eduevidence 6.0.0 → 6.2.0

package/examples/spaced-retrieval-practice/frame.json

@@ -0,0 +1,58 @@
+{
+  "question": "在大学的程序设计入门课程中，是否应该用间隔重复与检索练习替代传统的集中式复习？这对学生的长期知识保持是否有效？",
+  "decision_target": "teaching_decision",
+  "learner": {
+    "education_level": "undergraduate_year_1",
+    "major": "computer_science",
+    "prior_knowledge": "introductory_programming_no_prior_experience",
+    "special_characteristics": "large_lecture_with_weekly_labs"
+  },
+  "course": {
+    "subject": "introductory_programming",
+    "course_type": "lecture_lab",
+    "duration": "16_weeks_one_semester"
+  },
+  "intervention": {
+    "teaching_method": "spaced_retrieval_practice",
+    "ai_tool": "",
+    "allowed_usage": "",
+    "frequency": "weekly_short_quizzes",
+    "duration": "one_semester"
+  },
+  "comparison": "concentrated_review_before_exams (business as usual)",
+  "outcomes": {
+    "primary": [
+      "retention",
+      "transfer"
+    ],
+    "secondary": [
+      "knowledge_gain",
+      "independent_problem_solving"
+    ],
+    "risk": [
+      "reduced_effort"
+    ]
+  },
+  "context": {
+    "teacher_support": "TA_supported",
+    "class_size": "large",
+    "online_or_offline": "offline"
+  },
+  "scope": {
+    "time_range": "2000-2026",
+    "geography": "global",
+    "study_types": [
+      "rct",
+      "quasi_experimental"
+    ]
+  },
+  "inclusion_criteria": [
+    "studies measuring delayed retention or transfer",
+    "programming or STEM novices"
+  ],
+  "exclusion_criteria": [
+    "no delayed measurement",
+    "purely correlational"
+  ],
+  "success_condition": "delayed retention improves or holds while transfer does not decline"
+}

package/examples/spaced-retrieval-practice/gate_report.json

@@ -0,0 +1,101 @@
+{
+  "gate_version": "2026-08-13.v1",
+  "checked_at": "2026-09-13T03:17:13.784688+00:00",
+  "workspace": "examples/spaced-retrieval-practice",
+  "items": {
+    "research_frame_valid": {
+      "title": "Research Frame valid",
+      "status": "pass",
+      "detail": "frame.json valid (question=在大学的程序设计入门课程中，是否应该用间隔重复与检索练习替代传统的集中式复习？这对学生的长期知识保持是否有效？)",
+      "critical": true,
+      "blocks_high": true
+    },
+    "sources_valid": {
+      "title": "Sources valid",
+      "status": "pass",
+      "detail": "7 source record(s) schema-valid",
+      "critical": true,
+      "blocks_high": true
+    },
+    "evidence_schema_valid": {
+      "title": "Evidence Schema valid",
+      "status": "pass",
+      "detail": "6 evidence record(s) schema-valid",
+      "critical": true,
+      "blocks_high": true
+    },
+    "source_dedupe": {
+      "title": "Source dedupe",
+      "status": "pass",
+      "detail": "7 unique source(s), no duplicates",
+      "critical": true,
+      "blocks_high": true
+    },
+    "counter_evidence_search": {
+      "title": "Counter-evidence search",
+      "status": "pass",
+      "detail": "search_performed=true; 9/9 checks run; findings=2; contradictory_evidence_found=False",
+      "critical": true,
+      "blocks_high": true
+    },
+    "methodology_audit": {
+      "title": "Methodology audit",
+      "status": "pass",
+      "detail": "methodology verdict=PASS; task/learning separated",
+      "critical": true,
+      "blocks_high": true
+    },
+    "claim_evidence_audit": {
+      "title": "Claim-Evidence Audit",
+      "status": "pass",
+      "detail": "all verdict claims bind to existing evidence with consistent categories",
+      "critical": true,
+      "blocks_high": false
+    },
+    "outcome_mapping": {
+      "title": "Outcome mapping",
+      "status": "warn",
+      "detail": "outcome keys known; frame-declared outcomes without evidence: independent_problem_solving, knowledge_gain, reduced_effort",
+      "critical": false,
+      "blocks_high": false
+    },
+    "scope_calibration": {
+      "title": "Scope calibration",
+      "status": "pass",
+      "detail": "claims bounded: can=2, cannot=2, exceeds_boundary=0",
+      "critical": false,
+      "blocks_high": true
+    },
+    "independent_study_count": {
+      "title": "Independent study-sample count",
+      "status": "pass",
+      "detail": "independent studies=6, samples=6",
+      "critical": true,
+      "blocks_high": true
+    },
+    "deterministic_confidence": {
+      "title": "Deterministic confidence",
+      "status": "pass",
+      "detail": "deterministic confidence=High (score=0.893, policy=2026-08-12.v3)",
+      "critical": true,
+      "blocks_high": true
+    },
+    "decision_action_consistency": {
+      "title": "Decision action consistency",
+      "status": "pass",
+      "detail": "ADOPT is supported: High confidence with direct primary-outcome evidence",
+      "critical": true,
+      "blocks_high": false
+    }
+  },
+  "passed": true,
+  "critical_failures": [],
+  "high_confidence_allowed": true,
+  "max_confidence": "High",
+  "enforcement": {
+    "rule": "confidence capped at {max}; High confidence requires a fully passing gate and >= 2 independent studies",
+    "max_confidence": "High",
+    "requires_action_change": false,
+    "action_override": null
+  }
+}

