eduevidence 6.0.0 → 6.2.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (189) hide show
  1. package/CONTRIBUTING.md +105 -0
  2. package/README.md +93 -38
  3. package/README.zh-CN.md +26 -6
  4. package/SKILL.md +11 -2
  5. package/assets/readme/landing-tour.gif +0 -0
  6. package/assets/readme/studio-tour.gif +0 -0
  7. package/bin/eduevidence.js +2 -1
  8. package/docs/architecture.md +319 -43
  9. package/docs/demo-workplace-ai.md +1 -1
  10. package/docs/install-guide.md +1 -1
  11. package/docs/orchestration-role-model.md +1 -1
  12. package/docs/release-closeout/README.md +1 -1
  13. package/docs/sciverse-api.md +125 -0
  14. package/eduevidence_cli.py +10 -0
  15. package/engine/decision_policy.py +96 -0
  16. package/engine/evidence_graph.py +14 -10
  17. package/engine/gaps.py +42 -22
  18. package/engine/ids.py +2 -0
  19. package/engine/library.py +6 -2
  20. package/engine/living.py +34 -4
  21. package/engine/migration.py +88 -3
  22. package/engine/orchestration.py +5 -5
  23. package/engine/paths.py +2 -0
  24. package/engine/pilot.py +34 -32
  25. package/engine/taxonomy.py +211 -0
  26. package/engine/tribunal.py +43 -31
  27. package/engine/versions.py +1 -1
  28. package/examples/ai-coding-assistant-evidence/EduEvidence_Report.html +1360 -146
  29. package/examples/ai-coding-assistant-evidence/artifact_manifest.json +3 -3
  30. package/examples/ai-coding-assistant-evidence/citation_check.json +1 -1
  31. package/examples/ai-coding-assistant-evidence/final_verdict.json +107 -0
  32. package/examples/ai-coding-assistant-evidence/gate_report.json +101 -0
  33. package/examples/ai-coding-assistant-evidence/report_spec.json +23 -12
  34. package/examples/ai-coding-assistant-evidence/reports-5themes/EduEvidence_Report_academic.html +447 -127
  35. package/examples/ai-coding-assistant-evidence/reports-5themes/EduEvidence_Report_claude.html +447 -127
  36. package/examples/ai-coding-assistant-evidence/reports-5themes/EduEvidence_Report_datalab-dark.html +447 -127
  37. package/examples/ai-coding-assistant-evidence/reports-5themes/EduEvidence_Report_datalab.html +447 -127
  38. package/examples/ai-coding-assistant-evidence/reports-5themes/EduEvidence_Report_presentation.html +447 -127
  39. package/examples/ai-coding-assistant-evidence/reports-5themes/report_academic.html +1360 -146
  40. package/examples/ai-coding-assistant-evidence/reports-5themes/report_claude.html +1360 -146
  41. package/examples/ai-coding-assistant-evidence/reports-5themes/report_datalab-dark.html +1360 -146
  42. package/examples/ai-coding-assistant-evidence/reports-5themes/report_datalab.html +1360 -146
  43. package/examples/ai-coding-assistant-evidence/reports-5themes/report_presentation.html +1360 -146
  44. package/examples/ai-coding-assistant-evidence/result.json +13 -9
  45. package/examples/ai-coding-assistant-evidence/result.zh.json +45 -41
  46. package/examples/ai-coding-assistant-evidence/skeptic.json +72 -0
  47. package/examples/ai-coding-assistant-evidence/verdict.json +6 -2
  48. package/examples/spaced-retrieval-practice/applicability.json +14 -0
  49. package/examples/spaced-retrieval-practice/artifact_manifest.json +15 -0
  50. package/examples/spaced-retrieval-practice/claims.jsonl +3 -0
