harness-everything 0.28.0 → 0.30.0

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 (109) hide show
  1. package/.claude-plugin/marketplace.json +1 -1
  2. package/.claude-plugin/plugin.json +1 -1
  3. package/AGENTS.md +1 -0
  4. package/CHANGELOG.md +47 -0
  5. package/PRIVACY.md +9 -0
  6. package/benchmarks/fixtures/system-one-holdout-reviews.json +18 -18
  7. package/benchmarks/fixtures/system-one-holdout.json +9 -9
  8. package/benchmarks/fixtures/system-one-intent-holdout-draft.json +2228 -0
  9. package/benchmarks/fixtures/system-one-intent-holdout.json +16509 -0
  10. package/benchmarks/fixtures/system-one-intent-reviews.json +2723 -0
  11. package/benchmarks/results/system-one/harness-routing-v1-cpu-2026-09-24/README.md +75 -0
  12. package/benchmarks/results/system-one/harness-routing-v1-cpu-2026-09-24/report.json +10832 -0
  13. package/benchmarks/results/system-one/harness-routing-v1-ngram-2026-09-24/README.md +72 -0
  14. package/benchmarks/results/system-one/harness-routing-v1-ngram-2026-09-24/report.json +10817 -0
  15. package/benchmarks/results/system-one/harness-routing-v3-ngram-2026-09-24/README.md +63 -0
  16. package/benchmarks/results/system-one/harness-routing-v3-ngram-2026-09-24/report.json +10817 -0
  17. package/benchmarks/results/system-one/intent-ngram-v1-2026-09-24/README.md +64 -0
  18. package/benchmarks/results/system-one/intent-ngram-v1-2026-09-24/report.json +15177 -0
  19. package/benchmarks/results/system-one/labeler-holdout-check-2026-09-24/report.json +1104 -0
  20. package/benchmarks/results/system-one/labeler-holdout-check-codex-2026-09-24/report.json +1104 -0
  21. package/benchmarks/results/system-one/labeler-holdout-check-codex-tier3-2026-09-24/report.json +1104 -0
  22. package/benchmarks/results/system-one/labeler-holdout-check-intent-2026-09-24/report.json +2976 -0
  23. package/benchmarks/results/system-one/labeler-holdout-check-intent-scores-haiku-2026-09-24/report-005-steps.json +6125 -0
  24. package/benchmarks/results/system-one/labeler-holdout-check-intent-scores-haiku-2026-09-24/report-haiku-sonnet-escalation.json +6344 -0
  25. package/benchmarks/results/system-one/labeler-holdout-check-intent-scores-haiku-2026-09-24/report-scaled-margin-escalation.json +6206 -0
  26. package/benchmarks/results/system-one/labeler-holdout-check-intent-scores-haiku-2026-09-24/report.json +6103 -0
  27. package/benchmarks/results/system-one/laya-ft-2026-09-25/README.md +83 -0
  28. package/benchmarks/results/system-one/laya-ft-2026-09-25/report.json +71 -0
  29. package/benchmarks/results/system-one/laya-ft-2026-09-25/shadow-report.json +44 -0
  30. package/benchmarks/results/system-one/laya-zs-2026-09-25/README.md +68 -0
  31. package/benchmarks/results/system-one/laya-zs-2026-09-25/report.json +173 -0
  32. package/ci/mechanism-34-observations.test.js +550 -0
  33. package/ci/mechanism-system-one-collect.test.js +16 -0
  34. package/ci/mechanism-system-one-evaluation.test.js +17 -0
  35. package/ci/mechanism-system-one-intent.test.js +406 -0
  36. package/ci/mechanism-system-one-label.test.js +27 -0
  37. package/ci/mechanism-system-one-laya.test.js +45 -0
  38. package/ci/mechanism-system-one-ngram.test.js +161 -0
  39. package/ci/mechanism-system-one-relevance.test.js +112 -0
  40. package/ci/mechanism-system-one-resident.test.js +16 -0
  41. package/ci/mechanism-system-one-train.test.js +12 -0
  42. package/ci/system-one-laya-calibrate-test.py +65 -0
  43. package/ci/system-one-laya-export-test.py +155 -0
  44. package/ci/system-one-laya-label-test.py +201 -0
  45. package/ci/system-one-laya-perintent-test.py +60 -0
  46. package/ci/system-one-laya-provider-test.py +115 -0
  47. package/ci/system-one-laya-train-test.py +93 -0
  48. package/ci/system-one-ngram-parity.py +19 -0
  49. package/ci/system-one-train-test.py +6 -0
