evalrx 0.1.2__py3-none-any.whl

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 (339) hide show
  1. evalrx/__init__.py +139 -0
  2. evalrx/agent_assets/__init__.py +2 -0
  3. evalrx/agent_assets/skills/README.md +28 -0
  4. evalrx/agent_assets/skills/eval-chart-style/SKILL.md +172 -0
  5. evalrx/agent_assets/skills/evalrx-report-ui/SKILL.md +116 -0
  6. evalrx/agent_assets/skills/nature-figure/LICENSE +201 -0
  7. evalrx/agent_assets/skills/nature-figure/README.md +412 -0
  8. evalrx/agent_assets/skills/nature-figure/SKILL.md +60 -0
  9. evalrx/agent_assets/skills/nature-figure/manifest.yaml +59 -0
  10. evalrx/agent_assets/skills/nature-figure/references/api.md +436 -0
  11. evalrx/agent_assets/skills/nature-figure/references/backend-selection.md +100 -0
  12. evalrx/agent_assets/skills/nature-figure/references/chart-types.md +281 -0
  13. evalrx/agent_assets/skills/nature-figure/references/common-patterns.md +350 -0
  14. evalrx/agent_assets/skills/nature-figure/references/demos.md +65 -0
  15. evalrx/agent_assets/skills/nature-figure/references/design-theory.md +439 -0
  16. evalrx/agent_assets/skills/nature-figure/references/figure-contract.md +93 -0
  17. evalrx/agent_assets/skills/nature-figure/references/figure-legend-conventions.md +71 -0
  18. evalrx/agent_assets/skills/nature-figure/references/nature-2026-observations.md +112 -0
  19. evalrx/agent_assets/skills/nature-figure/references/qa-contract.md +119 -0
  20. evalrx/agent_assets/skills/nature-figure/references/r-template-index.md +66 -0
  21. evalrx/agent_assets/skills/nature-figure/references/r-workflow.md +161 -0
  22. evalrx/agent_assets/skills/nature-figure/references/tutorials.md +251 -0
  23. evalrx/agent_assets/skills/nature-figure/static/core/contract.md +29 -0
  24. evalrx/agent_assets/skills/nature-figure/static/core/stance.md +37 -0
  25. evalrx/agent_assets/skills/nature-figure/static/fragments/backend/python.md +37 -0
  26. evalrx/agent_assets/skills/nature-figure/static/fragments/backend/r.md +44 -0
  27. evalrx/agent_assets/skills/outcome-driver-analysis/SKILL.md +213 -0
  28. evalrx/agent_assets/skills/outcome-driver-analysis/assets/analysis_report_template.md +53 -0
  29. evalrx/agent_assets/skills/outcome-driver-analysis/references/model_selection.md +72 -0
  30. evalrx/agent_assets/skills/outcome-driver-analysis/scripts/explanatory_var_eda.R +130 -0
  31. evalrx/agent_assets/skills/outcome-driver-analysis/scripts/explanatory_var_eda.py +150 -0
  32. evalrx/agent_assets/skills/outcome-driver-analysis/scripts/fit_outcome_model.R +181 -0
  33. evalrx/agent_assets/skills/outcome-driver-analysis/scripts/fit_outcome_model.py +186 -0
  34. evalrx/agent_assets/skills/outcome-driver-analysis/scripts/univariate_eda.R +149 -0
  35. evalrx/agent_assets/skills/outcome-driver-analysis/scripts/univariate_eda.py +177 -0
  36. evalrx/agent_assets/skills.py +27 -0
  37. evalrx/agent_runtime/__init__.py +78 -0
  38. evalrx/agent_runtime/_docker_runner.py +89 -0
  39. evalrx/agent_runtime/cli_runtime.py +103 -0
  40. evalrx/agent_runtime/cli_transcript.py +138 -0
  41. evalrx/agent_runtime/cli_types.py +68 -0
  42. evalrx/agent_runtime/codegen/__init__.py +5 -0
  43. evalrx/agent_runtime/codegen/runner.py +94 -0
  44. evalrx/agent_runtime/experiment_harness.py +117 -0
  45. evalrx/agent_runtime/factory.py +102 -0
  46. evalrx/agent_runtime/json_shape.py +44 -0
  47. evalrx/agent_runtime/judges/__init__.py +28 -0
  48. evalrx/agent_runtime/judges/agy.py +179 -0
  49. evalrx/agent_runtime/judges/autodetect.py +135 -0
  50. evalrx/agent_runtime/judges/claude.py +159 -0
  51. evalrx/agent_runtime/judges/codex.py +120 -0
  52. evalrx/agent_runtime/providers/__init__.py +21 -0
  53. evalrx/agent_runtime/providers/antigravity.py +31 -0
  54. evalrx/agent_runtime/providers/base.py +145 -0
  55. evalrx/agent_runtime/providers/claude_code.py +49 -0
  56. evalrx/agent_runtime/providers/codex.py +37 -0
  57. evalrx/agent_runtime/providers/gemini_cli.py +26 -0
  58. evalrx/agent_runtime/providers/kimi_cli.py +27 -0
  59. evalrx/agent_runtime/providers/opencode.py +27 -0
  60. evalrx/agent_runtime/providers/registry.py +58 -0
  61. evalrx/agent_runtime/sandbox.py +517 -0
  62. evalrx/agent_runtime/skill_audit.py +143 -0
  63. evalrx/agent_runtime/skills/__init__.py +19 -0
  64. evalrx/agent_runtime/skills/installer.py +68 -0
  65. evalrx/agent_runtime/skills/prompt_policy.py +86 -0
  66. evalrx/agent_runtime/skills/resolver.py +19 -0
  67. evalrx/analysis/__init__.py +132 -0