  51. package/examples/spaced-retrieval-practice/evidence.jsonl +6 -0
  52. package/examples/spaced-retrieval-practice/final_verdict.json +93 -0
  53. package/examples/spaced-retrieval-practice/frame.json +58 -0
  54. package/examples/spaced-retrieval-practice/gate_report.json +101 -0
  55. package/examples/spaced-retrieval-practice/methodology.json +78 -0
  56. package/examples/spaced-retrieval-practice/report_spec.json +212 -0
  57. package/examples/spaced-retrieval-practice/reports-5themes/EduEvidence_Report_academic.html +2728 -0
  58. package/examples/spaced-retrieval-practice/reports-5themes/EduEvidence_Report_claude.html +2728 -0
  59. package/examples/spaced-retrieval-practice/reports-5themes/EduEvidence_Report_datalab-dark.html +2728 -0
  60. package/examples/spaced-retrieval-practice/reports-5themes/EduEvidence_Report_datalab.html +2728 -0
  61. package/examples/spaced-retrieval-practice/reports-5themes/EduEvidence_Report_presentation.html +2728 -0
  62. package/examples/spaced-retrieval-practice/reports-5themes/report_academic.html +2728 -0
  63. package/examples/spaced-retrieval-practice/reports-5themes/report_claude.html +2728 -0
  64. package/examples/spaced-retrieval-practice/reports-5themes/report_datalab-dark.html +2728 -0
  65. package/examples/spaced-retrieval-practice/reports-5themes/report_datalab.html +2728 -0
  66. package/examples/spaced-retrieval-practice/reports-5themes/report_presentation.html +2728 -0
  67. package/examples/spaced-retrieval-practice/result.json +942 -0
  68. package/examples/spaced-retrieval-practice/result.zh.json +942 -0
  69. package/examples/spaced-retrieval-practice/skeptic.json +70 -0
  70. package/examples/spaced-retrieval-practice/sources.jsonl +7 -0
  71. package/examples/spaced-retrieval-practice/verdict.json +93 -0
  72. package/examples/workplace-ai-assistant/artifact_manifest.json +15 -0
  73. package/examples/workplace-ai-assistant/claims.jsonl +4 -4
  74. package/examples/workplace-ai-assistant/evidence.jsonl +4 -4
  75. package/examples/workplace-ai-assistant/evidence_graph.json +15 -15
  76. package/examples/workplace-ai-assistant/final_verdict.json +78 -0
  77. package/examples/workplace-ai-assistant/gate_report.json +101 -0
  78. package/examples/workplace-ai-assistant/report_spec.json +209 -40
  79. package/examples/workplace-ai-assistant/reports-5themes/EduEvidence_Report_academic.html +435 -105
  80. package/examples/workplace-ai-assistant/reports-5themes/EduEvidence_Report_claude.html +435 -105
  81. package/examples/workplace-ai-assistant/reports-5themes/EduEvidence_Report_datalab-dark.html +435 -105
  82. package/examples/workplace-ai-assistant/reports-5themes/EduEvidence_Report_datalab.html +435 -105
  83. package/examples/workplace-ai-assistant/reports-5themes/EduEvidence_Report_presentation.html +435 -105
  84. package/examples/workplace-ai-assistant/reports-5themes/report_academic.html +2814 -0
  85. package/examples/workplace-ai-assistant/reports-5themes/report_claude.html +2814 -0
  86. package/examples/workplace-ai-assistant/reports-5themes/report_datalab-dark.html +2814 -0
  87. package/examples/workplace-ai-assistant/reports-5themes/report_datalab.html +2814 -0
  88. package/examples/workplace-ai-assistant/reports-5themes/report_presentation.html +2814 -0
