaround_translation_001",
+      "category": "qpi_owner_reviewed_year_end_development_office",
+      "input": "中层执行者知道指令和现实冲突，但仍把不可能的要求翻译成可运行的变通动作，让错误治理逻辑继续运转。",
+      "expected_selector_behavior": "select_qpi",
+      "expected_notes": "Owner-reviewed development-office case 007: role-boundary governance and workaround normalization."
+    },
+    {
+      "case_id": "selector_calibration_qpi_org_low_cost_indicator_survival_001",
+      "category": "qpi_owner_reviewed_year_end_development_office",
+      "input": "外部指标压力只是触发器，真正的问题是组织内部低投入、高压和形式主义治理，把指标生存变成对真实能力的吞噬。",
+      "expected_selector_behavior": "select_qpi",
+      "expected_notes": "Owner-reviewed development-office case 008: umbrella organization-level Issue; keep in QPI, not future CT this round."
+    },
+    {
+      "case_id": "selector_calibration_qpi_academic_ai_evidence_boundary_001",
+      "category": "qpi_owner_reviewed_year_end_academic_affairs",
+      "input": "看起来只是让 AI 帮忙生成评估材料，但实际是先定结论再倒推证据，我需要判断这是不是材料执行任务。",
+      "expected_selector_behavior": "select_qpi",
+      "expected_notes": "Owner-reviewed academic-affairs case 001: AI/tool request should route to QPI when evidence legitimacy and tool boundary are at stake."
+    },
+    {
+      "case_id": "selector_calibration_qpi_academic_staffing_deadlock_001",
+      "category": "qpi_owner_reviewed_year_end_academic_affairs",
+      "input": "外部政策要求资质指标，于是组织引进高学历人员，但课程、岗位、课时和能力模型都吸收不了这些人。",
+      "expected_selector_behavior": "select_qpi",
+      "expected_notes": "Owner-reviewed academic-affairs case 002: compliance staffing metric creates resource deadlock and governance scarcity."
+    },
+    {
+      "case_id": "selector_calibration_qpi_academic_policy_memory_001",
+      "category": "qpi_owner_reviewed_year_end_academic_affairs",
+      "input": "我们想取消一个诱发低质量产出的旧激励政策，但过去按这个规则投入过的人会觉得不公平，组织信任也已经受损。",
+      "expected_selector_behavior": "select_qpi",
+      "expected_notes": "Owner-reviewed academic-affairs case 003: policy cleanup is a QPI issue when policy memory and trust debt exist."
+    },
+    {
+      "case_id": "selector_calibration_qpi_academic_strategy_myopia_001",
+      "category": "qpi_owner_reviewed_year_end_academic_affairs",
+      "input": "一个项目方向短期更容易申报和包装，但可能偏离组织长期定位；这到底是资源可行妥协还是战略短视？",
+      "expected_selector_behavior": "select_qpi",
+      "expected_notes": "Owner-reviewed academic-affairs case 004: short-term packaging versus long-term strategy should route to QPI."
+    },
+    {
+      "case_id": "selector_calibration_qpi_academic_resource_reuse_001",
+      "category": "qpi_owner_reviewed_year_end_academic_affairs",
+      "input": "高层认为大学老师有空就可以去支援另一类课程，但课程对象、能力模型、课表结构和质量责任完全不同。",
+      "expected_selector_behavior": "select_qpi",
+      "expected_notes": "Owner-reviewed academic-affairs case 005: cross-boundary resource reuse can be violent reduction."
+    },
+    {
+      "case_id": "selector_calibration_qpi_academic_outcome_excuse_001",
+      "category": "qpi_owner_reviewed_year_end_academic_affairs",
+      "input": "学生结果和投诉指标变差，部门解释为生源质量问题，但还没有审计教学质量制度和管理杠杆。",
+      "expected_selector_behavior": "select_qpi",
+      "expected_notes": "Owner-reviewed academic-affairs case 006: input condition explanation cannot replace quality-assurance audit."
+    },
+    {
+      "case_id": "selector_calibration_qpi_academic_digital_governance_001",
+      "category": "qpi_owner_reviewed_year_end_academic_affairs",
+      "input": "平台和本地 AI 方案一直选不定，表面是工具比较，实际没人定义数据边界、安全、迭代、维护和迁移责任。",
+      "expected_selector_behavior": "select_qpi",
+      "expected_notes": "Owner-reviewed academic-affairs case 007: platform choice masks digital governance boundary."
+    },
+    {
+      "case_id": "selector_calibration_qpi_academic_bottom_line_control_001",
+      "category": "qpi_owner_reviewed_year_end_academic_affairs",
+      "input": "一次大型活动没有完成审批报备和安全风控，事后才补救；我想判断这只是流程缺口还是底线控制失败。",
+      "expected_selector_behavior": "select_qpi",
+      "expected_notes": "Owner-reviewed academic-affairs case 008: operational accident can reveal bottom-line control failure."
+    },
+    {
+      "case_id": "selector_calibration_qpi_employment_reverse_accountability_001",
+      "category": "qpi_owner_reviewed_year_end_employment_entrepreneurship",
+      "input": "就业指标压力很大，组织想让就业部门反向考核教学部门，甚至用就业结果否决课程和教师安排。",
+      "expected_selector_behavior": "select_qpi",
+      "expected_notes": "Owner-reviewed employment case 001: hard outcome metric hides authority redesign."
+    },
+    {
+      "case_id": "selector_calibration_qpi_employment_credential_compliance_001",
+      "category": "qpi_owner_reviewed_year_end_employment_entrepreneurship",
+      "input": "为了补资质指标，组织想快速挂靠或采购带资历的人，但这些人是否进入教学科研和学生发展完全不清楚。",
+      "expected_selector_behavior": "select_qpi",
+      "expected_notes": "Owner-reviewed employment case 002: credential metric repair can create compliance exposure."
+    },
+    {
+      "case_id": "selector_calibration_qpi_employment_reported_metric_legitimacy_001",
+      "category": "qpi_owner_reviewed_year_end_employment_entrepreneurship",
+      "input": "部门述职说自己创收很高，但这个数字按部门口径算，和组织财务确认标准不一致，还被用来争取更大权力。",
+      "expected_selector_behavior": "select_qpi",
+      "expected_notes": "Owner-reviewed employment case 003: reported metric lineage and performance legitimacy must be audited."
+    },
+    {
+      "case_id": "selector_calibration_qpi_employment_overpromising_pipeline_001",
+      "category": "qpi_owner_reviewed_year_end_employment_entrepreneurship",
+      "input": "招生时把就业结果作为核心承诺，但课程、企业岗位、学生基础和风险边界都没有证明，执行部门被迫过度承诺。",
+      "expected_selector_behavior": "select_qpi",
+      "expected_notes": "Owner-reviewed employment case 004: outcome promise can distort the student pipeline."
+    },
+    {
+      "case_id": "selector_calibration_qpi_employment_metric_credibility_001",
+      "category": "qpi_owner_reviewed_year_end_employment_entrepreneurship",
+      "input": "就业率数字很高，组织想直接拿来证明办学质量，但数据是在强 KPI 压力下生产的，学生和企业层面的核验机制不清楚。",
+      "expected_selector_behavior": "select_qpi",
+      "expected_notes": "Owner-reviewed employment case 005: high metric value must be distinguished from high metric credibility."
+    },
+    {
+      "case_id": "selector_calibration_qpi_employment_asset_integration_boundary_001",
+      "category": "qpi_owner_reviewed_year_end_employment_entrepreneurship",
+      "input": "组织有真实企业资源和实习项目，但这些资源更多像展示资产和实习证明，没有进入课程、项目、评价和学生作品。",
+      "expected_selector_behavior": "select_qpi",
+      "expected_notes": "Owner-reviewed employment case 006: real external asset with unproven learning integration is a boundary mixed case."
+    },
+    {
+      "case_id": "selector_calibration_qpi_employment_authority_transfer_001",
+      "category": "qpi_owner_reviewed_year_end_employment_entrepreneurship",
+      "input": "某个职能部门因为指标好、资源多，就被认为应该接管教学评价和组织控制权，我需要区分资源认可和权威转移。",
+      "expected_selector_behavior": "select_qpi",
+      "expected_notes": "Owner-reviewed employment case 007: asset recognition must not be inflated into authority transfer."
+    },
+    {
+      "case_id": "selector_calibration_qpi_employment_transactional_education_001",
+      "category": "qpi_owner_reviewed_year_end_employment_entrepreneurship",
+      "input": "组织为了生存越来越把教育做成就业率、创收和合规指标机器，我想判断这是经营调整还是教育价值定义被接管。",
+      "expected_selector_behavior": "select_qpi",
+      "expected_notes": "Owner-reviewed employment case 008: survival strategy may reframe education as transactional output."
+    },
+    {
+      "case_id": "selector_calibration_qpi_engineering_target_authenticity_001",
+      "category": "qpi_owner_reviewed_year_end_engineering_center",
+      "input": "一个原本做教学辅助和技能训练的技术单位，被要求快速做成产业化利润中心，但市场、人员、设备使用和交付闭环都没有验证。",
+      "expected_selector_behavior": "select_qpi",
+      "expected_notes": "Owner-reviewed engineering case 001: target authenticity gap between terminal target and bridge evidence."
+    },
+    {
+      "case_id": "selector_calibration_qpi_engineering_equipment_solutionism_001",
+      "category": "qpi_owner_reviewed_year_end_engineering_center",
+      "input": "组织想先买高端设备再等项目自然出现，但没有真实订单、操作者就绪度、安全规程和单位经济模型。",
+      "expected_selector_behavior": "select_qpi",
+      "expected_notes": "Owner-reviewed engineering case 002: equipment-led solutionism without market closure."
+    },
+    {
+      "case_id": "selector_calibration_qpi_engineering_shortcut_debt_001",
+      "category": "qpi_owner_reviewed_year_end_engineering_center",
+      "input": "过去一直用灵活替代人员顶上正式能力缺口，现在监管和事故风险让这个短路方案走不通了。",
+      "expected_selector_behavior": "select_qpi",
+      "expected_notes": "Owner-reviewed engineering case 003: shortcut debt meets hard boundary."
+    },
+    {
+      "case_id": "selector_calibration_qpi_engineering_credential_integrity_001",
+      "category": "qpi_owner_reviewed_year_end_engineering_center",
+      "input": "发现某个资质或履历存在异常，但组织还想按能不能干活来决定是否继续使用，我需要判断这是人员问题还是制度问题。",
+      "expected_selector_behavior": "select_qpi",
+      "expected_notes": "Owner-reviewed engineering case 004: route to policy review, not personnel verdict."
+    },
+    {
+      "case_id": "selector_calibration_qpi_engineering_market_closure_001",
+      "category": "qpi_owner_reviewed_year_end_engineering_center",
+      "input": "生产能力可能有一点，但没人知道客户从哪里来、谁负责获客、收入能否覆盖设备和人工，组织却已经下了产值目标。",
+      "expected_selector_behavior": "select_qpi",
+      "expected_notes": "Owner-reviewed engineering case 005: production capability without acquisition channel."