  68. evalrx/analysis/adjudicate.py +154 -0
  69. evalrx/analysis/analysis_module.py +361 -0
  70. evalrx/analysis/api.py +171 -0
  71. evalrx/analysis/case_studio.py +651 -0
  72. evalrx/analysis/cli.py +114 -0
  73. evalrx/analysis/dashboard.py +350 -0
  74. evalrx/analysis/eval_case_matrix.py +118 -0
  75. evalrx/analysis/eval_viz_theme.py +833 -0
  76. evalrx/analysis/explore_run.py +333 -0
  77. evalrx/analysis/explorer.py +1276 -0
  78. evalrx/analysis/failure_modes.py +607 -0
  79. evalrx/analysis/fused_pipeline.py +489 -0
  80. evalrx/analysis/holdout.py +300 -0
  81. evalrx/analysis/hypothesis_agent.py +230 -0
  82. evalrx/analysis/narration.py +177 -0
  83. evalrx/analysis/operationalize.py +442 -0
  84. evalrx/analysis/plain_language.py +42 -0
  85. evalrx/analysis/planner.py +283 -0
  86. evalrx/analysis/probe_search.py +203 -0
  87. evalrx/analysis/profile.py +268 -0
  88. evalrx/analysis/prompts/__init__.py +0 -0
  89. evalrx/analysis/prompts/explorer.py +417 -0
  90. evalrx/analysis/prompts/failure_modes.py +33 -0
  91. evalrx/analysis/prompts/holdout.py +27 -0
  92. evalrx/analysis/prompts/hypothesis_agent.py +78 -0
  93. evalrx/analysis/prompts/run_codebase.py +47 -0
  94. evalrx/analysis/prompts/stats_agent.py +72 -0
  95. evalrx/analysis/prompts/stats_tool_generator.py +43 -0
  96. evalrx/analysis/result_marker.py +47 -0
  97. evalrx/analysis/run_codebase.py +242 -0
  98. evalrx/analysis/run_view.py +205 -0
  99. evalrx/analysis/stage_views.py +93 -0
  100. evalrx/analysis/stats_agent.py +944 -0
  101. evalrx/analysis/stats_tool_agent.py +261 -0
  102. evalrx/analysis/stats_tool_generator.py +415 -0
  103. evalrx/analysis/stats_tools.py +1153 -0
  104. evalrx/analysis/trajectory_records.py +193 -0
  105. evalrx/analysis/workbench.py +431 -0
  106. evalrx/analyzers/__init__.py +42 -0
  107. evalrx/analyzers/agent/__init__.py +25 -0
  108. evalrx/analyzers/agent/counterfactual.py +84 -0
  109. evalrx/analyzers/agent/first_error_judge.py +96 -0
  110. evalrx/analyzers/agent/ignored_obs.py +81 -0
  111. evalrx/analyzers/agent/loop_detect.py +79 -0
  112. evalrx/analyzers/agent/reliability.py +165 -0
  113. evalrx/analyzers/agent/tool_shap.py +225 -0
  114. evalrx/analyzers/agent/trajectory_rubric.py +168 -0
  115. evalrx/analyzers/attention/__init__.py +19 -0
  116. evalrx/analyzers/attention/relative_attn.py +610 -0
  117. evalrx/analyzers/attention/rollout.py +73 -0
  118. evalrx/analyzers/attention/sink.py +56 -0
  119. evalrx/analyzers/attention/summary.py +190 -0
  120. evalrx/analyzers/attribution/__init__.py +6 -0
  121. evalrx/analyzers/attribution/generic_attn.py +31 -0
  122. evalrx/analyzers/attribution/gradcam.py +30 -0
  123. evalrx/analyzers/base.py +12 -0
  124. evalrx/analyzers/geometry/__init__.py +6 -0
  125. evalrx/analyzers/geometry/cka.py +70 -0
  126. evalrx/analyzers/geometry/linear_probe.py +157 -0
  127. evalrx/analyzers/hallucination/__init__.py +9 -0
  128. evalrx/analyzers/hallucination/chair.py +78 -0
  129. evalrx/analyzers/hallucination/opera.py +29 -0
  130. evalrx/analyzers/hallucination/pope.py +119 -0
  131. evalrx/analyzers/hallucination/selfcheck.py +155 -0
  132. evalrx/analyzers/hallucination/vcd.py +29 -0
  133. evalrx/analyzers/lens/__init__.py +7 -0
  134. evalrx/analyzers/lens/layer_contrast.py +133 -0
  135. evalrx/analyzers/lens/logit_lens.py +138 -0
  136. evalrx/analyzers/lens/tuned_lens.py +30 -0
  137. evalrx/analyzers/patching/__init__.py +5 -0
  138. evalrx/analyzers/patching/causal_trace.py +30 -0
  139. evalrx/analyzers/perturbation/__init__.py +23 -0
  140. evalrx/analyzers/perturbation/_shapley.py +54 -0
  141. evalrx/analyzers/perturbation/context_shap.py +174 -0
  142. evalrx/analyzers/perturbation/cot_faithfulness.py +239 -0
  143. evalrx/analyzers/perturbation/format_sensitivity.py +237 -0
  144. evalrx/analyzers/perturbation/mm_shap.py +146 -0
  145. evalrx/analyzers/perturbation/modality_ablation.py +196 -0
  146. evalrx/analyzers/perturbation/perturbation_battery.py +274 -0
  147. evalrx/analyzers/perturbation/prompt_contrast.py +265 -0
  148. evalrx/analyzers/perturbation/rise.py +94 -0
  149. evalrx/analyzers/perturbation/vl_shap.py +102 -0
  150. evalrx/analyzers/reasoning/__init__.py +33 -0
  151. evalrx/analyzers/reasoning/_text.py +328 -0
  152. evalrx/analyzers/reasoning/answer_extraction_audit.py +327 -0
  153. evalrx/analyzers/reasoning/arith_audit.py +226 -0
  154. evalrx/analyzers/reasoning/contamination.py +214 -0
