Cognitive-OS-Wantsong/models/intellectual-archaeology.md

111 lines
3.6 KiB
Markdown

# Intellectual Archaeology
model_id: intellectual_archaeology
file: models/intellectual-archaeology.md
runtime_scope: minimal_v0
governance_level: draft_callable
status: callable
model_level: L2_callable_model
default_role: depth_model
allowed_roles: depth_model, primary_model
reader_translation_required: true
## One-Sentence Definition
Intellectual Archaeology is a depth-processing model that drills from surface application down through deeper structural layers to expose hidden assumptions, core mechanisms, and action-relevant boundaries.
## Runtime Role
Intellectual Archaeology is the first deep-processing engine in this project.
It is not a front router, not a summary format, and not a default response style. It should be called only when Intake and QPI indicate that deeper modeling is worth the cost.
## Core Question
What deeper structural assumptions make this issue, model, or judgment work, and at what depth does further excavation stop changing the decision?
## Layer Framework
The model uses seven possible layers:
1. `application`: surface task, tool, behavior, or symptom.
2. `domain`: domain topology, evaluation frame, actors, and constraints.
3. `process`: time evolution, feedback, lifecycle, and path dependence.
4. `purpose`: value target, tradeoff, stakeholder balance, and QPI alignment.
5. `core_mechanism`: generative mechanism, system dynamics, and causal structure.
6. `human_capability`: cognitive, biological, organizational, or skill limits.
7. `philosophical_bedrock`: basic assumptions about reality, meaning, order, and agency.
## Minimum Sufficient Depth
Do not automatically drill to the deepest layer.
Continue deeper only if it changes at least one of:
- judgment;
- solution path;
- evidence requirement;
- risk weighting;
- action boundary;
- reusable model asset decision.
## Call When
- QPI classifies the input as a medium/heavy `problem` or `issue`.
- A surface explanation keeps failing.
- The issue has high reuse value.
- The owner wants to extract a model from source material.
- The problem needs hidden assumptions made explicit.
- A model or product logic needs depth inspection.
## Do Not Call When
- The input is a fact lookup.
- The user needs a short execution answer.
- There is not enough source material to distinguish mechanism from speculation.
- Deeper analysis will not change judgment or action.
- The user explicitly asks not to enter depth processing.
## Input Types
- complex issue;
- recurring failure;
- cognitive model draft;
- source article or report for model extraction;
- strategic, product, or organizational reasoning problem;
- hidden-assumption audit.
## Output Contract
Intellectual Archaeology output must include:
- `should_call`;
- `entry_reason`;
- `recommended_max_depth`;
- `layers_to_analyze`;
- `analysis_by_layer`;
- `stop_reason`;
- `no_deeper_reason`;
- `assumptions_by_layer`;
- `core_mechanism_summary`;
- `validation_needed`;
- `action_implication`;
- `reader_translation_notes`.
## Common Misuses
- Using the model as a long summary.
- Forcing every issue to the philosophical layer.
- Producing abstract depth without changing action.
- Ignoring QPI and value-assessment controls.
- Treating internal coherence as real-world validity.
- Forgetting reader translation.
## Source Seed Notes
Seeded from the old Intellectual Archaeology model/card and the seven-layer example report, rewritten for this runtime. Old regression suites, selector gates, review reports, and Local CCRA histories are not migrated.
## Current Limits
This model is callable for manual runtime use, but its depth stops and layer quality require real-run calibration before any upgrade.