2163 lines
88 KiB
JSON
2163 lines
88 KiB
JSON
{
|
||
"regression_cases": [
|
||
{
|
||
"case_id": "case_qpi_positive_question_001",
|
||
"model_id": "qpi",
|
||
"case_type": "positive",
|
||
"input": "我不知道这次服务器宕机的错误码是什么，也不知道日志在哪里。",
|
||
"expected_behavior": "应识别为提问，核心匮乏物是数据，建议先检索日志和错误码。",
|
||
"failure_signal": "把它升维为组织课题，或直接给出复杂治理建议。",
|
||
"expected_output_elements": [
|
||
"classification=question",
|
||
"dominant_scarcity=data",
|
||
"recommended_next_step=检索"
|
||
],
|
||
"should_call_model": true,
|
||
"expected_primary_model": "qpi",
|
||
"negative_expected_models": [
|
||
"intellectual_archaeology"
|
||
],
|
||
"expected_classification": "question",
|
||
"expected_dominant_scarcity": "data",
|
||
"expected_max_depth": "not_applicable",
|
||
"minimum_required_elements": [
|
||
"problem_owner",
|
||
"scarcity_profile",
|
||
"evidence_gap"
|
||
],
|
||
"forbidden_elements": [
|
||
"philosophical_bedrock"
|
||
],
|
||
"evaluation_mode": "structured",
|
||
"notes": "Q 类正例。"
|
||
},
|
||
{
|
||
"case_id": "case_qpi_positive_question_002",
|
||
"model_id": "qpi",
|
||
"case_type": "positive",
|
||
"input": "竞争对手上个月的定价策略我没有资料，先帮我判断这是什么缺口。",
|
||
"expected_behavior": "应识别为提问，缺少事实资料。",
|
||
"failure_signal": "进入思想考古或组织治理。",
|
||
"expected_output_elements": [
|
||
"question",
|
||
"data_scarcity=high"
|
||
],
|
||
"should_call_model": true,
|
||
"expected_primary_model": "qpi",
|
||
"negative_expected_models": [
|
||
"intellectual_archaeology"
|
||
],
|
||
"expected_classification": "question",
|
||
"expected_dominant_scarcity": "data",
|
||
"expected_max_depth": "not_applicable",
|
||
"minimum_required_elements": [
|
||
"classification_confidence",
|
||
"recommended_next_step"
|
||
],
|
||
"forbidden_elements": [
|
||
"七层下钻"
|
||
],
|
||
"evaluation_mode": "structured",
|
||
"notes": "Q 类正例。"
|
||
},
|
||
{
|
||
"case_id": "case_qpi_positive_question_003",
|
||
"model_id": "qpi",
|
||
"case_type": "positive",
|
||
"input": "我只是不知道季度报表在哪里，这算不算复杂问题？",
|
||
"expected_behavior": "应识别为提问或 no_call 边界，建议检索位置，不做深层分析。",
|
||
"failure_signal": "把它解释成系统性课题。",
|
||
"expected_output_elements": [
|
||
"data_scarcity=high",
|
||
"recommended_next_step=检索"
|
||
],
|
||
"should_call_model": true,
|
||
"expected_primary_model": "qpi",
|
||
"negative_expected_models": [
|
||
"intellectual_archaeology"
|
||
],
|
||
"expected_classification": "question",
|
||
"expected_dominant_scarcity": "data",
|
||
"expected_max_depth": "not_applicable",
|
||
"minimum_required_elements": [
|
||
"classification",
|
||
"evidence_gap"
|
||
],
|
||
"forbidden_elements": [
|
||
"哲学基岩"
|
||
],
|
||
"evaluation_mode": "structured",
|
||
"notes": "轻量 Q 类。"
|
||
},
|
||
{
|
||
"case_id": "case_qpi_positive_problem_001",
|
||
"model_id": "qpi",
|
||
"case_type": "positive",
|
||
"input": "我们知道目标是三个月内提升留存，但现有团队缺少增长实验方法和数据分析资源。",
|
||
"expected_behavior": "应识别为难题，核心匮乏物是路径、方法与资源。",
|
||
"failure_signal": "只要求团队开会达成共识，忽略路径和资源缺口。",
|
||
"expected_output_elements": [
|
||
"classification=problem",
|
||
"dominant_scarcity=path_resource"
|
||
],
|
||
"should_call_model": true,
|
||
"expected_primary_model": "qpi",
|
||
"negative_expected_models": [],
|
||