  155. evalrx/analyzers/reasoning/knowledge_split.py +253 -0
  156. evalrx/analyzers/reasoning/self_repair.py +246 -0
  157. evalrx/analyzers/reasoning/step_rollout_value.py +216 -0
  158. evalrx/analyzers/reasoning/termination_audit.py +258 -0
  159. evalrx/analyzers/uncertainty/__init__.py +18 -0
  160. evalrx/analyzers/uncertainty/calibration.py +174 -0
  161. evalrx/analyzers/uncertainty/coverage_gap.py +199 -0
  162. evalrx/analyzers/uncertainty/entropy.py +90 -0
  163. evalrx/analyzers/uncertainty/logprob_entropy.py +69 -0
  164. evalrx/analyzers/uncertainty/self_consistency.py +204 -0
  165. evalrx/analyzers/uncertainty/verbalized_conf.py +64 -0
  166. evalrx/cli.py +411 -0
  167. evalrx/config.py +77 -0
  168. evalrx/contract/__init__.py +179 -0
  169. evalrx/contract/common.py +452 -0
  170. evalrx/contract/emit.py +948 -0
  171. evalrx/contract/export.py +237 -0
  172. evalrx/contract/m1.py +325 -0
  173. evalrx/contract/m2.py +317 -0
  174. evalrx/contract/m3.py +165 -0
  175. evalrx/contract/m4.py +130 -0
  176. evalrx/contract/m5.py +292 -0
  177. evalrx/contract/methodology.py +76 -0
  178. evalrx/contract/pre_m1.py +58 -0
  179. evalrx/contract/typescript.py +140 -0
  180. evalrx/core/__init__.py +85 -0
  181. evalrx/core/analyzer.py +174 -0
  182. evalrx/core/capability.py +54 -0
  183. evalrx/core/case.py +443 -0
  184. evalrx/core/experiment.py +106 -0
  185. evalrx/core/model.py +198 -0
  186. evalrx/core/pipeline.py +42 -0
  187. evalrx/core/registry.py +142 -0
  188. evalrx/core/result.py +64 -0
  189. evalrx/core/spec.py +173 -0
  190. evalrx/core/tokentype.py +165 -0
  191. evalrx/core/tool.py +92 -0
  192. evalrx/datasets/__init__.py +41 -0
  193. evalrx/datasets/base.py +68 -0
  194. evalrx/datasets/gui_os.py +52 -0
  195. evalrx/datasets/llm_qa.py +57 -0
  196. evalrx/datasets/pure_qa.py +12 -0
  197. evalrx/datasets/vlm_qa.py +695 -0
  198. evalrx/datasets/web_search_qa.py +52 -0
  199. evalrx/eval_agent/__init__.py +341 -0
  200. evalrx/eval_agent/_tools.py +81 -0
  201. evalrx/eval_agent/ab_runner.py +50 -0
  202. evalrx/eval_agent/agentic/__init__.py +43 -0
  203. evalrx/eval_agent/agentic/actions.py +216 -0
  204. evalrx/eval_agent/agentic/board.py +107 -0
  205. evalrx/eval_agent/agentic/loop.py +190 -0
  206. evalrx/eval_agent/agentic/tools.py +538 -0
  207. evalrx/eval_agent/checkpoint.py +57 -0
  208. evalrx/eval_agent/cli_agent.py +59 -0
  209. evalrx/eval_agent/cli_skills.py +5 -0
  210. evalrx/eval_agent/evolution.py +396 -0
  211. evalrx/eval_agent/git_manager.py +215 -0
  212. evalrx/eval_agent/hypothesis.py +172 -0
  213. evalrx/eval_agent/label_quarantine.py +209 -0
  214. evalrx/eval_agent/legacy.py +530 -0
  215. evalrx/eval_agent/log_schema.py +497 -0
  216. evalrx/eval_agent/loop.py +2159 -0
  217. evalrx/eval_agent/loop_reports.py +116 -0
  218. evalrx/eval_agent/model_instrumentation.py +282 -0
  219. evalrx/eval_agent/narration.py +193 -0
  220. evalrx/eval_agent/nl_runner.py +460 -0
  221. evalrx/eval_agent/orchestrator.py +61 -0
  222. evalrx/eval_agent/preregister.py +93 -0
  223. evalrx/eval_agent/prompts/__init__.py +1 -0
  224. evalrx/eval_agent/prompts/agentic.py +46 -0
  225. evalrx/eval_agent/prompts/case_discovery.py +25 -0
  226. evalrx/eval_agent/prompts/diagnosis.py +125 -0
  227. evalrx/eval_agent/prompts/experiment_writer.py +265 -0
  228. evalrx/eval_agent/prompts/explore_step.py +37 -0
  229. evalrx/eval_agent/prompts/fix_agent.py +257 -0
  230. evalrx/eval_agent/prompts/hypothesis_tester.py +15 -0
  231. evalrx/eval_agent/prompts/nl_runner.py +38 -0
  232. evalrx/eval_agent/prompts/probe_agent.py +25 -0
  233. evalrx/eval_agent/prompts/probe_candidate_generator.py +14 -0
  234. evalrx/eval_agent/prompts/probe_generator.py +35 -0
  235. evalrx/eval_agent/prompts/whitebox_probe_generator.py +38 -0
  236. evalrx/eval_agent/report.py +58 -0
  237. evalrx/eval_agent/run_context.py +354 -0
  238. evalrx/eval_agent/run_log.schema.json +1215 -0
  239. evalrx/eval_agent/run_logger_v2.py +1764 -0
  240. evalrx/eval_agent/run_metadata.py +208 -0
  241. evalrx/eval_agent/stages/__init__.py +56 -0
  242. evalrx/eval_agent/stages/case_discovery.py +293 -0
  243. evalrx/eval_agent/stages/diagnosis.py +1017 -0
  244. evalrx/eval_agent/stages/experiment_writer.py +1634 -0
  245. evalrx/eval_agent/stages/fix_agent.py +3916 -0
  246. evalrx/eval_agent/stages/fix_internals.py +499 -0
  247. evalrx/eval_agent/stages/fix_pipeline.py +725 -0
  248. evalrx/eval_agent/stages/fix_tiers.py +187 -0
