25 lines
15 KiB
JSON
25 lines
15 KiB
JSON
{
|
||
"model_id": "intellectual_archaeology",
|
||
"regression_cases": [
|
||
{"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."}
|
||
]
|
||
}
|