"expected_classification": "problem",
|
||
"expected_dominant_scarcity": "path_resource",
|
||
"expected_max_depth": "not_applicable",
|
||
"minimum_required_elements": [
|
||
"recommended_next_step=工程拆解"
|
||
],
|
||
"forbidden_elements": [],
|
||
"evaluation_mode": "structured",
|
||
"notes": "P 类正例。"
|
||
},
|
||
{
|
||
"case_id": "case_qpi_positive_problem_002",
|
||
"model_id": "qpi",
|
||
"case_type": "positive",
|
||
"input": "我们要把模型库做出来，目标清楚，但不知道文件结构、schema 和验证脚本怎么排。",
|
||
"expected_behavior": "应识别为难题，缺路径和工程拆解。",
|
||
"failure_signal": "误判为课题或哲学问题。",
|
||
"expected_output_elements": [
|
||
"problem",
|
||
"path_or_resource_scarcity=high"
|
||
],
|
||
"should_call_model": true,
|
||
"expected_primary_model": "qpi",
|
||
"negative_expected_models": [
|
||
"intellectual_archaeology"
|
||
],
|
||
"expected_classification": "problem",
|
||
"expected_dominant_scarcity": "path_resource",
|
||
"expected_max_depth": "not_applicable",
|
||
"minimum_required_elements": [
|
||
"problem_owner",
|
||
"recommended_next_step"
|
||
],
|
||
"forbidden_elements": [
|
||
"philosophical_bedrock"
|
||
],
|
||
"evaluation_mode": "structured",
|
||
"notes": "工程路径正例。"
|
||
},
|
||
{
|
||
"case_id": "case_qpi_positive_problem_003",
|
||
"model_id": "qpi",
|
||
"case_type": "positive",
|
||
"input": "销售团队知道要触达老客户，但缺少名单清洗流程和跟进节奏。",
|
||
"expected_behavior": "应识别为难题，建议工程拆解和资源配置。",
|
||
"failure_signal": "把它归为价值观冲突。",
|
||
"expected_output_elements": [
|
||
"problem",
|
||
"工程拆解"
|
||
],
|
||
"should_call_model": true,
|
||
"expected_primary_model": "qpi",
|
||
"negative_expected_models": [],
|
||
"expected_classification": "problem",
|
||
"expected_dominant_scarcity": "path_resource",
|
||
"expected_max_depth": "not_applicable",
|
||
"minimum_required_elements": [
|
||
"scarcity_profile"
|
||
],
|
||
"forbidden_elements": [],
|
||
"evaluation_mode": "structured",
|
||
"notes": "P 类正例。"
|
||
},
|
||
{
|
||
"case_id": "case_qpi_positive_issue_001",
|
||
"model_id": "qpi",
|
||
"case_type": "positive",
|
||
"input": "公司各部门对增长目标、品牌定位和用户价值完全没有共识，每个方案都会引发新的抵抗。",
|
||
"expected_behavior": "应识别为课题，核心匮乏物是共识、确定性与动态秩序。",
|
||
"failure_signal": "把它简化成某个员工执行力不足或单一预算不足。",
|
||
"expected_output_elements": [
|
||
"classification=issue",
|
||
"dominant_scarcity=consensus_order"
|
||
],
|
||
"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": [],
|
||
"evaluation_mode": "structured",
|
||
"notes": "I 类正例。"
|
||
},
|
||
{
|
||
"case_id": "case_qpi_positive_issue_002",
|
||
"model_id": "qpi",
|
||
"case_type": "positive",
|
||
"input": "长期主义和季度 KPI 反复冲突，团队每次都回到短期动作。",
|
||
"expected_behavior": "应识别为课题或 mixed 偏 issue，指出时间尺度冲突和共识秩序缺口。",
|
||
"failure_signal": "只给执行清单。",
|
||
"expected_output_elements": [
|
||
"issue",
|
||
"time_scale=mixed"
|
||
],
|
||
"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": [
|
||
"time_scale",
|
||
"problem_source"
|
||
],
|
||
"forbidden_elements": [],
|
||
"evaluation_mode": "structured",
|
||
"notes": "组织时间尺度课题。"
|
||
},
|
||
{
|
||
"case_id": "case_qpi_positive_issue_003",
|
||
"model_id": "qpi",
|
||
"case_type": "positive",
|
||
"input": "教育资源不公平不是一个项目能终结的，但我们需要判断该怎么定义它。",
|
||
"expected_behavior": "应识别为课题，强调动态治理而非终结式解决。",
|
||