  89. package/examples/workplace-ai-assistant/result.json +82 -20
  90. package/examples/workplace-ai-assistant/result.zh.json +82 -20
  91. package/examples/workplace-ai-assistant/skeptic.json +72 -0
  92. package/examples/workplace-ai-assistant/verdict.json +36 -10
  93. package/integrations/agent_mcp.py +2 -2
  94. package/package.json +12 -3
  95. package/pyproject.toml +4 -3
  96. package/references/report-copy-style.md +67 -0
  97. package/references/retrieval-compliance.md +75 -0
  98. package/references/retrieval-protocol.md +20 -0
  99. package/retrieval/audit.py +27 -3
  100. package/retrieval/fetch.py +96 -0
  101. package/retrieval/sciverse.py +398 -0
  102. package/retrieval/search.py +47 -7
  103. package/schemas/applicability.schema.json +94 -0
  104. package/schemas/chart-spec.schema.json +10 -3
  105. package/schemas/evidence.schema.json +316 -43
  106. package/schemas/fetch-result.schema.json +2 -1
  107. package/schemas/report-result.schema.json +3 -3
  108. package/schemas/report-spec.schema.json +98 -100
  109. package/schemas/skeptic.schema.json +86 -0
  110. package/schemas/source.schema.json +21 -2
  111. package/schemas/v2/finding.schema.json +5 -1
  112. package/schemas/v2/methodology-audit.schema.json +5 -1
  113. package/schemas/v2/outcome.schema.json +28 -5
  114. package/schemas/v2/study.schema.json +5 -1
  115. package/schemas/vNext/autoevolve-session.schema.json +34 -1
  116. package/schemas/vNext/eval-snapshot.schema.json +77 -1
  117. package/schemas/vNext/execution-plan.schema.json +50 -1
  118. package/schemas/vNext/gap-priority.schema.json +54 -1
  119. package/schemas/vNext/negative-search-record.schema.json +68 -1
  120. package/schemas/vNext/research-iteration.schema.json +87 -1
  121. package/schemas/vNext/research-strategy.schema.json +62 -1
  122. package/schemas/vNext/skill-experiment.schema.json +90 -1
  123. package/schemas/vNext/task-spec.schema.json +156 -1
  124. package/schemas/vNext/worker-result.schema.json +60 -1
  125. package/schemas/verdict.schema.json +164 -28
  126. package/scripts/build_esl_artifacts.py +2 -2
  127. package/scripts/build_report_variants.py +18 -2
  128. package/scripts/build_result.py +74 -9
  129. package/scripts/check_package_parity.py +85 -0
  130. package/scripts/check_protocol_alignment.py +375 -0
  131. package/scripts/check_versioned_schemas.py +254 -0
  132. package/scripts/claim_audit.py +13 -8
  133. package/scripts/compute_confidence.py +10 -0
  134. package/scripts/did_regression.py +12 -2
  135. package/scripts/evidence_score.py +5 -2
  136. package/scripts/generate_new_projects.py +4 -4
  137. package/scripts/orchestrator.py +120 -24
  138. package/scripts/pre_verdict_gate.py +224 -26
  139. package/scripts/quickstart.py +18 -2
  140. package/scripts/run_workspace.py +7 -1
  141. package/scripts/skill_payload.py +4 -1
  142. package/scripts/test_adversarial_empirical.py +26 -19
  143. package/scripts/validate_schema.py +31 -1
  144. package/skill/agents/evaluation-designer.md +20 -4
  145. package/skill/agents/evidence-analyst.md +19 -3
  146. package/skill/agents/evidence-judge.md +50 -2
  147. package/skill/agents/evidence-retriever.md +20 -3
  148. package/skill/agents/intervention-designer.md +20 -4