  249. evalrx/eval_agent/stages/fix_tools.py +1034 -0
  250. evalrx/eval_agent/stages/hypothesis_tester.py +1014 -0
  251. evalrx/eval_agent/stages/probe.py +439 -0
  252. evalrx/eval_agent/stages/probe_agent.py +1079 -0
  253. evalrx/eval_agent/stages/probe_candidate_generator.py +128 -0
  254. evalrx/eval_agent/stages/probe_generator.py +326 -0
  255. evalrx/eval_agent/stages/probe_search_agent.py +106 -0
  256. evalrx/eval_agent/stages/protocol.py +112 -0
  257. evalrx/eval_agent/stages/repair_catalog.py +273 -0
  258. evalrx/eval_agent/stages/surgery.py +524 -0
  259. evalrx/eval_agent/stages/whitebox_probe_generator.py +351 -0
  260. evalrx/eval_agent/store.py +231 -0
  261. evalrx/logging_utils.py +112 -0
  262. evalrx/models/__init__.py +161 -0
  263. evalrx/models/_discover.py +101 -0
  264. evalrx/models/agent.py +380 -0
  265. evalrx/models/backends/__init__.py +58 -0
  266. evalrx/models/backends/api.py +169 -0
  267. evalrx/models/backends/base.py +57 -0
  268. evalrx/models/backends/gemini_compat.py +579 -0
  269. evalrx/models/backends/hf_local.py +2074 -0
  270. evalrx/models/backends/openai_compat.py +301 -0
  271. evalrx/models/backends/vllm_offline.py +116 -0
  272. evalrx/models/base.py +24 -0
  273. evalrx/models/blackbox/__init__.py +4 -0
  274. evalrx/models/blackbox/agent.py +31 -0
  275. evalrx/models/blackbox/base.py +29 -0
  276. evalrx/models/blackbox/gemini.py +279 -0
  277. evalrx/models/blackbox/llm_api.py +17 -0
  278. evalrx/models/blackbox/vlm_api.py +17 -0
  279. evalrx/models/compose.py +66 -0
  280. evalrx/models/inference.py +88 -0
  281. evalrx/models/paper_methods/__init__.py +8 -0
  282. evalrx/models/paper_methods/aad.py +53 -0
  283. evalrx/models/paper_methods/ifcd.py +204 -0
  284. evalrx/models/paper_methods/pai.py +164 -0
  285. evalrx/models/paper_methods/tcd.py +202 -0
  286. evalrx/models/paper_methods/vcd.py +45 -0
  287. evalrx/models/paper_methods/vicrop.py +137 -0
  288. evalrx/models/toolcodec.py +143 -0
  289. evalrx/models/tools/__init__.py +20 -0
  290. evalrx/models/tools/perception.py +300 -0
  291. evalrx/models/tools/visual.py +174 -0
  292. evalrx/models/whitebox/__init__.py +26 -0
  293. evalrx/models/whitebox/agent.py +31 -0
  294. evalrx/models/whitebox/base.py +24 -0
  295. evalrx/models/whitebox/qwen.py +61 -0
  296. evalrx/models/whitebox/qwen2_5_omni.py +29 -0
  297. evalrx/models/whitebox/qwen2_audio.py +25 -0
  298. evalrx/models/whitebox/qwen_omni.py +53 -0
  299. evalrx/models/whitebox/qwen_vl.py +62 -0
  300. evalrx/observability/__init__.py +21 -0
  301. evalrx/observability/envelope.py +122 -0
  302. evalrx/observability/outbox.py +111 -0
  303. evalrx/observability/tracer.py +882 -0
  304. evalrx/reporting/__init__.py +28 -0
  305. evalrx/reporting/case_study.py +947 -0
  306. evalrx/reporting/compiler.py +587 -0
  307. evalrx/reporting/dynamic.py +1882 -0
  308. evalrx/reporting/html_report.py +2225 -0
  309. evalrx/reporting/langfuse_exporter.py +38 -0
  310. evalrx/reporting/langfuse_source.py +155 -0
  311. evalrx/reporting/model.py +151 -0
  312. evalrx/reporting/run_events.py +184 -0
  313. evalrx/reporting/server.py +557 -0
  314. evalrx/reporting/stages.py +58 -0
  315. evalrx/reporting/static_export.py +142 -0
  316. evalrx/reporting/web_dist/index.html +146 -0
  317. evalrx/specs.py +727 -0
  318. evalrx/stats/__init__.py +47 -0
  319. evalrx/stats/api.py +192 -0
  320. evalrx/stats/bootstrap.py +86 -0
  321. evalrx/stats/ebh.py +27 -0
  322. evalrx/stats/evalue.py +98 -0
  323. evalrx/stats/friedman.py +138 -0
  324. evalrx/stats/mcnemar.py +40 -0
  325. evalrx/stats/multiplicity.py +159 -0
  326. evalrx/stats/subset_sampling.py +55 -0
  327. evalrx/term_links.py +43 -0
  328. evalrx/viz/__init__.py +7 -0
  329. evalrx/viz/labels.py +77 -0
  330. evalrx/viz/prompts.py +39 -0
  331. evalrx/viz/renderer.py +590 -0
  332. evalrx/viz/schema.py +36 -0
  333. evalrx/viz/style.py +134 -0
  334. evalrx-0.1.2.dist-info/METADATA +532 -0
  335. evalrx-0.1.2.dist-info/RECORD +339 -0
  336. evalrx-0.1.2.dist-info/WHEEL +5 -0
  337. evalrx-0.1.2.dist-info/entry_points.txt +3 -0
  338. evalrx-0.1.2.dist-info/licenses/LICENSE +121 -0
  339. evalrx-0.1.2.dist-info/top_level.txt +1 -0
@@ -0,0 +1,339 @@
1
+ evalrx/__init__.py,sha256=G6j6FLLRPPm37pLtQkYDtfb4_JIt_V1awFexuj6b7hg,4491
2
+ evalrx/cli.py,sha256=8YYmhesu4wpAY6RPpW-MIuYXvQXfa0rGRa7cgdOLgQI,19618
3
+ evalrx/config.py,sha256=DwlpsVWL9gzuQjNggaELKugPYUEXhxaJp-WHj0yAm7U,2395