"failure_signal": "承诺单一解决方案。",
|
||
"expected_output_elements": [
|
||
"issue",
|
||
"动态平衡"
|
||
],
|
||
"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": [
|
||
"recommended_next_step=共识协调"
|
||
],
|
||
"forbidden_elements": [
|
||
"一次性解决"
|
||
],
|
||
"evaluation_mode": "structured",
|
||
"notes": "社会系统课题。"
|
||
},
|
||
{
|
||
"case_id": "case_qpi_boundary_mixed_001",
|
||
"model_id": "qpi",
|
||
"case_type": "boundary",
|
||
"input": "用户流失率升高，既缺少分群数据，也不确定是产品路径问题还是品牌信任问题。",
|
||
"expected_behavior": "应先标出混合状态，建议补齐数据后再判断主导匮乏物。",
|
||
"failure_signal": "直接断言这是课题或难题，且不给出证据缺口。",
|
||
"expected_output_elements": [
|
||
"classification=mixed",
|
||
"evidence_gap"
|
||
],
|
||
"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": [
|
||
"evidence_gap",
|
||
"dominant_scarcity"
|
||
],
|
||
"forbidden_elements": [],
|
||
"evaluation_mode": "structured",
|
||
"notes": "mixed 边界。"
|
||
},
|
||
{
|
||
"case_id": "case_qpi_boundary_mixed_002",
|
||
"model_id": "qpi",
|
||
"case_type": "boundary",
|
||
"input": "产品上线失败，可能是缺数据、缺发布流程，也可能是团队对价值主张不一致。",
|
||
"expected_behavior": "应标 mixed，并要求补充证据以判断主导匮乏物。",
|
||
"failure_signal": "强行单标签。",
|
||
"expected_output_elements": [
|
||
"mixed",
|
||
"补充上下文"
|
||
],
|
||
"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": [
|
||
"scarcity_profile"
|
||
],
|
||
"forbidden_elements": [],
|
||
"evaluation_mode": "structured",
|
||
"notes": "三类匮乏物混合。"
|
||
},
|
||
{
|
||
"case_id": "case_qpi_boundary_mixed_003",
|
||
"model_id": "qpi",
|
||
"case_type": "boundary",
|
||
"input": "团队说这是战略课题，但实际只看到客户跟进表长期没人维护。",
|
||
"expected_behavior": "应警惕恶意升维，先切回可验证的路径/责任问题。",
|
||
"failure_signal": "接受战略课题叙事。",
|
||
"expected_output_elements": [
|
||
"恶意升维",
|
||
"problem"
|
||
],
|
||
"should_call_model": true,
|
||
"expected_primary_model": "qpi",
|
||
"negative_expected_models": [
|
||
"intellectual_archaeology"
|
||
],
|
||
"expected_classification": "problem",
|
||
"expected_dominant_scarcity": "path_resource",
|
||
"expected_max_depth": "not_applicable",
|
||
"minimum_required_elements": [
|
||
"misclassification_risk"
|
||
],
|
||
"forbidden_elements": [
|
||
"哲学基岩"
|
||
],
|
||
"evaluation_mode": "structured",
|
||
"notes": "边界加误用。"
|
||
},
|
||
{
|
||
"case_id": "case_qpi_misuse_inflation_001",
|
||
"model_id": "qpi",
|
||
"case_type": "misuse",
|
||
"input": "我没有跟进客户不是我的问题，是大环境不好，客户都没预算。",
|
||
"expected_behavior": "应警惕恶意升维，要求从宏大 Issue 中切割出当前可执行、可衡量的 Problem。",
|
||
"failure_signal": "完全接受大环境叙事，放弃执行责任拆解。",
|
||
"expected_output_elements": [
|
||
"恶意升维",
|
||
"具体障碍"
|
||
],
|
||
"should_call_model": true,
|
||
"expected_primary_model": "qpi",
|
||
"negative_expected_models": [
|
||
"intellectual_archaeology"
|
||
],
|
||
"expected_classification": "problem",
|
||
"expected_dominant_scarcity": "path_resource",
|
||
"expected_max_depth": "not_applicable",
|
||
"minimum_required_elements": [
|
||
"problem_source",
|
||
"misclassification_risk"
|
||
],
|
||
"forbidden_elements": [
|
||
"不可抗力所以无需行动"
|
||
],
|
||
"evaluation_mode": "structured",
|
||
"notes": "恶意升维。"
|
||
},
|
||
{
|
||
"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_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."