package/examples/spaced-retrieval-practice/methodology.json

@@ -0,0 +1,78 @@
+{
+  "target": "overall",
+  "verdict": "PASS",
+  "audit_items": {
+    "control_group": {
+      "status": "met",
+      "note": "由本轮真实检索到的证据集评估得出"
+    },
+    "randomization": {
+      "status": "partial",
+      "note": "由本轮真实检索到的证据集评估得出"
+    },
+    "pre_test": {
+      "status": "partial",
+      "note": "由本轮真实检索到的证据集评估得出"
+    },
+    "post_test": {
+      "status": "met",
+      "note": "由本轮真实检索到的证据集评估得出"
+    },
+    "retention_test": {
+      "status": "met",
+      "note": "由本轮真实检索到的证据集评估得出"
+    },
+    "transfer_test": {
+      "status": "partial",
+      "note": "由本轮真实检索到的证据集评估得出"
+    },
+    "sample_bias": {
+      "status": "partial",
+      "note": "由本轮真实检索到的证据集评估得出"
+    },
+    "self_selection": {
+      "status": "partial",
+      "note": "由本轮真实检索到的证据集评估得出"
+    },
+    "measurement_validity": {
+      "status": "met",
+      "note": "由本轮真实检索到的证据集评估得出"
+    },
+    "confounders": {
+      "status": "partial",
+      "note": "由本轮真实检索到的证据集评估得出"
+    },
+    "instructor_effect": {
+      "status": "missing",
+      "note": "由本轮真实检索到的证据集评估得出"
+    },
+    "novelty_effect": {
+      "status": "missing",
+      "note": "由本轮真实检索到的证据集评估得出"
+    },
+    "tool_version_effect": {
+      "status": "not_applicable",
+      "note": "由本轮真实检索到的证据集评估得出"
+    },
+    "ai_usage_policy": {
+      "status": "not_applicable",
+      "note": "由本轮真实检索到的证据集评估得出"
+    },
+    "dropout": {
+      "status": "missing",
+      "note": "由本轮真实检索到的证据集评估得出"
+    }
+  },
+  "task_vs_learning_guard": {
+    "measured_construct": "delayed retention and transfer, not immediate task speed",
+    "equates_task_with_learning": false,
+    "note": "本证据集以延迟保持与迁移为主要结果，未把即时练习表现等同于学习。"
+  },
+  "limitations": [
+    "多数研究来自心理学实验室材料，程序设计课程的现场证据相对有限",
+    "间隔长度与练习形式在研究中差异较大"
+  ],
+  "suggestions": [
+    "在课程内固定每周短检索练习并统一延迟后测口径"
+  ]
+}