  149. package/skill/agents/method-reviewer.md +18 -2
  150. package/skill/agents/{education-planner.md → research-planner.md} +19 -3
  151. package/skill/agents/skeptic.md +18 -2
  152. package/skill/roles/registry.yaml +11 -11
  153. package/skill/sub-skills/aihot-trend-analysis/SKILL.md +28 -9
  154. package/skill/sub-skills/contradiction-analysis/SKILL.md +31 -11
  155. package/skill/sub-skills/data-analysis/SKILL.md +34 -15
  156. package/skill/sub-skills/ethics-review/SKILL.md +33 -10
  157. package/skill/sub-skills/evidence-extraction/SKILL.md +29 -11
  158. package/skill/sub-skills/evidence-review/SKILL.md +31 -12
  159. package/skill/sub-skills/gap-analysis/SKILL.md +31 -9
  160. package/skill/sub-skills/literature-review/SKILL.md +35 -14
  161. package/skill/sub-skills/methodology-audit/SKILL.md +29 -12
  162. package/skill/sub-skills/report-generation/SKILL.md +28 -0
  163. package/skill/sub-skills/research-planning/SKILL.md +41 -14
  164. package/skill/sub-skills/study-design/SKILL.md +30 -9
  165. package/skill/task-briefs/adjudicate.md +32 -7
  166. package/skill/task-briefs/applicability.md +37 -2
  167. package/skill/task-briefs/audit.md +32 -7
  168. package/skill/task-briefs/challenge.md +34 -5
  169. package/skill/task-briefs/evaluate.md +30 -5
  170. package/skill/task-briefs/extract.md +31 -8
  171. package/skill/task-briefs/frame.md +39 -10
  172. package/skill/task-briefs/intervene.md +32 -6
  173. package/skill/task-briefs/present.md +32 -8
  174. package/skill/task-briefs/projection.md +36 -2
  175. package/skill/task-briefs/retrieve.md +36 -6
  176. package/skill/workflows/decision-and-pilot.md +76 -1
  177. package/skill/workflows/evaluate-and-update.md +83 -0
  178. package/skill/workflows/evidence-review.md +104 -0
  179. package/visualization/eduevidence-report/scripts/build_figures.py +25 -3
  180. package/visualization/eduevidence-report/scripts/build_infographics.py +5 -1
  181. package/visualization/eduevidence-report/scripts/build_report.py +512 -65
  182. package/visualization/eduevidence-report/scripts/charts_data.py +2 -0
  183. package/visualization/eduevidence-report/scripts/lieflat_engine.py +349 -38
  184. package/visualization/eduevidence-report/scripts/zh_labels.py +80 -1
  185. package/web/architecture.html +14885 -0
  186. package/web/studio/assets/index-B8tkF44Q.css +1 -0
  187. package/web/studio/index.html +2 -2
  188. package/web/studio/assets/index-CzXocaGv.css +0 -1
  189. /package/web/studio/assets/{index-pa7jD7n4.js → index-CQ6Keoyc.js} +0 -0
@@ -1,55 +1,224 @@
1
1
  {
2
- "title": "Should an enterprise customer-support team introduce a generative AI assistant?",
3
- "theme": "claude",
4
- "mode": "demo",
5
- "sections": [
6
- {
7
- "id": "decision",
8
- "title": "Decision and boundaries",
9
- "component": "DecisionCard",
10
- "data_ref": "decision"
2
+ "generated_by": "build_report.py",
3
+ "source": "result.json + result.zh.json",
4
+ "question": "Should an enterprise customer-support team introduce a generative AI assistant?",
5
+ "theme_selected": "claude",
6
+ "theme_display": "Claude Research [Light]",
7
+ "theme_available": [
8
+ "claude",
9
+ "academic",
10
+ "datalab",
11
+ "datalab-dark",
12
+ "presentation"
13
+ ],
14
+ "theme_selection": "generation_time",
15