|
||
},
|
||
{
|
||
"case_id": "case_qpi_international_logistics_no_call_001",
|
||
"model_id": "qpi",
|
||
"case_type": "no_call",
|
||
"input": "帮我把这些学生按宿舍容量排一下床位表。",
|
||
"expected_behavior": "应 no_call：这是直接物流/排床位执行任务，不应仅因出现容量词而调用 QPI。",
|
||
"failure_signal": "selector 选中 QPI，或把排床位执行误判为容量治理问题。",
|
||
"expected_output_elements": [
|
||
"classification=no_call",
|
||
"recommended_next_step=不调用"
|
||
],
|
||
"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": [
|
||
"hard_no_call_gate"
|
||
],
|
||
"forbidden_elements": [
|
||
"capacity_governance_analysis",
|
||
"classification=mixed"
|
||
],
|
||
"evaluation_mode": "structured",
|
||
"source_case_digest_id": "qpi-year-end-international-college-002",
|
||
"notes": "Round 03.1 no-call trap paired with international capacity governance case."
|
||
},
|
||
{
|
||
"case_id": "case_qpi_research_capacity_problem_not_issue_001",
|
||
"model_id": "qpi",
|
||
"case_type": "boundary",
|
||
"input": "增长活动已经承诺，但物理空间、床位、设施和服务容量不足。现在主要问题是硬容量无法被行政命令解决，虽然继续扩张会带来治理风险。",
|
||
"expected_behavior": "应识别为 problem，dominant_scarcity=path_resource；治理风险存在但不应覆盖硬资源约束的主导地位。",
|
||
"failure_signal": "直接升维为 issue，忽略硬资源约束仍是主导稀缺。",
|
||
"expected_output_elements": [
|
||
"classification=problem",
|
||
"dominant_scarcity=path_resource",
|
||
"governance_risk=medium"
|
||
],
|
||
"should_call_model": true,
|
||
"expected_primary_model": "qpi",
|
||
"negative_expected_models": [],
|
||
"expected_classification": "problem",
|
||
"expected_dominant_scarcity": "path_resource",
|
||
"expected_max_depth": "not_applicable",
|
||
"minimum_required_elements": [
|
||
"physical_capacity",
|
||
"path_resource",
|
||
"governance_risk_boundary"
|
||
],
|
||
"forbidden_elements": [
|
||
"issue_by_governance_load_only",
|
||
"ignore_hard_capacity"
|
||
],
|
||
"evaluation_mode": "structured",
|
||
"source_case_digest_id": "qpi-year-end-research-office-006",
|
||
"notes": "Round 03.1 boundary trap: capacity plus governance risk does not automatically become Issue."
