skilldrop-cli 0.16.36 → 0.16.38
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.
- package/README.md +1 -1
- package/catalogue.json +3 -1
- package/model-routing.json +8 -0
- package/package.json +1 -1
- package/packs/ai-engineering/skills/judge-audit/SKILL.md +157 -0
- package/packs/ai-engineering/skills/judge-audit/evals/eval_queries.json +11 -0
- package/packs/ai-engineering/skills/judge-audit/evals/evals.json +136 -0
- package/packs/ai-engineering/skills/judge-audit/evals/files/1/judgements.csv +321 -0
- package/packs/ai-engineering/skills/judge-audit/evals/files/1/notes.md +28 -0
- package/packs/ai-engineering/skills/judge-audit/evals/files/2/pairwise.csv +101 -0
- package/packs/ai-engineering/skills/judge-audit/evals/files/2/run-notes.md +16 -0
- package/packs/ai-engineering/skills/judge-audit/evals/files/4/grades.csv +97 -0
- package/packs/ai-engineering/skills/judge-audit/evals/files/5/pairwise_judgements.jsonl +120 -0
- package/packs/ai-engineering/skills/judge-audit/evals/files/6/rag-judge/README.md +36 -0
- package/packs/ai-engineering/skills/judge-audit/evals/files/6/rag-judge/judgments.csv +301 -0
- package/packs/ai-engineering/skills/judge-audit/evals/files/7/moderation/gold_labels.csv +101 -0
- package/packs/ai-engineering/skills/judge-audit/evals/files/7/moderation/run_1.jsonl +100 -0
- package/packs/ai-engineering/skills/judge-audit/evals/files/7/moderation/run_2.jsonl +100 -0
- package/packs/ai-engineering/skills/judge-audit/evals/files/8/patches.csv +241 -0
- package/packs/ai-engineering/skills/judge-audit/evals/files/9/adequacy_ratings.csv +151 -0
- package/packs/ai-engineering/skills/judge-audit/examples/summary-panel.md +70 -0
- package/packs/ai-engineering/skills/judge-audit/manifest.json +44 -0
- package/packs/ai-engineering/skills/judge-audit/reference.md +176 -0
- package/packs/ai-engineering/skills/judge-audit/scripts/judge_stats.py +1735 -0
- package/packs/frontend/pack.json +9 -3
- package/packs/frontend/skills/bundle-size-review/SKILL.md +114 -0
- package/packs/frontend/skills/bundle-size-review/evals/eval_queries.json +12 -0
- package/packs/frontend/skills/bundle-size-review/evals/evals.json +108 -0
- package/packs/frontend/skills/bundle-size-review/evals/files/1/package.json +28 -0
- package/packs/frontend/skills/bundle-size-review/evals/files/1/src/utils/format.js +26 -0
- package/packs/frontend/skills/bundle-size-review/evals/files/1/stats.json +1334 -0
- package/packs/frontend/skills/bundle-size-review/evals/files/2/PR.md +21 -0
- package/packs/frontend/skills/bundle-size-review/evals/files/2/meta-after.json +440 -0
- package/packs/frontend/skills/bundle-size-review/evals/files/2/meta-before.json +360 -0
- package/packs/frontend/skills/bundle-size-review/evals/files/3/package.json +29 -0
- package/packs/frontend/skills/bundle-size-review/evals/files/3/stats.json +1583 -0
- package/packs/frontend/skills/bundle-size-review/evals/files/4/src/components/CommentBox.jsx +24 -0
- package/packs/frontend/skills/bundle-size-review/evals/files/4/stats/after.json +299 -0
- package/packs/frontend/skills/bundle-size-review/evals/files/4/stats/before.json +275 -0
- package/packs/frontend/skills/bundle-size-review/evals/files/5/.browserslistrc +3 -0
- package/packs/frontend/skills/bundle-size-review/evals/files/5/build/meta.json +371 -0
- package/packs/frontend/skills/bundle-size-review/evals/files/5/build.mjs +18 -0
- package/packs/frontend/skills/bundle-size-review/evals/files/5/package-lock.json +39 -0
- package/packs/frontend/skills/bundle-size-review/evals/files/5/package.json +22 -0
- package/packs/frontend/skills/bundle-size-review/evals/files/5/src/components/Icon.jsx +8 -0
- package/packs/frontend/skills/bundle-size-review/evals/files/5/src/polyfills.js +7 -0
- package/packs/frontend/skills/bundle-size-review/evals/files/5/src/utils/groupRows.js +4 -0
- package/packs/frontend/skills/bundle-size-review/evals/files/6/.browserslistrc +3 -0
- package/packs/frontend/skills/bundle-size-review/evals/files/6/package.json +25 -0
- package/packs/frontend/skills/bundle-size-review/evals/files/6/src/App.tsx +8 -0
- package/packs/frontend/skills/bundle-size-review/evals/files/6/src/i18n/chartLocales.ts +16 -0
- package/packs/frontend/skills/bundle-size-review/evals/files/6/src/i18n/index.ts +8 -0
- package/packs/frontend/skills/bundle-size-review/evals/files/6/src/i18n/messages/de.ts +5 -0
- package/packs/frontend/skills/bundle-size-review/evals/files/6/src/i18n/messages/en.ts +5 -0
- package/packs/frontend/skills/bundle-size-review/evals/files/6/src/i18n/useLocale.ts +14 -0
- package/packs/frontend/skills/bundle-size-review/evals/files/6/src/main.tsx +10 -0
- package/packs/frontend/skills/bundle-size-review/evals/files/6/src/pages/Home.tsx +14 -0
- package/packs/frontend/skills/bundle-size-review/evals/files/6/src/pages/Reports.tsx +31 -0
- package/packs/frontend/skills/bundle-size-review/evals/files/6/src/routes.tsx +17 -0
- package/packs/frontend/skills/bundle-size-review/evals/files/6/stats.json +1869 -0
- package/packs/frontend/skills/bundle-size-review/evals/files/6/vite.config.ts +13 -0
- package/packs/frontend/skills/bundle-size-review/evals/files/7/apps/backoffice/package.json +26 -0
- package/packs/frontend/skills/bundle-size-review/evals/files/7/apps/backoffice/src/App.tsx +27 -0
- package/packs/frontend/skills/bundle-size-review/evals/files/7/apps/backoffice/src/pages/Analytics.tsx +10 -0
- package/packs/frontend/skills/bundle-size-review/evals/files/7/apps/backoffice/src/pages/Users.tsx +13 -0
- package/packs/frontend/skills/bundle-size-review/evals/files/7/apps/backoffice/stats.json +1421 -0
- package/packs/frontend/skills/bundle-size-review/evals/files/7/apps/backoffice/webpack.config.js +25 -0