+    },
+    {
+      "case_id": "selector_calibration_qpi_engineering_micro_control_001",
+      "category": "qpi_owner_reviewed_year_end_engineering_center",
+      "input": "执行负责人越来越疲惫，表面像是不主动，实际每个细节都被领导反复改、反复拍板，责任边界不清。",
+      "expected_selector_behavior": "select_qpi",
+      "expected_notes": "Owner-reviewed engineering case 006: execution fatigue may reveal decision-rights architecture failure."
+    },
+    {
+      "case_id": "selector_calibration_qpi_engineering_asset_liability_001",
+      "category": "qpi_owner_reviewed_year_end_engineering_center",
+      "input": "一个强势部门放弃的项目被转给较弱部门，接收方把它当资产，但还不知道转移原因、维护成本、责任边界和真实收益。",
+      "expected_selector_behavior": "select_qpi",
+      "expected_notes": "Owner-reviewed engineering case 007: inherited asset may hide liability."
+    },
+    {
+      "case_id": "selector_calibration_qpi_engineering_personnel_transition_001",
+      "category": "qpi_owner_reviewed_year_end_engineering_center",
+      "input": "技术方向升级后，老员工能力不匹配，老板想裁掉或换新人，但培训、转岗、补偿、协商和法律审查路径都没有。",
+      "expected_selector_behavior": "select_qpi",
+      "expected_notes": "Owner-reviewed engineering case 008: capability upgrade requires legitimate personnel transition path."
+    },
+    {
+      "case_id": "selector_calibration_qpi_international_compliance_retention_001",
+      "category": "qpi_owner_reviewed_year_end_international_college",
+      "input": "招生团队想用路径调整留住学生，但这个留存动作可能改变机构合规姿态、证书信任和未来投诉审计风险。",
+      "expected_selector_behavior": "select_qpi",
+      "expected_notes": "Owner-reviewed international case 001: retention workaround crosses compliance boundary."
+    },
+    {
+      "case_id": "selector_calibration_qpi_international_capacity_gate_001",
+      "category": "qpi_owner_reviewed_year_end_international_college",
+      "input": "增长项目承诺扩招，但宿舍和服务容量不足，需要挤占其他单元资源，组织还没有硬性容量闸门。",
+      "expected_selector_behavior": "select_qpi",
+      "expected_notes": "Owner-reviewed international case 002: cross-unit conflict under missing hard capacity gate."
+    },
+    {
+      "case_id": "selector_calibration_qpi_international_logistics_no_call_001",
+      "category": "qpi_no_call_boundary_year_end_international_college",
+      "input": "帮我把这些学生按宿舍容量排一下床位表。",
+      "expected_selector_behavior": "no_call_or_low_priority",
+      "expected_notes": "Paired no-call trap for case 002: simple logistics execution is not QPI unless capacity governance is present."
+    },
+    {
+      "case_id": "selector_calibration_qpi_international_role_inflation_001",
+      "category": "qpi_owner_reviewed_year_end_international_college",
+      "input": "一个高业绩团队希望用贡献换取更高职级、对外代表权和内部资源例外，但权责和继任机制还没设计。",
+      "expected_selector_behavior": "select_qpi",
+      "expected_notes": "Owner-reviewed international case 003: performance-backed role inflation."
+    },
+    {
+      "case_id": "selector_calibration_qpi_international_viewpoint_divergence_001",
+      "category": "qpi_owner_reviewed_year_end_international_college",
+      "input": "执行层只想把招生转化做好，决策层要的是从招生、培养到结果的完整链条，双方其实在定义不同的工作对象。",
+      "expected_selector_behavior": "select_qpi",
+      "expected_notes": "Owner-reviewed international case 004: inter-viewpoint divergence with classification_by_viewpoint."
+    },
+    {
+      "case_id": "selector_calibration_qpi_international_metric_distortion_001",
+      "category": "qpi_owner_reviewed_year_end_international_college",
+      "input": "执行层提交了好看的资质指标，决策层怀疑这些指标急功近利，只是为了评估和述职，不代表真实教学能力。",
+      "expected_selector_behavior": "select_qpi",
+      "expected_notes": "Owner-reviewed international case 005: metric fact verification embedded in governance distortion."
+    },
+    {
+      "case_id": "selector_calibration_qpi_international_pricing_trust_001",
+      "category": "qpi_owner_reviewed_year_end_international_college",
+      "input": "高客单价项目招生困难，表面是价格太高或降价会伤害老生公平，深层是组织没有建立可信承诺和可验证结果。",
+      "expected_selector_behavior": "select_qpi",
+      "expected_notes": "Owner-reviewed international case 006: pricing deadlock as trust-system failure."
+    },
+    {
+      "case_id": "selector_calibration_qpi_international_capability_institutionalization_001",
+      "category": "qpi_owner_reviewed_year_end_international_college",
+      "input": "一个小团队执行力很强，但流程、客户关系、文档和继任都没沉淀到组织里，关键人离开业务可能失控。",
+      "expected_selector_behavior": "select_qpi",
+      "expected_notes": "Owner-reviewed international case 007: high-performing capability not yet institutionalized."
+    },
+    {
+      "case_id": "selector_calibration_qpi_international_asset_expansion_001",
+      "category": "qpi_owner_reviewed_year_end_international_college",
+      "input": "组织有真实外部渠道和合作资产，想用它支撑快速扩张，但内部交付、合规、质量和容量还没准备好。",
+      "expected_selector_behavior": "select_qpi",
+      "expected_notes": "Owner-reviewed international case 008: real external asset used as license for unready internal expansion."
+    },
+    {
+      "case_id": "selector_calibration_qpi_research_identity_simulation_001",
+      "category": "qpi_owner_reviewed_year_end_research_office",
+      "input": "组织没有真实科研能力，却想通过人员、费用、专利和论文包装出研究身份，以满足外部优惠或认证要求。",
+      "expected_selector_behavior": "select_qpi",
+      "expected_notes": "Owner-reviewed research case 001: umbrella research identity simulation case."
+    },
+    {
+      "case_id": "selector_calibration_qpi_research_accounting_reduction_001",
+      "category": "qpi_owner_reviewed_year_end_research_office",
+      "input": "研究人员数量和费用类别不够，组织想把非研究角色和薪资类别调成研究相关口径来补表。",
+      "expected_selector_behavior": "select_qpi",
+      "expected_notes": "Owner-reviewed research case 002: data completeness is not truthfulness."
+    },
+    {
+      "case_id": "selector_calibration_qpi_research_transactional_assets_001",
+      "category": "qpi_owner_reviewed_year_end_research_office",
+      "input": "组织想通过交易性专利、论文或研究资产形成科研证据，但这些证据不一定对应真实科研能力。",
+      "expected_selector_behavior": "select_qpi",
+      "expected_notes": "Owner-reviewed research case 003: transactional research assets as subcase evidence."
+    },
+    {
+      "case_id": "selector_calibration_qpi_research_ranking_trap_001",
+      "category": "qpi_owner_reviewed_year_end_research_office",
+      "input": "我们想快速提升排名和科研指标，可以通过购买、包装或短期冲刺论文专利来改善外部可见度吗？",
+      "expected_selector_behavior": "select_qpi",
+      "expected_notes": "Owner-reviewed research case 004: quick ranking improvement can be a QPI selector trap."
+    },
+    {
+      "case_id": "selector_calibration_qpi_research_talent_role_mismatch_001",
+      "category": "qpi_owner_reviewed_year_end_research_office",
+      "input": "组织引进了高端人才，但没有平台、任务和角色设计，只把他当外部指标和展示资产。",
+      "expected_selector_behavior": "select_qpi",
+      "expected_notes": "Owner-reviewed research case 005: high-level talent as role-governance case."
+    },
+    {
+      "case_id": "selector_calibration_qpi_research_hard_capacity_001",
+      "category": "qpi_owner_reviewed_year_end_research_office",
+      "input": "业务扩张需要更多空间和设施，但物理容量不够，领导想靠协调和临时腾挪解决。",
+      "expected_selector_behavior": "select_qpi",
+      "expected_notes": "Owner-reviewed research case 006: hard capacity cannot be solved by administrative command."
+    },
+    {
+      "case_id": "selector_calibration_qpi_research_safety_accountability_001",
+      "category": "qpi_owner_reviewed_year_end_research_office",
+      "input": "安全事项临近截止才发现没人牵头，最后靠最高层临时抓人指派完成。",
+      "expected_selector_behavior": "select_qpi",
+      "expected_notes": "Owner-reviewed research case 007: Q-like responsibility question reveals accountability Issue."
+    },
+    {
+      "case_id": "selector_calibration_qpi_research_penalty_integrity_001",
+      "category": "qpi_owner_reviewed_year_end_research_office",
+      "input": "组织认为只要没有罚款、没有被约谈、没有报销损失，就说明合规风险不大。",
+      "expected_selector_behavior": "select_qpi",
+      "expected_notes": "Owner-reviewed research case 008: punishment state versus integrity state."