|
||
},
|
||
{
|
||
"case_id": "case_qpi_multi_perspective_requires_viewpoint_output_001",
|
||
"model_id": "qpi",
|
||
"case_type": "boundary",
|
||
"input": "执行层认为这是线索转化问题，决策层认为这是完整教育链战略问题，学生视角还涉及证书信任和交付承诺。请判断这到底是什么问题。",
|
||
"expected_behavior": "应识别 multi_perspective / inter_viewpoint_divergence，并输出 classification_by_viewpoint 或 viewpoint_summary。",
|
||
"failure_signal": "只给单一 issue/mixed 标签，没有列出不同视角下的问题定义。",
|
||
"expected_output_elements": [
|
||
"classification_scope=multi_perspective",
|
||
"classification_by_viewpoint",
|
||
"inter_viewpoint_divergence"
|
||
],
|
||
"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": [
|
||
"classification_by_viewpoint",
|
||
"viewpoint_summary"
|
||
],
|
||
"forbidden_elements": [
|
||
"single_viewpoint_only"
|
||
],
|
||
"evaluation_mode": "structured",
|
||
"source_case_digest_id": "qpi-year-end-international-college-004",
|
||
"notes": "Round 03.1 contract trap for multi-perspective output."
|
||
},
|
||
{
|
||
"case_id": "case_qpi_low_context_provisional_no_high_confidence_001",
|
||
"model_id": "qpi",
|
||
"case_type": "boundary",
|
||
"input": "这个项目推进不顺，到底是问题还是课题？",
|
||
"expected_behavior": "上下文不足时应 is_provisional=true，context_sufficiency=low，classification_confidence 不得为 high，并列出 missing_context。",
|
||
"failure_signal": "在缺少主体、场景、目标、资源和责任信息时输出高置信 Q/P/I。",
|
||
"expected_output_elements": [
|
||
"is_provisional=true",
|
||
"context_sufficiency=low",
|
||
"missing_context",
|
||
"classification_confidence!=high"
|
||
],
|
||
"should_call_model": true,
|
||
"expected_primary_model": "qpi",
|
||
"negative_expected_models": [],
|
||
"expected_classification": "mixed",
|
||
"expected_dominant_scarcity": "unknown",
|
||
"expected_max_depth": "not_applicable",
|
||
"minimum_required_elements": [
|
||
"missing_context",
|
||
"recommended_clarifying_questions"
|
||
],
|
||
"forbidden_elements": [
|
||
"classification_confidence=high"
|
||
],
|
||
"evaluation_mode": "structured",
|
||
"notes": "Round 03.1 dependency trap for low-context provisional classification."
|
||
},
|
||
{
|
||
"case_id": "case_qpi_direct_summary_no_call_001",
|
||
"model_id": "qpi",
|
||
"case_type": "no_call",
|
||
"input": "请把下面内容总结成三点。",
|
||
"expected_behavior": "应 no_call：纯摘要执行任务不需要 QPI。",
|
||
"failure_signal": "selector 因默认分选中 QPI。",
|
||
"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": [
|
||
"hard_no_call_gate"
|
||
],
|
||
"forbidden_elements": [
|
||
"problem_definition"
|
||
],
|
||
"evaluation_mode": "structured",
|
||
"notes": "Round 03.1 direct execution no-call."
|
||
},
|
||
{
|
||
"case_id": "case_qpi_how_to_excel_no_call_001",
|
||
"model_id": "qpi",
|
||
"case_type": "no_call",
|
||
"input": "如何在 Excel 里冻结首行？",
|
||
"expected_behavior": "应 no_call：普通工具 how-to 不应因裸“如何”触发 QPI。",
|
||
"failure_signal": "selector 选中 QPI。",
|
||
"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": [
|
||
"no_call"
|
||
],
|
||
"forbidden_elements": [
|
||
"problem_definition"
|
||
],
|
||
"evaluation_mode": "structured",
|
||
"notes": "Round 03.2 no-call trap: narrow bare qpi_gate_signals."
|
||
},
|
||
{
|
||
"case_id": "case_qpi_how_to_markdown_pdf_no_call_001",
|
||
"model_id": "qpi",
|
||
"case_type": "no_call",
|
||
"input": "如何把 Markdown 转 PDF？",
|
||
"expected_behavior": "应 no_call：普通格式转换 how-to 不应调用 QPI。",
|
||
"failure_signal": "selector 选中 QPI。",
|
||
"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": [
|
||
"no_call"
|
||
],
|
||
"forbidden_elements": [
|
||
"problem_definition"
|
||
],
|
||
"evaluation_mode": "structured",
|
||
"notes": "Round 03.2 no-call trap: generic how-to is not QPI."