- package/packs/frontend/skills/bundle-size-review/evals/files/7/apps/storefront/package.json +27 -0
- package/packs/frontend/skills/bundle-size-review/evals/files/7/apps/storefront/src/App.tsx +18 -0
- package/packs/frontend/skills/bundle-size-review/evals/files/7/apps/storefront/src/index.tsx +4 -0
- package/packs/frontend/skills/bundle-size-review/evals/files/7/apps/storefront/src/pages/Home.tsx +10 -0
- package/packs/frontend/skills/bundle-size-review/evals/files/7/apps/storefront/src/pages/Product.tsx +13 -0
- package/packs/frontend/skills/bundle-size-review/evals/files/7/apps/storefront/stats.json +1496 -0
- package/packs/frontend/skills/bundle-size-review/evals/files/7/apps/storefront/webpack.config.js +26 -0
- package/packs/frontend/skills/bundle-size-review/evals/files/7/package.json +9 -0
- package/packs/frontend/skills/bundle-size-review/evals/files/7/packages/ui/dist/Button.css +3 -0
- package/packs/frontend/skills/bundle-size-review/evals/files/7/packages/ui/dist/Button.js +14 -0
- package/packs/frontend/skills/bundle-size-review/evals/files/7/packages/ui/dist/Chart.js +21 -0
- package/packs/frontend/skills/bundle-size-review/evals/files/7/packages/ui/dist/index.js +22 -0
- package/packs/frontend/skills/bundle-size-review/evals/files/7/packages/ui/package.json +20 -0
- package/packs/frontend/skills/bundle-size-review/evals/files/7/packages/ui/src/Button.css +3 -0
- package/packs/frontend/skills/bundle-size-review/evals/files/7/packages/ui/src/Button.tsx +9 -0
- package/packs/frontend/skills/bundle-size-review/evals/files/7/packages/ui/src/Chart.tsx +14 -0
- package/packs/frontend/skills/bundle-size-review/evals/files/7/packages/ui/src/index.ts +6 -0
- package/packs/frontend/skills/bundle-size-review/evals/files/7/packages/ui/tsconfig.json +14 -0
- package/packs/frontend/skills/bundle-size-review/examples/inputs/stats-after.json +1358 -0
- package/packs/frontend/skills/bundle-size-review/examples/inputs/stats-before.json +1334 -0
- package/packs/frontend/skills/bundle-size-review/examples/larkspur-sparkline.md +52 -0
- package/packs/frontend/skills/bundle-size-review/manifest.json +52 -0
- package/packs/frontend/skills/bundle-size-review/reference.md +147 -0
- package/packs/frontend/skills/bundle-size-review/scripts/bundle_stats.py +1633 -0
- package/packs/frontend/skills/web-performance-review/SKILL.md +3 -3
- package/packs/frontend/skills/web-performance-review/manifest.json +2 -1
|
@@ -0,0 +1,120 @@
|
|
|
1
|
+
{"item_id": "q101", "judge": "orca-judge-large", "trial": 1, "first_shown": "A", "verdict": "tie"}
|
|
2
|
+
{"item_id": "q101", "judge": "orca-judge-large", "trial": 2, "first_shown": "A", "verdict": "A"}
|
|
3
|
+
{"item_id": "q101", "judge": "wren-judge-small", "trial": 1, "first_shown": "A", "verdict": "B"}
|
|
4
|
+
{"item_id": "q101", "judge": "wren-judge-small", "trial": 2, "first_shown": "A", "verdict": "A"}
|
|
5
|
+
{"item_id": "q102", "judge": "orca-judge-large", "trial": 1, "first_shown": "B", "verdict": "B"}
|
|
6
|
+
{"item_id": "q102", "judge": "orca-judge-large", "trial": 2, "first_shown": "B", "verdict": "B"}
|
|
7
|
+
{"item_id": "q102", "judge": "wren-judge-small", "trial": 1, "first_shown": "B", "verdict": "B"}
|
|
8
|
+
{"item_id": "q102", "judge": "wren-judge-small", "trial": 2, "first_shown": "B", "verdict": "B"}
|
|
9
|
+
{"item_id": "q103", "judge": "orca-judge-large", "trial": 1, "first_shown": "B", "verdict": "B"}
|
|
10
|
+
{"item_id": "q103", "judge": "orca-judge-large", "trial": 2, "first_shown": "B", "verdict": "B"}
|
|
11
|
+
{"item_id": "q103", "judge": "wren-judge-small", "trial": 1, "first_shown": "B", "verdict": "B"}
|
|
12
|
+
{"item_id": "q103", "judge": "wren-judge-small", "trial": 2, "first_shown": "B", "verdict": "A"}
|
|
13
|
+
{"item_id": "q104", "judge": "orca-judge-large", "trial": 1, "first_shown": "A", "verdict": "A"}
|
|
14
|
+
{"item_id": "q104", "judge": "orca-judge-large", "trial": 2, "first_shown": "A", "verdict": "A"}
|
|
15
|
+
{"item_id": "q104", "judge": "wren-judge-small", "trial": 1, "first_shown": "A", "verdict": "A"}
|
|
16
|
+
{"item_id": "q104", "judge": "wren-judge-small", "trial": 2, "first_shown": "A", "verdict": "A"}
|
|
17
|
+
{"item_id": "q105", "judge": "orca-judge-large", "trial": 1, "first_shown": "B", "verdict": "B"}
|
|
18
|
+
{"item_id": "q105", "judge": "orca-judge-large", "trial": 2, "first_shown": "B", "verdict": "B"}
|
|
19
|
+
{"item_id": "q105", "judge": "wren-judge-small", "trial": 1, "first_shown": "B", "verdict": "B"}
|
|
20
|
+
{"item_id": "q105", "judge": "wren-judge-small", "trial": 2, "first_shown": "B", "verdict": "B"}
|
|
21
|
+
{"item_id": "q106", "judge": "orca-judge-large", "trial": 1, "first_shown": "B", "verdict": "B"}
|
|
22
|
+
{"item_id": "q106", "judge": "orca-judge-large", "trial": 2, "first_shown": "B", "verdict": "B"}
|
|
23
|
+
{"item_id": "q106", "judge": "wren-judge-small", "trial": 1, "first_shown": "B", "verdict": "tie"}
|
|
24
|
+
{"item_id": "q106", "judge": "wren-judge-small", "trial": 2, "first_shown": "B", "verdict": "tie"}
|
|
25
|
+
{"item_id": "q107", "judge": "orca-judge-large", "trial": 1, "first_shown": "B", "verdict": "B"}
|
|
26
|
+
{"item_id": "q107", "judge": "orca-judge-large", "trial": 2, "first_shown": "B", "verdict": "B"}
|
|
27
|
+
{"item_id": "q107", "judge": "wren-judge-small", "trial": 1, "first_shown": "B", "verdict": "B"}
|
|
28
|
+
{"item_id": "q107", "judge": "wren-judge-small", "trial": 2, "first_shown": "B", "verdict": "B"}
|
|
29
|
+
{"item_id": "q108", "judge": "orca-judge-large", "trial": 1, "first_shown": "B", "verdict": "B"}
|
|
30
|
+
{"item_id": "q108", "judge": "orca-judge-large", "trial": 2, "first_shown": "B", "verdict": "B"}
|
|
31
|
+
{"item_id": "q108", "judge": "wren-judge-small", "trial": 1, "first_shown": "B", "verdict": "B"}
