@openpond/evals 0.11.21 → 0.12.1

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 (311) hide show
  1. package/README.md +12 -0
  2. package/dist/artifact-verification.js +2 -0
  3. package/dist/connected-evidence/codex-command-observations.js +81 -0
  4. package/dist/connected-evidence/contracts.js +13 -0
  5. package/dist/connected-evidence/git-file-contracts.js +16 -0
  6. package/dist/connected-evidence/git-file-proof.js +86 -0
  7. package/dist/connected-evidence/git-starting-state.js +81 -0
  8. package/dist/connected-evidence/git.js +2 -0
  9. package/dist/connected-evidence/imports.js +2 -1
  10. package/dist/connected-evidence/index.js +1 -0
  11. package/dist/connected-evidence/normalize.js +1 -0
  12. package/dist/connected-evidence/sources/claude-branches.js +34 -1
  13. package/dist/connected-evidence/sources/claude-code.js +1 -1
  14. package/dist/connected-evidence/sources/codex-metadata.js +33 -0
  15. package/dist/connected-evidence/sources/codex.js +16 -2
  16. package/dist/graders.js +10 -4
  17. package/dist/javascript-verifier.js +1 -0
  18. package/dist/native-conversations/codex-window-inventory.js +6 -7
  19. package/dist/native-conversations/collector-acquisition.js +17 -6
  20. package/dist/native-conversations/collector-source-cache.js +1 -1
  21. package/dist/native-conversations/collector-store.js +27 -2
  22. package/dist/native-conversations/collector.js +4 -3
  23. package/dist/native-conversations/git-assets.js +61 -0
  24. package/dist/native-conversations/history.js +7 -0
  25. package/dist/native-conversations/index.js +2 -0
  26. package/dist/native-conversations/selection.js +57 -0
  27. package/dist/native-conversations/supervisor.js +2 -0
  28. package/dist/prepared-process-isolation.js +131 -0
  29. package/dist/rewards.js +17 -5
  30. package/dist/tasksets.js +7 -0
  31. package/dist/types/artifact-verification.d.ts.map +1 -1
  32. package/dist/types/benchmarks.d.ts +22 -22
  33. package/dist/types/benchmarks.d.ts.map +1 -1
  34. package/dist/types/builtin-benchmarks/harness-refiner.d.ts +40 -35
  35. package/dist/types/builtin-benchmarks/harness-refiner.d.ts.map +1 -1
  36. package/dist/types/compatibility.d.ts.map +1 -1
  37. package/dist/types/conformance.d.ts +98 -88
  38. package/dist/types/conformance.d.ts.map +1 -1
  39. package/dist/types/connected-evidence/codex-command-observations.d.ts +15 -0
  40. package/dist/types/connected-evidence/codex-command-observations.d.ts.map +1 -0
  41. package/dist/types/connected-evidence/collector-coverage-contracts.d.ts +6 -6
  42. package/dist/types/connected-evidence/collector-coverage-contracts.d.ts.map +1 -1
  43. package/dist/types/connected-evidence/contracts.d.ts +80 -58
  44. package/dist/types/connected-evidence/contracts.d.ts.map +1 -1
  45. package/dist/types/connected-evidence/git-file-contracts.d.ts +18 -0
  46. package/dist/types/connected-evidence/git-file-contracts.d.ts.map +1 -0
  47. package/dist/types/connected-evidence/git-file-proof.d.ts +13 -0
  48. package/dist/types/connected-evidence/git-file-proof.d.ts.map +1 -0
  49. package/dist/types/connected-evidence/git-starting-state.d.ts +28 -0
  50. package/dist/types/connected-evidence/git-starting-state.d.ts.map +1 -0
  51. package/dist/types/connected-evidence/git.d.ts +3 -0
  52. package/dist/types/connected-evidence/git.d.ts.map +1 -0
  53. package/dist/types/connected-evidence/imports.d.ts.map +1 -1
  54. package/dist/types/connected-evidence/index.d.ts +1 -0
  55. package/dist/types/connected-evidence/index.d.ts.map +1 -1
  56. package/dist/types/connected-evidence/normalize.d.ts +1 -0
  57. package/dist/types/connected-evidence/normalize.d.ts.map +1 -1
  58. package/dist/types/connected-evidence/python-correctness.d.ts +38 -38
  59. package/dist/types/connected-evidence/python-correctness.d.ts.map +1 -1
  60. package/dist/types/connected-evidence/sources/claude-branches.d.ts +1 -0
  61. package/dist/types/connected-evidence/sources/claude-branches.d.ts.map +1 -1
  62. package/dist/types/connected-evidence/sources/claude-code.d.ts +25 -15
  63. package/dist/types/connected-evidence/sources/claude-code.d.ts.map +1 -1
  64. package/dist/types/connected-evidence/sources/codex-authorization.d.ts.map +1 -1