     }
   ]
 }

tests/qpi.regression.json

@@ -17,6 +17,35 @@
     {"case_id": "case_qpi_misuse_reduction_001", "model_id": "qpi", "case_type": "misuse", "input": "组织创新乏力就是员工不够努力，给他们加 KPI 就行。", "expected_behavior": "应识别暴力降维，提示系统性课题被压缩成个人执行难题。", "failure_signal": "接受单一执行力解释。", "expected_output_elements": ["暴力降维", "issue"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["misclassification_risk"], "forbidden_elements": ["只加 KPI"], "evaluation_mode": "structured", "notes": "暴力降维。"},
     {"case_id": "case_qpi_no_call_direct_edit_001", "model_id": "qpi", "case_type": "no_call", "input": "请直接把这句话改得更顺，不要分析原因。", "expected_behavior": "应 no_call，不进入 QPI 分析。", "failure_signal": "输出问题类型判断。", "expected_output_elements": ["classification=no_call"], "should_call_model": false, "expected_primary_model": "none", "negative_expected_models": ["qpi", "intellectual_archaeology"], "expected_classification": "no_call", "expected_dominant_scarcity": "not_applicable", "expected_max_depth": "not_applicable", "minimum_required_elements": ["recommended_next_step=不调用"], "forbidden_elements": ["dominant_scarcity=data"], "evaluation_mode": "structured", "notes": "纯改写 no-call。"},
     {"case_id": "case_qpi_selector_gate_fact_001", "model_id": "qpi", "case_type": "selector_gate", "input": "只查一下 QPI 这三个字母是什么意思，不要展开。", "expected_behavior": "selector 应低分或 no_call，思想考古必须被拒绝。", "failure_signal": "因为出现 QPI 或模型词而召回 IA。", "expected_output_elements": ["no_call"], "should_call_model": false, "expected_primary_model": "none", "negative_expected_models": ["intellectual_archaeology"], "expected_classification": "no_call", "expected_dominant_scarcity": "not_applicable", "expected_max_depth": "not_applicable", "minimum_required_elements": ["rejected_models"], "forbidden_elements": ["七层"], "evaluation_mode": "structured", "notes": "selector 防误召回。"},
-    {"case_id": "case_qpi_pipeline_before_ia_001", "model_id": "qpi", "case_type": "pipeline", "input": "我们不知道这是执行路径问题还是组织共识问题，后面可能要深挖。", "expected_behavior": "应先调用 QPI，再决定是否进入思想考古。", "failure_signal": "直接调用思想考古。", "expected_output_elements": ["qpi first"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "mixed", "expected_dominant_scarcity": "mixed", "expected_max_depth": "not_applicable", "minimum_required_elements": ["next_model_candidates"], "forbidden_elements": [], "evaluation_mode": "structured", "notes": "QPI-before-IA pipeline gate。"}
+    {"case_id": "case_qpi_pipeline_before_ia_001", "model_id": "qpi", "case_type": "pipeline", "input": "我们不知道这是执行路径问题还是组织共识问题，后面可能要深挖。", "expected_behavior": "应先调用 QPI，再决定是否进入思想考古。", "failure_signal": "直接调用思想考古。", "expected_output_elements": ["qpi first"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "mixed", "expected_dominant_scarcity": "mixed", "expected_max_depth": "not_applicable", "minimum_required_elements": ["next_model_candidates"], "forbidden_elements": [], "evaluation_mode": "structured", "notes": "QPI-before-IA pipeline gate。"},
+    {"case_id": "case_qpi_flow_no_simulation_001", "model_id": "qpi", "case_type": "misuse", "input": "这个多代理评审包看起来有完整报告，但其实只是主会话模拟，没有真实独立 agent 调用记录；我需要判断它能不能作为正式输出。", "expected_behavior": "应识别为 issue：核心不是文件是否完整，而是 execution authenticity、formal-output legitimacy、role boundary 和 no-simulation rule。应标记 simulated output 不能进入正式综合，必须 blocked_until_real_invocation。", "failure_signal": "把它当成普通文件格式问题或调用包实现问题，允许模拟报告进入正式评审综合。", "expected_output_elements": ["classification=issue", "dominant_scarcity=consensus_order", "formal_output=false", "blocked_until_real_invocation=true"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": ["intellectual_archaeology"], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["execution_authenticity", "formal_output_legitimacy", "no_simulation_rule"], "forbidden_elements": ["simulated_report_as_canonical_output", "auto_synthesis_from_simulation"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-flow-redesign-002", "notes": "Owner-reviewed flow-redesign case 002. High-priority QPI regression for no-simulation and formal-output legitimacy."},
+    {"case_id": "case_qpi_disappointment_label_as_identity_001", "model_id": "qpi", "case_type": "boundary", "input": "我不是只想查这个心理标签是什么意思，它已经影响我怎么理解自己、怎么设关系边界和要不要寻求帮助。", "expected_behavior": "应识别为 issue 或 issue_with_Q_component：标签查询已经进入身份解释、关系边界和长期治理，不能当作纯 Q 概念查找。", "failure_signal": "只解释标签定义，或因为出现心理标签就无条件升维为临床判断。", "expected_output_elements": ["classification=issue", "dominant_scarcity=consensus_order", "classification_note=issue_with_Q_component"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": ["intellectual_archaeology"], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["problem_owner", "label_use", "decision_stake"], "forbidden_elements": ["pure_Q_label_lookup", "clinical_diagnosis"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-disappointment-002", "notes": "Owner-reviewed disappointment case 002. Conditional what-is-X false-positive trap."},
+    {"case_id": "case_qpi_disappointment_single_factor_totalization_001", "model_id": "qpi", "case_type": "misuse", "input": "我不想把情感隔离全部归因于童年或某一个人，我需要判断哪些是触发、维持条件、高权重要素和当前行动杠杆。", "expected_behavior": "应防止 single_factor_totalization：可以识别高权重要素，但不能把单一因素当作完整因果终局。", "failure_signal": "输出唯一根本原因，或禁止识别任何高权重要素。", "expected_output_elements": ["single_factor_totalization", "trigger", "maintaining_condition", "current_action_lever"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["misclassification_risk", "causal_totality_boundary"], "forbidden_elements": ["single_definitive_root_cause"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-disappointment-003", "notes": "Owner-reviewed disappointment case 003. Explanatory usefulness is not causal finality."},
+    {"case_id": "case_qpi_disappointment_one_time_fix_001", "model_id": "qpi", "case_type": "misuse", "input": "这个心理关系问题不能靠三步修复或一次干预解决，我需要判断它是不是只能阶段性重构和长期治理。", "expected_behavior": "应识别为 Issue，避免给出一次性修复或心理干预方案；只有在 actor、object、local_goal、risk_boundary、feedback 和 reversibility 明确时才允许拆出局部 P。", "failure_signal": "直接给三步修复、单点干预或治疗建议。", "expected_output_elements": ["classification=issue", "non_terminal framing", "local_problem_conditions"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["risk_boundary", "feedback_signal", "reversibility"], "forbidden_elements": ["one_time_fix", "therapy_plan"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-disappointment-004", "notes": "Owner-reviewed disappointment case 004. Prevents over-routing psychological-relational Issue to Problem."},
+    {"case_id": "case_qpi_disappointment_mismatch_diagnostics_001", "model_id": "qpi", "case_type": "selector_gate", "input": "这个问题到底有没有被误路由：把 I 当 Q、把 I 当 P、把 P 过度升维成 I，或者把保护性边界病理化？", "expected_behavior": "selector 应先选 QPI；QPI 应输出 wrong_route_to_avoid 或等价误路由诊断，而不是只给最终分类。", "failure_signal": "只给单一标签，或直接调用思想考古。", "expected_output_elements": ["wrong_route_to_avoid", "I_as_Q", "I_as_P", "P_as_I"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": ["intellectual_archaeology"], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["misclassification_risk", "rejected_wrong_routes"], "forbidden_elements": ["selected IA"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-disappointment-007", "notes": "Owner-reviewed disappointment case 007. QPI mismatch diagnostics regression."},
+    {"case_id": "case_qpi_disappointment_one_person_issue_001", "model_id": "qpi", "case_type": "positive", "input": "只有我一个人在做自我治理，但我要长期校准隔离什么时候是保护，什么时候是过度泛化防御，这是不是仍然可以是 Issue？", "expected_behavior": "应识别为 Issue：Issue 不需要多人；单人主体在保护、开放、风险、能量、反馈和关系实验之间持续校准时，也有治理负荷。", "failure_signal": "因为只有一个人就降为 Problem，或给出二元好坏判断。", "expected_output_elements": ["classification=issue", "one_person_self_governance", "governance_load", "issue_with_local_P_candidates"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["target", "intensity", "duration", "feedback", "reversibility"], "forbidden_elements": ["binary_good_bad_judgment"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-disappointment-008", "notes": "Owner-reviewed disappointment case 008. Canonical anchor: one-person self-governance can still be Issue."},
+    {"case_id": "case_qpi_org_hard_resource_documentation_001", "model_id": "qpi", "case_type": "misuse", "input": "组织面对硬性资源缺口，没有真实补资源，而是想通过重命名、材料包装和合规口径让指标看起来达标。", "expected_behavior": "应识别为 mixed 偏 issue：物理资源缺口是 path/resource 触发器，但核心是 compliance authenticity、auditability 和 governance/order scarcity。", "failure_signal": "把它当成普通文书整理问题、缺数据问题，或只归为 path_resource 而忽略合规真实性风险。", "expected_output_elements": ["classification=mixed", "dominant_scarcity=consensus_order", "path_resource_trigger_with_compliance_governance_failure"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": ["intellectual_archaeology"], "expected_classification": "mixed", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["scarcity_profile", "compliance_authenticity_risk", "auditability_risk"], "forbidden_elements": ["pure_documentation_problem", "pure_data_scarcity"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-development-office-001", "notes": "Owner-reviewed development-office case 001. Hard resource gap disguised as documentation problem."},
+    {"case_id": "case_qpi_org_credential_continuity_001", "model_id": "qpi", "case_type": "misuse", "input": "为了修复人员资质指标，组织准备替换或重分类一批岗位，但这些人承担运营记忆、角色连续性和信任关系。", "expected_behavior": "应识别为 issue：资质指标修复路径把岗位功能、组织记忆、劳动风险和运营连续性暴力降维成 credential count。", "failure_signal": "只建议优化招聘或替换清单，接受资质指标就是完整质量指标。", "expected_output_elements": ["classification=issue", "dominant_scarcity=consensus_order", "violent_reduction", "operational_continuity"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["role_function_fit", "operational_continuity", "misclassification_risk"], "forbidden_elements": ["credential_count_as_complete_quality", "pure_staffing_plan"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-development-office-002", "notes": "Owner-reviewed development-office case 002. High-priority organization-type QPI regression."},
+    {"case_id": "case_qpi_org_untrusted_data_001", "model_id": "qpi", "case_type": "boundary", "input": "材料和台账都很完整，但它们对应的真实运营并不稳定，也经不起审计核查；这不是缺数据，而是数据不可信。", "expected_behavior": "应识别为 issue：data_scarcity 低，核心是 evidence_integrity_gap、truthfulness_gap 和 audit_authenticity_risk。推荐先做 evidence authenticity audit。", "failure_signal": "把它判为普通 Q 类缺数据，或直接进入资源规划而不检查证据真实性。", "expected_output_elements": ["classification=issue", "dominant_scarcity=consensus_order", "data_scarcity=low", "evidence_authenticity_audit"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": ["intellectual_archaeology"], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["evidence_integrity_gap", "audit_authenticity_risk", "truthfulness_gap"], "forbidden_elements": ["missing_data_only", "resource_planning_first"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-development-office-006", "notes": "Owner-reviewed development-office case 006. Regression for missing data versus untrusted data."},
