39 lines
27 KiB
JSON
39 lines
27 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_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。"}
|
||
]
|
||
}
|