  50. package/docs/routing.md +25 -0
  51. package/docs/system-one-corpus.md +31 -3
  52. package/docs/system-one-intent-gates.md +102 -0
  53. package/docs/system-one-intent.md +173 -0
  54. package/docs/system-one-laya-training.md +38 -0
  55. package/docs/system-one-observations.md +206 -0
  56. package/docs/system-one-routing.md +102 -5
  57. package/docs/system-one-suggestion-gates.md +292 -0
  58. package/docs/system-one-training.md +69 -7
  59. package/harness-everything/SKILL.md +1 -1
  60. package/harness-everything/scripts/kernel-router.js +10 -0
  61. package/harness-everything/scripts/system-one/catalogs.js +35 -0
  62. package/harness-everything/scripts/system-one/contract.js +45 -1
  63. package/harness-everything/scripts/system-one/evaluate.js +118 -21
  64. package/harness-everything/scripts/system-one/intent.js +22 -0
  65. package/harness-everything/scripts/system-one/laya_adapter.py +141 -0
  66. package/harness-everything/scripts/system-one/ngram.js +84 -0
  67. package/harness-everything/scripts/system-one/provider.js +24 -7
  68. package/harness-everything/scripts/system-one/resident.js +8 -3
  69. package/harness-everything/scripts/system-one/router.js +1 -1
  70. package/hooks/hooks.json +40 -0
  71. package/hooks/scripts/codex-user-prompt.js +39 -0
  72. package/hooks/scripts/lib/observations.js +581 -0
  73. package/hooks/scripts/observation-hook.js +25 -0
  74. package/opencode-plugin/plugin.json +1 -1
  75. package/package.json +1 -1
  76. package/plugins/harness-everything/.codex-plugin/plugin.json +1 -1
  77. package/plugins/harness-everything/hooks/hooks.json +35 -2
  78. package/plugins/harness-everything/hooks/scripts/codex-user-prompt.js +39 -0
  79. package/plugins/harness-everything/hooks/scripts/lib/observations.js +581 -0
  80. package/plugins/harness-everything/hooks/scripts/observation-hook.js +25 -0
  81. package/plugins/harness-everything/plugin.json +1 -1
  82. package/plugins/harness-everything/skills/harness-everything/SKILL.md +1 -1
  83. package/plugins/harness-everything/skills/harness-everything/scripts/kernel-router.js +10 -0
  84. package/plugins/harness-everything/skills/harness-everything/scripts/system-one/catalogs.js +35 -0
  85. package/plugins/harness-everything/skills/harness-everything/scripts/system-one/contract.js +45 -1
  86. package/plugins/harness-everything/skills/harness-everything/scripts/system-one/evaluate.js +118 -21
  87. package/plugins/harness-everything/skills/harness-everything/scripts/system-one/intent.js +22 -0
  88. package/plugins/harness-everything/skills/harness-everything/scripts/system-one/laya_adapter.py +141 -0
  89. package/plugins/harness-everything/skills/harness-everything/scripts/system-one/ngram.js +84 -0
  90. package/plugins/harness-everything/skills/harness-everything/scripts/system-one/provider.js +24 -7
  91. package/plugins/harness-everything/skills/harness-everything/scripts/system-one/resident.js +8 -3
  92. package/plugins/harness-everything/skills/harness-everything/scripts/system-one/router.js +1 -1
  93. package/sbom.cdx.json +7 -7
  94. package/scripts/evaluate-system-one.js +32 -13
  95. package/scripts/system-one-calibrate-laya.py +165 -0
  96. package/scripts/system-one-calibrate.js +42 -13
  97. package/scripts/system-one-collect.js +7 -3
  98. package/scripts/system-one-compare-laya.py +156 -0
  99. package/scripts/system-one-corpus.js +22 -15
  100. package/scripts/system-one-eval-laya.js +112 -0
  101. package/scripts/system-one-export-laya.py +197 -0
  102. package/scripts/system-one-label-laya.py +243 -0
  103. package/scripts/system-one-label.js +192 -37
  104. package/scripts/system-one-observations-export.js +106 -0
  105. package/scripts/system-one-observations-review.js +86 -0
  106. package/scripts/system-one-perintent-laya.py +134 -0
  107. package/scripts/system-one-train-laya.py +344 -0