  65. package/dist/types/connected-evidence/sources/codex-metadata.d.ts +10 -0
  66. package/dist/types/connected-evidence/sources/codex-metadata.d.ts.map +1 -0
  67. package/dist/types/connected-evidence/sources/codex.d.ts +25 -15
  68. package/dist/types/connected-evidence/sources/codex.d.ts.map +1 -1
  69. package/dist/types/connected-evidence/sources/grok-build.d.ts +25 -15
  70. package/dist/types/connected-evidence/sources/grok-build.d.ts.map +1 -1
  71. package/dist/types/connected-evidence/sources/history.d.ts +50 -30
  72. package/dist/types/connected-evidence/sources/history.d.ts.map +1 -1
  73. package/dist/types/connected-evidence/sources/opencode.d.ts +25 -15
  74. package/dist/types/connected-evidence/sources/opencode.d.ts.map +1 -1
  75. package/dist/types/connected-evidence/sources/pi.d.ts +25 -15
  76. package/dist/types/connected-evidence/sources/pi.d.ts.map +1 -1
  77. package/dist/types/connected-evidence/sources/usage.d.ts.map +1 -1
  78. package/dist/types/connected-evidence/usage-summary.d.ts.map +1 -1
  79. package/dist/types/deterministic-graders.d.ts.map +1 -1
  80. package/dist/types/environment-execution-services-contract.d.ts +19 -19
  81. package/dist/types/environment-execution-services-contract.d.ts.map +1 -1
  82. package/dist/types/environment-execution-services.d.ts.map +1 -1
  83. package/dist/types/evidence/authoring.d.ts.map +1 -1
  84. package/dist/types/evidence/conformance.d.ts +98 -98
  85. package/dist/types/evidence/conformance.d.ts.map +1 -1
  86. package/dist/types/evidence/contracts.d.ts +183 -183
  87. package/dist/types/evidence/contracts.d.ts.map +1 -1
  88. package/dist/types/evidence/eligibility.d.ts +160 -160
  89. package/dist/types/evidence/eligibility.d.ts.map +1 -1
  90. package/dist/types/evidence/index.d.ts.map +1 -1
  91. package/dist/types/execution-contracts.d.ts +118 -110
  92. package/dist/types/execution-contracts.d.ts.map +1 -1
  93. package/dist/types/execution-receipts.d.ts.map +1 -1
  94. package/dist/types/experiments.d.ts +96 -96
  95. package/dist/types/experiments.d.ts.map +1 -1
  96. package/dist/types/graders.d.ts +38 -35
  97. package/dist/types/graders.d.ts.map +1 -1
  98. package/dist/types/harness-experiment-source.d.ts.map +1 -1
  99. package/dist/types/harness.d.ts.map +1 -1
  100. package/dist/types/human-review/comparison.d.ts +189 -189
  101. package/dist/types/human-review/comparison.d.ts.map +1 -1
  102. package/dist/types/human-review/contracts.d.ts +178 -178
  103. package/dist/types/human-review/contracts.d.ts.map +1 -1
  104. package/dist/types/human-review/execution.d.ts +53 -53
  105. package/dist/types/human-review/execution.d.ts.map +1 -1
  106. package/dist/types/human-review/handoff.d.ts +43 -43
  107. package/dist/types/human-review/handoff.d.ts.map +1 -1
  108. package/dist/types/human-review/index.d.ts.map +1 -1
  109. package/dist/types/human-review/local-publication.d.ts +4 -4
  110. package/dist/types/human-review/local-publication.d.ts.map +1 -1
  111. package/dist/types/human-review/repository.d.ts.map +1 -1
  112. package/dist/types/human-review/results.d.ts +8 -8
  113. package/dist/types/human-review/results.d.ts.map +1 -1
  114. package/dist/types/human-review/service.d.ts +292 -292
  115. package/dist/types/human-review/service.d.ts.map +1 -1
  116. package/dist/types/human-review/task-proposals.d.ts +2 -2
  117. package/dist/types/human-review/task-proposals.d.ts.map +1 -1
  118. package/dist/types/index.d.ts.map +1 -1
  119. package/dist/types/javascript-environment-attempt.d.ts.map +1 -1
  120. package/dist/types/javascript-environment-contract.d.ts +39 -39
  121. package/dist/types/javascript-environment-contract.d.ts.map +1 -1
  122. package/dist/types/javascript-environment-node.d.ts.map +1 -1
  123. package/dist/types/javascript-environment.d.ts +14 -14
  124. package/dist/types/javascript-environment.d.ts.map +1 -1
  125. package/dist/types/javascript-isolate-node.d.ts.map +1 -1
  126. package/dist/types/javascript-isolate-process-entry.d.ts.map +1 -1
  127. package/dist/types/javascript-isolate-process.d.ts.map +1 -1
  128. package/dist/types/javascript-isolate.d.ts.map +1 -1
  129. package/dist/types/javascript-verifier-contract.d.ts.map +1 -1
  130. package/dist/types/javascript-verifier-node.d.ts.map +1 -1