|
|
32
|
+
{"item_id": "q108", "judge": "wren-judge-small", "trial": 2, "first_shown": "B", "verdict": "B"}
|
|
33
|
+
{"item_id": "q109", "judge": "orca-judge-large", "trial": 1, "first_shown": "B", "verdict": "B"}
|
|
34
|
+
{"item_id": "q109", "judge": "orca-judge-large", "trial": 2, "first_shown": "B", "verdict": "A"}
|
|
35
|
+
{"item_id": "q109", "judge": "wren-judge-small", "trial": 1, "first_shown": "B", "verdict": "B"}
|
|
36
|
+
{"item_id": "q109", "judge": "wren-judge-small", "trial": 2, "first_shown": "B", "verdict": "A"}
|
|
37
|
+
{"item_id": "q110", "judge": "orca-judge-large", "trial": 1, "first_shown": "B", "verdict": "B"}
|
|
38
|
+
{"item_id": "q110", "judge": "orca-judge-large", "trial": 2, "first_shown": "B", "verdict": "B"}
|
|
39
|
+
{"item_id": "q110", "judge": "wren-judge-small", "trial": 1, "first_shown": "B", "verdict": "B"}
|
|
40
|
+
{"item_id": "q110", "judge": "wren-judge-small", "trial": 2, "first_shown": "B", "verdict": "B"}
|
|
41
|
+
{"item_id": "q111", "judge": "orca-judge-large", "trial": 1, "first_shown": "A", "verdict": "A"}
|
|
42
|
+
{"item_id": "q111", "judge": "orca-judge-large", "trial": 2, "first_shown": "A", "verdict": "B"}
|
|
43
|
+
{"item_id": "q111", "judge": "wren-judge-small", "trial": 1, "first_shown": "A", "verdict": "A"}
|
|
44
|
+
{"item_id": "q111", "judge": "wren-judge-small", "trial": 2, "first_shown": "A", "verdict": "A"}
|
|
45
|
+
{"item_id": "q112", "judge": "orca-judge-large", "trial": 1, "first_shown": "B", "verdict": "B"}
|
|
46
|
+
{"item_id": "q112", "judge": "orca-judge-large", "trial": 2, "first_shown": "B", "verdict": "B"}
|
|
47
|
+
{"item_id": "q112", "judge": "wren-judge-small", "trial": 1, "first_shown": "B", "verdict": "B"}
|
|
48
|
+
{"item_id": "q112", "judge": "wren-judge-small", "trial": 2, "first_shown": "B", "verdict": "B"}
|
|
49
|
+
{"item_id": "q113", "judge": "orca-judge-large", "trial": 1, "first_shown": "B", "verdict": "B"}
|
|
50
|
+
{"item_id": "q113", "judge": "orca-judge-large", "trial": 2, "first_shown": "B", "verdict": "A"}
|
|
51
|
+
{"item_id": "q113", "judge": "wren-judge-small", "trial": 1, "first_shown": "B", "verdict": "B"}
|
|
52
|
+
{"item_id": "q113", "judge": "wren-judge-small", "trial": 2, "first_shown": "B", "verdict": "B"}
|
|
53
|
+
{"item_id": "q114", "judge": "orca-judge-large", "trial": 1, "first_shown": "B", "verdict": "B"}
|
|
54
|
+
{"item_id": "q114", "judge": "orca-judge-large", "trial": 2, "first_shown": "B", "verdict": "B"}
|
|
55
|
+
{"item_id": "q114", "judge": "wren-judge-small", "trial": 1, "first_shown": "B", "verdict": "B"}
|
|
56
|
+
{"item_id": "q114", "judge": "wren-judge-small", "trial": 2, "first_shown": "B", "verdict": "A"}
|
|
57
|
+
{"item_id": "q115", "judge": "orca-judge-large", "trial": 1, "first_shown": "A", "verdict": "A"}
|
|
58
|
+
{"item_id": "q115", "judge": "orca-judge-large", "trial": 2, "first_shown": "A", "verdict": "A"}
|
|
59
|
+
{"item_id": "q115", "judge": "wren-judge-small", "trial": 1, "first_shown": "A", "verdict": "B"}
|
|
60
|
+
{"item_id": "q115", "judge": "wren-judge-small", "trial": 2, "first_shown": "A", "verdict": "A"}
|
|
61
|
+
{"item_id": "q116", "judge": "orca-judge-large", "trial": 1, "first_shown": "B", "verdict": "B"}
|
|
62
|
+
{"item_id": "q116", "judge": "orca-judge-large", "trial": 2, "first_shown": "B", "verdict": "B"}
|
|
63
|
+
{"item_id": "q116", "judge": "wren-judge-small", "trial": 1, "first_shown": "B", "verdict": "B"}
|
|
64
|
+
{"item_id": "q116", "judge": "wren-judge-small", "trial": 2, "first_shown": "B", "verdict": "B"}
|
|
65
|
+
{"item_id": "q117", "judge": "orca-judge-large", "trial": 1, "first_shown": "B", "verdict": "A"}
|
|
66
|
+
{"item_id": "q117", "judge": "orca-judge-large", "trial": 2, "first_shown": "B", "verdict": "B"}
|
|
67
|
+
{"item_id": "q117", "judge": "wren-judge-small", "trial": 1, "first_shown": "B", "verdict": "A"}
|
|
68
|
+
{"item_id": "q117", "judge": "wren-judge-small", "trial": 2, "first_shown": "B", "verdict": "B"}
|
|
69
|
+
{"item_id": "q118", "judge": "orca-judge-large", "trial": 1, "first_shown": "B", "verdict": "B"}
|
|
70
|
+
{"item_id": "q118", "judge": "orca-judge-large", "trial": 2, "first_shown": "B", "verdict": "B"}
|
|
71
|
+
{"item_id": "q118", "judge": "wren-judge-small", "trial": 1, "first_shown": "B", "verdict": "B"}
|
|
72
|
+
{"item_id": "q118", "judge": "wren-judge-small", "trial": 2, "first_shown": "B", "verdict": "B"}
|
|
73
|
+
{"item_id": "q119", "judge": "orca-judge-large", "trial": 1, "first_shown": "A", "verdict": "A"}
|
|
74
|
+
{"item_id": "q119", "judge": "orca-judge-large", "trial": 2, "first_shown": "A", "verdict": "A"}
|
|
75
|
+
{"item_id": "q119", "judge": "wren-judge-small", "trial": 1, "first_shown": "A", "verdict": "A"}
|
|
76
|
+
{"item_id": "q119", "judge": "wren-judge-small", "trial": 2, "first_shown": "A", "verdict": "A"}
|
|
77
|
+
{"item_id": "q120", "judge": "orca-judge-large", "trial": 1, "first_shown": "A", "verdict": "A"}
|
|
78
|
+
{"item_id": "q120", "judge": "orca-judge-large", "trial": 2, "first_shown": "A", "verdict": "A"}
|
|
79
|
+
{"item_id": "q120", "judge": "wren-judge-small", "trial": 1, "first_shown": "A", "verdict": "A"}
|
|
80
|
+
{"item_id": "q120", "judge": "wren-judge-small", "trial": 2, "first_shown": "A", "verdict": "tie"}
|
|
81
|
+
{"item_id": "q121", "judge": "orca-judge-large", "trial": 1, "first_shown": "B", "verdict": "A"}
|
|
82
|
+
{"item_id": "q121", "judge": "orca-judge-large", "trial": 2, "first_shown": "B", "verdict": "A"}
|
|
83
|
+
{"item_id": "q121", "judge": "wren-judge-small", "trial": 1, "first_shown": "B", "verdict": "A"}
|
|
84
|
+
{"item_id": "q121", "judge": "wren-judge-small", "trial": 2, "first_shown": "B", "verdict": "tie"}