  108. package/scripts/system-one-train-ngram.py +181 -0
  109. package/scripts/system-one-train.py +14 -1
@@ -0,0 +1,1104 @@
1
+ {
2
+ "schemaVersion": 1,
3
+ "labeler": {
4
+ "model": "gpt-5.6-luna",
5
+ "rulesSha256": "e153bd5ff747d6c9",
6
+ "engine": "codex"
7
+ },
8
+ "cases": 215,
9
+ "agreement": 0.8186046511627907,
10
+ "recall": {
11
+ "tier1": 0.8723404255319149,
12
+ "tier2": 0.7216494845360825,
13
+ "tier3": 0.9019607843137255,
14
+ "unclassified": 0.95
15
+ },
16
+ "confusion": {
17
+ "tier2->tier1": 9,
18
+ "tier1->tier2": 4,
19
+ "tier3->tier2": 5,
20
+ "tier2->tier3": 13,
21
+ "tier2->unclassified": 5,
22
+ "tier1->unclassified": 2,
23
+ "unclassified->tier1": 1
24
+ },
25
+ "missing": 0,
26
+ "failed": 0,
27
+ "perCase": [
28
+ {
29
+ "id": "h-git-commit-1",
30
+ "gold": "tier1",
31
+ "predicted": "tier1"
32
+ },
33
+ {
34
+ "id": "h-git-commit-2",
35
+ "gold": "tier1",
36
+ "predicted": "tier1"
37
+ },
38
+ {
39
+ "id": "h-git-commit-3",
40
+ "gold": "tier1",
41
+ "predicted": "tier1"
42
+ },
43
+ {
44
+ "id": "h-git-commit-4",
45
+ "gold": "tier1",
46
+ "predicted": "tier1"
47
+ },
48
+ {
49
+ "id": "h-git-push-open-pr-1",
50
+ "gold": "tier1",
51
+ "predicted": "tier1"
52
+ },
53
+ {
54
+ "id": "h-git-push-open-pr-2",
55
+ "gold": "tier1",
56
+ "predicted": "tier1"
57
+ },
58
+ {
59
+ "id": "h-git-push-open-pr-3",
60
+ "gold": "tier1",
61
+ "predicted": "tier1"
62
+ },
63
+ {
64
+ "id": "h-git-push-open-pr-4",
65
+ "gold": "tier1",
66
+ "predicted": "tier1"
67
+ },
68
+ {
69
+ "id": "h-git-sync-branch-1",
70
+ "gold": "tier1",
71
+ "predicted": "tier1"
72
+ },
73
+ {
74
+ "id": "h-git-sync-branch-2",
75
+ "gold": "tier1",
76
+ "predicted": "tier1"
77
+ },
78
+ {
79
+ "id": "h-git-sync-branch-3",
80
+ "gold": "tier1",
81
+ "predicted": "tier1"
82
+ },
83
+ {
84
+ "id": "h-git-sync-branch-4",
85
+ "gold": "tier1",
86
+ "predicted": "tier1"
87
+ },
88
+ {
89
+ "id": "h-git-revert-last-1",
90
+ "gold": "tier2",
91
+ "predicted": "tier2"
92
+ },
93
+ {
94
+ "id": "h-git-revert-last-2",
95
+ "gold": "tier2",
96
+ "predicted": "tier2"
97
+ },
98
+ {
99
+ "id": "h-git-revert-last-3",
100
+ "gold": "tier2",
101
+ "predicted": "tier2"
102
+ },
103
+ {
104
+ "id": "h-issue-pr-status-1",
105
+ "gold": "tier1",
106
+ "predicted": "tier1"
107
+ },
108
+ {
109
+ "id": "h-issue-pr-status-2",
110
+ "gold": "tier1",
111
+ "predicted": "tier1"
112
+ },
113
+ {
114
+ "id": "h-issue-pr-status-3",
115
+ "gold": "tier1",
116
+ "predicted": "tier1"
117
+ },
118
+ {
119
+ "id": "h-issue-pr-status-4",
120
+ "gold": "tier1",
121
+ "predicted": "tier1"
122
+ },
123
+ {
124
+ "id": "h-comment-results-on-issue-1",
125
+ "gold": "tier1",
126
+ "predicted": "tier1"
127
+ },
128
+ {
129
+ "id": "h-comment-results-on-issue-2",
130
+ "gold": "tier1",
131
+ "predicted": "tier1"
132
+ },
133
+ {
134
+ "id": "h-comment-results-on-issue-3",
135
+ "gold": "tier1",
136
+ "predicted": "tier1"
137
+ },
138
+ {
139
+ "id": "h-open-issue-described-1",
140
+ "gold": "tier2",
141
+ "predicted": "tier2"
142
+ },
143
+ {
144
+ "id": "h-open-issue-described-2",
145
+ "gold": "tier2",
146
+ "predicted": "tier2"
147
+ },
148
+ {
149
+ "id": "h-open-issue-described-3",
150
+ "gold": "tier2",
151
+ "predicted": "tier2"
152
+ },
153
+ {
154
+ "id": "h-open-issue-described-4",
155
+ "gold": "tier2",
156
+ "predicted": "tier2"
157
+ },
158
+ {
159
+ "id": "h-typo-doc-fix-1",
160
+ "gold": "tier1",
161
+ "predicted": "tier1"
162
+ },
163
+ {
164
+ "id": "h-typo-doc-fix-2",
165
+ "gold": "tier2",
166
+ "predicted": "tier1"
167
+ },
168
+ {
169
+ "id": "h-typo-doc-fix-3",
170
+ "gold": "tier1",
171
+ "predicted": "tier1"
172
+ },
173
+ {
174
+ "id": "h-typo-doc-fix-4",
175
+ "gold": "tier2",
176
+ "predicted": "tier1"
177
+ },
178
+ {
179
+ "id": "h-single-line-edit-1",
180
+ "gold": "tier2",
181
+ "predicted": "tier2"