  131. package/dist/types/javascript-verifier-worker.d.ts.map +1 -1
  132. package/dist/types/javascript-verifier.d.ts +1 -0
  133. package/dist/types/javascript-verifier.d.ts.map +1 -1
  134. package/dist/types/learned-preference.d.ts +10 -10
  135. package/dist/types/learned-preference.d.ts.map +1 -1
  136. package/dist/types/learning/acceptance-group.d.ts +44 -44
  137. package/dist/types/learning/acceptance-group.d.ts.map +1 -1
  138. package/dist/types/learning/acceptance-plan.d.ts +8 -8
  139. package/dist/types/learning/acceptance-plan.d.ts.map +1 -1
  140. package/dist/types/learning/admission.d.ts +38 -36
  141. package/dist/types/learning/admission.d.ts.map +1 -1
  142. package/dist/types/learning/assets.d.ts +2 -2
  143. package/dist/types/learning/assets.d.ts.map +1 -1
  144. package/dist/types/learning/authoring-service.d.ts +11 -9
  145. package/dist/types/learning/authoring-service.d.ts.map +1 -1
  146. package/dist/types/learning/authoring.d.ts +46 -38
  147. package/dist/types/learning/authoring.d.ts.map +1 -1
  148. package/dist/types/learning/batch-service.d.ts +75 -68
  149. package/dist/types/learning/batch-service.d.ts.map +1 -1
  150. package/dist/types/learning/budgeted-reward-fixtures.d.ts.map +1 -1
  151. package/dist/types/learning/contracts.d.ts +314 -290
  152. package/dist/types/learning/contracts.d.ts.map +1 -1
  153. package/dist/types/learning/errors.d.ts.map +1 -1
  154. package/dist/types/learning/grade-judge-budget.d.ts.map +1 -1
  155. package/dist/types/learning/grade-worker.d.ts.map +1 -1
  156. package/dist/types/learning/index.d.ts.map +1 -1
  157. package/dist/types/learning/intake-contracts.d.ts +10 -10
  158. package/dist/types/learning/intake-contracts.d.ts.map +1 -1
  159. package/dist/types/learning/intake-csv.d.ts.map +1 -1
  160. package/dist/types/learning/intake-history.d.ts.map +1 -1
  161. package/dist/types/learning/intake-service.d.ts.map +1 -1
  162. package/dist/types/learning/intake-text.d.ts.map +1 -1
  163. package/dist/types/learning/intake.d.ts.map +1 -1
  164. package/dist/types/learning/iteration-budget.d.ts.map +1 -1
  165. package/dist/types/learning/iteration-candidate-decision.d.ts +16 -16
  166. package/dist/types/learning/iteration-candidate-decision.d.ts.map +1 -1
  167. package/dist/types/learning/iteration-dispatch-commands.d.ts.map +1 -1
  168. package/dist/types/learning/iteration-dispatch-contracts.d.ts +4 -4
  169. package/dist/types/learning/iteration-dispatch-contracts.d.ts.map +1 -1
  170. package/dist/types/learning/iteration-dispatch-worker.d.ts.map +1 -1
  171. package/dist/types/learning/iteration-eligibility.d.ts +1 -1
  172. package/dist/types/learning/iteration-eligibility.d.ts.map +1 -1
  173. package/dist/types/learning/iteration-reservation-cancellation.d.ts.map +1 -1
  174. package/dist/types/learning/iteration-reservation-contracts.d.ts.map +1 -1
  175. package/dist/types/learning/iteration-reservation-service.d.ts.map +1 -1
  176. package/dist/types/learning/iteration-training-parent.d.ts.map +1 -1
  177. package/dist/types/learning/judge-budget.d.ts +1 -1
  178. package/dist/types/learning/judge-budget.d.ts.map +1 -1
  179. package/dist/types/learning/model-judge.d.ts.map +1 -1
  180. package/dist/types/learning/nightly-schedule.d.ts.map +1 -1
  181. package/dist/types/learning/operations.d.ts +312 -298
  182. package/dist/types/learning/operations.d.ts.map +1 -1
  183. package/dist/types/learning/policy-inspection.d.ts.map +1 -1
  184. package/dist/types/learning/rating-reward-fixture.d.ts.map +1 -1
  185. package/dist/types/learning/repository.d.ts +197 -180
  186. package/dist/types/learning/repository.d.ts.map +1 -1
  187. package/dist/types/learning/reward-authoring.d.ts.map +1 -1
  188. package/dist/types/learning/reward-calibration-closure.d.ts +252 -244
  189. package/dist/types/learning/reward-calibration-closure.d.ts.map +1 -1
  190. package/dist/types/learning/reward-calibration.d.ts +62 -62
  191. package/dist/types/learning/reward-calibration.d.ts.map +1 -1
  192. package/dist/types/learning/reward-check-budget.d.ts.map +1 -1
  193. package/dist/types/learning/reward-check-service.d.ts.map +1 -1
  194. package/dist/types/learning/reward-check-worker.d.ts.map +1 -1