+    {"case_id": "case_qpi_academic_ai_evidence_boundary_001", "model_id": "qpi", "case_type": "misuse", "input": "看起来只是让 AI 帮忙生成评估材料，但实际是先定结论再倒推证据，我需要判断这是不是材料执行任务。", "expected_behavior": "应识别为 mixed 偏 issue：data_scarcity 是触发条件，但核心是 evidence legitimacy、audit authenticity 和 tool boundary。AI 可以整理证据，不能制造证据关系。", "failure_signal": "把它当成普通材料生成、润色或执行任务，允许用工具从结论倒推证据。", "expected_output_elements": ["classification=mixed", "dominant_scarcity=consensus_order", "tool_boundary", "evidence_legitimacy"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": ["intellectual_archaeology"], "expected_classification": "mixed", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["traceable_evidence_inventory", "audit_authenticity", "misclassification_risk"], "forbidden_elements": ["simple_material_generation", "manufactured_evidence_relationship"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-academic-affairs-001", "notes": "Owner-reviewed academic-affairs case 001. AI/tool execution request that requires QPI."},
+    {"case_id": "case_qpi_academic_policy_memory_001", "model_id": "qpi", "case_type": "boundary", "input": "我们想取消一个诱发低质量产出的旧激励政策，但过去按这个规则投入过的人会觉得不公平，组织信任也已经受损。", "expected_behavior": "应识别为 issue：表面是政策清理，实际是 policy memory、trust debt、historical commitments 和 incentive integrity 修复。", "failure_signal": "把它当成简单政策取消任务，只输出新规则而不处理旧政策记忆和信任债务。", "expected_output_elements": ["classification=issue", "dominant_scarcity=consensus_order", "policy_memory", "trust_debt"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["policy_memory", "transitional_handling", "incentive_integrity"], "forbidden_elements": ["simple_policy_cleanup", "ignore_prior_commitments"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-academic-affairs-003", "notes": "Owner-reviewed academic-affairs case 003. False-negative trap for policy cleanup."},
+    {"case_id": "case_qpi_academic_outcome_quality_assurance_001", "model_id": "qpi", "case_type": "misuse", "input": "学生结果和投诉指标变差，部门解释为生源质量问题，但还没有审计教学质量制度和管理杠杆。", "expected_behavior": "应识别为 mixed，dominant_scarcity=consensus_order：输入条件可能影响结果，但不能替代对管理杠杆和质量保障制度的审计。", "failure_signal": "完全接受生源质量解释，或把全部因果责任无证据地压给单一部门。", "expected_output_elements": ["classification=mixed", "dominant_scarcity=consensus_order", "quality_assurance_gap", "management_lever_audit"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "mixed", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["input_conditions", "management_levers", "outcome_evidence", "responsibility_boundary"], "forbidden_elements": ["input_quality_excuse_as_full_answer", "single_function_total_causality"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-academic-affairs-006", "notes": "Owner-reviewed academic-affairs case 006. Input conditions versus quality-assurance audit."},
+    {"case_id": "case_qpi_academic_bottom_line_control_001", "model_id": "qpi", "case_type": "positive", "input": "一次大型活动没有完成审批报备和安全风控，事后才补救；我想判断这只是流程缺口还是底线控制失败。", "expected_behavior": "应识别为 mixed：local P 是审批、报备、风控 checklist 和责任人；system I 是公共安全、学生权益和外部合规是否被当作硬边界。", "failure_signal": "只补一个流程表，或只把它升维成抽象文化问题而不要求硬门禁流程。", "expected_output_elements": ["classification=mixed", "dominant_scarcity=consensus_order", "bottom_line_control_failure", "hard_gate"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "mixed", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["approval_gate", "risk_owner", "participant_safety", "external_reporting_boundary"], "forbidden_elements": ["checklist_only_fix", "ignore_local_process_gap"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-academic-affairs-008", "notes": "Owner-reviewed academic-affairs case 008. Concrete operating accident revealing bottom-line control failure."},
+    {"case_id": "case_qpi_employment_credential_compliance_exposure_001", "model_id": "qpi", "case_type": "misuse", "input": "为了补资质指标，组织想快速挂靠或采购带资历的人，但这些人是否进入教学科研和学生发展完全不清楚。", "expected_behavior": "应识别为 mixed，dominant_scarcity=consensus_order：credential gap 是真实资源缺口，但指标修补路径会制造 compliance exposure，不能当成简单采购或人事补缺。", "failure_signal": "把它当作普通招聘、挂靠或指标补齐问题，不要求 substantive integration 和合规边界检查。", "expected_output_elements": ["classification=mixed", "dominant_scarcity=consensus_order", "compliance_exposure", "substantive_integration_not_proven"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "mixed", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["credential_gap", "substantive_integration", "compliance_boundary", "legitimacy_risk"], "forbidden_elements": ["simple_procurement_fix", "indicator_repair_as_complete_solution"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-employment-entrepreneurship-002", "notes": "Owner-reviewed employment case 002. Credential metric repair versus compliance exposure."},
+    {"case_id": "case_qpi_employment_reported_metric_legitimacy_001", "model_id": "qpi", "case_type": "boundary", "input": "部门述职说自己创收很高，但这个数字按部门口径算，和组织财务确认标准不一致，还被用来争取更大权力。", "expected_behavior": "应识别为 mixed，dominant_scarcity=consensus_order：数据口径问题是入口，核心是 reported metric lineage、financial recognition 和 performance legitimacy。", "failure_signal": "照单全收述职数据，或只要求补一个数据表而不处理绩效正当性和权力扩张风险。", "expected_output_elements": ["classification=mixed", "dominant_scarcity=consensus_order", "reported_metric_lineage", "performance_legitimacy"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "mixed", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["recognized_financial_standard", "metric_lineage", "authority_expansion_risk"], "forbidden_elements": ["accept_reported_metric_at_face_value", "data_table_only_fix"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-employment-entrepreneurship-003", "notes": "Owner-reviewed employment case 003. False-positive trap for reported metrics."},
+    {"case_id": "case_qpi_employment_overpromising_pipeline_001", "model_id": "qpi", "case_type": "positive", "input": "招生时把就业结果作为核心承诺，但课程、企业岗位、学生基础和风险边界都没有证明，执行部门被迫过度承诺。", "expected_behavior": "应识别为 mixed，dominant_scarcity=consensus_order：既有交付路径问题，也有学生承诺、招生 pipeline、信任和组织身份风险。", "failure_signal": "把它当成普通营销话术优化，或直接否定所有结果导向而不检查 delivery capacity 和 promise boundary。", "expected_output_elements": ["classification=mixed", "dominant_scarcity=consensus_order", "delivery_capacity", "promise_boundary"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "mixed", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["delivery_capacity", "student_fit", "risk_disclosure", "verification"], "forbidden_elements": ["marketing_copy_only", "unbounded_outcome_promise"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-employment-entrepreneurship-004", "notes": "Owner-reviewed employment case 004. Legitimate outcome orientation versus overpromising."},
+    {"case_id": "case_qpi_employment_metric_credibility_001", "model_id": "qpi", "case_type": "misuse", "input": "就业率数字很高，组织想直接拿来证明办学质量，但数据是在强 KPI 压力下生产的，学生和企业层面的核验机制不清楚。", "expected_behavior": "应识别为 mixed，dominant_scarcity=consensus_order：高指标值不等于高指标可信度，必须输出 evidence_gap 并审计数据生产机制。", "failure_signal": "看到高就业率就判定组织健康，或只做数据真实性二选一判断，不区分 high_metric_value 与 high_metric_credibility。", "expected_output_elements": ["classification=mixed", "dominant_scarcity=consensus_order", "evidence_gap", "metric_credibility"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "mixed", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["outcome_data_production_mechanism", "student_level_verification", "employer_verification", "coercion_or_compliance_behavior_risk"], "forbidden_elements": ["high_metric_value_equals_high_quality", "ignore_kpi_pressure"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-employment-entrepreneurship-005", "notes": "Owner-reviewed employment case 005. High metric value versus high metric credibility."},
+    {"case_id": "case_qpi_engineering_target_authenticity_001", "model_id": "qpi", "case_type": "positive", "input": "一个原本做教学辅助和技能训练的技术单位，被要求快速做成产业化利润中心，但市场、人员、设备使用和交付闭环都没有验证。", "expected_behavior": "应识别为 mixed，dominant_scarcity=consensus_order：真实存在能力和路径缺口，但核心是 target_authenticity_gap，必须区分 milestone target、terminal target 和 bridge evidence。", "failure_signal": "照单接受高目标为执行任务，或只把它降维成买设备、招人、做项目。", "expected_output_elements": ["classification=mixed", "dominant_scarcity=consensus_order", "target_authenticity_gap", "bridge_evidence"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "mixed", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["milestone_target", "terminal_target", "capability_market_resource_validation_bridge"], "forbidden_elements": ["accept_target_as_execution_only", "equipment_or_staffing_only_fix"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-engineering-center-001", "notes": "Owner-reviewed engineering case 001. Target authenticity gap."},
+    {"case_id": "case_qpi_engineering_equipment_solutionism_001", "model_id": "qpi", "case_type": "misuse", "input": "组织想先买高端设备再等项目自然出现，但没有真实订单、操作者就绪度、安全规程和单位经济模型。", "expected_behavior": "应识别为 mixed，dominant_scarcity=consensus_order：设备不是能力本身，需求证明、操作者、安全、经济模型和试点结果没有过 gate 前，不能当作执行问题。", "failure_signal": "把问题当成设备选型或采购清单，忽略市场闭环和操作者 readiness。", "expected_output_elements": ["classification=mixed", "dominant_scarcity=consensus_order", "equipment_led_solutionism", "hard_gate"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "mixed", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["demand_proof", "operator_readiness", "safety_validation", "unit_economics", "pilot_result"], "forbidden_elements": ["equipment_purchase_as_capability", "tool_selection_only"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-engineering-center-002", "notes": "Owner-reviewed engineering case 002. Equipment-led solutionism."},
+    {"case_id": "case_qpi_engineering_credential_integrity_policy_001", "model_id": "qpi", "case_type": "boundary", "input": "发现某个资质或履历存在异常，但组织还想按能不能干活来决定是否继续使用，我需要判断这是人员问题还是制度问题。", "expected_behavior": "应识别为 issue，dominant_scarcity=consensus_order，并明确 no_personnel_verdict：QPI 不判断具体人员，只路由到筛查制度、例外政策和风险归属审查。", "failure_signal": "直接判断某个人能不能用、是否造假、是否应辞退，或只按短期可用性处理。", "expected_output_elements": ["classification=issue", "dominant_scarcity=consensus_order", "no_personnel_verdict", "credential_integrity"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["credential_verification_lineage", "exception_policy", "risk_owner", "policy_review"], "forbidden_elements": ["specific_personnel_verdict", "usability_only_decision"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-engineering-center-004", "notes": "Owner-reviewed engineering case 004. Credential integrity versus usability."},