182
+ },
183
+ {
184
+ "id": "h-single-line-edit-2",
185
+ "gold": "tier2",
186
+ "predicted": "tier2"
187
+ },
188
+ {
189
+ "id": "h-single-line-edit-3",
190
+ "gold": "tier2",
191
+ "predicted": "tier2"
192
+ },
193
+ {
194
+ "id": "h-local-rename-1",
195
+ "gold": "tier2",
196
+ "predicted": "tier2"
197
+ },
198
+ {
199
+ "id": "h-local-rename-2",
200
+ "gold": "tier2",
201
+ "predicted": "tier2"
202
+ },
203
+ {
204
+ "id": "h-local-rename-3",
205
+ "gold": "tier2",
206
+ "predicted": "tier2"
207
+ },
208
+ {
209
+ "id": "h-config-tweak-1",
210
+ "gold": "tier2",
211
+ "predicted": "tier2"
212
+ },
213
+ {
214
+ "id": "h-config-tweak-2",
215
+ "gold": "tier2",
216
+ "predicted": "tier2"
217
+ },
218
+ {
219
+ "id": "h-config-tweak-3",
220
+ "gold": "tier2",
221
+ "predicted": "tier2"
222
+ },
223
+ {
224
+ "id": "h-config-tweak-4",
225
+ "gold": "tier1",
226
+ "predicted": "tier1"
227
+ },
228
+ {
229
+ "id": "h-run-named-command-1",
230
+ "gold": "tier2",
231
+ "predicted": "tier2"
232
+ },
233
+ {
234
+ "id": "h-run-named-command-2",
235
+ "gold": "tier2",
236
+ "predicted": "tier2"
237
+ },
238
+ {
239
+ "id": "h-run-named-command-3",
240
+ "gold": "tier2",
241
+ "predicted": "tier2"
242
+ },
243
+ {
244
+ "id": "h-run-named-command-4",
245
+ "gold": "tier2",
246
+ "predicted": "tier2"
247
+ },
248
+ {
249
+ "id": "h-bounded-explanation-1",
250
+ "gold": "tier1",
251
+ "predicted": "tier2"
252
+ },
253
+ {
254
+ "id": "h-bounded-explanation-2",
255
+ "gold": "tier2",
256
+ "predicted": "tier1"
257
+ },
258
+ {
259
+ "id": "h-bounded-explanation-3",
260
+ "gold": "tier2",
261
+ "predicted": "tier2"
262
+ },
263
+ {
264
+ "id": "h-bounded-explanation-4",
265
+ "gold": "tier2",
266
+ "predicted": "tier2"
267
+ },
268
+ {
269
+ "id": "h-read-log-report-1",
270
+ "gold": "tier1",
271
+ "predicted": "tier1"
272
+ },
273
+ {
274
+ "id": "h-read-log-report-2",
275
+ "gold": "tier1",
276
+ "predicted": "tier1"
277
+ },
278
+ {
279
+ "id": "h-read-log-report-3",
280
+ "gold": "tier1",
281
+ "predicted": "tier1"
282
+ },
283
+ {
284
+ "id": "h-list-remaining-tasks-1",
285
+ "gold": "tier2",
286
+ "predicted": "tier1"
287
+ },
288
+ {
289
+ "id": "h-list-remaining-tasks-2",
290
+ "gold": "tier2",
291
+ "predicted": "tier1"
292
+ },
293
+ {
294
+ "id": "h-list-remaining-tasks-3",
295
+ "gold": "tier2",
296
+ "predicted": "tier1"
297
+ },
298
+ {
299
+ "id": "h-add-link-docs-1",
300
+ "gold": "tier1",
301
+ "predicted": "tier1"
302
+ },
303
+ {
304
+ "id": "h-add-link-docs-2",
305
+ "gold": "tier1",
306
+ "predicted": "tier1"
307
+ },
308
+ {
309
+ "id": "h-fix-cli-error-log-1",
310
+ "gold": "tier2",
311
+ "predicted": "tier2"
312
+ },
313
+ {
314
+ "id": "h-fix-cli-error-log-2",
315
+ "gold": "tier2",
316
+ "predicted": "tier2"
317
+ },
318
+ {
319
+ "id": "h-fix-cli-error-log-3",
320
+ "gold": "tier3",
321
+ "predicted": "tier2"
322
+ },
323
+ {
324
+ "id": "h-fix-cli-error-log-4",
325
+ "gold": "tier3",
326
+ "predicted": "tier2"
327
+ },
328
+ {
329
+ "id": "h-fix-failing-test-1",
330
+ "gold": "tier2",
331
+ "predicted": "tier2"
332
+ },
333
+ {
334
+ "id": "h-fix-failing-test-2",
335
+ "gold": "tier2",
336
+ "predicted": "tier2"
337
+ },
338
+ {
339
+ "id": "h-fix-failing-test-3",
340
+ "gold": "tier3",
341
+ "predicted": "tier2"
342
+ },
343
+ {
344
+ "id": "h-fix-failing-test-4",
345
+ "gold": "tier2",
346
+ "predicted": "tier2"
347
+ },
348
+ {
349
+ "id": "h-add-cli-flag-1",
350
+ "gold": "tier3",
351
+ "predicted": "tier3"
352
+ },
353
+ {
354
+ "id": "h-add-cli-flag-2",
355
+ "gold": "tier3",
356
+ "predicted": "tier3"
357
+ },
358
+ {
359
+ "id": "h-add-cli-flag-3",
360
+ "gold": "tier3",
361
+ "predicted": "tier3"
362
+ },
363
+ {
364
+ "id": "h-nondeterministic-output-1",
365
+ "gold": "tier2",
366
+ "predicted": "tier3"
367
+ },
368
+ {
369
+ "id": "h-nondeterministic-output-2",