  195. package/dist/types/learning/reward-checks.d.ts +30 -28
  196. package/dist/types/learning/reward-checks.d.ts.map +1 -1
  197. package/dist/types/learning/reward-fixture-executor.d.ts.map +1 -1
  198. package/dist/types/learning/schedule-contracts.d.ts +3 -3
  199. package/dist/types/learning/schedule-contracts.d.ts.map +1 -1
  200. package/dist/types/learning/schedule-service.d.ts +2 -2
  201. package/dist/types/learning/schedule-service.d.ts.map +1 -1
  202. package/dist/types/learning/schedule-worker.d.ts.map +1 -1
  203. package/dist/types/learning/service.d.ts +3 -3
  204. package/dist/types/learning/service.d.ts.map +1 -1
  205. package/dist/types/learning/task-queue-inspection.d.ts.map +1 -1
  206. package/dist/types/learning/training-handoff.d.ts +9 -9
  207. package/dist/types/learning/training-handoff.d.ts.map +1 -1
  208. package/dist/types/learning/transport.d.ts +2203 -2179
  209. package/dist/types/learning/transport.d.ts.map +1 -1
  210. package/dist/types/metric-policy.d.ts +6 -6
  211. package/dist/types/metric-policy.d.ts.map +1 -1
  212. package/dist/types/metrics-node.d.ts.map +1 -1
  213. package/dist/types/metrics.d.ts.map +1 -1
  214. package/dist/types/model-improvement-qualification.d.ts +17 -17
  215. package/dist/types/model-improvement-qualification.d.ts.map +1 -1
  216. package/dist/types/native-conversations/appimage-runtime.d.ts.map +1 -1
  217. package/dist/types/native-conversations/codex-window-inventory.d.ts.map +1 -1
  218. package/dist/types/native-conversations/collector-acquisition.d.ts.map +1 -1
  219. package/dist/types/native-conversations/collector-branches.d.ts.map +1 -1
  220. package/dist/types/native-conversations/collector-calendar-gate.d.ts.map +1 -1
  221. package/dist/types/native-conversations/collector-contracts.d.ts +3 -0
  222. package/dist/types/native-conversations/collector-contracts.d.ts.map +1 -1
  223. package/dist/types/native-conversations/collector-coverage.d.ts +2 -2
  224. package/dist/types/native-conversations/collector-coverage.d.ts.map +1 -1
  225. package/dist/types/native-conversations/collector-cron.d.ts.map +1 -1
  226. package/dist/types/native-conversations/collector-destinations.d.ts.map +1 -1
  227. package/dist/types/native-conversations/collector-errors.d.ts.map +1 -1
  228. package/dist/types/native-conversations/collector-progress.d.ts.map +1 -1
  229. package/dist/types/native-conversations/collector-schedule.d.ts.map +1 -1
  230. package/dist/types/native-conversations/collector-service-files.d.ts.map +1 -1
  231. package/dist/types/native-conversations/collector-snapshots.d.ts.map +1 -1
  232. package/dist/types/native-conversations/collector-source-cache.d.ts +2 -2
  233. package/dist/types/native-conversations/collector-source-cache.d.ts.map +1 -1
  234. package/dist/types/native-conversations/collector-store.d.ts.map +1 -1
  235. package/dist/types/native-conversations/collector-sync-requests.d.ts.map +1 -1
  236. package/dist/types/native-conversations/collector.d.ts.map +1 -1
  237. package/dist/types/native-conversations/contracts.d.ts.map +1 -1
  238. package/dist/types/native-conversations/database.d.ts.map +1 -1
  239. package/dist/types/native-conversations/discovery.d.ts.map +1 -1
  240. package/dist/types/native-conversations/git-assets.d.ts +32 -0
  241. package/dist/types/native-conversations/git-assets.d.ts.map +1 -0
  242. package/dist/types/native-conversations/history.d.ts +1 -0
  243. package/dist/types/native-conversations/history.d.ts.map +1 -1
  244. package/dist/types/native-conversations/index.d.ts +2 -0
  245. package/dist/types/native-conversations/index.d.ts.map +1 -1
  246. package/dist/types/native-conversations/location.d.ts.map +1 -1
  247. package/dist/types/native-conversations/openclaw-cold-archive.d.ts.map +1 -1
  248. package/dist/types/native-conversations/openclaw-database.d.ts.map +1 -1
  249. package/dist/types/native-conversations/readiness.d.ts.map +1 -1
  250. package/dist/types/native-conversations/selection.d.ts +32 -0
  251. package/dist/types/native-conversations/selection.d.ts.map +1 -0
  252. package/dist/types/native-conversations/source-locations.d.ts.map +1 -1
  253. package/dist/types/native-conversations/supervisor.d.ts.map +1 -1