+    {"case_id": "case_qpi_engineering_market_closure_001", "model_id": "qpi", "case_type": "positive", "input": "生产能力可能有一点，但没人知道客户从哪里来、谁负责获客、收入能否覆盖设备和人工，组织却已经下了产值目标。", "expected_behavior": "应识别为 mixed，dominant_scarcity=consensus_order：对经营主体，这不是先查订单来源的普通 Question，而是把生产能力误当成商业闭环的第一性错位。", "failure_signal": "先判为单纯 question，或只要求市场调研而不处理主体目的、客户、渠道、交付和单位经济模型。", "expected_output_elements": ["classification=mixed", "dominant_scarcity=consensus_order", "business_purpose", "acquisition_channel"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "mixed", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["problem_owner", "primary_purpose", "customer_segment", "demand_signal", "acquisition_channel", "unit_economics"], "forbidden_elements": ["production_capacity_equals_business_viability", "question_only_classification"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-engineering-center-005", "notes": "Owner-reviewed engineering case 005. Production capability without market closure."},
+    {"case_id": "case_qpi_international_compliance_retention_001", "model_id": "qpi", "case_type": "misuse", "input": "招生团队想用路径调整留住学生，但这个留存动作可能改变机构合规姿态、证书信任和未来投诉审计风险。", "expected_behavior": "应识别为 issue，dominant_scarcity=consensus_order：留存压力和路径缺口存在，但合规红线占主导，不能把它当作普通招生留存 Problem。", "failure_signal": "只输出留存方案或招生话术，不先确认 compliance red line、credential trust 和 audit risk。", "expected_output_elements": ["classification=issue", "dominant_scarcity=consensus_order", "compliance_red_line", "credential_trust"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["retention_pressure", "compliance_boundary", "future_complaint_or_audit_risk"], "forbidden_elements": ["retention_tactic_only", "pathway_workaround_without_red_line"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-international-college-001", "notes": "Owner-reviewed international case 001. Retention workaround crossing compliance boundary."},
+    {"case_id": "case_qpi_international_capacity_governance_001", "model_id": "qpi", "case_type": "boundary", "input": "增长项目承诺扩招，但宿舍和服务容量不足，需要挤占其他单元资源，组织还没有硬性容量闸门。", "expected_behavior": "应识别为 mixed，dominant_scarcity=path_resource：硬约束是容量，但跨单元冲突和承诺边界使其成为容量治理问题。", "failure_signal": "把它当作简单排宿舍或物流调度，或只抽象成文化冲突而不处理 hard capacity gate。", "expected_output_elements": ["classification=mixed", "dominant_scarcity=path_resource", "hard_capacity_gate", "cross_unit_conflict"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "mixed", "expected_dominant_scarcity": "path_resource", "expected_max_depth": "not_applicable", "minimum_required_elements": ["physical_capacity", "resource_displacement", "delivery_assurance", "arbitration_rule"], "forbidden_elements": ["simple_logistics_only", "ignore_capacity_limit"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-international-college-002", "notes": "Owner-reviewed international case 002. Capacity governance versus simple logistics."},
+    {"case_id": "case_qpi_international_metric_governance_001", "model_id": "qpi", "case_type": "misuse", "input": "执行层提交了好看的资质指标，决策层怀疑这些指标急功近利，只是为了评估和述职，不代表真实教学能力。", "expected_behavior": "应识别为 issue，dominant_scarcity=consensus_order：事实核验嵌在治理扭曲中，必须检查指标是否连接长期目标、真实能力、多方收益和可审计证据。", "failure_signal": "停留在问指标真假，或直接接受指标为能力证明。", "expected_output_elements": ["classification=issue", "dominant_scarcity=consensus_order", "metric_distortion", "traceable_evidence_chain"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["long_term_goal_alignment", "real_capability", "multi_party_value", "audit_evidence"], "forbidden_elements": ["question_only_classification", "metric_appearance_as_capability"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-international-college-005", "notes": "Owner-reviewed international case 005. Metric fact verification embedded in governance distortion."},
+    {"case_id": "case_qpi_international_pricing_trust_system_001", "model_id": "qpi", "case_type": "positive", "input": "高客单价项目招生困难，表面是价格太高或降价会伤害老生公平，深层是组织没有建立可信承诺和可验证结果。", "expected_behavior": "应识别为 issue，dominant_scarcity=consensus_order：定价僵局是表象，高客单价教育产品需要组织级信任体系、可信承诺、可验证结果和协同交付。", "failure_signal": "只建议降价、促销或销售话术，不处理 trust system、legacy price anchor 和 fairness debt。", "expected_output_elements": ["classification=issue", "dominant_scarcity=consensus_order", "trust_system", "legacy_price_anchor"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["credible_promise", "verifiable_outcome", "organizational_delivery", "fairness_debt"], "forbidden_elements": ["price_adjustment_only", "sales_script_only"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-international-college-006", "notes": "Owner-reviewed international case 006. Pricing deadlock as high-ticket trust-system failure."},
+    {"case_id": "case_qpi_research_identity_simulation_001", "model_id": "qpi", "case_type": "positive", "input": "组织没有真实科研能力，却想通过人员、费用、专利和论文包装出研究身份，以满足外部优惠或认证要求。", "expected_behavior": "应识别为 issue，dominant_scarcity=consensus_order：底层有 path/resource shortage，但核心是 research identity simulation，不能把能力建设问题降维成证据包装。", "failure_signal": "当成普通认证材料准备、税务筹划或指标补齐任务，不区分真实能力建设与身份模拟。", "expected_output_elements": ["classification=issue", "dominant_scarcity=consensus_order", "research_identity_simulation", "compliance_red_line"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["capability_building", "evidence_simulation", "transactional_assets", "audit_risk"], "forbidden_elements": ["certification_materials_only", "evidence_packaging_as_solution"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-research-office-001", "notes": "Owner-reviewed research case 001. Umbrella research identity simulation case."},
+    {"case_id": "case_qpi_research_data_truthfulness_001", "model_id": "qpi", "case_type": "misuse", "input": "研究人员数量和费用类别不够，组织想把非研究角色和薪资类别调成研究相关口径来补表。", "expected_behavior": "应识别为 issue，dominant_scarcity=consensus_order，并区分 data completeness、data truthfulness 与 evidence legitimacy；不能输出高置信法律/税务结论。", "failure_signal": "只检查表格是否填满，或直接判断一定合规/违法，而不要求实际研究角色、薪资类别和贡献证据链。", "expected_output_elements": ["classification=issue", "dominant_scarcity=consensus_order", "data_completeness_is_not_truthfulness", "requires_compliance_review"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["actual_research_role_evidence", "payroll_category_validity", "research_contribution_trace"], "forbidden_elements": ["spreadsheet_completion_as_truth", "high_confidence_legal_tax_verdict"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-research-office-002", "notes": "Owner-reviewed research case 002. Data completeness versus truthfulness."},
+    {"case_id": "case_qpi_research_ranking_reduction_001", "model_id": "qpi", "case_type": "misuse", "input": "我们想快速提升排名和科研指标，可以通过购买、包装或短期冲刺论文专利来改善外部可见度吗？", "expected_behavior": "应识别为 issue，dominant_scarcity=consensus_order：这是 violent_reduction，把研究价值压缩成可购买、可填报、可冲刺的排名输入。", "failure_signal": "直接给快速提升排名清单，或把购买/包装指标当作普通执行路径。", "expected_output_elements": ["classification=issue", "dominant_scarcity=consensus_order", "violent_reduction", "metric_improvement_without_capability_improvement"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["research_value", "capability_improvement", "ranking_metric_trap"], "forbidden_elements": ["quick_ranking_tactics_only", "purchasable_metric_as_research_value"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-research-office-004", "notes": "Owner-reviewed research case 004. Ranking trap and violent reduction."},
+    {"case_id": "case_qpi_research_penalty_integrity_001", "model_id": "qpi", "case_type": "boundary", "input": "组织认为只要没有罚款、没有被约谈、没有报销损失，就说明合规风险不大。", "expected_behavior": "应识别为 issue，dominant_scarcity=consensus_order，并输出 punishment_state_vs_integrity_state：没有即时惩罚不等于行为正当或可审计。", "failure_signal": "把无处罚当作合规证明，或只建议继续观察处罚结果。", "expected_output_elements": ["classification=issue", "dominant_scarcity=consensus_order", "absence_of_penalty_is_not_legitimacy", "integrity_state"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["punishment_state_frame", "integrity_state_frame", "auditability", "substantive_compliance"], "forbidden_elements": ["no_penalty_equals_compliance", "minimum_punishment_game"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-research-office-008", "notes": "Owner-reviewed research case 008. Punishment state versus integrity state."}
   ]
 }

tests/regression_cases.json

@@ -17,6 +17,12 @@
     {"case_id": "case_qpi_no_call_direct_edit_001", "model_id": "qpi", "case_type": "no_call", "input": "请直接把这句话改得更顺，不要分析原因。", "expected_behavior": "应 no_call，不进入 QPI 分析。", "failure_signal": "输出问题类型判断。", "expected_output_elements": ["classification=no_call"], "should_call_model": false, "expected_primary_model": "none", "negative_expected_models": ["qpi", "intellectual_archaeology"], "expected_classification": "no_call", "expected_dominant_scarcity": "not_applicable", "expected_max_depth": "not_applicable", "minimum_required_elements": ["recommended_next_step=不调用"], "forbidden_elements": ["dominant_scarcity=data"], "evaluation_mode": "structured", "notes": "纯改写 no-call。"},
     {"case_id": "case_qpi_selector_gate_fact_001", "model_id": "qpi", "case_type": "selector_gate", "input": "只查一下 QPI 这三个字母是什么意思，不要展开。", "expected_behavior": "selector 应低分或 no_call，思想考古必须被拒绝。", "failure_signal": "因为出现 QPI 或模型词而召回 IA。", "expected_output_elements": ["no_call"], "should_call_model": false, "expected_primary_model": "none", "negative_expected_models": ["intellectual_archaeology"], "expected_classification": "no_call", "expected_dominant_scarcity": "not_applicable", "expected_max_depth": "not_applicable", "minimum_required_elements": ["rejected_models"], "forbidden_elements": ["七层"], "evaluation_mode": "structured", "notes": "selector 防误召回。"},
     {"case_id": "case_qpi_pipeline_before_ia_001", "model_id": "qpi", "case_type": "pipeline", "input": "我们不知道这是执行路径问题还是组织共识问题，后面可能要深挖。", "expected_behavior": "应先调用 QPI，再决定是否进入思想考古。", "failure_signal": "直接调用思想考古。", "expected_output_elements": ["qpi first"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "mixed", "expected_dominant_scarcity": "mixed", "expected_max_depth": "not_applicable", "minimum_required_elements": ["next_model_candidates"], "forbidden_elements": [], "evaluation_mode": "structured", "notes": "QPI-before-IA pipeline gate。"},