370
+ "gold": "tier2",
371
+ "predicted": "tier3"
372
+ },
373
+ {
374
+ "id": "h-nondeterministic-output-3",
375
+ "gold": "tier2",
376
+ "predicted": "tier2"
377
+ },
378
+ {
379
+ "id": "h-warning-level-fix-1",
380
+ "gold": "tier2",
381
+ "predicted": "tier2"
382
+ },
383
+ {
384
+ "id": "h-warning-level-fix-2",
385
+ "gold": "tier2",
386
+ "predicted": "tier2"
387
+ },
388
+ {
389
+ "id": "h-warning-level-fix-3",
390
+ "gold": "tier2",
391
+ "predicted": "tier2"
392
+ },
393
+ {
394
+ "id": "h-debug-crash-after-start-1",
395
+ "gold": "tier2",
396
+ "predicted": "tier2"
397
+ },
398
+ {
399
+ "id": "h-debug-crash-after-start-2",
400
+ "gold": "tier2",
401
+ "predicted": "tier2"
402
+ },
403
+ {
404
+ "id": "h-debug-crash-after-start-3",
405
+ "gold": "tier2",
406
+ "predicted": "tier2"
407
+ },
408
+ {
409
+ "id": "h-multi-file-feature-1",
410
+ "gold": "tier3",
411
+ "predicted": "tier3"
412
+ },
413
+ {
414
+ "id": "h-multi-file-feature-2",
415
+ "gold": "tier3",
416
+ "predicted": "tier3"
417
+ },
418
+ {
419
+ "id": "h-multi-file-feature-3",
420
+ "gold": "tier3",
421
+ "predicted": "tier3"
422
+ },
423
+ {
424
+ "id": "h-focused-review-1",
425
+ "gold": "tier2",
426
+ "predicted": "tier2"
427
+ },
428
+ {
429
+ "id": "h-focused-review-2",
430
+ "gold": "tier2",
431
+ "predicted": "tier2"
432
+ },
433
+ {
434
+ "id": "h-focused-review-3",
435
+ "gold": "tier2",
436
+ "predicted": "tier2"
437
+ },
438
+ {
439
+ "id": "h-focused-benchmark-1",
440
+ "gold": "tier2",
441
+ "predicted": "tier2"
442
+ },
443
+ {
444
+ "id": "h-focused-benchmark-2",
445
+ "gold": "tier2",
446
+ "predicted": "tier2"
447
+ },
448
+ {
449
+ "id": "h-function-refactor-1",
450
+ "gold": "tier3",
451
+ "predicted": "tier2"
452
+ },
453
+ {
454
+ "id": "h-function-refactor-2",
455
+ "gold": "tier3",
456
+ "predicted": "tier2"
457
+ },
458
+ {
459
+ "id": "h-function-refactor-3",
460
+ "gold": "tier2",
461
+ "predicted": "tier2"
462
+ },
463
+ {
464
+ "id": "h-hash-algorithm-support-1",
465
+ "gold": "tier3",
466
+ "predicted": "tier3"
467
+ },
468
+ {
469
+ "id": "h-hash-algorithm-support-2",
470
+ "gold": "tier3",
471
+ "predicted": "tier3"
472
+ },
473
+ {
474
+ "id": "h-toolchain-check-1",
475
+ "gold": "tier2",
476
+ "predicted": "tier2"
477
+ },
478
+ {
479
+ "id": "h-toolchain-check-2",
480
+ "gold": "tier2",
481
+ "predicted": "tier2"
482
+ },
483
+ {
484
+ "id": "h-relative-paths-1",
485
+ "gold": "tier3",
486
+ "predicted": "tier3"
487
+ },
488
+ {
489
+ "id": "h-relative-paths-2",
490
+ "gold": "tier3",
491
+ "predicted": "tier3"
492
+ },
493
+ {
494
+ "id": "h-validation-rule-1",
495
+ "gold": "tier2",
496
+ "predicted": "tier3"
497
+ },
498
+ {
499
+ "id": "h-validation-rule-2",
500
+ "gold": "tier2",
501
+ "predicted": "tier3"
502
+ },
503
+ {
504
+ "id": "h-update-docs-examples-1",
505
+ "gold": "tier2",
506
+ "predicted": "tier2"
507
+ },
508
+ {
509
+ "id": "h-update-docs-examples-2",
510
+ "gold": "tier2",
511
+ "predicted": "tier2"
512
+ },
513
+ {
514
+ "id": "h-audit-all-repos-1",
515
+ "gold": "tier3",
516
+ "predicted": "tier3"
517
+ },
518
+ {
519
+ "id": "h-audit-all-repos-2",
520
+ "gold": "tier3",
521
+ "predicted": "tier3"
522
+ },
523
+ {
524
+ "id": "h-audit-all-repos-3",
525
+ "gold": "tier1",
526
+ "predicted": "tier1"
527
+ },
528
+ {
529
+ "id": "h-phase-plan-to-issue-1",
530
+ "gold": "tier2",
531
+ "predicted": "tier2"
532
+ },
533
+ {
534
+ "id": "h-phase-plan-to-issue-2",
535
+ "gold": "tier2",
536
+ "predicted": "tier2"
537
+ },
538
+ {
539
+ "id": "h-phase-plan-to-issue-3",
540
+ "gold": "tier2",
541
+ "predicted": "tier3"
542
+ },
543
+ {
544
+ "id": "h-roadmap-phase-implement-1",
545
+ "gold": "tier2",
546
+ "predicted": "tier3"
547
+ },
548
+ {
549
+ "id": "h-roadmap-phase-implement-2",
550
+ "gold": "tier3",
551
+ "predicted": "tier3"
552
+ },
553