|
||
},
|
||
{
|
||
"case_id": "case_qpi_dictionary_judgment_no_call_001",
|
||
"model_id": "qpi",
|
||
"case_type": "no_call",
|
||
"input": "判断这个词是什么意思。",
|
||
"expected_behavior": "应 no_call：普通词义判断不应因裸“判断”触发 QPI。",
|
||
"failure_signal": "selector 选中 QPI。",
|
||
"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": [
|
||
"no_call"
|
||
],
|
||
"forbidden_elements": [
|
||
"problem_definition"
|
||
],
|
||
"evaluation_mode": "structured",
|
||
"notes": "Round 03.2 no-call trap: dictionary judgment is not QPI."
|
||
},
|
||
{
|
||
"case_id": "case_qpi_analysis_override_should_call_001",
|
||
"model_id": "qpi",
|
||
"case_type": "selector_gate",
|
||
"input": "请把下面内容总结成三点，但不要只执行，请分析背后的问题定义和组织结构冲突。",
|
||
"expected_behavior": "显式 analysis override 应覆盖直接执行 no-call，selector 应选择 QPI。",
|
||
"failure_signal": "hard no-call 误杀包含明确分析 override 的混合请求。",
|
||
"expected_output_elements": [
|
||
"selected=qpi",
|
||
"analysis_override"
|
||
],
|
||
"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": [
|
||
"override_preserved"
|
||
],
|
||
"forbidden_elements": [
|
||
"hard_no_call_without_override_check"
|
||
],
|
||
"evaluation_mode": "structured",
|
||
"notes": "Round 03.1 override trap: direct execution phrase plus explicit analysis request."
|
||
},
|
||
{
|
||
"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。"
|
||
},
|
||
{
|
||
"case_id": "case_ia_positive_heavy_failure_001",
|
||
"model_id": "intellectual_archaeology",
|
||
"case_type": "positive",
|
||
"input": "这个战略方案连续三次失败，但每次复盘都只停留在执行动作，我们怀疑底层目的和机制错了。",
|
||
"expected_behavior": "应调用，允许下潜到目的层或核心机理层。",
|
||
"failure_signal": "只给执行建议。",
|
||
"expected_output_elements": [
|
||
"entry_reason",
|
||
"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": [
|
||
"no_deeper_reason"
|
||
],
|
||
"forbidden_elements": [],
|
||
"evaluation_mode": "structured",
|
||
"notes": "重型失败复盘。"
|
||
},
|
||
{
|
||
"case_id": "case_ia_positive_heavy_philosophy_001",
|
||
"model_id": "intellectual_archaeology",
|
||
"case_type": "positive",
|
||
"input": "我们正在定义问题本身的模型，涉及认知主体和现实映射的关系。",
|
||
"expected_behavior": "可下潜到哲学基岩层，但必须说明为何需要。",
|
||
"failure_signal": "不说明理由就上哲学。",
|
||
"expected_output_elements": [
|
||
"philosophical_bedrock",
|
||
"entry_reason"
|
||
],
|
||
"should_call_model": true,
|
||
"expected_primary_model": "intellectual_archaeology",
|
||
"negative_expected_models": [],
|
||
"expected_classification": "not_applicable",
|
||
"expected_dominant_scarcity": "not_applicable",
|
||
"expected_max_depth": "philosophical_bedrock",
|
||
"minimum_required_elements": [
|
||
"stop_reason",
|
||
"action_implication"
|
||
],
|
||
"forbidden_elements": [],
|
||
"evaluation_mode": "structured",
|
||
"notes": "少数可到哲学基岩的正例。"
|
||
},
|
||
{
|
||
"case_id": "case_ia_boundary_medium_purpose_001",
|
||
"model_id": "intellectual_archaeology",
|
||
"case_type": "boundary",
|
||
"input": "我们知道课堂评价指标，但不知道它服务的教育目的是否一致。",
|
||
"expected_behavior": "应下潜到目的层后停止。",
|
||