+ "lang_default": "zh",
16
+ "lang_switchable": [
17
+ "zh",
18
+ "en"
19
+ ],
20
+ "report_pages": [
21
+ "visual_brief",
22
+ "full_report"
23
+ ],
24
+ "full_report_outline": {
25
+ "chapter_count": 6,
26
+ "source": "safe_fallback",
27
+ "chapters": [
28
+ {
29
+ "key": "decision",
30
+ "title_zh": "结论、裁决与研究边界",
31
+ "title_en": "Decision, Adjudication & Research Boundary",
32
+ "modules": [
33
+ "decision",
34
+ "scope"
35
+ ]
36
+ },
37
+ {
38
+ "key": "evidence",
39
+ "title_zh": "关键证据与结果分离",
40
+ "title_en": "Key Evidence & Outcome Separation",
41
+ "modules": [
42
+ "retrieval",
43
+ "outcomes",
44
+ "evidence"
45
+ ]
46
+ },
47
+ {
48
+ "key": "quality",
49
+ "title_zh": "证据可信度、反证与方法审计",
50
+ "title_en": "Evidence Quality, Counterevidence & Method Audit",
51
+ "modules": [
52
+ "quality",
53
+ "conflicts",
54
+ "trace"
55
+ ]
56
+ },
57
+ {
58
+ "key": "action",
59
+ "title_zh": "适用范围与教学行动",
60
+ "title_en": "Applicability & Teaching Action",
61
+ "modules": [
62
+ "applicability",
63
+ "intervention"
64
+ ]
65
+ },
66
+ {
67
+ "key": "evaluation",
68
+ "title_zh": "试点设计、评估与停止条件",
69
+ "title_en": "Pilot, Evaluation & Stop Conditions",
70
+ "modules": [
71
+ "evaluation"
72
+ ]
73
+ },
74
+ {
75
+ "key": "sources",
76
+ "title_zh": "来源、溯源与附录",
77
+ "title_en": "Sources, Traceability & Appendix",
78
+ "modules": [
79
+ "sources"
80
+ ]
81
+ }
82
+ ]
83
+ },
84
+ "visualization_decisions": {
85
+ "outcome_separation": {
86
+ "render": true,
87
+ "reason": "multiple outcome constructs present"
11
88
  },
12
- {
13
- "id": "evidence",
14
- "title": "Direct and indirect evidence",
15
- "component": "EvidenceMatrix",
16
- "data_ref": "evidence"
89
+ "outcome_evidence_balance": {
90
+ "render": false,
91
+ "reason": "suppressed: sparse effect counts (total=4, active=2, nonzero_cells=2, max_cell=2)"
92
+ },
93
+ "claim_trace": {
94
+ "render": true,
95
+ "reason": "claim-evidence-source relationships present"
17
96
  },
97
+ "benchmark": {
98
+ "render": false,
99
+ "reason": "suppressed: absent, simulated, or fewer than two baselines"
100
+ }
101
+ },
102
+ "lieflat_gallery": {
103
+ "layout_source": "deterministic_fallback",
104
+ "selected": [
105
+ {
106
+ "chart_id": "lieflat-bubble-almanac.svg",
107
+ "type": "bubble_almanac",
108
+ "catalog_ref": "L9 Bubble Almanac",
109
+ "source": "evidence.year_x_dimension"
110
+ },
111
+ {
112
+ "chart_id": "lieflat-matrix-heat.svg",
113
+ "type": "matrix_heat",
114
+ "catalog_ref": "L16 Matrix Heat",
115
+ "source": "evidence.year_x_outcome_counts"
116
+ },
117
+ {
118
+ "chart_id": "lieflat-hundred-field.svg",
119
+ "type": "hundred_field",
120
+ "catalog_ref": "L14 Hundred Field",
121
+ "source": "evidence.study_type_composition"
122
+ },
123
+ {
124
+ "chart_id": "lieflat-tick-gauge.svg",
125
+ "type": "tick_gauge",
126
+ "catalog_ref": "F11 Tick Gauge",
127
+ "source": "decision.confidence_score"
128
+ },
129
+ {
130
+ "chart_id": "lieflat-ballot-tally.svg",
131
+ "type": "ballot_tally",
132
+ "catalog_ref": "L15 Ballot Tally",
133
+ "source": "methodology.flag_rates"
134
+ }
135
+ ],
136
+ "suppressed": [],
137
+ "rejected": [],
138
+ "warnings": [
139
+ "visual_layout missing or fully invalid — data-driven fallback selected bubble_almanac, matrix_heat, hundred_field, tick_gauge, ballot_tally"