+ {
554
+ "id": "h-roadmap-phase-implement-3",
555
+ "gold": "tier3",
556
+ "predicted": "tier3"
557
+ },
558
+ {
559
+ "id": "h-migration-1",
560
+ "gold": "tier3",
561
+ "predicted": "tier3"
562
+ },
563
+ {
564
+ "id": "h-migration-2",
565
+ "gold": "tier3",
566
+ "predicted": "tier3"
567
+ },
568
+ {
569
+ "id": "h-migration-3",
570
+ "gold": "tier3",
571
+ "predicted": "tier3"
572
+ },
573
+ {
574
+ "id": "h-migration-4",
575
+ "gold": "tier3",
576
+ "predicted": "tier3"
577
+ },
578
+ {
579
+ "id": "h-large-scale-rename-1",
580
+ "gold": "tier3",
581
+ "predicted": "tier3"
582
+ },
583
+ {
584
+ "id": "h-large-scale-rename-2",
585
+ "gold": "tier3",
586
+ "predicted": "tier3"
587
+ },
588
+ {
589
+ "id": "h-architecture-design-1",
590
+ "gold": "tier3",
591
+ "predicted": "tier3"
592
+ },
593
+ {
594
+ "id": "h-architecture-design-2",
595
+ "gold": "tier3",
596
+ "predicted": "tier3"
597
+ },
598
+ {
599
+ "id": "h-architecture-design-3",
600
+ "gold": "tier2",
601
+ "predicted": "tier2"
602
+ },
603
+ {
604
+ "id": "h-parallel-delegation-1",
605
+ "gold": "tier3",
606
+ "predicted": "tier3"
607
+ },
608
+ {
609
+ "id": "h-parallel-delegation-2",
610
+ "gold": "tier3",
611
+ "predicted": "tier3"
612
+ },
613
+ {
614
+ "id": "h-parallel-delegation-3",
615
+ "gold": "tier3",
616
+ "predicted": "tier3"
617
+ },
618
+ {
619
+ "id": "h-repo-wide-replace-1",
620
+ "gold": "tier3",
621
+ "predicted": "tier3"
622
+ },
623
+ {
624
+ "id": "h-repo-wide-replace-2",
625
+ "gold": "tier3",
626
+ "predicted": "tier3"
627
+ },
628
+ {
629
+ "id": "h-repo-wide-replace-3",
630
+ "gold": "tier2",
631
+ "predicted": "tier3"
632
+ },
633
+ {
634
+ "id": "h-broad-synthesis-1",
635
+ "gold": "tier2",
636
+ "predicted": "tier2"
637
+ },
638
+ {
639
+ "id": "h-broad-synthesis-2",
640
+ "gold": "tier2",
641
+ "predicted": "tier2"
642
+ },
643
+ {
644
+ "id": "h-cross-platform-ci-1",
645
+ "gold": "tier2",
646
+ "predicted": "tier3"
647
+ },
648
+ {
649
+ "id": "h-cross-platform-ci-2",
650
+ "gold": "tier3",
651
+ "predicted": "tier3"
652
+ },
653
+ {
654
+ "id": "h-long-spec-feature-program-1",
655
+ "gold": "tier3",
656
+ "predicted": "tier3"
657
+ },
658
+ {
659
+ "id": "h-long-spec-feature-program-2",
660
+ "gold": "tier3",
661
+ "predicted": "tier3"
662
+ },
663
+ {
664
+ "id": "h-bare-continuation-1",
665
+ "gold": null,
666
+ "predicted": null
667
+ },
668
+ {
669
+ "id": "h-bare-continuation-2",
670
+ "gold": null,
671
+ "predicted": null
672
+ },
673
+ {
674
+ "id": "h-bare-continuation-3",
675
+ "gold": null,
676
+ "predicted": null
677
+ },
678
+ {
679
+ "id": "h-bare-continuation-4",
680
+ "gold": null,
681
+ "predicted": null
682
+ },
683
+ {
684
+ "id": "h-bare-continuation-5",
685
+ "gold": null,
686
+ "predicted": null
687
+ },
688
+ {
689
+ "id": "h-bare-continuation-6",
690
+ "gold": null,
691
+ "predicted": null
692
+ },
693
+ {
694
+ "id": "h-bare-continuation-7",
695
+ "gold": null,
696
+ "predicted": null
697
+ },
698
+ {
699
+ "id": "h-bare-continuation-8",
700
+ "gold": null,
701
+ "predicted": null
702
+ },
703
+ {
704
+ "id": "h-numbered-answers-1",
705
+ "gold": "tier2",
706
+ "predicted": "tier1"
707
+ },
708
+ {
709
+ "id": "h-numbered-answers-2",
710
+ "gold": "tier2",
711
+ "predicted": "tier1"
712
+ },
713
+ {
714
+ "id": "h-numbered-answers-3",
715
+ "gold": "tier2",
716
+ "predicted": "tier2"
717
+ },
718
+ {
719
+ "id": "h-numbered-answers-4",
720
+ "gold": "tier2",
721
+ "predicted": "tier2"
722
+ },
723
+ {
724
+ "id": "h-numbered-answers-5",
725
+ "gold": "tier2",
726
+ "predicted": "tier2"
727
+ },
728
+ {
729
+ "id": "h-unstated-reference-1",
730
+ "gold": "tier2",
731
+ "predicted": null
732
+ },
733
+ {
734
+ "id": "h-unstated-reference-2",
735
+ "gold": null,
736
+ "predicted": null
737
+ },
738
+ {
739
+ "id": "h-unstated-reference-3",
740
+ "gold": null,
741