4
+ evalrx/logging_utils.py,sha256=S8p-5wfx3WZVIqx2ePrGgUbVCto1dk5yMh3spQMhgCY,4700
5
+ evalrx/specs.py,sha256=q0I3WOQnygalhhBPz9zq4s1reO-EFdWJs_b4rAdUyIw,41218
6
+ evalrx/term_links.py,sha256=LB4GdKFZ56FsAV4kmT1ZRLVIdhyvBPBUq24A1EcLNb8,1713
7
+ evalrx/agent_assets/__init__.py,sha256=Z0R3hgh-cFnpa2z0OT_As_3qVBdwq6vDqKBSc30P4ZY,49
8
+ evalrx/agent_assets/skills.py,sha256=s1RsTzQIfOnkjWSzfeGnpJ69J78a-x7Kw0dABLgI_FA,955
9
+ evalrx/agent_assets/skills/README.md,sha256=paBpLe5FbjBwHWa1K_75EMWUWmIfg41Mj90-WbUPdBY,1375
10
+ evalrx/agent_assets/skills/eval-chart-style/SKILL.md,sha256=iTt8OMeX-Zx6zqnJwU017zDhU_5WEGiZwd7C_-YWvDE,9364
11
+ evalrx/agent_assets/skills/evalrx-report-ui/SKILL.md,sha256=-OQnEGyozoRrzQtTU2u1h70C4GHvHIB0HDlliPog0P0,4402
12
+ evalrx/agent_assets/skills/nature-figure/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
13
+ evalrx/agent_assets/skills/nature-figure/README.md,sha256=KQaYDcXqJEjR2jNAg3_Ls1jdrQq3o7PzmhSHasiFOs4,20238
14
+ evalrx/agent_assets/skills/nature-figure/SKILL.md,sha256=fN3ukze8K7b-a3LhzYnPBesA8m2Uf0weN7Ur3VZvN4E,5244
15
+ evalrx/agent_assets/skills/nature-figure/manifest.yaml,sha256=J513xKCHqpaqy60NKf-00SWNeVGNWUNJTwqCeZFYoVM,3200
16
+ evalrx/agent_assets/skills/nature-figure/references/api.md,sha256=f1RTWbtNLVjCQ1aCohVjj0aYm3Kw4VFsQB-hjjfTCq8,14063
17
+ evalrx/agent_assets/skills/nature-figure/references/backend-selection.md,sha256=8ws-XJKT6HMsbeJ8L2lShNMmesX07PIdjVIJAg6y4FI,4694
18
+ evalrx/agent_assets/skills/nature-figure/references/chart-types.md,sha256=WFteWcClKOAgdQ32t3kUdZ6qKF-KKgJdOBDkCoY3wqs,8911
19
+ evalrx/agent_assets/skills/nature-figure/references/common-patterns.md,sha256=yPXNMmA4x4TGPcf5bFnwfTVZ3mnVAiXsu0bXbgO69BY,9950
20
+ evalrx/agent_assets/skills/nature-figure/references/demos.md,sha256=kPC-FL8qeChT9cccaotJM6JGx6lsT2xZ2A6cL3zqsDY,4118
21
+ evalrx/agent_assets/skills/nature-figure/references/design-theory.md,sha256=6lQbjKt69JAEXfNfjSi4kSybKdlbJIRU2Nuc6NNTytg,15938
22
+ evalrx/agent_assets/skills/nature-figure/references/figure-contract.md,sha256=2Ym069s66rFMCeJhmAdWq-cqZ7xeuGbhuRzarJxdUgE,3970
23
+ evalrx/agent_assets/skills/nature-figure/references/figure-legend-conventions.md,sha256=6Vkaw7Id_CbHX5q4yilQ5cHiIugHs2Rd9wOcEuQMM8Q,3607
24
+ evalrx/agent_assets/skills/nature-figure/references/nature-2026-observations.md,sha256=5PeAAxZ0ApeuNXOy8YMKLRUOPjBlRhRPbAVHgGQxwwc,5622
25
+ evalrx/agent_assets/skills/nature-figure/references/qa-contract.md,sha256=UyPyNPpTGXhM5LBuTrodJCujmnLOgxmPniuhJutQAzk,4736
26
+ evalrx/agent_assets/skills/nature-figure/references/r-template-index.md,sha256=Dru9QXGJa2FjnXlpoBBAHQqiV7r7mXgwJqG6Mskc4Z4,3903
27
+ evalrx/agent_assets/skills/nature-figure/references/r-workflow.md,sha256=Z8pRJuVLIjc6ZkbH98I8iS7yNxdAkqK1yU7b2bJerV4,5275
28
+ evalrx/agent_assets/skills/nature-figure/references/tutorials.md,sha256=kgunUpTAmsWnx9-awYBwYHN7gzEUnRBbPQ8NoEHlBEU,8169
29
+ evalrx/agent_assets/skills/nature-figure/static/core/contract.md,sha256=QLBAi7WgNuvCGOvc-xloEnuA4S1mlvkRwi-n6fSIZO0,3076
30
+ evalrx/agent_assets/skills/nature-figure/static/core/stance.md,sha256=RtGklgjM8kCvQje1_beSW2f0WJ1_RF0ryzZQboiYWy8,3371
31
+ evalrx/agent_assets/skills/nature-figure/static/fragments/backend/python.md,sha256=YrYxzuDveq-MrqR-tMTp3-T1nUGWjcVTrMm68agdkq4,1936
32
+ evalrx/agent_assets/skills/nature-figure/static/fragments/backend/r.md,sha256=PzH_SSn72GN_ThDunqp95T2m5Iw8hu4b0_wwZ8QfoVY,2075
33
+ evalrx/agent_assets/skills/outcome-driver-analysis/SKILL.md,sha256=cGUNlgvKuGGBYMYBgZanZ9oGV2gSCANglxo48-tJWS4,12195
34
+ evalrx/agent_assets/skills/outcome-driver-analysis/assets/analysis_report_template.md,sha256=hHEoM_2mPsoRsBsjijzEKpntACs6SQ8ACf_ZMsPwI6U,1607
35
+ evalrx/agent_assets/skills/outcome-driver-analysis/references/model_selection.md,sha256=caOyerVpA65XwqOsYK9wF229WxWiKH3TY-LJ0BVkqrs,5810
36
+ evalrx/agent_assets/skills/outcome-driver-analysis/scripts/explanatory_var_eda.R,sha256=rLlKvZNNVC8evw-1jVCeqfcLhgRFmEDhfd-EoTDy4wM,5044
37
+ evalrx/agent_assets/skills/outcome-driver-analysis/scripts/explanatory_var_eda.py,sha256=89P6f6bytmei1UvZKkrbg0PV9HfBtbltn6s40X-gVeg,6156
38
+ evalrx/agent_assets/skills/outcome-driver-analysis/scripts/fit_outcome_model.R,sha256=_H0v_e05W8qC2hTxRU1ycv07ptHN_O8JG3GqwgRQCm4,8234
39
+ evalrx/agent_assets/skills/outcome-driver-analysis/scripts/fit_outcome_model.py,sha256=aDxD3Hzo2B0UMYVJZDbYZSOCF9YMPJ3Fcjn6Z-Dh_B0,8437
40
+ evalrx/agent_assets/skills/outcome-driver-analysis/scripts/univariate_eda.R,sha256=B0Y4DGIekg9InfHy6c1I014F0a60pMKP9MDwaw9Icuk,6429