|
|
85
|
+
{"item_id": "q122", "judge": "orca-judge-large", "trial": 1, "first_shown": "B", "verdict": "B"}
|
|
86
|
+
{"item_id": "q122", "judge": "orca-judge-large", "trial": 2, "first_shown": "B", "verdict": "B"}
|
|
87
|
+
{"item_id": "q122", "judge": "wren-judge-small", "trial": 1, "first_shown": "B", "verdict": "A"}
|
|
88
|
+
{"item_id": "q122", "judge": "wren-judge-small", "trial": 2, "first_shown": "B", "verdict": "B"}
|
|
89
|
+
{"item_id": "q123", "judge": "orca-judge-large", "trial": 1, "first_shown": "B", "verdict": "B"}
|
|
90
|
+
{"item_id": "q123", "judge": "orca-judge-large", "trial": 2, "first_shown": "B", "verdict": "B"}
|
|
91
|
+
{"item_id": "q123", "judge": "wren-judge-small", "trial": 1, "first_shown": "B", "verdict": "B"}
|
|
92
|
+
{"item_id": "q123", "judge": "wren-judge-small", "trial": 2, "first_shown": "B", "verdict": "B"}
|
|
93
|
+
{"item_id": "q124", "judge": "orca-judge-large", "trial": 1, "first_shown": "B", "verdict": "B"}
|
|
94
|
+
{"item_id": "q124", "judge": "orca-judge-large", "trial": 2, "first_shown": "B", "verdict": "tie"}
|
|
95
|
+
{"item_id": "q124", "judge": "wren-judge-small", "trial": 1, "first_shown": "B", "verdict": "A"}
|
|
96
|
+
{"item_id": "q124", "judge": "wren-judge-small", "trial": 2, "first_shown": "B", "verdict": "A"}
|
|
97
|
+
{"item_id": "q125", "judge": "orca-judge-large", "trial": 1, "first_shown": "A", "verdict": "B"}
|
|
98
|
+
{"item_id": "q125", "judge": "orca-judge-large", "trial": 2, "first_shown": "A", "verdict": "A"}
|
|
99
|
+
{"item_id": "q125", "judge": "wren-judge-small", "trial": 1, "first_shown": "A", "verdict": "A"}
|
|
100
|
+
{"item_id": "q125", "judge": "wren-judge-small", "trial": 2, "first_shown": "A", "verdict": "tie"}
|
|
101
|
+
{"item_id": "q126", "judge": "orca-judge-large", "trial": 1, "first_shown": "B", "verdict": "B"}
|
|
102
|
+
{"item_id": "q126", "judge": "orca-judge-large", "trial": 2, "first_shown": "B", "verdict": "B"}
|
|
103
|
+
{"item_id": "q126", "judge": "wren-judge-small", "trial": 1, "first_shown": "B", "verdict": "B"}
|
|
104
|
+
{"item_id": "q126", "judge": "wren-judge-small", "trial": 2, "first_shown": "B", "verdict": "B"}
|
|
105
|
+
{"item_id": "q127", "judge": "orca-judge-large", "trial": 1, "first_shown": "B", "verdict": "B"}
|
|
106
|
+
{"item_id": "q127", "judge": "orca-judge-large", "trial": 2, "first_shown": "B", "verdict": "B"}
|
|
107
|
+
{"item_id": "q127", "judge": "wren-judge-small", "trial": 1, "first_shown": "B", "verdict": "A"}
|
|
108
|
+
{"item_id": "q127", "judge": "wren-judge-small", "trial": 2, "first_shown": "B", "verdict": "A"}
|
|
109
|
+
{"item_id": "q128", "judge": "orca-judge-large", "trial": 1, "first_shown": "B", "verdict": "B"}
|
|
110
|
+
{"item_id": "q128", "judge": "orca-judge-large", "trial": 2, "first_shown": "B", "verdict": "B"}
|
|
111
|
+
{"item_id": "q128", "judge": "wren-judge-small", "trial": 1, "first_shown": "B", "verdict": "A"}
|
|
112
|
+
{"item_id": "q128", "judge": "wren-judge-small", "trial": 2, "first_shown": "B", "verdict": "A"}
|
|
113
|
+
{"item_id": "q129", "judge": "orca-judge-large", "trial": 1, "first_shown": "A", "verdict": "A"}
|
|
114
|
+
{"item_id": "q129", "judge": "orca-judge-large", "trial": 2, "first_shown": "A", "verdict": "B"}
|
|
115
|
+
{"item_id": "q129", "judge": "wren-judge-small", "trial": 1, "first_shown": "A", "verdict": "B"}
|
|
116
|
+
{"item_id": "q129", "judge": "wren-judge-small", "trial": 2, "first_shown": "A", "verdict": "A"}
|
|
117
|
+
{"item_id": "q130", "judge": "orca-judge-large", "trial": 1, "first_shown": "B", "verdict": "B"}
|
|
118
|
+
{"item_id": "q130", "judge": "orca-judge-large", "trial": 2, "first_shown": "B", "verdict": "B"}
|
|
119
|
+
{"item_id": "q130", "judge": "wren-judge-small", "trial": 1, "first_shown": "B", "verdict": "B"}
|
|
120
|
+
{"item_id": "q130", "judge": "wren-judge-small", "trial": 2, "first_shown": "B", "verdict": "B"}
|
|
@@ -0,0 +1,36 @@
|
|
|
1
|
+
# Relevance judge bake-off — Wayfinder search (Kestrel Docs)
|
|
2
|
+
|
|
3
|
+
## What the judge is for
|
|
4
|
+
|
|
5
|
+
Our nightly retrieval eval asks an LLM judge whether each retrieved passage is `relevant` or
|
|
6
|
+
`irrelevant` to its query. From those labels we compute precision@5 per retriever build.
|
|
7
|
+
|
|
8
|
+
**The gate:** a retriever change ships only if its precision@5 is no more than 1.0 point below
|
|
9
|
+
the current production retriever's. So the judge's labels directly decide what ships.
|
|
10
|
+
|
|
11
|
+
## Volume and price
|
|
12
|
+
|
|
13
|
+
- Nightly run: ~20,000 query–passage judgments.
|
|
14
|
+
- Price per 1,000 judgments (from the vendor's October price sheet):
|
|
15
|
+
|
|
16
|
+
| Judge | $ / 1k judgments |
|
|
17
|
+
|-------------|------------------|
|
|
18
|
+
| atlas-xl | 4.80 |
|
|
19
|
+
| atlas-m | 1.10 |
|
|
20
|
+
| atlas-nano | 0.18 |
|
|
21
|
+
|
|
22
|
+
atlas-xl is the current production judge.
|
|
23
|
+
|
|
24
|
+
## This bake-off (`judgments.csv`)
|
|
25
|
+
|
|
26
|
+
- 300 query–passage pairs: 30 queries (`q01`–`q30`) x their top-10 retrieved passages.
|
|
27
|
+
- Each of the three judges labelled every pair once, same prompt, temperature 0.
|
|
28
|
+
- `passage_tokens` is the passage length. The index currently mixes legacy ~900-token chunks
|
|
29
|
+
with newer short chunks (under ~400 tokens).
|
|
30
|
+
- `expert_label`: Priya Halvorsen (search lead) hand-labelled 60 pairs drawn uniformly at random
|
|
31
|
+
from the 300. Blank means not expert-labelled. She was the only annotator.
|
|
32
|
+
|
|
33
|
+
## What's next
|
|
34
|
+
|
|
35
|
+
Q1 experiment: re-chunk the whole index to large chunks (~900 tokens) and compare the new
|
|
36
|
+
retriever against production through this same gate.