  254. package/dist/types/native-conversations/titles.d.ts.map +1 -1
  255. package/dist/types/native-harness-experiment-attempt.d.ts.map +1 -1
  256. package/dist/types/preferences.d.ts +22 -22
  257. package/dist/types/preferences.d.ts.map +1 -1
  258. package/dist/types/prepared-process-isolation.d.ts +5 -0
  259. package/dist/types/prepared-process-isolation.d.ts.map +1 -0
  260. package/dist/types/profile-evaluation-comparisons.d.ts +18 -18
  261. package/dist/types/profile-evaluation-comparisons.d.ts.map +1 -1
  262. package/dist/types/profile-evaluation-execution.d.ts.map +1 -1
  263. package/dist/types/profile-evaluation-reports.d.ts +2 -2
  264. package/dist/types/profile-evaluation-reports.d.ts.map +1 -1
  265. package/dist/types/profile-evaluation-suites.d.ts.map +1 -1
  266. package/dist/types/profile-evaluation-target.d.ts.map +1 -1
  267. package/dist/types/profile-evaluations.d.ts +15 -15
  268. package/dist/types/profile-evaluations.d.ts.map +1 -1
  269. package/dist/types/profile-external-evaluation.d.ts +84 -84
  270. package/dist/types/profile-external-evaluation.d.ts.map +1 -1
  271. package/dist/types/profile-source-candidate.d.ts.map +1 -1
  272. package/dist/types/review-conformance.d.ts +58 -58
  273. package/dist/types/review-conformance.d.ts.map +1 -1
  274. package/dist/types/rewards.d.ts +110 -101
  275. package/dist/types/rewards.d.ts.map +1 -1
  276. package/dist/types/rollouts.d.ts +16 -16
  277. package/dist/types/rollouts.d.ts.map +1 -1
  278. package/dist/types/runs.d.ts +22 -22
  279. package/dist/types/runs.d.ts.map +1 -1
  280. package/dist/types/sql-execution-contract.d.ts +3 -3
  281. package/dist/types/sql-execution-contract.d.ts.map +1 -1
  282. package/dist/types/sql-execution-engine.d.ts.map +1 -1
  283. package/dist/types/sql-execution-node.d.ts.map +1 -1
  284. package/dist/types/sql-execution-process-entry.d.ts.map +1 -1
  285. package/dist/types/task-schema-validation.d.ts.map +1 -1
  286. package/dist/types/task-schema.d.ts.map +1 -1
  287. package/dist/types/task-value-validator.d.ts.map +1 -1
  288. package/dist/types/taskset-run-contract.d.ts +26 -26
  289. package/dist/types/taskset-run-contract.d.ts.map +1 -1
  290. package/dist/types/tasksets.d.ts +89 -69
  291. package/dist/types/tasksets.d.ts.map +1 -1
  292. package/dist/types/telemetry/index.d.ts.map +1 -1
  293. package/dist/types/telemetry-analysis.d.ts +6 -6
  294. package/dist/types/telemetry-analysis.d.ts.map +1 -1
  295. package/dist/types/telemetry-bundle.d.ts +42 -42
  296. package/dist/types/telemetry-bundle.d.ts.map +1 -1
  297. package/dist/types/telemetry-catalog.d.ts +67 -67
  298. package/dist/types/telemetry-catalog.d.ts.map +1 -1
  299. package/dist/types/telemetry.d.ts +44 -44
  300. package/dist/types/telemetry.d.ts.map +1 -1
  301. package/package.json +6 -1
  302. package/schemas/learning/v1/binding.schema.json +8 -0
  303. package/schemas/learning/v1/command-request.schema.json +12 -0
  304. package/schemas/learning/v1/decision.schema.json +5 -1
  305. package/schemas/learning/v1/definition.schema.json +4 -0
  306. package/schemas/learning/v1/draft.schema.json +8 -0
  307. package/schemas/learning/v1/evidence.schema.json +4 -0
  308. package/schemas/learning/v1/example-submission.schema.json +4 -0
  309. package/schemas/learning/v1/grade.schema.json +5 -1
  310. package/schemas/learning/v1/package.schema.json +117 -93
  311. package/schemas/learning/v1/reward_check.schema.json +2 -1
@@ -184,22 +184,22 @@
184
184
  "type": "object",
185
185
  "properties": {
186
186
  "schemaVersion": {
187
- "$ref": "#/$defs/__schema45"
187
+ "$ref": "#/$defs/__schema46"
188
188
  },
189
189
  "primaryMetric": {
190
- "$ref": "#/$defs/__schema46"
190
+ "$ref": "#/$defs/__schema47"
191
191
  },
192
192
  "aggregation": {
193
- "$ref": "#/$defs/__schema47"
193
+ "$ref": "#/$defs/__schema48"
194
194
  },
195
195
  "missingReward": {
196
- "$ref": "#/$defs/__schema48"
196
+ "$ref": "#/$defs/__schema49"
197
197
  },
198
198
  "taskWeights": {
199
- "$ref": "#/$defs/__schema49"
199
+ "$ref": "#/$defs/__schema50"
200
200
  },
201
201
  "customAggregator": {
202
- "$ref": "#/$defs/__schema50"
202
+ "$ref": "#/$defs/__schema51"
203
203
  }
204
204
  },
205
205
  "required": [
@@ -500,6 +500,10 @@