41
+ evalrx/agent_assets/skills/outcome-driver-analysis/scripts/univariate_eda.py,sha256=Xj-xfhrrH8cVo_JsvwIT3J8wkG_71iMpxilLShjv0Dk,8243
42
+ evalrx/agent_runtime/__init__.py,sha256=l_kGs_IqNSaQk5SnZTTWhqiyqlWAMPTIYysMb06Lq6s,2565
43
+ evalrx/agent_runtime/_docker_runner.py,sha256=1OnVtjM4DHZOaLz-chLpbuu5MuAMGpiKChRRr3OVImE,2597
44
+ evalrx/agent_runtime/cli_runtime.py,sha256=b7eH2NhB9aWVTKv-MkPZ2pZMh_Fw91zrNyTVYTX72Rk,3222
45
+ evalrx/agent_runtime/cli_transcript.py,sha256=OcvgeuRGOUSdxbtq4qTLk8uMx0kL4Ogw13o4X-OHg4I,5573
46
+ evalrx/agent_runtime/cli_types.py,sha256=B_HHDavio4PyqN7CoNavhhfmAZozX8idpx-t-mehI0k,2120
47
+ evalrx/agent_runtime/experiment_harness.py,sha256=PqeUnOT0voKXpFAsiLFRTyzqeQ5pJIg0iD_h_83bxxM,4140
48
+ evalrx/agent_runtime/factory.py,sha256=8PdqgNMqpOIqp7MrT8JDNchw66c0NIxWVbZJTNC_rpw,3355
49
+ evalrx/agent_runtime/json_shape.py,sha256=cn2vt_rPQPp1jl3hJ3C2p35Vyjp6mbHjGFCs2FEqr3g,1932
50
+ evalrx/agent_runtime/sandbox.py,sha256=qcqNy6bEPSTAxL1p12rbZ6RW5KqqlyX_4Kih_-TjZ4I,18987
51
+ evalrx/agent_runtime/skill_audit.py,sha256=1qK3wCy8KwkQB72srH3UvuqjJBIhRYzYT1ihTrvvH3Y,4820
52
+ evalrx/agent_runtime/codegen/__init__.py,sha256=3p4JYdXgmCBtDwXL5wCWS8b_YQ7-8vc-JOWGNT-wI8w,184
53
+ evalrx/agent_runtime/codegen/runner.py,sha256=8xCUhAWwrv0GRanP5QoE7cZ4A72UnqdeCpcvI2EZgoA,2852
54
+ evalrx/agent_runtime/judges/__init__.py,sha256=n6el5E4KTLnMh8pUIM4yQHttIwDMDoU1omWANW2n2mQ,710
55
+ evalrx/agent_runtime/judges/agy.py,sha256=ex_xf_19xVEFuNa9X2tavGd1uRX03Ldf1S5Lpwik55s,6723
56
+ evalrx/agent_runtime/judges/autodetect.py,sha256=3GfBvZ9RlBBa7R_7Hva86wmdmQRo-G3MvP95apvM968,4897
57
+ evalrx/agent_runtime/judges/claude.py,sha256=uZ0oFffyvJBxCo4O3KxZZz76e3dn3KNUkt6NmowjI9Q,6610
58
+ evalrx/agent_runtime/judges/codex.py,sha256=-3mteLaao73EIbZ2czeZ3GVJXiWC3cNjcDAUXm2aXNA,4457
59
+ evalrx/agent_runtime/providers/__init__.py,sha256=xAo5MCqp2S6GvliUh9mArWKzO9aQPeX6xK6Hp5h5tiM,757
60
+ evalrx/agent_runtime/providers/antigravity.py,sha256=Nbt2VsBZLW6np56NWBy2KgdLcmJSVAJ8AC2yZVEkd4s,923
61
+ evalrx/agent_runtime/providers/base.py,sha256=jCD8TDSA8pPngf68mOhU5ju4fRmRqnkRFw9-QnIjDr8,5900
62
+ evalrx/agent_runtime/providers/claude_code.py,sha256=5Zyad1yybqFG8OlPkSTypauqy6UKA5IvdzYHpJlSvfk,1901
63
+ evalrx/agent_runtime/providers/codex.py,sha256=eOZFS7UvBzerk67xDvBdi-c5SiyR2TeqRs22GhivHEM,1151
64
+ evalrx/agent_runtime/providers/gemini_cli.py,sha256=VG7JF1eFch53SSb1QvanaAcW3icYLceR8NOYcnJzoA4,614
65
+ evalrx/agent_runtime/providers/kimi_cli.py,sha256=VzzmLaJ_5PsbuZ8GB-XqAeWggn7TSFUUcvE_oSU0664,637
66
+ evalrx/agent_runtime/providers/opencode.py,sha256=L84Z3_JRWdWhET9r_mKqm5Z6fb8a5suz_pG0g5a8RYI,644
67
+ evalrx/agent_runtime/providers/registry.py,sha256=Vs2yRZbW3db3dYOcS-GRY2wK7vmw7ST1QdOi0Z9Hmns,2097
68
+ evalrx/agent_runtime/skills/__init__.py,sha256=8u83dGVlrLTmsh3MvfR-QcToccEslOMdZnt5shidIjk,532
69
+ evalrx/agent_runtime/skills/installer.py,sha256=V5a9ToYYOhdNfyxvvjp3e5Olerq9zkixjUT5_ZErnSQ,2305
70
+ evalrx/agent_runtime/skills/prompt_policy.py,sha256=Q6xfBmBFqPN5AFJaDlTabY_1JV6hEz-p_lepmk69T2M,4290
71
+ evalrx/agent_runtime/skills/resolver.py,sha256=OcH_832rosCD9koBUVwVJ29BNTdiKTwQTwMWGJSX84Y,657
72
+ evalrx/analysis/__init__.py,sha256=GTtNsJFUj_4clabysu4-cJzITvtpmhK9WKjTsFnTK-M,3738
73
+ evalrx/analysis/adjudicate.py,sha256=1A01ycPMjSpEPJp0iautSQG0OmbTrRL-qNgCuUwgDmE,6488
74
+ evalrx/analysis/analysis_module.py,sha256=iq4ghqLGudRf1mF-Kb2OdouI6KGNYDtyAC0luYO4t1I,13524
75
+ evalrx/analysis/api.py,sha256=Z_luYbSHORNqoQIoTGRQnpPWrfFTvQaFC5YF_beg-G4,6933
76
+ evalrx/analysis/case_studio.py,sha256=h7124NCD7GZb3Pz_BopBfFvmqNRr10gEl9s-mAIWoZU,26863
77
+ evalrx/analysis/cli.py,sha256=aLLqbi7_fU5mIJxURUoLGjjynNGTM4C5MHZ0EsAQ__8,4444
78
+ evalrx/analysis/dashboard.py,sha256=LGBU07mC8ZqQlkq0nYZgz7VrXN06pUBjc8vMzIa_fJ4,15015
79
+ evalrx/analysis/eval_case_matrix.py,sha256=VlrBXouoppJhpXrArFrDodRnsjYInTr7MpiC5PhkchI,4682
80
+ evalrx/analysis/eval_viz_theme.py,sha256=xBFBtT4aQxDX1YKYCqQJ9oVwbDcMZDTrwDz2sEb67jE,38858
81
+ evalrx/analysis/explore_run.py,sha256=GfI3ZJSF5g_AWiUGURTbL4fF18vHQFyQnydEYFYc5vc,14154
82
+ evalrx/analysis/explorer.py,sha256=GOmAXSoB-nV9rYIjAX4AtoznocNR07iSQg6l8GoXS8s,52987
83
+ evalrx/analysis/failure_modes.py,sha256=CE9b8n8OvDeYEzNlUnNpUV1185k3InVjG88Uj0x8UBA,23663
84
+ evalrx/analysis/fused_pipeline.py,sha256=3X8uMS65ksm6HFVDCGLchXG75pi8VKvPQuKxT1or1J8,20381
85
+ evalrx/analysis/holdout.py,sha256=8UsfvrUmLVvAHpyicreJudgBeVxbUHjM0zBDrTwYobQ,12098
86
+ evalrx/analysis/hypothesis_agent.py,sha256=doSMDeW0TDnPjpAqxGFymkLR37VDtIdPTf7St-Vwajw,9780