|
|
@@ -0,0 +1,301 @@
|
|
|
1
|
+
passage_id,query_id,passage_tokens,atlas_xl,atlas_m,atlas_nano,expert_label
|
|
2
|
+
p001,q01,247,relevant,relevant,relevant,
|
|
3
|
+
p002,q01,214,relevant,relevant,relevant,
|
|
4
|
+
p003,q01,717,relevant,relevant,relevant,
|
|
5
|
+
p004,q01,145,relevant,relevant,relevant,relevant
|
|
6
|
+
p005,q01,330,relevant,relevant,relevant,
|
|
7
|
+
p006,q01,156,relevant,relevant,relevant,
|
|
8
|
+
p007,q01,721,irrelevant,irrelevant,relevant,
|
|
9
|
+
p008,q01,164,relevant,relevant,relevant,
|
|
10
|
+
p009,q01,335,irrelevant,irrelevant,relevant,
|
|
11
|
+
p010,q01,455,relevant,relevant,relevant,
|
|
12
|
+
p011,q02,109,irrelevant,irrelevant,relevant,
|
|
13
|
+
p012,q02,795,irrelevant,relevant,relevant,
|
|
14
|
+
p013,q02,128,relevant,relevant,relevant,
|
|
15
|
+
p014,q02,265,relevant,irrelevant,relevant,
|
|
16
|
+
p015,q02,958,relevant,relevant,relevant,
|
|
17
|
+
p016,q02,801,relevant,relevant,relevant,
|
|
18
|
+
p017,q02,459,irrelevant,irrelevant,relevant,irrelevant
|
|
19
|
+
p018,q02,346,relevant,relevant,relevant,
|
|
20
|
+
p019,q02,339,relevant,relevant,relevant,
|
|
21
|
+
p020,q02,239,relevant,irrelevant,relevant,relevant
|
|
22
|
+
p021,q03,266,relevant,relevant,relevant,
|
|
23
|
+
p022,q03,164,relevant,relevant,relevant,
|
|
24
|
+
p023,q03,804,irrelevant,irrelevant,relevant,
|
|
25
|
+
p024,q03,180,relevant,relevant,relevant,relevant
|
|
26
|
+
p025,q03,366,relevant,relevant,relevant,
|
|
27
|
+
p026,q03,964,irrelevant,irrelevant,relevant,irrelevant
|
|
28
|
+
p027,q03,528,irrelevant,irrelevant,relevant,
|
|
29
|
+
p028,q03,917,relevant,relevant,relevant,
|
|
30
|
+
p029,q03,154,irrelevant,relevant,relevant,
|
|
31
|
+
p030,q03,610,relevant,relevant,relevant,
|
|
32
|
+
p031,q04,918,relevant,relevant,relevant,
|
|
33
|
+
p032,q04,127,relevant,relevant,relevant,relevant
|
|
34
|
+
p033,q04,922,irrelevant,irrelevant,relevant,
|
|
35
|
+
p034,q04,972,irrelevant,relevant,relevant,relevant
|
|
36
|
+
p035,q04,498,relevant,relevant,relevant,
|
|
37
|
+
p036,q04,692,relevant,relevant,relevant,
|
|
38
|
+
p037,q04,258,relevant,relevant,relevant,
|
|
39
|
+
p038,q04,528,relevant,relevant,relevant,
|
|
40
|
+
p039,q04,886,relevant,relevant,relevant,
|
|
41
|
+
p040,q04,174,relevant,relevant,relevant,
|
|
42
|
+
p041,q05,583,relevant,relevant,relevant,
|
|
43
|
+
p042,q05,258,relevant,relevant,relevant,relevant
|
|
44
|
+
p043,q05,437,irrelevant,relevant,relevant,
|
|
45
|
+
p044,q05,469,relevant,relevant,relevant,
|
|
46
|
+
p045,q05,920,relevant,relevant,relevant,
|
|
47
|
+
p046,q05,500,irrelevant,irrelevant,relevant,
|
|
48
|
+
p047,q05,449,relevant,relevant,relevant,relevant
|
|
49
|
+
p048,q05,243,relevant,relevant,relevant,relevant
|
|
50
|
+
p049,q05,668,relevant,relevant,relevant,relevant
|
|
51
|
+
p050,q05,508,relevant,relevant,relevant,
|
|
52
|
+
p051,q06,705,irrelevant,irrelevant,relevant,
|
|
53
|
+
p052,q06,143,relevant,relevant,relevant,
|
|
54
|
+
p053,q06,320,irrelevant,relevant,relevant,
|
|
55
|
+
p054,q06,276,relevant,irrelevant,irrelevant,
|
|
56
|
+
p055,q06,280,irrelevant,relevant,irrelevant,
|
|
57
|
+
p056,q06,969,irrelevant,irrelevant,relevant,
|
|
58
|
+
p057,q06,187,relevant,irrelevant,relevant,
|
|
59
|
+
p058,q06,219,relevant,relevant,relevant,
|
|
60
|
+
p059,q06,915,relevant,relevant,relevant,relevant
|
|
61
|
+
p060,q06,349,relevant,relevant,relevant,
|
|
62
|
+
p061,q07,100,relevant,relevant,relevant,
|
|
63
|
+
p062,q07,525,relevant,relevant,relevant,
|
|
64
|
+
p063,q07,302,irrelevant,relevant,relevant,
|
|
65
|
+
p064,q07,191,relevant,relevant,relevant,
|
|
66
|
+
p065,q07,222,relevant,relevant,relevant,
|
|
67
|
+
p066,q07,691,irrelevant,irrelevant,relevant,
|
|
68
|
+
p067,q07,569,irrelevant,irrelevant,relevant,irrelevant
|
|
69
|
+
p068,q07,593,relevant,relevant,relevant,
|
|
70
|
+
p069,q07,781,irrelevant,relevant,relevant,
|
|
71
|
+
p070,q07,236,relevant,relevant,relevant,
|
|
72
|
+
p071,q08,787,irrelevant,irrelevant,relevant,irrelevant
|
|
73
|
+
p072,q08,893,irrelevant,irrelevant,relevant,
|
|
74
|
+
p073,q08,784,irrelevant,relevant,irrelevant,
|
|
75
|
+
p074,q08,128,relevant,relevant,relevant,
|
|
76
|
+
p075,q08,753,relevant,relevant,relevant,
|
|
77
|
+
p076,q08,247,relevant,relevant,relevant,relevant
|
|
78
|
+
p077,q08,466,irrelevant,irrelevant,relevant,
|
|
79
|
+
p078,q08,147,relevant,irrelevant,relevant,
|
|
80
|
+
p079,q08,671,irrelevant,irrelevant,relevant,irrelevant
|
|
81
|
+
p080,q08,291,irrelevant,irrelevant,irrelevant,
|
|
82
|
+
p081,q09,557,relevant,relevant,relevant,relevant
|
|
83
|
+
p082,q09,839,relevant,relevant,relevant,relevant
|
|
84
|
+
p083,q09,130,relevant,relevant,relevant,
|
|
85
|
+
p084,q09,359,irrelevant,relevant,irrelevant,
|
|
86
|
+
p085,q09,157,relevant,irrelevant,relevant,
|
|
87
|
+
p086,q09,614,relevant,relevant,relevant,
|
|
88