140
+ ]
141
+ },
142
+ "charts": [
18
143
  {
19
- "id": "methodology_reviews",
20
- "title": "Methodological limits",
21
- "component": "MethodologyPanel",
22
- "data_ref": "methodology_reviews"
144
+ "chart_id": "outcome-evidence-overview",
145
+ "purpose": "interactive_analysis",
146
+ "engine": "echarts",
147
+ "data_ref": null,
148
+ "title": "Outcome Evidence Overview",
149
+ "integrity": {
150
+ "numbers_match_result": "NOT_CHECKED",
151
+ "no_axis_distortion": "NOT_CHECKED",
152
+ "no_false_precision": "NOT_CHECKED",
153
+ "colorblind_safe": "NOT_CHECKED"
154
+ }
23
155
  },
24
156
  {
25
- "id": "applicability",
26
- "title": "Deployment conditions",
27
- "component": "ApplicabilityCard",
28
- "data_ref": "applicability"
157
+ "chart_id": "claim-evidence-trace",
158
+ "purpose": "interactive_analysis",
159
+ "engine": "echarts",
160
+ "data_ref": null,
161
+ "title": "Claim-Evidence Trace",
162
+ "integrity": {
163
+ "numbers_match_result": "NOT_CHECKED",
164
+ "no_axis_distortion": "NOT_CHECKED",
165
+ "no_false_precision": "NOT_CHECKED",
166
+ "colorblind_safe": "NOT_CHECKED"
167
+ }
168
+ }
169
+ ],
170
+ "infographics": [
171
+ {
172
+ "chart_id": "workflow",
173
+ "purpose": "process_or_story",
174
+ "engine": "antv_infographic",
175
+ "title": ""
29
176
  },
30
177
  {
31
- "id": "intervention",
32
- "title": "Proposed pilot",
33
- "component": "InterventionTimeline",
34
- "data_ref": "intervention"
178
+ "chart_id": "tribunal",
179
+ "purpose": "process_or_story",
180
+ "engine": "antv_infographic",
181
+ "title": ""
35
182
  },
36
183
  {
37
- "id": "evaluation",
38
- "title": "Evaluation and stopping",
39
- "component": "EvaluationFlow",
40
- "data_ref": "evaluation"
184
+ "chart_id": "intervention",
185
+ "purpose": "process_or_story",
186
+ "engine": "antv_infographic",
187
+ "title": ""
41
188
  },
42
189
  {
43
- "id": "sources",
44
- "title": "Verified primary sources",
45
- "component": "SourceList",
46
- "data_ref": "sources"
190
+ "chart_id": "evaluation",
191
+ "purpose": "process_or_story",
192
+ "engine": "antv_infographic",
193
+ "title": ""
194
+ }
195
+ ],
196
+ "academic_figures": [
197
+ {
198
+ "chart_id": "outcome-comparison",
199
+ "purpose": "statistical_publication",
200
+ "engine": "academic_figure",
201
+ "caption": "Fig. 1. Counts of positive / negative / null effects per outcome type (based on effect_direction; publication figure, theme-independent). Source: EduEvidence result.json."
47
202
  }
48
203
  ],
49
- "extensions": {
50
- "data_origin": "manual_curated",
51
- "domain": "policy",
52
- "benchmark_eligible": false,
53
- "render_status": "not_generated"
204
+ "integrity_gate": {
205
+ "status": "PASS",
206
+ "contract_valid": "PASS",
207
+ "claims_bound": "PASS",
208
+ "evidence_bound": 4,
209
+ "sources_resolved": 3,
210
+ "numbers_match_result": "PASS",
211
+ "bilingual_structure_match": "PASS",
212
+ "language_match": "PASS",
213
+ "no_false_precision": "PASS",
214
+ "lieflat_data_bound": "PASS",
215
+ "no_axis_distortion": "NOT_CHECKED",
216
+ "colorblind_safe": "NOT_CHECKED",
217
+ "langs": [
218
+ "zh",
219
+ "en"
220
+ ],
221
+ "generated_by": "build_report.py",
222
+ "source": "result.json + result.zh.json"
54
223
  }
55
- }
224
+ }