500
500
  }
501
501
  ]
502
502
  },
503
+ "submissionMode": {
504
+ "type": "string",
505
+ "const": "structured_json"
506
+ },
503
507
  "maxBytes": {
504
508
  "default": null,
505
509
  "anyOf": [
@@ -542,21 +546,24 @@
542
546
  "id": {
543
547
  "$ref": "#/$defs/__schema0"
544
548
  },
545
- "version": {
549
+ "taskIds": {
546
550
  "$ref": "#/$defs/__schema11"
547
551
  },
548
- "weight": {
552
+ "version": {
549
553
  "$ref": "#/$defs/__schema12"
550
554
  },
551
- "hardGate": {
555
+ "weight": {
552
556
  "$ref": "#/$defs/__schema13"
553
557
  },
554
- "rewardEligible": {
558
+ "hardGate": {
555
559
  "$ref": "#/$defs/__schema14"
556
560
  },
557
- "privileged": {
561
+ "rewardEligible": {
558
562
  "$ref": "#/$defs/__schema15"
559
563
  },
564
+ "privileged": {
565
+ "$ref": "#/$defs/__schema16"
566
+ },
560
567
  "kind": {
561
568
  "type": "string",
562
569
  "enum": [
@@ -593,21 +600,24 @@
593
600
  "id": {
594
601
  "$ref": "#/$defs/__schema0"
595
602
  },
596
- "version": {
603
+ "taskIds": {
597
604
  "$ref": "#/$defs/__schema11"
598
605
  },
599
- "weight": {
606
+ "version": {
600
607
  "$ref": "#/$defs/__schema12"
601
608
  },
602
- "hardGate": {
609
+ "weight": {
603
610
  "$ref": "#/$defs/__schema13"
604
611
  },
605
- "rewardEligible": {
612
+ "hardGate": {
606
613
  "$ref": "#/$defs/__schema14"
607
614
  },
608
- "privileged": {
615
+ "rewardEligible": {
609
616
  "$ref": "#/$defs/__schema15"
610
617
  },
618
+ "privileged": {
619
+ "$ref": "#/$defs/__schema16"
620
+ },
611
621
  "kind": {
612
622
  "type": "string",
613
623
  "const": "model_judge"
@@ -677,21 +687,24 @@
677
687
  "id": {
678
688
  "$ref": "#/$defs/__schema0"
679
689
  },
680
- "version": {
690
+ "taskIds": {
681
691
  "$ref": "#/$defs/__schema11"
682
692
  },
683
- "weight": {
693
+ "version": {
684
694
  "$ref": "#/$defs/__schema12"
685
695
  },
686
- "hardGate": {
696
+ "weight": {
687
697
  "$ref": "#/$defs/__schema13"
688
698
  },
689
- "rewardEligible": {
699
+ "hardGate": {
690
700
  "$ref": "#/$defs/__schema14"
691
701
  },
692
- "privileged": {
702
+ "rewardEligible": {
693
703
  "$ref": "#/$defs/__schema15"
694
704
  },
705
+ "privileged": {
706
+ "$ref": "#/$defs/__schema16"
707
+ },
695
708
  "kind": {
696
709
  "type": "string",
697
710
  "const": "custom_verifier"
@@ -741,21 +754,24 @@
741
754
  "id": {
742
755
  "$ref": "#/$defs/__schema0"
743
756
  },
744
- "version": {
757
+ "taskIds": {
745
758
  "$ref": "#/$defs/__schema11"
746
759
  },
747
- "weight": {
760
+ "version": {
748
761
  "$ref": "#/$defs/__schema12"
749
762
  },
750
- "hardGate": {
763
+ "weight": {
751
764
  "$ref": "#/$defs/__schema13"
752
765
  },
753
- "rewardEligible": {
766
+ "hardGate": {
754
767
  "$ref": "#/$defs/__schema14"
755
768
  },
756
- "privileged": {
769
+ "rewardEligible": {
757
770
  "$ref": "#/$defs/__schema15"
758
771
  },
772
+ "privileged": {
773
+ "$ref": "#/$defs/__schema16"
774
+ },
759
775
  "kind": {
760
776
  "type": "string",
761
777
  "const": "human"
@@ -772,16 +788,16 @@
772
788
  "type": "object",
773
789
  "properties": {
774
790
  "schemaVersion": {
775
- "$ref": "#/$defs/__schema16"
791
+ "$ref": "#/$defs/__schema17"
776
792
  },
777
793
  "mode": {
778
- "$ref": "#/$defs/__schema17"
794
+ "$ref": "#/$defs/__schema18"
779
795
  },
780
796
  "instructions": {
781
- "$ref": "#/$defs/__schema18"
797
+ "$ref": "#/$defs/__schema19"
782
798
  },
783
799
  "criteria": {
784
- "$ref": "#/$defs/__schema19"
800
+ "$ref": "#/$defs/__schema20"
785
801
  }
786
802
  },
787
803
  "required": [
@@ -809,20 +825,24 @@
809
825
  ]
810
826
  },
811
827
  "__schema11": {
828
+ "minItems": 1,
829
+ "maxItems": 10000,
830
+ "type": "array",
831
+ "items": {
832
+ "$ref": "#/$defs/__schema0"
833
+ }
834
+ },
835
+ "__schema12": {
812
836
  "type": "string",
813
837
  "minLength": 1,
814
838
  "maxLength": 100
815
839
  },
816
- "__schema12": {
840
+ "__schema13": {
817
841
  "default": 1,
818
842
  "type": "number",
819
843
  "minimum": 0,
820
844
  "maximum": 1000
821
845
  },
822
- "__schema13": {
823
- "default": false,
824
- "type": "boolean"
825
- },
826
846
  "__schema14": {
827
847
  "default": false,
828
848
  "type": "boolean"
@@ -832,29 +852,33 @@
832
852
  "type": "boolean"
833
853
  },