+    {"case_id": "case_qpi_flow_no_simulation_001", "model_id": "qpi", "case_type": "misuse", "input": "这个多代理评审包看起来有完整报告，但其实只是主会话模拟，没有真实独立 agent 调用记录；我需要判断它能不能作为正式输出。", "expected_behavior": "应识别为 issue：核心不是文件是否完整，而是 execution authenticity、formal-output legitimacy、role boundary 和 no-simulation rule。应标记 simulated output 不能进入正式综合，必须 blocked_until_real_invocation。", "failure_signal": "把它当成普通文件格式问题或调用包实现问题，允许模拟报告进入正式评审综合。", "expected_output_elements": ["classification=issue", "dominant_scarcity=consensus_order", "formal_output=false", "blocked_until_real_invocation=true"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": ["intellectual_archaeology"], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["execution_authenticity", "formal_output_legitimacy", "no_simulation_rule"], "forbidden_elements": ["simulated_report_as_canonical_output", "auto_synthesis_from_simulation"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-flow-redesign-002", "notes": "Owner-reviewed flow-redesign case 002. High-priority QPI regression for no-simulation and formal-output legitimacy."},
+    {"case_id": "case_qpi_disappointment_label_as_identity_001", "model_id": "qpi", "case_type": "boundary", "input": "我不是只想查这个心理标签是什么意思，它已经影响我怎么理解自己、怎么设关系边界和要不要寻求帮助。", "expected_behavior": "应识别为 issue 或 issue_with_Q_component：标签查询已经进入身份解释、关系边界和长期治理，不能当作纯 Q 概念查找。", "failure_signal": "只解释标签定义，或因为出现心理标签就无条件升维为临床判断。", "expected_output_elements": ["classification=issue", "dominant_scarcity=consensus_order", "classification_note=issue_with_Q_component"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": ["intellectual_archaeology"], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["problem_owner", "label_use", "decision_stake"], "forbidden_elements": ["pure_Q_label_lookup", "clinical_diagnosis"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-disappointment-002", "notes": "Owner-reviewed disappointment case 002. Conditional what-is-X false-positive trap."},
+    {"case_id": "case_qpi_disappointment_single_factor_totalization_001", "model_id": "qpi", "case_type": "misuse", "input": "我不想把情感隔离全部归因于童年或某一个人，我需要判断哪些是触发、维持条件、高权重要素和当前行动杠杆。", "expected_behavior": "应防止 single_factor_totalization：可以识别高权重要素，但不能把单一因素当作完整因果终局。", "failure_signal": "输出唯一根本原因，或禁止识别任何高权重要素。", "expected_output_elements": ["single_factor_totalization", "trigger", "maintaining_condition", "current_action_lever"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["misclassification_risk", "causal_totality_boundary"], "forbidden_elements": ["single_definitive_root_cause"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-disappointment-003", "notes": "Owner-reviewed disappointment case 003. Explanatory usefulness is not causal finality."},
+    {"case_id": "case_qpi_disappointment_one_time_fix_001", "model_id": "qpi", "case_type": "misuse", "input": "这个心理关系问题不能靠三步修复或一次干预解决，我需要判断它是不是只能阶段性重构和长期治理。", "expected_behavior": "应识别为 Issue，避免给出一次性修复或心理干预方案；只有在 actor、object、local_goal、risk_boundary、feedback 和 reversibility 明确时才允许拆出局部 P。", "failure_signal": "直接给三步修复、单点干预或治疗建议。", "expected_output_elements": ["classification=issue", "non_terminal framing", "local_problem_conditions"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["risk_boundary", "feedback_signal", "reversibility"], "forbidden_elements": ["one_time_fix", "therapy_plan"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-disappointment-004", "notes": "Owner-reviewed disappointment case 004. Prevents over-routing psychological-relational Issue to Problem."},
+    {"case_id": "case_qpi_disappointment_mismatch_diagnostics_001", "model_id": "qpi", "case_type": "selector_gate", "input": "这个问题到底有没有被误路由：把 I 当 Q、把 I 当 P、把 P 过度升维成 I，或者把保护性边界病理化？", "expected_behavior": "selector 应先选 QPI；QPI 应输出 wrong_route_to_avoid 或等价误路由诊断，而不是只给最终分类。", "failure_signal": "只给单一标签，或直接调用思想考古。", "expected_output_elements": ["wrong_route_to_avoid", "I_as_Q", "I_as_P", "P_as_I"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": ["intellectual_archaeology"], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["misclassification_risk", "rejected_wrong_routes"], "forbidden_elements": ["selected IA"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-disappointment-007", "notes": "Owner-reviewed disappointment case 007. QPI mismatch diagnostics regression."},
+    {"case_id": "case_qpi_disappointment_one_person_issue_001", "model_id": "qpi", "case_type": "positive", "input": "只有我一个人在做自我治理，但我要长期校准隔离什么时候是保护，什么时候是过度泛化防御，这是不是仍然可以是 Issue？", "expected_behavior": "应识别为 Issue：Issue 不需要多人；单人主体在保护、开放、风险、能量、反馈和关系实验之间持续校准时，也有治理负荷。", "failure_signal": "因为只有一个人就降为 Problem，或给出二元好坏判断。", "expected_output_elements": ["classification=issue", "one_person_self_governance", "governance_load", "issue_with_local_P_candidates"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["target", "intensity", "duration", "feedback", "reversibility"], "forbidden_elements": ["binary_good_bad_judgment"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-disappointment-008", "notes": "Owner-reviewed disappointment case 008. Canonical anchor: one-person self-governance can still be Issue."},
     {"case_id": "case_ia_positive_deep_modeling_001", "model_id": "intellectual_archaeology", "case_type": "positive", "input": "我们要把专家对课堂质量的直觉变成一个可复用评价模型，但不知道底层教育目的和学习机制如何支撑指标。", "expected_behavior": "应调用思想考古学，下潜到核心机理层，标出验证需求。", "failure_signal": "只总结表层指标。", "expected_output_elements": ["should_call=true", "recommended_max_depth=core_mechanism"], "should_call_model": true, "expected_primary_model": "intellectual_archaeology", "negative_expected_models": [], "expected_classification": "not_applicable", "expected_dominant_scarcity": "not_applicable", "expected_max_depth": "core_mechanism", "minimum_required_elements": ["stop_reason", "validation_needed"], "forbidden_elements": [], "evaluation_mode": "structured", "notes": "重型正例。"},
     {"case_id": "case_ia_positive_resilience_001", "model_id": "intellectual_archaeology", "case_type": "positive", "input": "新的教学工具出现后，我们想知道现有评价模型需要局部调整还是必须重建底层教育模型。", "expected_behavior": "应区分稳定内核和可变外壳，判断冲击层级。", "failure_signal": "动辄推倒全部模型。", "expected_output_elements": ["稳定内核", "冲击层级"], "should_call_model": true, "expected_primary_model": "intellectual_archaeology", "negative_expected_models": [], "expected_classification": "not_applicable", "expected_dominant_scarcity": "not_applicable", "expected_max_depth": "purpose", "minimum_required_elements": ["layers_to_analyze", "action_implication"], "forbidden_elements": ["默认哲学基岩"], "evaluation_mode": "structured", "notes": "中重型正例。"},
     {"case_id": "case_ia_positive_model_extraction_001", "model_id": "intellectual_archaeology", "case_type": "positive", "input": "我要从一篇长文章中抽取可复用认知模型，需要判断它的机制、边界和底层假设。", "expected_behavior": "应调用思想考古，最多到核心机理层或人类能力层。", "failure_signal": "只做摘要或直接上哲学。", "expected_output_elements": ["模型抽取", "recommended_max_depth"], "should_call_model": true, "expected_primary_model": "intellectual_archaeology", "negative_expected_models": [], "expected_classification": "not_applicable", "expected_dominant_scarcity": "not_applicable", "expected_max_depth": "core_mechanism", "minimum_required_elements": ["assumptions_by_layer", "validation_needed"], "forbidden_elements": [], "evaluation_mode": "structured", "notes": "模型抽取场景。"},
@@ -33,6 +39,29 @@
     {"case_id": "case_ia_misuse_layer_jump_001", "model_id": "intellectual_archaeology", "case_type": "misuse", "input": "我们还没弄清应用层事实，就想直接讨论哲学基岩。", "expected_behavior": "应阻止层级跳跃，从应用层事实和证据缺口开始。", "failure_signal": "跳过中间层级。", "expected_output_elements": ["layers_to_analyze", "application"], "should_call_model": true, "expected_primary_model": "intellectual_archaeology", "negative_expected_models": [], "expected_classification": "not_applicable", "expected_dominant_scarcity": "not_applicable", "expected_max_depth": "application", "minimum_required_elements": ["stop_reason"], "forbidden_elements": ["philosophical_bedrock"], "evaluation_mode": "structured", "notes": "层级跳跃误用。"},
     {"case_id": "case_ia_selector_gate_qpi_first_001", "model_id": "intellectual_archaeology", "case_type": "selector_gate", "input": "这个问题到底是缺数据、缺路径还是缺共识？", "expected_behavior": "selector 应先选 QPI，不应直接选思想考古。", "failure_signal": "IA 抢在 QPI 前。", "expected_output_elements": ["qpi first"], "should_call_model": false, "expected_primary_model": "qpi", "negative_expected_models": ["intellectual_archaeology"], "expected_classification": "not_applicable", "expected_dominant_scarcity": "not_applicable", "expected_max_depth": "no_call", "minimum_required_elements": ["rejected_models"], "forbidden_elements": ["selected IA"], "evaluation_mode": "structured", "notes": "QPI-before-IA gate。"},
     {"case_id": "case_ia_selector_gate_no_heavy_signal_001", "model_id": "intellectual_archaeology", "case_type": "selector_gate", "input": "底层这个词怎么翻译？只要一个英文。", "expected_behavior": "虽然有底层一词，也不应召回思想考古。", "failure_signal": "关键词误召回。", "expected_output_elements": ["rejected_models"], "should_call_model": false, "expected_primary_model": "none", "negative_expected_models": ["intellectual_archaeology"], "expected_classification": "not_applicable", "expected_dominant_scarcity": "not_applicable", "expected_max_depth": "no_call", "minimum_required_elements": ["negative trigger"], "forbidden_elements": ["七层"], "evaluation_mode": "structured", "notes": "关键词误召回防护。"},
-    {"case_id": "case_ia_pipeline_after_qpi_001", "model_id": "intellectual_archaeology", "case_type": "pipeline", "input": "QPI 已判断为中重型课题，且需要抽取底层机制和验证路径。", "expected_behavior": "IA 可作为 QPI 后续模型被调用。", "failure_signal": "在 QPI 放行后仍拒绝。", "expected_output_elements": ["QPI 后续", "should_call=true"], "should_call_model": true, "expected_primary_model": "intellectual_archaeology", "negative_expected_models": [], "expected_classification": "not_applicable", "expected_dominant_scarcity": "not_applicable", "expected_max_depth": "core_mechanism", "minimum_required_elements": ["entry_reason"], "forbidden_elements": [], "evaluation_mode": "structured", "notes": "QPI 后续 pipeline。"}
+    {"case_id": "case_ia_pipeline_after_qpi_001", "model_id": "intellectual_archaeology", "case_type": "pipeline", "input": "QPI 已判断为中重型课题，且需要抽取底层机制和验证路径。", "expected_behavior": "IA 可作为 QPI 后续模型被调用。", "failure_signal": "在 QPI 放行后仍拒绝。", "expected_output_elements": ["QPI 后续", "should_call=true"], "should_call_model": true, "expected_primary_model": "intellectual_archaeology", "negative_expected_models": [], "expected_classification": "not_applicable", "expected_dominant_scarcity": "not_applicable", "expected_max_depth": "core_mechanism", "minimum_required_elements": ["entry_reason"], "forbidden_elements": [], "evaluation_mode": "structured", "notes": "QPI 后续 pipeline。"},