+ "predicted": null
742
+ },
743
+ {
744
+ "id": "h-unstated-reference-4",
745
+ "gold": "tier2",
746
+ "predicted": null
747
+ },
748
+ {
749
+ "id": "h-unstated-reference-5",
750
+ "gold": "tier2",
751
+ "predicted": null
752
+ },
753
+ {
754
+ "id": "h-unstated-reference-6",
755
+ "gold": "tier2",
756
+ "predicted": null
757
+ },
758
+ {
759
+ "id": "h-status-without-object-1",
760
+ "gold": "tier1",
761
+ "predicted": "tier1"
762
+ },
763
+ {
764
+ "id": "h-status-without-object-2",
765
+ "gold": "tier1",
766
+ "predicted": "tier1"
767
+ },
768
+ {
769
+ "id": "h-status-without-object-3",
770
+ "gold": "tier1",
771
+ "predicted": null
772
+ },
773
+ {
774
+ "id": "h-status-without-object-4",
775
+ "gold": null,
776
+ "predicted": "tier1"
777
+ },
778
+ {
779
+ "id": "h-status-without-object-5",
780
+ "gold": "tier1",
781
+ "predicted": "tier1"
782
+ },
783
+ {
784
+ "id": "h-non-engineering-1",
785
+ "gold": "tier1",
786
+ "predicted": "tier1"
787
+ },
788
+ {
789
+ "id": "h-non-engineering-2",
790
+ "gold": "tier1",
791
+ "predicted": "tier1"
792
+ },
793
+ {
794
+ "id": "h-non-engineering-3",
795
+ "gold": "tier1",
796
+ "predicted": "tier1"
797
+ },
798
+ {
799
+ "id": "h-non-engineering-4",
800
+ "gold": "tier1",
801
+ "predicted": "tier1"
802
+ },
803
+ {
804
+ "id": "h-non-engineering-5",
805
+ "gold": "tier1",
806
+ "predicted": "tier1"
807
+ },
808
+ {
809
+ "id": "h-vague-intent-1",
810
+ "gold": null,
811
+ "predicted": null
812
+ },
813
+ {
814
+ "id": "h-vague-intent-2",
815
+ "gold": null,
816
+ "predicted": null
817
+ },
818
+ {
819
+ "id": "h-vague-intent-3",
820
+ "gold": null,
821
+ "predicted": null
822
+ },
823
+ {
824
+ "id": "h-vague-intent-4",
825
+ "gold": null,
826
+ "predicted": null
827
+ },
828
+ {
829
+ "id": "h-clarification-confusion-1",
830
+ "gold": null,
831
+ "predicted": null
832
+ },
833
+ {
834
+ "id": "h-clarification-confusion-2",
835
+ "gold": null,
836
+ "predicted": null
837
+ },
838
+ {
839
+ "id": "h-clarification-confusion-3",
840
+ "gold": "tier1",
841
+ "predicted": null
842
+ },
843
+ {
844
+ "id": "h-long-context-pasted-discussion-1",
845
+ "gold": "tier2",
846
+ "predicted": "tier2"
847
+ },
848
+ {
849
+ "id": "h-long-context-pasted-discussion-2",
850
+ "gold": "tier2",
851
+ "predicted": null
852
+ },
853
+ {
854
+ "id": "h-long-bugfix-report-1",
855
+ "gold": "tier2",
856
+ "predicted": "tier2"
857
+ },
858
+ {
859
+ "id": "h-long-bugfix-report-2",
860
+ "gold": "tier2",
861
+ "predicted": "tier2"
862
+ },
863
+ {
864
+ "id": "h-long-release-ops-1",
865
+ "gold": "tier1",
866
+ "predicted": "tier1"
867
+ },
868
+ {
869
+ "id": "h-long-release-ops-2",
870
+ "gold": "tier1",
871
+ "predicted": "tier1"
872
+ },
873
+ {
874
+ "id": "h-long-migration-brief-1",
875
+ "gold": "tier3",
876
+ "predicted": "tier3"
877
+ },
878
+ {
879
+ "id": "h-long-migration-brief-2",
880
+ "gold": "tier3",
881
+ "predicted": "tier3"
882
+ },
883
+ {
884
+ "id": "h-explain-design-choice-1",
885
+ "gold": "tier2",
886
+ "predicted": "tier2"
887
+ },
888
+ {
889
+ "id": "h-explain-design-choice-2",
890
+ "gold": "tier2",
891
+ "predicted": "tier2"
892
+ },
893
+ {
894
+ "id": "h-small-test-addition-1",
895
+ "gold": "tier2",
896
+ "predicted": "tier2"
897
+ },
898
+ {
899
+ "id": "h-small-test-addition-2",
900
+ "gold": "tier2",
901
+ "predicted": "tier2"
902
+ },
903
+ {
904
+ "id": "h-dependency-upgrade-1",
905
+ "gold": "tier3",
906
+ "predicted": "tier3"
907
+ },
908
+ {
909
+ "id": "h-dependency-upgrade-2",
910
+ "gold": "tier2",
911
+ "predicted": "tier3"
912
+ },
913
+ {
914
+ "id": "h-ci-workflow-small-1",
915
+ "gold": "tier2",
916
+ "predicted": "tier2"
917
+ },
918
+ {
919
+ "id": "h-ci-workflow-small-2",
920
+ "gold": "tier2",
921
+ "predicted": "tier2"
922
+ },
923
+ {
924
+ "id": "h-long-audit-and-fix-1",
925
+ "gold": "tier2",
926