834
854
  "__schema16": {
855
+ "default": false,
856
+ "type": "boolean"
857
+ },
858
+ "__schema17": {
835
859
  "type": "string",
836
860
  "const": "openpond.humanForm.v1"
837
861
  },
838
- "__schema17": {
862
+ "__schema18": {
839
863
  "type": "string",
840
864
  "enum": [
841
865
  "individual",
842
866
  "pairwise"
843
867
  ]
844
868
  },
845
- "__schema18": {
869
+ "__schema19": {
846
870
  "type": "string",
847
871
  "maxLength": 20000
848
872
  },
849
- "__schema19": {
873
+ "__schema20": {
850
874
  "minItems": 1,
851
875
  "maxItems": 100,
852
876
  "type": "array",
853
877
  "items": {
854
- "$ref": "#/$defs/__schema20"
878
+ "$ref": "#/$defs/__schema21"
855
879
  }
856
880
  },
857
- "__schema20": {
881
+ "__schema21": {
858
882
  "oneOf": [
859
883
  {
860
884
  "type": "object",
@@ -863,34 +887,34 @@
863
887
  "$ref": "#/$defs/__schema0"
864
888
  },
865
889
  "label": {
866
- "$ref": "#/$defs/__schema21"
890
+ "$ref": "#/$defs/__schema22"
867
891
  },
868
892
  "instructions": {
869
- "$ref": "#/$defs/__schema22"
893
+ "$ref": "#/$defs/__schema23"
870
894
  },
871
895
  "required": {
872
- "$ref": "#/$defs/__schema23"
896
+ "$ref": "#/$defs/__schema24"
873
897
  },
874
898
  "allowAbstain": {
875
- "$ref": "#/$defs/__schema24"
899
+ "$ref": "#/$defs/__schema25"
876
900
  },
877
901
  "requireRationale": {
878
- "$ref": "#/$defs/__schema25"
902
+ "$ref": "#/$defs/__schema26"
879
903
  },
880
904
  "anchors": {
881
- "$ref": "#/$defs/__schema26"
905
+ "$ref": "#/$defs/__schema27"
882
906
  },
883
907
  "kind": {
884
- "$ref": "#/$defs/__schema28"
908
+ "$ref": "#/$defs/__schema29"
885
909
  },
886
910
  "minimum": {
887
- "$ref": "#/$defs/__schema29"
911
+ "$ref": "#/$defs/__schema30"
888
912
  },
889
913
  "maximum": {
890
- "$ref": "#/$defs/__schema30"
914
+ "$ref": "#/$defs/__schema31"
891
915
  },
892
916
  "step": {
893
- "$ref": "#/$defs/__schema31"
917
+ "$ref": "#/$defs/__schema32"
894
918
  }
895
919
  },
896
920
  "required": [
@@ -913,28 +937,28 @@
913
937
  "$ref": "#/$defs/__schema0"
914
938
  },
915
939
  "label": {
916
- "$ref": "#/$defs/__schema32"
940
+ "$ref": "#/$defs/__schema33"
917
941
  },
918
942
  "instructions": {
919
- "$ref": "#/$defs/__schema33"
943
+ "$ref": "#/$defs/__schema34"
920
944
  },
921
945
  "required": {
922
- "$ref": "#/$defs/__schema34"
946
+ "$ref": "#/$defs/__schema35"
923
947
  },
924
948
  "allowAbstain": {
925
- "$ref": "#/$defs/__schema35"
949
+ "$ref": "#/$defs/__schema36"
926
950
  },
927
951
  "requireRationale": {
928
- "$ref": "#/$defs/__schema36"
952
+ "$ref": "#/$defs/__schema37"
929
953
  },
930
954
  "anchors": {
931
- "$ref": "#/$defs/__schema37"
955
+ "$ref": "#/$defs/__schema38"
932
956
  },
933
957
  "kind": {
934
- "$ref": "#/$defs/__schema39"
958
+ "$ref": "#/$defs/__schema40"
935
959
  },
936
960
  "options": {
937
- "$ref": "#/$defs/__schema40"
961
+ "$ref": "#/$defs/__schema41"
938
962
  }
939
963
  },
940
964
  "required": [
@@ -976,7 +1000,7 @@
976
1000
  "maxItems": 100,
977
1001
  "type": "array",
978
1002
  "items": {
979
- "$ref": "#/$defs/__schema42"
1003
+ "$ref": "#/$defs/__schema43"
980
1004
  }
981
1005
  },
982
1006
  "kind": {
@@ -1022,7 +1046,7 @@
1022
1046
  "maxItems": 100,
1023
1047
  "type": "array",
1024
1048
  "items": {
1025
- "$ref": "#/$defs/__schema43"
1049
+ "$ref": "#/$defs/__schema44"
1026
1050
  }
1027
1051
  },
1028
1052
  "kind": {
@@ -1079,7 +1103,7 @@
1079
1103
  "maxItems": 100,
1080
1104
  "type": "array",
1081
1105
  "items": {
1082
- "$ref": "#/$defs/__schema44"
1106
+ "$ref": "#/$defs/__schema45"
1083
1107
  }
1084
1108
  },
1085
1109
  "kind": {
@@ -1106,18 +1130,15 @@
1106
1130
  }
1107
1131
  ]
1108
1132
  },
1109
- "__schema21": {
1133
+ "__schema22": {
1110
1134
  "type": "string",
1111
1135
  "minLength": 1,
1112
1136
  "maxLength": 500
1113
1137
  },
1114
- "__schema22": {
1138
+ "__schema23": {
1115
1139
  "type": "string",
1116
1140
  "maxLength": 20000
1117
1141
  },
1118
- "__schema23": {
1119
- "type": "boolean"
1120
- },
1121
1142
  "__schema24": {
1122
1143
  "type": "boolean"
1123
1144
  },
@@ -1125,13 +1146,16 @@
1125
1146
  "type": "boolean"
1126
1147
  },
1127
1148
  "__schema26": {
1149
+ "type": "boolean"
1150
+ },
1151
+ "__schema27": {
1128
1152