package/examples/spaced-retrieval-practice/report_spec.json

@@ -0,0 +1,212 @@
+{
+  "generated_by": "build_report.py",
+  "source": "result.json + result.zh.json",
+  "question": "在大学的程序设计入门课程中，是否应该用间隔重复与检索练习替代传统的集中式复习？这对学生的长期知识保持是否有效？",
+  "theme_selected": "claude",
+  "theme_display": "Claude Research [Light]",
+  "theme_available": [
+    "claude",
+    "academic",
+    "datalab",
+    "datalab-dark",
+    "presentation"
+  ],
+  "theme_selection": "generation_time",
+  "lang_default": "zh",
+  "lang_switchable": [
+    "zh",
+    "en"
+  ],
+  "report_pages": [
+    "visual_brief",
+    "full_report"
+  ],
+  "full_report_outline": {
+    "chapter_count": 6,
+    "source": "safe_fallback",
+    "chapters": [
+      {
+        "key": "decision",
+        "title_zh": "结论、裁决与研究边界",
+        "title_en": "Decision, Adjudication & Research Boundary",
+        "modules": [
+          "decision",
+          "scope"
+        ]
+      },
+      {
+        "key": "evidence",
+        "title_zh": "关键证据与结果分离",
+        "title_en": "Key Evidence & Outcome Separation",
+        "modules": [
+          "retrieval",
+          "outcomes",
+          "evidence"
+        ]
+      },
+      {
+        "key": "quality",
+        "title_zh": "证据可信度、反证与方法审计",
+        "title_en": "Evidence Quality, Counterevidence & Method Audit",
+        "modules": [
+          "quality",
+          "conflicts",
+          "trace"
+        ]
+      },
+      {
+        "key": "action",
+        "title_zh": "适用范围与教学行动",
+        "title_en": "Applicability & Teaching Action",
+        "modules": [
+          "applicability",
+          "intervention"
+        ]
+      },
+      {
+        "key": "evaluation",
+        "title_zh": "试点设计、评估与停止条件",
+        "title_en": "Pilot, Evaluation & Stop Conditions",
+        "modules": [
+          "evaluation"
+        ]
+      },
+      {
+        "key": "sources",
+        "title_zh": "来源、溯源与附录",
+        "title_en": "Sources, Traceability & Appendix",
+        "modules": [
+          "sources"
+        ]
+      }
+    ]
+  },
+  "visualization_decisions": {
+    "outcome_separation": {
+      "render": true,
+      "reason": "multiple outcome constructs present"
+    },
+    "outcome_evidence_balance": {
+      "render": false,
+      "reason": "suppressed: sparse effect counts (total=6, active=2, nonzero_cells=3, max_cell=4)"
+    },
+    "claim_trace": {
+      "render": true,
+      "reason": "claim-evidence-source relationships present"
+    },
+    "benchmark": {
+      "render": false,
+      "reason": "suppressed: absent, simulated, or fewer than two baselines"
+    }
+  },
+  "lieflat_gallery": {
+    "layout_source": "deterministic_fallback",
+    "selected": [
+      {
+        "chart_id": "lieflat-hundred-field.svg",
+        "type": "hundred_field",
+        "catalog_ref": "L14 Hundred Field",
+        "source": "evidence.study_type_composition"
+      },
+      {
+        "chart_id": "lieflat-tick-gauge.svg",
+        "type": "tick_gauge",
+        "catalog_ref": "F11 Tick Gauge",
+        "source": "decision.confidence_score"
+      },
+      {
+        "chart_id": "lieflat-ballot-tally.svg",
+        "type": "ballot_tally",
+        "catalog_ref": "L15 Ballot Tally",
+        "source": "methodology.flag_rates"
+      }
+    ],
+    "suppressed": [],
+    "rejected": [],
+    "warnings": [
+      "visual_layout missing or fully invalid — data-driven fallback selected hundred_field, tick_gauge, ballot_tally"
+    ]
+  },
+  "charts": [
+    {
+      "chart_id": "outcome-evidence-overview",
+      "purpose": "interactive_analysis",
+      "engine": "echarts",
+      "data_ref": null,
+      "title": "Outcome Evidence Overview",
+      "integrity": {
+        "numbers_match_result": "NOT_CHECKED",
+        "no_axis_distortion": "NOT_CHECKED",
+        "no_false_precision": "NOT_CHECKED",
+        "colorblind_safe": "NOT_CHECKED"
+      }
+    },
+    {
+      "chart_id": "claim-evidence-trace",
+      "purpose": "interactive_analysis",
+      "engine": "echarts",
+      "data_ref": null,
+      "title": "Claim-Evidence Trace",
+      "integrity": {
+        "numbers_match_result": "NOT_CHECKED",
+        "no_axis_distortion": "NOT_CHECKED",
+        "no_false_precision": "NOT_CHECKED",
+        "colorblind_safe": "NOT_CHECKED"
+      }
+    }
+  ],
+  "infographics": [
+    {
+      "chart_id": "workflow",
+      "purpose": "process_or_story",
+      "engine": "antv_infographic",
+      "title": ""
+    },
+    {
+      "chart_id": "tribunal",
+      "purpose": "process_or_story",
+      "engine": "antv_infographic",
+      "title": ""
+    },
+    {
+      "chart_id": "intervention",
+      "purpose": "process_or_story",
+      "engine": "antv_infographic",
+      "title": ""
+    },
+    {
+      "chart_id": "evaluation",
+      "purpose": "process_or_story",
+      "engine": "antv_infographic",
+      "title": ""
+    }
+  ],
+  "academic_figures": [
+    {
+      "chart_id": "outcome-comparison",
+      "purpose": "statistical_publication",
+      "engine": "academic_figure",
+      "caption": "Fig. 1. Counts of positive / negative / null effects per outcome type (based on effect_direction; publication figure, theme-independent). Source: EduEvidence result.json."
+    }
+  ],
+  "integrity_gate": {
+    "status": "PASS",
+    "contract_valid": "PASS",
+    "claims_bound": "PASS",
+    "evidence_bound": 6,
+    "sources_resolved": 7,
+    "numbers_match_result": "PASS",
+    "bilingual_structure_match": "PASS",
+    "language_match": "PASS",
+    "no_false_precision": "PASS",
+    "lieflat_data_bound": "PASS",
+    "no_axis_distortion": "NOT_CHECKED",
+    "colorblind_safe": "NOT_CHECKED",
+    "langs": [
+      "zh",
+      "en"
+    ],
+    "generated_by": "build_report.py",
+    "source": "result.json + result.zh.json"
+  }
+}