|
+
p087,q09,299,relevant,relevant,relevant,
|
|
89
|
+
p088,q09,149,irrelevant,irrelevant,irrelevant,irrelevant
|
|
90
|
+
p089,q09,256,irrelevant,irrelevant,irrelevant,
|
|
91
|
+
p090,q09,230,relevant,relevant,relevant,
|
|
92
|
+
p091,q10,336,relevant,relevant,relevant,
|
|
93
|
+
p092,q10,655,relevant,relevant,relevant,
|
|
94
|
+
p093,q10,275,relevant,irrelevant,relevant,relevant
|
|
95
|
+
p094,q10,179,relevant,relevant,relevant,
|
|
96
|
+
p095,q10,228,relevant,irrelevant,relevant,
|
|
97
|
+
p096,q10,194,relevant,relevant,relevant,
|
|
98
|
+
p097,q10,483,relevant,relevant,relevant,
|
|
99
|
+
p098,q10,686,relevant,relevant,relevant,relevant
|
|
100
|
+
p099,q10,160,relevant,relevant,relevant,relevant
|
|
101
|
+
p100,q10,315,relevant,relevant,relevant,
|
|
102
|
+
p101,q11,717,irrelevant,irrelevant,relevant,
|
|
103
|
+
p102,q11,522,relevant,relevant,irrelevant,
|
|
104
|
+
p103,q11,436,relevant,relevant,relevant,
|
|
105
|
+
p104,q11,358,relevant,relevant,relevant,
|
|
106
|
+
p105,q11,372,irrelevant,irrelevant,irrelevant,irrelevant
|
|
107
|
+
p106,q11,262,irrelevant,irrelevant,relevant,relevant
|
|
108
|
+
p107,q11,891,irrelevant,irrelevant,irrelevant,
|
|
109
|
+
p108,q11,123,relevant,relevant,relevant,relevant
|
|
110
|
+
p109,q11,742,relevant,relevant,relevant,relevant
|
|
111
|
+
p110,q11,317,relevant,irrelevant,relevant,irrelevant
|
|
112
|
+
p111,q12,738,relevant,relevant,relevant,relevant
|
|
113
|
+
p112,q12,172,irrelevant,irrelevant,relevant,
|
|
114
|
+
p113,q12,739,relevant,relevant,relevant,
|
|
115
|
+
p114,q12,674,irrelevant,irrelevant,irrelevant,irrelevant
|
|
116
|
+
p115,q12,330,irrelevant,irrelevant,relevant,
|
|
117
|
+
p116,q12,704,irrelevant,irrelevant,relevant,
|
|
118
|
+
p117,q12,438,relevant,relevant,relevant,
|
|
119
|
+
p118,q12,912,irrelevant,irrelevant,relevant,
|
|
120
|
+
p119,q12,280,irrelevant,irrelevant,irrelevant,
|
|
121
|
+
p120,q12,781,relevant,irrelevant,irrelevant,
|
|
122
|
+
p121,q13,539,relevant,relevant,relevant,
|
|
123
|
+
p122,q13,252,irrelevant,irrelevant,irrelevant,
|
|
124
|
+
p123,q13,264,relevant,relevant,relevant,
|
|
125
|
+
p124,q13,973,relevant,relevant,relevant,
|
|
126
|
+
p125,q13,755,relevant,irrelevant,relevant,
|
|
127
|
+
p126,q13,540,relevant,relevant,relevant,
|
|
128
|
+
p127,q13,359,irrelevant,relevant,irrelevant,irrelevant
|
|
129
|
+
p128,q13,186,relevant,relevant,relevant,
|
|
130
|
+
p129,q13,599,relevant,relevant,relevant,
|
|
131
|
+
p130,q13,626,relevant,irrelevant,relevant,
|
|
132
|
+
p131,q14,543,relevant,relevant,irrelevant,
|
|
133
|
+
p132,q14,320,relevant,relevant,relevant,
|
|
134
|
+
p133,q14,272,irrelevant,relevant,relevant,
|
|
135
|
+
p134,q14,857,relevant,relevant,relevant,
|
|
136
|
+
p135,q14,150,relevant,relevant,relevant,
|
|
137
|
+
p136,q14,189,relevant,relevant,relevant,
|
|
138
|
+
p137,q14,141,relevant,relevant,relevant,
|
|
139
|
+
p138,q14,154,irrelevant,irrelevant,irrelevant,irrelevant
|
|
140
|
+
p139,q14,109,irrelevant,relevant,relevant,
|
|
141
|
+
p140,q14,372,relevant,relevant,relevant,
|
|
142
|
+
p141,q15,269,relevant,relevant,relevant,relevant
|
|
143
|
+
p142,q15,607,relevant,relevant,relevant,
|
|
144
|
+
p143,q15,729,relevant,relevant,relevant,
|
|
145
|
+
p144,q15,100,relevant,relevant,irrelevant,
|
|
146
|
+
p145,q15,160,relevant,relevant,relevant,
|
|
147
|
+
p146,q15,149,relevant,relevant,relevant,
|
|
148
|
+
p147,q15,171,relevant,relevant,relevant,
|
|
149
|
+
p148,q15,574,relevant,relevant,relevant,
|
|
150
|
+
p149,q15,314,relevant,irrelevant,relevant,
|
|
151
|
+
p150,q15,271,relevant,relevant,relevant,
|
|
152
|
+
p151,q16,108,relevant,relevant,relevant,
|
|
153
|
+
p152,q16,183,relevant,relevant,relevant,
|
|
154
|
+
p153,q16,115,irrelevant,irrelevant,irrelevant,
|
|
155
|
+
p154,q16,106,relevant,relevant,relevant,
|
|
156
|
+
p155,q16,179,relevant,irrelevant,relevant,
|
|
157
|
+
p156,q16,473,relevant,relevant,relevant,
|
|
158
|
+
p157,q16,320,relevant,relevant,relevant,
|
|
159
|
+
p158,q16,357,relevant,relevant,relevant,
|
|
160
|
+
p159,q16,747,relevant,irrelevant,relevant,
|
|
161
|
+
p160,q16,368,relevant,relevant,relevant,relevant
|
|
162
|
+
p161,q17,561,irrelevant,irrelevant,relevant,irrelevant
|
|
163
|
+
p162,q17,216,relevant,relevant,relevant,
|
|
164
|
+
p163,q17,719,relevant,relevant,relevant,
|
|
165
|
+
p164,q17,512,relevant,relevant,relevant,irrelevant
|
|
166
|
+
p165,q17,773,relevant,relevant,relevant,relevant
|
|
167
|
+
p166,q17,362,relevant,relevant,relevant,relevant
|
|
168
|
+
p167,q17,739,relevant,relevant,relevant,
|
|
169
|
+
p168,q17,960,irrelevant,irrelevant,relevant,
|
|
170
|
+
p169,q17,253,relevant,relevant,relevant,
|
|
171
|
+
p170,q17,220,relevant,relevant,relevant,
|
|
172
|
+
p171,q18,352,relevant,relevant,relevant,
|
|
173
|
+
p172,q18,219,irrelevant,irrelevant,irrelevant,
|
|
174
|
+