  "maxItems": 100,
1129
1153
  "type": "array",
1130
1154
  "items": {
1131
- "$ref": "#/$defs/__schema27"
1155
+ "$ref": "#/$defs/__schema28"
1132
1156
  }
1133
1157
  },
1134
- "__schema27": {
1158
+ "__schema28": {
1135
1159
  "type": "object",
1136
1160
  "properties": {
1137
1161
  "value": {
@@ -1159,32 +1183,29 @@
1159
1183
  ],
1160
1184
  "additionalProperties": false
1161
1185
  },
1162
- "__schema28": {
1186
+ "__schema29": {
1163
1187
  "type": "string",
1164
1188
  "const": "score"
1165
1189
  },
1166
- "__schema29": {
1167
- "type": "number"
1168
- },
1169
1190
  "__schema30": {
1170
1191
  "type": "number"
1171
1192
  },
1172
1193
  "__schema31": {
1194
+ "type": "number"
1195
+ },
1196
+ "__schema32": {
1173
1197
  "type": "number",
1174
1198
  "exclusiveMinimum": 0
1175
1199
  },
1176
- "__schema32": {
1200
+ "__schema33": {
1177
1201
  "type": "string",
1178
1202
  "minLength": 1,
1179
1203
  "maxLength": 500
1180
1204
  },
1181
- "__schema33": {
1205
+ "__schema34": {
1182
1206
  "type": "string",
1183
1207
  "maxLength": 20000
1184
1208
  },
1185
- "__schema34": {
1186
- "type": "boolean"
1187
- },
1188
1209
  "__schema35": {
1189
1210
  "type": "boolean"
1190
1211
  },
@@ -1192,13 +1213,16 @@
1192
1213
  "type": "boolean"
1193
1214
  },
1194
1215
  "__schema37": {
1216
+ "type": "boolean"
1217
+ },
1218
+ "__schema38": {
1195
1219
  "maxItems": 100,
1196
1220
  "type": "array",
1197
1221
  "items": {
1198
- "$ref": "#/$defs/__schema38"
1222
+ "$ref": "#/$defs/__schema39"
1199
1223
  }
1200
1224
  },
1201
- "__schema38": {
1225
+ "__schema39": {
1202
1226
  "type": "object",
1203
1227
  "properties": {
1204
1228
  "value": {
@@ -1226,24 +1250,24 @@
1226
1250
  ],
1227
1251
  "additionalProperties": false
1228
1252
  },
1229
- "__schema39": {
1253
+ "__schema40": {
1230
1254
  "type": "string",
1231
1255
  "const": "category"
1232
1256
  },
1233
- "__schema40": {
1257
+ "__schema41": {
1234
1258
  "minItems": 2,
1235
1259
  "maxItems": 100,
1236
1260
  "type": "array",
1237
1261
  "items": {
1238
- "$ref": "#/$defs/__schema41"
1262
+ "$ref": "#/$defs/__schema42"
1239
1263
  }
1240
1264
  },
1241
- "__schema41": {
1265
+ "__schema42": {
1242
1266
  "type": "string",
1243
1267
  "minLength": 1,
1244
1268
  "maxLength": 500
1245
1269
  },
1246
- "__schema42": {
1270
+ "__schema43": {
1247
1271
  "type": "object",
1248
1272
  "properties": {
1249
1273
  "value": {
@@ -1271,7 +1295,7 @@
1271
1295
  ],
1272
1296
  "additionalProperties": false
1273
1297
  },
1274
- "__schema43": {
1298
+ "__schema44": {
1275
1299
  "type": "object",
1276
1300
  "properties": {
1277
1301
  "value": {
@@ -1299,7 +1323,7 @@
1299
1323
  ],
1300
1324
  "additionalProperties": false
1301
1325
  },
1302
- "__schema44": {
1326
+ "__schema45": {
1303
1327
  "type": "object",
1304
1328
  "properties": {
1305
1329
  "value": {
@@ -1327,16 +1351,16 @@
1327
1351
  ],
1328
1352
  "additionalProperties": false
1329
1353
  },
1330
- "__schema45": {
1354
+ "__schema46": {
1331
1355
  "type": "string",
1332
1356
  "const": "openpond.tasksetMetricPolicy.v1"
1333
1357
  },
1334
- "__schema46": {
1358
+ "__schema47": {
1335
1359
  "type": "string",
1336
1360
  "minLength": 1,
1337
1361
  "maxLength": 240
1338
1362
  },
1339
- "__schema47": {
1363
+ "__schema48": {
1340
1364
  "type": "string",
1341
1365
  "enum": [
1342
1366
  "mean_score",
@@ -1345,17 +1369,17 @@
1345
1369
  "custom"
1346
1370
  ]
1347
1371
  },
1348
- "__schema48": {
1372
+ "__schema49": {
1349
1373
  "type": "string",
1350
1374
  "enum": [
1351
1375
  "zero",
1352
1376
  "exclude"
1353
1377
  ]
1354
1378
  },
1355
- "__schema49": {
1379
+ "__schema50": {
1356
1380
  "type": "object",
1357
1381
  "propertyNames": {
1358
- "$ref": "#/$defs/__schema46"
1382
+ "$ref": "#/$defs/__schema47"
1359
1383
  },
1360
1384
  "additionalProperties": {
1361
1385
  "type": "number",
@@ -1363,7 +1387,7 @@
1363
1387
  "maximum": 1000000
1364
1388
  }
1365
1389
  },
1366
- "__schema50": {
1390
+ "__schema51": {
1367
1391
  "anyOf": [
1368
1392
  {
1369
1393
  "type": "object",
@@ -264,7 +264,8 @@
264
264
  "scored",
265
265
  "pending",
266
266
  "unavailable",
267
- "failed"
267
+ "failed",
268
+ "not_applicable"
268
269
  ]
269
270
  },
270
271
  "rawScore": {