87
+ evalrx/analysis/narration.py,sha256=rSYXne0wQf4RpUFl0-iVrVJf5H2UZad90uTj3X0nW8U,7123
88
+ evalrx/analysis/operationalize.py,sha256=igK-cTbzXlHa9G5Su1gJmgyAP8j8ODG_DQVZO8ZktVg,16976
89
+ evalrx/analysis/plain_language.py,sha256=hFcvnqliPJ6NaKRudVlRHlagvsfCrZ0UzTBs8_AxVHU,1822
90
+ evalrx/analysis/planner.py,sha256=HisLcdJrplOUuVF5no2mlEJDCp951SHFrjc2jTL4Mtk,11819
91
+ evalrx/analysis/probe_search.py,sha256=_VDx-4Av5LQhg6VtWeW0UsC-YFDdRRGMUMJnUjg9pb8,8054
92
+ evalrx/analysis/profile.py,sha256=WGU-sG452dIWg06-IShtDV4sIHnCrp8umb0xgsHR930,10569
93
+ evalrx/analysis/result_marker.py,sha256=hT1GABuWA1703K7ScnHjU-ORFJK3lVMvsYbHKrrpbfs,2046
94
+ evalrx/analysis/run_codebase.py,sha256=kBWZ5X-jpzUGu3G-VnNUPMKxIb4_cSXxK0KfMVrPJ-o,8783
95
+ evalrx/analysis/run_view.py,sha256=bsGYTMHCgN6AnyuCn84XibaaH7SsxddIYoPDuv7Zfeg,8500
96
+ evalrx/analysis/stage_views.py,sha256=5gBkQGeB9qcsELaxUZQwan4abcMiLpkE8J5extE7X1M,4235
97
+ evalrx/analysis/stats_agent.py,sha256=wLAj-qS2d0nXCLJ1032NfVjfDFJWhnZFSRtG2r6bKR4,39325
98
+ evalrx/analysis/stats_tool_agent.py,sha256=RmRlWGhm8lpTNTdjsfwKDXT5swP1t6R_ExTBpuWZJRE,8750
99
+ evalrx/analysis/stats_tool_generator.py,sha256=mjyGlRL1Uz6xmaxAfxJeyUcul7BQn5TdgjVm6AHu9Zs,16874
100
+ evalrx/analysis/stats_tools.py,sha256=btZKwkckQz7M_kEaIjxPCW8XyVRSPer_K6YnaLTjLms,48772
101
+ evalrx/analysis/trajectory_records.py,sha256=npC5wu8xF_ZyATQo-VhH9uEUhHArbbZJnAR-7CVbbys,8492
102
+ evalrx/analysis/workbench.py,sha256=4COOtcwhPzhp1ki7XEwVljyKxFd9JyVa93k4wNQqWUY,17325
103
+ evalrx/analysis/prompts/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
104
+ evalrx/analysis/prompts/explorer.py,sha256=iU--D8_r5bIK__ZOEElsPvn3-SBMEket9TcZw0bjDso,23731
105
+ evalrx/analysis/prompts/failure_modes.py,sha256=zMNjxYV_QifC4oKdYgu2ilwCkBY68oSmVmas-xXVUo8,1440
106
+ evalrx/analysis/prompts/holdout.py,sha256=YI2abaMwrqy3I8h3oWfIjbZZ-bfMEoEOFHuqN5FG7k0,1203
107
+ evalrx/analysis/prompts/hypothesis_agent.py,sha256=Saw53rngmnhof-qFfX4DINyVYdIqx3PUKI8Gns2bQN4,3740
108
+ evalrx/analysis/prompts/run_codebase.py,sha256=UiTOR-ChTXQ79AHChdXOpgm4AK4W02UXONxc0KehvUM,2294
109
+ evalrx/analysis/prompts/stats_agent.py,sha256=y3zM-A6dYdqPwkse8Byk33YQqp_WGDlSK6jURWbr4zc,3122
110
+ evalrx/analysis/prompts/stats_tool_generator.py,sha256=pfJ2bqz1kI89O9KGFP9qei1UvPdnzVMj2gbh9MAkS4A,2186
111
+ evalrx/analyzers/__init__.py,sha256=Fne2qZ188wQ6O8XUQ36X9I865zkPvrZZG3eFnVMOm4Y,1880
112
+ evalrx/analyzers/base.py,sha256=Qn726UMXo4hyfeN4PkDigaH2xflYJskQgwMiYnfrQC0,397
113
+ evalrx/analyzers/agent/__init__.py,sha256=T5IgaxzsM5FPgj7ZAR4FFgOHIAzIs290FEsKz1ma0rE,1041
114
+ evalrx/analyzers/agent/counterfactual.py,sha256=Mmfh1Y7SiGsp2uYyMZ5V9LIqqVSNAv57lW1d1KsKYf0,3573
115
+ evalrx/analyzers/agent/first_error_judge.py,sha256=tfV0tJmQmDJdKRnqBwAj3VLStdQ0aTORuYP2K9r3R-g,3962
116
+ evalrx/analyzers/agent/ignored_obs.py,sha256=1tTDGHp2c7JZAHDSVbpeoh2ksllCkvhMpaJ5M-VEA2E,3389
117
+ evalrx/analyzers/agent/loop_detect.py,sha256=k9f-LFPklF6pJnZHs5SYKYMaZ-vG87R2z3nwfh2MCxI,2836
118
+ evalrx/analyzers/agent/reliability.py,sha256=7wUGm2BI75RNhMEHq_STXa83CYPcNMNaaN92VUx2pV0,7109
119
+ evalrx/analyzers/agent/tool_shap.py,sha256=n0Zp0w0bj4Jjn7ZGnqfJPyKDkG32-tJcvy51oSxNvYM,10054
120
+ evalrx/analyzers/agent/trajectory_rubric.py,sha256=8r0DQAa659aRr_ms_GAYs6RmJ-I6koAAxgu4UxLea-k,7042
121
+ evalrx/analyzers/attention/__init__.py,sha256=j48vygGZYmwpPLBYcMUEKw5RmqSmslxrvwbW6ZuXIyM,749
122
+ evalrx/analyzers/attention/relative_attn.py,sha256=BRiDVOZ2CQjOWaEFwQZp1b9uRP2Rzat4mTjHiGeUxLs,26699
123
+ evalrx/analyzers/attention/rollout.py,sha256=WmHTuNPPMb42VEV54MQQtsrPlnHLJ7GfUpxLC6Nlti8,2640
124
+ evalrx/analyzers/attention/sink.py,sha256=-m4axUdyqFIn3J3DGeyMOmsyMW5Qq9xrHkM0ArBvS5Y,2096
125
+ evalrx/analyzers/attention/summary.py,sha256=EpwLCMobfX6AZPBTHvfQC3HqyYr7SXYHBVSbXmT3DoE,7426
126
+ evalrx/analyzers/attribution/__init__.py,sha256=GHdF6CYga20sSc4EMWmiBGY4e8iD3XmT0XrzO8NIjIU,295
127
+ evalrx/analyzers/attribution/generic_attn.py,sha256=YFzJ4STM2J4rtIoKQ8QDB9RcaeZnPYnP1zo3bc7aorY,1248
128
+ evalrx/analyzers/attribution/gradcam.py,sha256=3P45d6DgaCQEjtOitLzpIamQ-_DAzPWj2sMnOm7QaXI,1107
129
+ evalrx/analyzers/geometry/__init__.py,sha256=zKY4qbNEoO5O7gAuSZsvO7TA6anXzZ0iE3_4lzeBjpw,296
130
+ evalrx/analyzers/geometry/cka.py,sha256=OcrrR3w8huKm_9ZiMhhk5DrGIdD9RN8dmREoN_Id0HQ,2701
131
+ evalrx/analyzers/geometry/linear_probe.py,sha256=d6DPkr_ffSbibYm7_bNjQaRlrXU4Riwptoy8k1hx4PQ,7129
132