p173,q18,131,relevant,relevant,relevant,
|
|
175
|
+
p174,q18,338,relevant,relevant,relevant,
|
|
176
|
+
p175,q18,94,relevant,relevant,relevant,
|
|
177
|
+
p176,q18,659,irrelevant,irrelevant,relevant,
|
|
178
|
+
p177,q18,719,relevant,relevant,relevant,
|
|
179
|
+
p178,q18,245,relevant,relevant,relevant,
|
|
180
|
+
p179,q18,215,relevant,irrelevant,relevant,
|
|
181
|
+
p180,q18,531,relevant,relevant,relevant,
|
|
182
|
+
p181,q19,351,relevant,irrelevant,relevant,
|
|
183
|
+
p182,q19,723,relevant,relevant,relevant,
|
|
184
|
+
p183,q19,298,irrelevant,relevant,irrelevant,
|
|
185
|
+
p184,q19,455,relevant,relevant,relevant,
|
|
186
|
+
p185,q19,205,irrelevant,irrelevant,irrelevant,
|
|
187
|
+
p186,q19,243,relevant,irrelevant,irrelevant,
|
|
188
|
+
p187,q19,254,relevant,relevant,relevant,
|
|
189
|
+
p188,q19,366,relevant,relevant,relevant,relevant
|
|
190
|
+
p189,q19,914,relevant,irrelevant,relevant,
|
|
191
|
+
p190,q19,749,relevant,relevant,relevant,
|
|
192
|
+
p191,q20,813,relevant,relevant,relevant,
|
|
193
|
+
p192,q20,312,relevant,irrelevant,relevant,
|
|
194
|
+
p193,q20,501,irrelevant,irrelevant,relevant,
|
|
195
|
+
p194,q20,324,irrelevant,irrelevant,irrelevant,
|
|
196
|
+
p195,q20,220,relevant,relevant,relevant,
|
|
197
|
+
p196,q20,852,relevant,relevant,relevant,
|
|
198
|
+
p197,q20,767,irrelevant,relevant,relevant,
|
|
199
|
+
p198,q20,715,relevant,relevant,relevant,
|
|
200
|
+
p199,q20,452,relevant,relevant,relevant,
|
|
201
|
+
p200,q20,615,relevant,relevant,relevant,
|
|
202
|
+
p201,q21,281,irrelevant,relevant,irrelevant,
|
|
203
|
+
p202,q21,252,relevant,relevant,relevant,relevant
|
|
204
|
+
p203,q21,172,relevant,relevant,relevant,
|
|
205
|
+
p204,q21,272,relevant,relevant,relevant,relevant
|
|
206
|
+
p205,q21,941,irrelevant,irrelevant,relevant,irrelevant
|
|
207
|
+
p206,q21,173,relevant,relevant,relevant,relevant
|
|
208
|
+
p207,q21,962,relevant,relevant,relevant,
|
|
209
|
+
p208,q21,101,relevant,irrelevant,relevant,
|
|
210
|
+
p209,q21,269,relevant,relevant,irrelevant,relevant
|
|
211
|
+
p210,q21,594,relevant,relevant,relevant,
|
|
212
|
+
p211,q22,594,relevant,relevant,relevant,
|
|
213
|
+
p212,q22,105,relevant,relevant,relevant,
|
|
214
|
+
p213,q22,160,irrelevant,irrelevant,relevant,
|
|
215
|
+
p214,q22,104,irrelevant,irrelevant,irrelevant,
|
|
216
|
+
p215,q22,183,relevant,relevant,relevant,
|
|
217
|
+
p216,q22,177,irrelevant,irrelevant,irrelevant,
|
|
218
|
+
p217,q22,289,relevant,relevant,irrelevant,
|
|
219
|
+
p218,q22,292,relevant,relevant,relevant,
|
|
220
|
+
p219,q22,809,irrelevant,relevant,relevant,irrelevant
|
|
221
|
+
p220,q22,349,irrelevant,irrelevant,irrelevant,
|
|
222
|
+
p221,q23,95,relevant,relevant,relevant,
|
|
223
|
+
p222,q23,169,relevant,relevant,relevant,
|
|
224
|
+
p223,q23,180,irrelevant,irrelevant,irrelevant,
|
|
225
|
+
p224,q23,128,relevant,relevant,relevant,
|
|
226
|
+
p225,q23,283,relevant,relevant,relevant,
|
|
227
|
+
p226,q23,360,relevant,relevant,relevant,
|
|
228
|
+
p227,q23,347,irrelevant,irrelevant,irrelevant,
|
|
229
|
+
p228,q23,279,relevant,relevant,relevant,relevant
|
|
230
|
+
p229,q23,192,irrelevant,relevant,irrelevant,
|
|
231
|
+
p230,q23,361,relevant,relevant,relevant,
|
|
232
|
+
p231,q24,339,relevant,relevant,relevant,
|
|
233
|
+
p232,q24,372,relevant,relevant,relevant,
|
|
234
|
+
p233,q24,362,irrelevant,irrelevant,irrelevant,
|
|
235
|
+
p234,q24,762,irrelevant,irrelevant,relevant,
|
|
236
|
+
p235,q24,588,relevant,relevant,relevant,relevant
|
|
237
|
+
p236,q24,796,relevant,relevant,relevant,relevant
|
|
238
|
+
p237,q24,332,relevant,relevant,relevant,
|
|
239
|
+
p238,q24,268,relevant,relevant,relevant,
|
|
240
|
+
p239,q24,806,relevant,relevant,relevant,relevant
|
|
241
|
+
p240,q24,708,irrelevant,irrelevant,relevant,
|
|
242
|
+
p241,q25,698,irrelevant,relevant,relevant,
|
|
243
|
+
p242,q25,578,relevant,relevant,relevant,
|
|
244
|
+
p243,q25,805,relevant,irrelevant,relevant,
|
|
245
|
+
p244,q25,814,relevant,irrelevant,irrelevant,
|
|
246
|
+
p245,q25,100,irrelevant,relevant,irrelevant,
|
|
247
|
+
p246,q25,860,relevant,relevant,relevant,
|
|
248
|
+
p247,q25,189,relevant,relevant,relevant,relevant
|
|
249
|
+
p248,q25,342,relevant,relevant,relevant,
|
|
250
|
+
p249,q25,541,relevant,relevant,relevant,
|
|
251
|
+
p250,q25,178,irrelevant,relevant,relevant,
|
|
252
|
+
p251,q26,239,relevant,relevant,relevant,
|
|
253
|
+
p252,q26,247,relevant,relevant,relevant,
|
|
254
|
+
p253,q26,317,relevant,irrelevant,relevant,
|
|
255
|
+
p254,q26,575,irrelevant,irrelevant,relevant,irrelevant
|
|
256
|
+
p255,q26,91,relevant,relevant,relevant,
|
|
257
|
+
p256,q26,189,relevant,relevant,relevant,
|
|
258
|
+
p257,q26,183,relevant,relevant,relevant,
|
|
259
|
+
p258,q26,807,relevant,relevant,relevant,
|
|
260
|
+
p259,q26,730,relevant,relevant,relevant,relevant
|
|
261
|
+