+    {"case_id": "case_qpi_org_hard_resource_documentation_001", "model_id": "qpi", "case_type": "misuse", "input": "组织面对硬性资源缺口，没有真实补资源，而是想通过重命名、材料包装和合规口径让指标看起来达标。", "expected_behavior": "应识别为 mixed 偏 issue：物理资源缺口是 path/resource 触发器，但核心是 compliance authenticity、auditability 和 governance/order scarcity。", "failure_signal": "把它当成普通文书整理问题、缺数据问题，或只归为 path_resource 而忽略合规真实性风险。", "expected_output_elements": ["classification=mixed", "dominant_scarcity=consensus_order", "path_resource_trigger_with_compliance_governance_failure"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": ["intellectual_archaeology"], "expected_classification": "mixed", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["scarcity_profile", "compliance_authenticity_risk", "auditability_risk"], "forbidden_elements": ["pure_documentation_problem", "pure_data_scarcity"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-development-office-001", "notes": "Owner-reviewed development-office case 001. Hard resource gap disguised as documentation problem."},
+    {"case_id": "case_qpi_org_credential_continuity_001", "model_id": "qpi", "case_type": "misuse", "input": "为了修复人员资质指标，组织准备替换或重分类一批岗位，但这些人承担运营记忆、角色连续性和信任关系。", "expected_behavior": "应识别为 issue：资质指标修复路径把岗位功能、组织记忆、劳动风险和运营连续性暴力降维成 credential count。", "failure_signal": "只建议优化招聘或替换清单，接受资质指标就是完整质量指标。", "expected_output_elements": ["classification=issue", "dominant_scarcity=consensus_order", "violent_reduction", "operational_continuity"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["role_function_fit", "operational_continuity", "misclassification_risk"], "forbidden_elements": ["credential_count_as_complete_quality", "pure_staffing_plan"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-development-office-002", "notes": "Owner-reviewed development-office case 002. High-priority organization-type QPI regression."},
+    {"case_id": "case_qpi_org_untrusted_data_001", "model_id": "qpi", "case_type": "boundary", "input": "材料和台账都很完整，但它们对应的真实运营并不稳定，也经不起审计核查；这不是缺数据，而是数据不可信。", "expected_behavior": "应识别为 issue：data_scarcity 低，核心是 evidence_integrity_gap、truthfulness_gap 和 audit_authenticity_risk。推荐先做 evidence authenticity audit。", "failure_signal": "把它判为普通 Q 类缺数据，或直接进入资源规划而不检查证据真实性。", "expected_output_elements": ["classification=issue", "dominant_scarcity=consensus_order", "data_scarcity=low", "evidence_authenticity_audit"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": ["intellectual_archaeology"], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["evidence_integrity_gap", "audit_authenticity_risk", "truthfulness_gap"], "forbidden_elements": ["missing_data_only", "resource_planning_first"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-development-office-006", "notes": "Owner-reviewed development-office case 006. Regression for missing data versus untrusted data."},
+    {"case_id": "case_qpi_academic_ai_evidence_boundary_001", "model_id": "qpi", "case_type": "misuse", "input": "看起来只是让 AI 帮忙生成评估材料，但实际是先定结论再倒推证据，我需要判断这是不是材料执行任务。", "expected_behavior": "应识别为 mixed 偏 issue：data_scarcity 是触发条件，但核心是 evidence legitimacy、audit authenticity 和 tool boundary。AI 可以整理证据，不能制造证据关系。", "failure_signal": "把它当成普通材料生成、润色或执行任务，允许用工具从结论倒推证据。", "expected_output_elements": ["classification=mixed", "dominant_scarcity=consensus_order", "tool_boundary", "evidence_legitimacy"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": ["intellectual_archaeology"], "expected_classification": "mixed", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["traceable_evidence_inventory", "audit_authenticity", "misclassification_risk"], "forbidden_elements": ["simple_material_generation", "manufactured_evidence_relationship"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-academic-affairs-001", "notes": "Owner-reviewed academic-affairs case 001. AI/tool execution request that requires QPI."},
+    {"case_id": "case_qpi_academic_policy_memory_001", "model_id": "qpi", "case_type": "boundary", "input": "我们想取消一个诱发低质量产出的旧激励政策，但过去按这个规则投入过的人会觉得不公平，组织信任也已经受损。", "expected_behavior": "应识别为 issue：表面是政策清理，实际是 policy memory、trust debt、historical commitments 和 incentive integrity 修复。", "failure_signal": "把它当成简单政策取消任务，只输出新规则而不处理旧政策记忆和信任债务。", "expected_output_elements": ["classification=issue", "dominant_scarcity=consensus_order", "policy_memory", "trust_debt"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["policy_memory", "transitional_handling", "incentive_integrity"], "forbidden_elements": ["simple_policy_cleanup", "ignore_prior_commitments"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-academic-affairs-003", "notes": "Owner-reviewed academic-affairs case 003. False-negative trap for policy cleanup."},
+    {"case_id": "case_qpi_academic_outcome_quality_assurance_001", "model_id": "qpi", "case_type": "misuse", "input": "学生结果和投诉指标变差，部门解释为生源质量问题，但还没有审计教学质量制度和管理杠杆。", "expected_behavior": "应识别为 mixed，dominant_scarcity=consensus_order：输入条件可能影响结果，但不能替代对管理杠杆和质量保障制度的审计。", "failure_signal": "完全接受生源质量解释，或把全部因果责任无证据地压给单一部门。", "expected_output_elements": ["classification=mixed", "dominant_scarcity=consensus_order", "quality_assurance_gap", "management_lever_audit"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "mixed", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["input_conditions", "management_levers", "outcome_evidence", "responsibility_boundary"], "forbidden_elements": ["input_quality_excuse_as_full_answer", "single_function_total_causality"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-academic-affairs-006", "notes": "Owner-reviewed academic-affairs case 006. Input conditions versus quality-assurance audit."},
+    {"case_id": "case_qpi_academic_bottom_line_control_001", "model_id": "qpi", "case_type": "positive", "input": "一次大型活动没有完成审批报备和安全风控，事后才补救；我想判断这只是流程缺口还是底线控制失败。", "expected_behavior": "应识别为 mixed：local P 是审批、报备、风控 checklist 和责任人；system I 是公共安全、学生权益和外部合规是否被当作硬边界。", "failure_signal": "只补一个流程表，或只把它升维成抽象文化问题而不要求硬门禁流程。", "expected_output_elements": ["classification=mixed", "dominant_scarcity=consensus_order", "bottom_line_control_failure", "hard_gate"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "mixed", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["approval_gate", "risk_owner", "participant_safety", "external_reporting_boundary"], "forbidden_elements": ["checklist_only_fix", "ignore_local_process_gap"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-academic-affairs-008", "notes": "Owner-reviewed academic-affairs case 008. Concrete operating accident revealing bottom-line control failure."},
+    {"case_id": "case_qpi_employment_credential_compliance_exposure_001", "model_id": "qpi", "case_type": "misuse", "input": "为了补资质指标，组织想快速挂靠或采购带资历的人，但这些人是否进入教学科研和学生发展完全不清楚。", "expected_behavior": "应识别为 mixed，dominant_scarcity=consensus_order：credential gap 是真实资源缺口，但指标修补路径会制造 compliance exposure，不能当成简单采购或人事补缺。", "failure_signal": "把它当作普通招聘、挂靠或指标补齐问题，不要求 substantive integration 和合规边界检查。", "expected_output_elements": ["classification=mixed", "dominant_scarcity=consensus_order", "compliance_exposure", "substantive_integration_not_proven"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "mixed", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["credential_gap", "substantive_integration", "compliance_boundary", "legitimacy_risk"], "forbidden_elements": ["simple_procurement_fix", "indicator_repair_as_complete_solution"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-employment-entrepreneurship-002", "notes": "Owner-reviewed employment case 002. Credential metric repair versus compliance exposure."},
+    {"case_id": "case_qpi_employment_reported_metric_legitimacy_001", "model_id": "qpi", "case_type": "boundary", "input": "部门述职说自己创收很高，但这个数字按部门口径算，和组织财务确认标准不一致，还被用来争取更大权力。", "expected_behavior": "应识别为 mixed，dominant_scarcity=consensus_order：数据口径问题是入口，核心是 reported metric lineage、financial recognition 和 performance legitimacy。", "failure_signal": "照单全收述职数据，或只要求补一个数据表而不处理绩效正当性和权力扩张风险。", "expected_output_elements": ["classification=mixed", "dominant_scarcity=consensus_order", "reported_metric_lineage", "performance_legitimacy"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "mixed", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["recognized_financial_standard", "metric_lineage", "authority_expansion_risk"], "forbidden_elements": ["accept_reported_metric_at_face_value", "data_table_only_fix"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-employment-entrepreneurship-003", "notes": "Owner-reviewed employment case 003. False-positive trap for reported metrics."},
+    {"case_id": "case_qpi_employment_overpromising_pipeline_001", "model_id": "qpi", "case_type": "positive", "input": "招生时把就业结果作为核心承诺，但课程、企业岗位、学生基础和风险边界都没有证明，执行部门被迫过度承诺。", "expected_behavior": "应识别为 mixed，dominant_scarcity=consensus_order：既有交付路径问题，也有学生承诺、招生 pipeline、信任和组织身份风险。", "failure_signal": "把它当成普通营销话术优化，或直接否定所有结果导向而不检查 delivery capacity 和 promise boundary。", "expected_output_elements": ["classification=mixed", "dominant_scarcity=consensus_order", "delivery_capacity", "promise_boundary"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "mixed", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["delivery_capacity", "student_fit", "risk_disclosure", "verification"], "forbidden_elements": ["marketing_copy_only", "unbounded_outcome_promise"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-employment-entrepreneurship-004", "notes": "Owner-reviewed employment case 004. Legitimate outcome orientation versus overpromising."},
+    {"case_id": "case_qpi_employment_metric_credibility_001", "model_id": "qpi", "case_type": "misuse", "input": "就业率数字很高，组织想直接拿来证明办学质量，但数据是在强 KPI 压力下生产的，学生和企业层面的核验机制不清楚。", "expected_behavior": "应识别为 mixed，dominant_scarcity=consensus_order：高指标值不等于高指标可信度，必须输出 evidence_gap 并审计数据生产机制。", "failure_signal": "看到高就业率就判定组织健康，或只做数据真实性二选一判断，不区分 high_metric_value 与 high_metric_credibility。", "expected_output_elements": ["classification=mixed", "dominant_scarcity=consensus_order", "evidence_gap", "metric_credibility"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "mixed", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["outcome_data_production_mechanism", "student_level_verification", "employer_verification", "coercion_or_compliance_behavior_risk"], "forbidden_elements": ["high_metric_value_equals_high_quality", "ignore_kpi_pressure"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-employment-entrepreneurship-005", "notes": "Owner-reviewed employment case 005. High metric value versus high metric credibility."},
+    {"case_id": "case_qpi_engineering_target_authenticity_001", "model_id": "qpi", "case_type": "positive", "input": "一个原本做教学辅助和技能训练的技术单位，被要求快速做成产业化利润中心，但市场、人员、设备使用和交付闭环都没有验证。", "expected_behavior": "应识别为 mixed，dominant_scarcity=consensus_order：真实存在能力和路径缺口，但核心是 target_authenticity_gap，必须区分 milestone target、terminal target 和 bridge evidence。", "failure_signal": "照单接受高目标为执行任务，或只把它降维成买设备、招人、做项目。", "expected_output_elements": ["classification=mixed", "dominant_scarcity=consensus_order", "target_authenticity_gap", "bridge_evidence"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "mixed", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["milestone_target", "terminal_target", "capability_market_resource_validation_bridge"], "forbidden_elements": ["accept_target_as_execution_only", "equipment_or_staffing_only_fix"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-engineering-center-001", "notes": "Owner-reviewed engineering case 001. Target authenticity gap."},