"failure_signal": "自动下潜到哲学基岩。",
|
||
"expected_output_elements": [
|
||
"recommended_max_depth=purpose"
|
||
],
|
||
"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": [
|
||
"no_deeper_reason"
|
||
],
|
||
"forbidden_elements": [
|
||
"philosophical_bedrock"
|
||
],
|
||
"evaluation_mode": "structured",
|
||
"notes": "中型目的层。"
|
||
},
|
||
{
|
||
"case_id": "case_ia_boundary_medium_process_001",
|
||
"model_id": "intellectual_archaeology",
|
||
"case_type": "boundary",
|
||
"input": "流程卡住了，我们需要理解实际业务过程，而不是重写价值观。",
|
||
"expected_behavior": "最多到过程层，说明停止理由。",
|
||
"failure_signal": "展开人类能力或哲学层。",
|
||
"expected_output_elements": [
|
||
"recommended_max_depth=process"
|
||
],
|
||
"should_call_model": true,
|
||
"expected_primary_model": "intellectual_archaeology",
|
||
"negative_expected_models": [],
|
||
"expected_classification": "not_applicable",
|
||
"expected_dominant_scarcity": "not_applicable",
|
||
"expected_max_depth": "process",
|
||
"minimum_required_elements": [
|
||
"stop_reason"
|
||
],
|
||
"forbidden_elements": [
|
||
"human_capability",
|
||
"philosophical_bedrock"
|
||
],
|
||
"evaluation_mode": "structured",
|
||
"notes": "过程层停止。"
|
||
},
|
||
{
|
||
"case_id": "case_ia_boundary_medium_core_001",
|
||
"model_id": "intellectual_archaeology",
|
||
"case_type": "boundary",
|
||
"input": "我们已经有流程图，但不知道学习机制是否支撑这个流程。",
|
||
"expected_behavior": "可下潜到核心机理层，不应继续到哲学基岩。",
|
||
"failure_signal": "无条件七层全开。",
|
||
"expected_output_elements": [
|
||
"core_mechanism",
|
||
"no_deeper_reason"
|
||
],
|
||
"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": [
|
||
"validation_needed"
|
||
],
|
||
"forbidden_elements": [
|
||
"philosophical_bedrock"
|
||
],
|
||
"evaluation_mode": "structured",
|
||
"notes": "核心机理层停止。"
|
||
},
|
||
{
|
||
"case_id": "case_ia_no_call_fact_001",
|
||
"model_id": "intellectual_archaeology",
|
||
"case_type": "no_call",
|
||
"input": "我只是想知道这篇文章里有没有提到某个工具名称。",
|
||
"expected_behavior": "不应调用思想考古，应建议直接检索。",
|
||
"failure_signal": "强行展开七层哲学分析。",
|
||
"expected_output_elements": [
|
||
"should_call=false"
|
||
],
|
||
"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": [
|
||
"entry_reason"
|
||
],
|
||
"forbidden_elements": [
|
||
"七层"
|
||
],
|
||
"evaluation_mode": "structured",
|
||
"notes": "事实检索 no-call。"
|
||
},
|
||
{
|
||
"case_id": "case_ia_no_call_edit_001",
|
||
"model_id": "intellectual_archaeology",
|
||
"case_type": "no_call",
|
||
"input": "请把这段话润色一下，不要深入分析。",
|
||
"expected_behavior": "不调用。",
|
||
"failure_signal": "展开底层假设。",
|
||
"expected_output_elements": [
|
||
"should_call=false"
|
||
],
|
||
"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": [
|
||
"no_deeper_reason"
|
||
],
|
||
"forbidden_elements": [
|
||
"底层假设"
|
||
],
|
||
"evaluation_mode": "structured",
|
||
"notes": "润色 no-call。"
|
||
},
|
||
{
|
||
"case_id": "case_ia_no_call_light_execution_001",
|
||
"model_id": "intellectual_archaeology",
|
||
"case_type": "no_call",
|
||
"input": "按钮文案写错了，直接改成保存即可。",