p260,q26,379,irrelevant,irrelevant,irrelevant,irrelevant
|
|
262
|
+
p261,q27,576,relevant,relevant,relevant,relevant
|
|
263
|
+
p262,q27,184,relevant,relevant,relevant,
|
|
264
|
+
p263,q27,556,relevant,irrelevant,relevant,
|
|
265
|
+
p264,q27,270,irrelevant,irrelevant,irrelevant,
|
|
266
|
+
p265,q27,777,relevant,relevant,relevant,
|
|
267
|
+
p266,q27,781,relevant,relevant,relevant,
|
|
268
|
+
p267,q27,96,irrelevant,irrelevant,irrelevant,
|
|
269
|
+
p268,q27,117,relevant,relevant,relevant,
|
|
270
|
+
p269,q27,640,irrelevant,irrelevant,relevant,
|
|
271
|
+
p270,q27,126,relevant,irrelevant,relevant,
|
|
272
|
+
p271,q28,522,relevant,relevant,relevant,relevant
|
|
273
|
+
p272,q28,455,irrelevant,irrelevant,relevant,
|
|
274
|
+
p273,q28,234,relevant,irrelevant,relevant,
|
|
275
|
+
p274,q28,301,irrelevant,irrelevant,irrelevant,
|
|
276
|
+
p275,q28,847,irrelevant,relevant,relevant,
|
|
277
|
+
p276,q28,321,irrelevant,irrelevant,irrelevant,
|
|
278
|
+
p277,q28,685,relevant,relevant,relevant,relevant
|
|
279
|
+
p278,q28,220,relevant,relevant,relevant,
|
|
280
|
+
p279,q28,105,irrelevant,irrelevant,irrelevant,
|
|
281
|
+
p280,q28,235,irrelevant,irrelevant,irrelevant,
|
|
282
|
+
p281,q29,757,irrelevant,irrelevant,relevant,
|
|
283
|
+
p282,q29,890,relevant,relevant,relevant,
|
|
284
|
+
p283,q29,306,relevant,relevant,relevant,irrelevant
|
|
285
|
+
p284,q29,551,irrelevant,irrelevant,relevant,
|
|
286
|
+
p285,q29,738,relevant,relevant,relevant,relevant
|
|
287
|
+
p286,q29,735,relevant,relevant,relevant,
|
|
288
|
+
p287,q29,199,relevant,relevant,relevant,
|
|
289
|
+
p288,q29,374,relevant,relevant,irrelevant,
|
|
290
|
+
p289,q29,481,relevant,relevant,relevant,
|
|
291
|
+
p290,q29,645,relevant,relevant,relevant,
|
|
292
|
+
p291,q30,124,relevant,relevant,relevant,
|
|
293
|
+
p292,q30,369,relevant,relevant,relevant,relevant
|
|
294
|
+
p293,q30,548,relevant,relevant,relevant,
|
|
295
|
+
p294,q30,208,irrelevant,irrelevant,irrelevant,
|
|
296
|
+
p295,q30,663,relevant,relevant,relevant,
|
|
297
|
+
p296,q30,128,relevant,relevant,relevant,
|
|
298
|
+
p297,q30,187,relevant,relevant,relevant,
|
|
299
|
+
p298,q30,282,relevant,relevant,relevant,relevant
|
|
300
|
+
p299,q30,215,relevant,relevant,relevant,relevant
|
|
301
|
+
p300,q30,118,relevant,relevant,irrelevant,
|
|
@@ -0,0 +1,101 @@
|
|
|
1
|
+
item_id,gold_label,policy_category
|
|
2
|
+
fp-30011,ok,
|
|
3
|
+
fp-30039,ok,
|
|
4
|
+
fp-30134,ok,
|
|
5
|
+
fp-30209,ok,
|
|
6
|
+
fp-30281,ok,
|
|
7
|
+
fp-30437,ok,
|
|
8
|
+
fp-30464,ok,
|
|
9
|
+
fp-30575,ok,
|
|
10
|
+
fp-30646,ok,
|
|
11
|
+
fp-30855,ok,
|
|
12
|
+
fp-30916,ok,
|
|
13
|
+
fp-30923,violation,harassment
|
|
14
|
+
fp-31019,ok,
|
|
15
|
+
fp-31177,ok,
|
|
16
|
+
fp-31250,violation,spam
|
|
17
|
+
fp-31299,ok,
|
|
18
|
+
fp-31326,ok,
|
|
19
|
+
fp-31428,ok,
|
|
20
|
+
fp-31437,ok,
|
|
21
|
+
fp-31504,ok,
|
|
22
|
+
fp-31555,ok,
|
|
23
|
+
fp-31559,ok,
|
|
24
|
+
fp-31635,ok,
|
|
25
|
+
fp-31744,ok,
|
|
26
|
+
fp-31885,ok,
|
|
27
|
+
fp-31921,ok,
|
|
28
|
+
fp-31931,ok,
|
|
29
|
+
fp-31990,ok,
|
|
30
|
+
fp-32266,ok,
|
|
31
|
+
fp-32383,ok,
|
|
32
|
+
fp-32399,ok,
|
|
33
|
+
fp-32415,ok,
|
|
34
|
+
fp-32829,ok,
|
|
35
|
+
fp-32996,ok,
|
|
36
|
+
fp-33133,ok,
|
|
37
|
+
fp-33140,ok,
|
|
38
|
+
fp-33164,ok,
|
|
39
|
+
fp-33232,ok,
|
|
40
|
+
fp-33278,ok,
|
|
41
|
+
fp-33358,ok,
|
|
42
|
+
fp-33474,ok,
|
|
43
|
+
fp-33590,ok,
|
|
44
|
+
fp-33696,ok,
|
|
45
|
+
fp-33896,ok,
|
|
46
|
+
fp-33930,ok,
|
|
47
|
+
fp-33940,ok,
|
|
48
|
+
fp-34060,ok,
|
|
49
|
+
fp-34140,ok,
|
|
50
|
+
fp-34194,ok,
|
|
51
|
+
fp-34265,violation,self_harm
|
|
52
|
+
fp-34455,ok,
|
|
53
|
+
fp-34586,ok,
|
|
54
|
+
fp-34789,ok,
|
|
55
|
+
fp-34886,ok,
|
|
56
|
+
fp-35267,ok,
|
|
57
|
+
fp-35339,ok,
|
|
58
|
+
fp-35388,ok,
|
|
59
|
+
fp-35431,ok,
|
|
60
|
+
fp-35757,ok,
|
|
61
|
+
fp-35782,violation,harassment
|
|
62
|
+
fp-35866,ok,
|
|
63
|
+
fp-36296,ok,
|
|
64
|
+
fp-36366,ok,
|
|
65
|
+
fp-36596,ok,
|
|
66
|
+
fp-36620,ok,
|
|
67
|
+
fp-36807,ok,
|
|
68
|
+
fp-37091,ok,
|
|
69
|
+
fp-37170,ok,
|
|
70
|
+
fp-37286,ok,
|
|
71
|
+
fp-37556,ok,
|
|
72
|
+
fp-37694,ok,
|
|
73
|
+
fp-37725,ok,
|
|
74
|
+
fp-37737,ok,
|
|
75
|
+
fp-37802,ok,
|
|
76
|
+
fp-37887,ok,
|
|
77
|
+
fp-37954,ok,
|
|
78
|
+
fp-38009,ok,
|
|
79
|
+
fp-38123,ok,
|
|
80
|
+
fp-38145,ok,
|
|
81
|
+
fp-38202,ok,
|
|
82
|
+
fp-38257,ok,
|
|
83
|
+
fp-38311,ok,
|
|
84
|
+
fp-38678,ok,
|
|
85
|
+
fp-38699,ok,
|
|
86
|
+
fp-38702,ok,
|
|
87
|
+
fp-38748,violation,spam
|
|
88
|
+
fp-38814,ok,
|
|
89
|
+
fp-38826,ok,
|
|
90
|
+
fp-39027,ok,
|
|
91
|
+
fp-39044,ok,
|
|
92
|
+
fp-39107,ok,
|
|
93
|
+
fp-39140,ok,
|
|
94
|
+
fp-39176,ok,
|
|
95
|
+
fp-39221,ok,
|
|
96
|
+
fp-39382,ok,
|
|
97
|
+
fp-39430,ok,
|
|
98
|
+
fp-39451,ok,
|
|
99
|
+
fp-39543,ok,
|
|
100
|
+
fp-39753,ok,
|
|
101
|
+
fp-39922,ok,
|