+    {"case_id": "case_qpi_engineering_equipment_solutionism_001", "model_id": "qpi", "case_type": "misuse", "input": "组织想先买高端设备再等项目自然出现，但没有真实订单、操作者就绪度、安全规程和单位经济模型。", "expected_behavior": "应识别为 mixed，dominant_scarcity=consensus_order：设备不是能力本身，需求证明、操作者、安全、经济模型和试点结果没有过 gate 前，不能当作执行问题。", "failure_signal": "把问题当成设备选型或采购清单，忽略市场闭环和操作者 readiness。", "expected_output_elements": ["classification=mixed", "dominant_scarcity=consensus_order", "equipment_led_solutionism", "hard_gate"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "mixed", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["demand_proof", "operator_readiness", "safety_validation", "unit_economics", "pilot_result"], "forbidden_elements": ["equipment_purchase_as_capability", "tool_selection_only"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-engineering-center-002", "notes": "Owner-reviewed engineering case 002. Equipment-led solutionism."},
+    {"case_id": "case_qpi_engineering_credential_integrity_policy_001", "model_id": "qpi", "case_type": "boundary", "input": "发现某个资质或履历存在异常，但组织还想按能不能干活来决定是否继续使用，我需要判断这是人员问题还是制度问题。", "expected_behavior": "应识别为 issue，dominant_scarcity=consensus_order，并明确 no_personnel_verdict：QPI 不判断具体人员，只路由到筛查制度、例外政策和风险归属审查。", "failure_signal": "直接判断某个人能不能用、是否造假、是否应辞退，或只按短期可用性处理。", "expected_output_elements": ["classification=issue", "dominant_scarcity=consensus_order", "no_personnel_verdict", "credential_integrity"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["credential_verification_lineage", "exception_policy", "risk_owner", "policy_review"], "forbidden_elements": ["specific_personnel_verdict", "usability_only_decision"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-engineering-center-004", "notes": "Owner-reviewed engineering case 004. Credential integrity versus usability."},
+    {"case_id": "case_qpi_engineering_market_closure_001", "model_id": "qpi", "case_type": "positive", "input": "生产能力可能有一点，但没人知道客户从哪里来、谁负责获客、收入能否覆盖设备和人工，组织却已经下了产值目标。", "expected_behavior": "应识别为 mixed，dominant_scarcity=consensus_order：对经营主体，这不是先查订单来源的普通 Question，而是把生产能力误当成商业闭环的第一性错位。", "failure_signal": "先判为单纯 question，或只要求市场调研而不处理主体目的、客户、渠道、交付和单位经济模型。", "expected_output_elements": ["classification=mixed", "dominant_scarcity=consensus_order", "business_purpose", "acquisition_channel"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "mixed", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["problem_owner", "primary_purpose", "customer_segment", "demand_signal", "acquisition_channel", "unit_economics"], "forbidden_elements": ["production_capacity_equals_business_viability", "question_only_classification"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-engineering-center-005", "notes": "Owner-reviewed engineering case 005. Production capability without market closure."},
+    {"case_id": "case_qpi_international_compliance_retention_001", "model_id": "qpi", "case_type": "misuse", "input": "招生团队想用路径调整留住学生，但这个留存动作可能改变机构合规姿态、证书信任和未来投诉审计风险。", "expected_behavior": "应识别为 issue，dominant_scarcity=consensus_order：留存压力和路径缺口存在，但合规红线占主导，不能把它当作普通招生留存 Problem。", "failure_signal": "只输出留存方案或招生话术，不先确认 compliance red line、credential trust 和 audit risk。", "expected_output_elements": ["classification=issue", "dominant_scarcity=consensus_order", "compliance_red_line", "credential_trust"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["retention_pressure", "compliance_boundary", "future_complaint_or_audit_risk"], "forbidden_elements": ["retention_tactic_only", "pathway_workaround_without_red_line"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-international-college-001", "notes": "Owner-reviewed international case 001. Retention workaround crossing compliance boundary."},
+    {"case_id": "case_qpi_international_capacity_governance_001", "model_id": "qpi", "case_type": "boundary", "input": "增长项目承诺扩招，但宿舍和服务容量不足，需要挤占其他单元资源，组织还没有硬性容量闸门。", "expected_behavior": "应识别为 mixed，dominant_scarcity=path_resource：硬约束是容量，但跨单元冲突和承诺边界使其成为容量治理问题。", "failure_signal": "把它当作简单排宿舍或物流调度，或只抽象成文化冲突而不处理 hard capacity gate。", "expected_output_elements": ["classification=mixed", "dominant_scarcity=path_resource", "hard_capacity_gate", "cross_unit_conflict"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "mixed", "expected_dominant_scarcity": "path_resource", "expected_max_depth": "not_applicable", "minimum_required_elements": ["physical_capacity", "resource_displacement", "delivery_assurance", "arbitration_rule"], "forbidden_elements": ["simple_logistics_only", "ignore_capacity_limit"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-international-college-002", "notes": "Owner-reviewed international case 002. Capacity governance versus simple logistics."},
+    {"case_id": "case_qpi_international_metric_governance_001", "model_id": "qpi", "case_type": "misuse", "input": "执行层提交了好看的资质指标，决策层怀疑这些指标急功近利，只是为了评估和述职，不代表真实教学能力。", "expected_behavior": "应识别为 issue，dominant_scarcity=consensus_order：事实核验嵌在治理扭曲中，必须检查指标是否连接长期目标、真实能力、多方收益和可审计证据。", "failure_signal": "停留在问指标真假，或直接接受指标为能力证明。", "expected_output_elements": ["classification=issue", "dominant_scarcity=consensus_order", "metric_distortion", "traceable_evidence_chain"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["long_term_goal_alignment", "real_capability", "multi_party_value", "audit_evidence"], "forbidden_elements": ["question_only_classification", "metric_appearance_as_capability"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-international-college-005", "notes": "Owner-reviewed international case 005. Metric fact verification embedded in governance distortion."},
+    {"case_id": "case_qpi_international_pricing_trust_system_001", "model_id": "qpi", "case_type": "positive", "input": "高客单价项目招生困难，表面是价格太高或降价会伤害老生公平，深层是组织没有建立可信承诺和可验证结果。", "expected_behavior": "应识别为 issue，dominant_scarcity=consensus_order：定价僵局是表象，高客单价教育产品需要组织级信任体系、可信承诺、可验证结果和协同交付。", "failure_signal": "只建议降价、促销或销售话术，不处理 trust system、legacy price anchor 和 fairness debt。", "expected_output_elements": ["classification=issue", "dominant_scarcity=consensus_order", "trust_system", "legacy_price_anchor"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["credible_promise", "verifiable_outcome", "organizational_delivery", "fairness_debt"], "forbidden_elements": ["price_adjustment_only", "sales_script_only"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-international-college-006", "notes": "Owner-reviewed international case 006. Pricing deadlock as high-ticket trust-system failure."},
+    {"case_id": "case_qpi_research_identity_simulation_001", "model_id": "qpi", "case_type": "positive", "input": "组织没有真实科研能力，却想通过人员、费用、专利和论文包装出研究身份，以满足外部优惠或认证要求。", "expected_behavior": "应识别为 issue，dominant_scarcity=consensus_order：底层有 path/resource shortage，但核心是 research identity simulation，不能把能力建设问题降维成证据包装。", "failure_signal": "当成普通认证材料准备、税务筹划或指标补齐任务，不区分真实能力建设与身份模拟。", "expected_output_elements": ["classification=issue", "dominant_scarcity=consensus_order", "research_identity_simulation", "compliance_red_line"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["capability_building", "evidence_simulation", "transactional_assets", "audit_risk"], "forbidden_elements": ["certification_materials_only", "evidence_packaging_as_solution"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-research-office-001", "notes": "Owner-reviewed research case 001. Umbrella research identity simulation case."},
+    {"case_id": "case_qpi_research_data_truthfulness_001", "model_id": "qpi", "case_type": "misuse", "input": "研究人员数量和费用类别不够，组织想把非研究角色和薪资类别调成研究相关口径来补表。", "expected_behavior": "应识别为 issue，dominant_scarcity=consensus_order，并区分 data completeness、data truthfulness 与 evidence legitimacy；不能输出高置信法律/税务结论。", "failure_signal": "只检查表格是否填满，或直接判断一定合规/违法，而不要求实际研究角色、薪资类别和贡献证据链。", "expected_output_elements": ["classification=issue", "dominant_scarcity=consensus_order", "data_completeness_is_not_truthfulness", "requires_compliance_review"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["actual_research_role_evidence", "payroll_category_validity", "research_contribution_trace"], "forbidden_elements": ["spreadsheet_completion_as_truth", "high_confidence_legal_tax_verdict"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-research-office-002", "notes": "Owner-reviewed research case 002. Data completeness versus truthfulness."},
+    {"case_id": "case_qpi_research_ranking_reduction_001", "model_id": "qpi", "case_type": "misuse", "input": "我们想快速提升排名和科研指标，可以通过购买、包装或短期冲刺论文专利来改善外部可见度吗？", "expected_behavior": "应识别为 issue，dominant_scarcity=consensus_order：这是 violent_reduction，把研究价值压缩成可购买、可填报、可冲刺的排名输入。", "failure_signal": "直接给快速提升排名清单，或把购买/包装指标当作普通执行路径。", "expected_output_elements": ["classification=issue", "dominant_scarcity=consensus_order", "violent_reduction", "metric_improvement_without_capability_improvement"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["research_value", "capability_improvement", "ranking_metric_trap"], "forbidden_elements": ["quick_ranking_tactics_only", "purchasable_metric_as_research_value"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-research-office-004", "notes": "Owner-reviewed research case 004. Ranking trap and violent reduction."},
+    {"case_id": "case_qpi_research_penalty_integrity_001", "model_id": "qpi", "case_type": "boundary", "input": "组织认为只要没有罚款、没有被约谈、没有报销损失，就说明合规风险不大。", "expected_behavior": "应识别为 issue，dominant_scarcity=consensus_order，并输出 punishment_state_vs_integrity_state：没有即时惩罚不等于行为正当或可审计。", "failure_signal": "把无处罚当作合规证明，或只建议继续观察处罚结果。", "expected_output_elements": ["classification=issue", "dominant_scarcity=consensus_order", "absence_of_penalty_is_not_legitimacy", "integrity_state"], "should_call_model": true, "expected_primary_model": "qpi", "negative_expected_models": [], "expected_classification": "issue", "expected_dominant_scarcity": "consensus_order", "expected_max_depth": "not_applicable", "minimum_required_elements": ["punishment_state_frame", "integrity_state_frame", "auditability", "substantive_compliance"], "forbidden_elements": ["no_penalty_equals_compliance", "minimum_punishment_game"], "evaluation_mode": "structured", "source_case_digest_id": "qpi-year-end-research-office-008", "notes": "Owner-reviewed research case 008. Punishment state versus integrity state."}
   ]
 }