|
||
"expected_behavior": "不调用。",
|
||
"failure_signal": "重新定义用户关系。",
|
||
"expected_output_elements": [
|
||
"should_call=false"
|
||
],
|
||
"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": [
|
||
"action_implication"
|
||
],
|
||
"forbidden_elements": [
|
||
"philosophical_bedrock"
|
||
],
|
||
"evaluation_mode": "structured",
|
||
"notes": "轻量执行 no-call。"
|
||
},
|
||
{
|
||
"case_id": "case_ia_misuse_philosophizing_001",
|
||
"model_id": "intellectual_archaeology",
|
||
"case_type": "misuse",
|
||
"input": "我们已经知道方案只需要修一个按钮文案，但还想顺便从哲学基岩重新定义用户关系。",
|
||
"expected_behavior": "应拒绝过度下钻，说明继续下潜不会改变判断或行动。",
|
||
"failure_signal": "接受无必要的哲学化扩展。",
|
||
"expected_output_elements": [
|
||
"停止下钻",
|
||
"行动不改变"
|
||
],
|
||
"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": [
|
||
"no_deeper_reason"
|
||
],
|
||
"forbidden_elements": [
|
||
"philosophical_bedrock"
|
||
],
|
||
"evaluation_mode": "structured",
|
||
"notes": "过度哲学化。"
|
||
},
|
||
{
|
||
"case_id": "case_ia_misuse_no_validation_001",
|
||
"model_id": "intellectual_archaeology",
|
||
"case_type": "misuse",
|
||
"input": "我们用七层结构写出一个很自洽的模型，准备直接上线，不做红队、数据对撞或专家盲审。",
|
||
"expected_behavior": "应指出内部自洽不等于现实有效，要求补充验证机制。",
|
||
"failure_signal": "把七层结构本身视为充分验证。",
|
||
"expected_output_elements": [
|
||
"validation_needed"
|
||
],
|
||
"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": [
|
||
"validation_needed"
|
||
],
|
||
"forbidden_elements": [
|
||
"直接上线"
|
||
],
|
||
"evaluation_mode": "structured",
|
||
"notes": "无验证误用。"
|
||
},
|
||
{
|
||
"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_negative_explicit_do_not_call_001",
|
||
"model_id": "intellectual_archaeology",
|
||
"case_type": "selector_gate",
|
||
"input": "QPI 已判断：这是 Issue。先不要思想考古，只做问题定性复核。",
|
||
"expected_behavior": "selector 应选择 QPI，并硬拒绝思想考古。",
|
||
"failure_signal": "因为“思想考古”和“QPI 已判断”加分而仍选中 IA。",
|
||
"expected_output_elements": [
|
||
"selected=qpi",
|
||
"rejected=intellectual_archaeology"
|
||
],
|
||
"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": [
|
||
"model_level_hard_exclusion"
|
||
],
|
||
"forbidden_elements": [
|
||
"selected IA"
|
||
],
|
||
"evaluation_mode": "structured",
|
||
"notes": "Round 03.2 hard exclusion trap: explicit IA refusal must override score."
|
||
},
|
||
{
|
||
"case_id": "case_ia_negative_only_qpi_001",
|
||
"model_id": "intellectual_archaeology",
|
||
"case_type": "selector_gate",
|
||
"input": "不要思想考古，只做 QPI 复核。",
|
||
"expected_behavior": "selector 应选择 QPI，并硬拒绝思想考古。",
|
||
"failure_signal": "IA 负触发只被当作 penalty，仍可能被选中。",
|
||
"expected_output_elements": [
|
||
"selected=qpi",
|
||
"rejected=intellectual_archaeology"
|
||
],
|
||
"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": [
|
||
"model_level_hard_exclusion"
|
||
],
|
||
"forbidden_elements": [
|
||
"selected IA"
|
||
],
|
||
"evaluation_mode": "structured",
|
||
"notes": "Round 03.2 hard exclusion trap: only-QPI instruction rejects IA."
|
||
}
|
||
]
|
||
}
|