+ "predicted": "tier3"
927
+ },
928
+ {
929
+ "id": "h-long-audit-and-fix-2",
930
+ "gold": "tier2",
931
+ "predicted": "tier3"
932
+ },
933
+ {
934
+ "id": "h-monorepo-restructure-1",
935
+ "gold": "tier3",
936
+ "predicted": "tier3"
937
+ },
938
+ {
939
+ "id": "h-monorepo-restructure-2",
940
+ "gold": "tier3",
941
+ "predicted": "tier3"
942
+ },
943
+ {
944
+ "id": "h-monorepo-restructure-3",
945
+ "gold": "tier3",
946
+ "predicted": "tier3"
947
+ },
948
+ {
949
+ "id": "h-security-hardening-program-1",
950
+ "gold": "tier3",
951
+ "predicted": "tier3"
952
+ },
953
+ {
954
+ "id": "h-security-hardening-program-2",
955
+ "gold": "tier3",
956
+ "predicted": "tier3"
957
+ },
958
+ {
959
+ "id": "h-security-hardening-program-3",
960
+ "gold": "tier2",
961
+ "predicted": "tier3"
962
+ },
963
+ {
964
+ "id": "h-observability-rollout-1",
965
+ "gold": "tier2",
966
+ "predicted": "tier3"
967
+ },
968
+ {
969
+ "id": "h-observability-rollout-2",
970
+ "gold": "tier3",
971
+ "predicted": "tier3"
972
+ },
973
+ {
974
+ "id": "h-api-versioning-1",
975
+ "gold": "tier3",
976
+ "predicted": "tier3"
977
+ },
978
+ {
979
+ "id": "h-api-versioning-2",
980
+ "gold": "tier3",
981
+ "predicted": "tier3"
982
+ },
983
+ {
984
+ "id": "h-long-regression-log-1",
985
+ "gold": "tier2",
986
+ "predicted": "tier2"
987
+ },
988
+ {
989
+ "id": "h-long-regression-log-2",
990
+ "gold": "tier2",
991
+ "predicted": "tier2"
992
+ },
993
+ {
994
+ "id": "h-long-perf-regression-1",
995
+ "gold": "tier2",
996
+ "predicted": "tier2"
997
+ },
998
+ {
999
+ "id": "h-long-perf-regression-2",
1000
+ "gold": "tier2",
1001
+ "predicted": "tier2"
1002
+ },
1003
+ {
1004
+ "id": "h-long-flaky-e2e-1",
1005
+ "gold": "tier2",
1006
+ "predicted": "tier2"
1007
+ },
1008
+ {
1009
+ "id": "h-long-flaky-e2e-2",
1010
+ "gold": "tier2",
1011
+ "predicted": "tier2"
1012
+ },
1013
+ {
1014
+ "id": "h-long-bounded-edit-1",
1015
+ "gold": "tier2",
1016
+ "predicted": "tier2"
1017
+ },
1018
+ {
1019
+ "id": "h-long-bounded-edit-2",
1020
+ "gold": "tier2",
1021
+ "predicted": "tier2"
1022
+ },
1023
+ {
1024
+ "id": "h-long-issue-comment-1",
1025
+ "gold": "tier1",
1026
+ "predicted": "tier1"
1027
+ },
1028
+ {
1029
+ "id": "h-long-issue-comment-2",
1030
+ "gold": "tier1",
1031
+ "predicted": "tier1"
1032
+ },
1033
+ {
1034
+ "id": "h-long-status-pasted-1",
1035
+ "gold": null,
1036
+ "predicted": null
1037
+ },
1038
+ {
1039
+ "id": "h-long-status-pasted-2",
1040
+ "gold": null,
1041
+ "predicted": null
1042
+ },
1043
+ {
1044
+ "id": "h-acknowledgement-2",
1045
+ "gold": null,
1046
+ "predicted": null
1047
+ },
1048
+ {
1049
+ "id": "h-long-bounded-explanation-1",
1050
+ "gold": "tier1",
1051
+ "predicted": "tier2"
1052
+ },
1053
+ {
1054
+ "id": "h-long-bounded-explanation-2",
1055
+ "gold": "tier1",
1056
+ "predicted": "tier2"
1057
+ },
1058
+ {
1059
+ "id": "h-long-dependency-conflict-1",
1060
+ "gold": "tier3",
1061
+ "predicted": "tier3"
1062
+ },
1063
+ {
1064
+ "id": "h-long-dependency-conflict-2",
1065
+ "gold": "tier3",
1066
+ "predicted": "tier3"
1067
+ },
1068
+ {
1069
+ "id": "h-long-data-migration-script-1",
1070
+ "gold": "tier3",
1071
+ "predicted": "tier3"
1072
+ },
1073
+ {
1074
+ "id": "h-long-docs-overhaul-1",
1075
+ "gold": "tier3",
1076
+ "predicted": "tier3"
1077
+ },
1078
+ {
1079
+ "id": "h-long-docs-overhaul-2",
1080
+ "gold": "tier3",
1081
+ "predicted": "tier3"
1082
+ },
1083
+ {
1084
+ "id": "h-long-context-question-1",
1085
+ "gold": "tier1",
1086
+ "predicted": "tier2"
1087
+ },
1088
+ {
1089
+ "id": "h-long-context-question-2",
1090
+ "gold": "tier1",
1091
+ "predicted": "tier1"
1092
+ },
1093
+ {
1094
+ "id": "h-long-focused-review-1",
1095
+ "gold": "tier2",
1096
+ "predicted": "tier2"
1097
+ },
1098
+ {
1099
+ "id": "h-long-git-ops-1",
1100
+ "gold": "tier2",
1101
+ "predicted": "tier1"
1102
+ }
1103
+ ]
1104
+ }