+ evalrx/analyzers/hallucination/__init__.py,sha256=Mv6GUBxZNeyNWrWU75r7tAnqIw052Tp5vRHa3E8cKIM,561
133
+ evalrx/analyzers/hallucination/chair.py,sha256=AO6cGay0IToKlqHte8uKyOaajpWImSsJdY-fbS2ghkU,3301
134
+ evalrx/analyzers/hallucination/opera.py,sha256=eX-RtLpuVxfkUzZmOzoZo1TY80Ao7jgXfG7j8NgqBdE,1113
135
+ evalrx/analyzers/hallucination/pope.py,sha256=AAVwM6Yu-FcXoFxMpuFAbe9fFRqSGloj7fgcb4u3fgo,5097
136
+ evalrx/analyzers/hallucination/selfcheck.py,sha256=82uIP67d1jQLNCy-hLUAYeoC7maf9S5chpWaNcP_zd8,6760
137
+ evalrx/analyzers/hallucination/vcd.py,sha256=yQvmWKkqCqI1x30KM2YU2HqTvVKJuxRFonNGVI-pTgY,1126
138
+ evalrx/analyzers/lens/__init__.py,sha256=_NCdniZj4aQFKiU9pvWvgC9V49a-r6We14sY09aL_aE,347
139
+ evalrx/analyzers/lens/layer_contrast.py,sha256=HkIhmk2AuoxyFRX5L1AtlX6tX0jOginat0wUouOpmx8,6554
140
+ evalrx/analyzers/lens/logit_lens.py,sha256=Uheqk7JOakW25psfjIWwNJEAB0CGjp1hYOcjK4xK4MY,6713
141
+ evalrx/analyzers/lens/tuned_lens.py,sha256=e7Vd7RpV0Tf6rWORG96BTBaQlHU6NVHz6d6-sZeTIGc,1081
142
+ evalrx/analyzers/patching/__init__.py,sha256=4U0XGyuKAJGtPlpnnyfli6rssw7IyKjIfNJ1NeFt86o,183
143
+ evalrx/analyzers/patching/causal_trace.py,sha256=VtZ1L5sW0dEcZmalsFOEJFEdLtycfCZtUQstQH7Fsnw,1187
144
+ evalrx/analyzers/perturbation/__init__.py,sha256=GVp-rOhmj3mbwlTiCaQY8VANbT5V6gDut5qjFxkNQBQ,1030
145
+ evalrx/analyzers/perturbation/_shapley.py,sha256=ncH7OsI_ZygXfsMuuuQz7DS_JjFqTGreU2kJWmOFkMI,1841
146
+ evalrx/analyzers/perturbation/context_shap.py,sha256=ITzh177_00iW6XaVD-PWq3IFrR6A0Y3p7RzieBuOvfU,7756
147
+ evalrx/analyzers/perturbation/cot_faithfulness.py,sha256=7C3f8AMwzvG37MFxFu6kQr9H5I5FdCNfgFlutvGwz3k,11638
148
+ evalrx/analyzers/perturbation/format_sensitivity.py,sha256=z0TfSFUw1tCXpGIVUVu_2UfNXK8JemfNu_22EWqKP24,10808
149
+ evalrx/analyzers/perturbation/mm_shap.py,sha256=p9SvoBGoBp8bbpIZm_0K--BuBBHnNmmtWMmLHE0BpKE,6962
150
+ evalrx/analyzers/perturbation/modality_ablation.py,sha256=HSdVjn9Mp61aIVYfYFcgmqWHwvyjVGWoKYeb6d_FCGw,10122
151
+ evalrx/analyzers/perturbation/perturbation_battery.py,sha256=Ml1zYwmI421U38A330IvyzSAjhl4NwEmdJAusz3u_xM,12999
152
+ evalrx/analyzers/perturbation/prompt_contrast.py,sha256=-PcXvyQ3nzlVFupYquzazIt4SakPSs0Xd9auq16twd8,13344
153
+ evalrx/analyzers/perturbation/rise.py,sha256=lb8qlhdFoB7S7BoMh4-26xeEk7-AbQHFowu4Zt3QlHk,3513
154
+ evalrx/analyzers/perturbation/vl_shap.py,sha256=LGh2ort10R2gQGLk-zLWvia93P4l0tlhcWsVW-cJ3MM,4153
155
+ evalrx/analyzers/reasoning/__init__.py,sha256=1o4a3jSC-LAIH9_mvhRKMXv2P28GMeKqOGF3q6B6-UU,1596
156
+ evalrx/analyzers/reasoning/_text.py,sha256=Zx_RRvDxpkunyT5kixskMIW9nvp-gS7cJXBO3qaETxc,13788
157
+ evalrx/analyzers/reasoning/answer_extraction_audit.py,sha256=ZHD_gIEcK6nXUB-W_K0Nag134E2qZGm0h2H3qA9PJ3c,16743
158
+ evalrx/analyzers/reasoning/arith_audit.py,sha256=v6WIjjgmqtGM_DbXjcRBeG-uGb8f3TpGPlGaNh_Ka8o,9532
159
+ evalrx/analyzers/reasoning/contamination.py,sha256=WvTvbv8GrSRBKvyWs6_Ltnwp0kLloHdug-gThzjmgLg,9470
160
+ evalrx/analyzers/reasoning/knowledge_split.py,sha256=tM72HHL8UKz2sgVltop0qFlC-3ZULMooBE4I4wWDIVw,10744
161
+ evalrx/analyzers/reasoning/self_repair.py,sha256=5uSas2KjWHP7f-0-WbF4fchgz3vCuinxErF5Db4vjO4,10792
162
+ evalrx/analyzers/reasoning/step_rollout_value.py,sha256=KOwu5u-zA374dw7BzHaMo3yQV9v-wNrf3Gg0eCMdO6I,10138
163
+ evalrx/analyzers/reasoning/termination_audit.py,sha256=1Q1uU9aS--qeM9n7AAp_-3K8R5ndzLETrRjfRYK1gec,12199
164
+ evalrx/analyzers/uncertainty/__init__.py,sha256=nnPJu2OXwTlT52-6-_FBm3p0zNOSI1HC3Hxs3IKBxf8,800
165
+ evalrx/analyzers/uncertainty/calibration.py,sha256=QtNpFdaBaIpP0sxw9fvF2IpLi7lsxUXApjXlcuQNG7Q,7852
166
+ evalrx/analyzers/uncertainty/coverage_gap.py,sha256=10iGCN739a6xg6ums2EVHw008pe0j9q2cEZXww6PR3g,8789
167
+ evalrx/analyzers/uncertainty/entropy.py,sha256=-XoLiSNPg8M6Ju8qL3CvhKUXTFOaSuXxyqQ7pYd5LM8,3046
168
+ evalrx/analyzers/uncertainty/logprob_entropy.py,sha256=Y6eUbdKkaLYL_ajbKmQAAxq3wLjReuYK_4eP9JdnJXg,2711
169
+ evalrx/analyzers/uncertainty/self_consistency.py,sha256=mRv7A5iXuYCag9wjMsEN4ja7clBU9CXvjALRL1mdgJQ,9815
170
+ evalrx/analyzers/uncertainty/verbalized_conf.py,sha256=MgQ7GPi--7Fqljwv76KW8omG72OuO6BvS41rwMpo5lU,2239
171
+ evalrx/contract/__init__.py,sha256=U5anOXkMIeZ1EqhKFLhgUp114zxbrT8E-f-f0T1hwpQ,6071
172
+ evalrx/contract/common.py,sha256=GW-_wsl0h0T-43oaz2WfQHTRwhhF05IRC86UDSB-RR4,17774
173
+ evalrx/contract/emit.py,sha256=fh553_iHRa15w2ZDUkQLllVOc5qPqYuTsJ3du2dN61c,42386
174
+ evalrx/contract/export.py,sha256=-tqHTFLz6wqe2bhzvHFrcEQoPu_iOHTUBzQb5YjoP5s,10810
175
+ evalrx/contract/m1.py,sha256=VluHnp4zScrOgxNXx1XC3J0_RUZIJMRDqH4TysVYscY,13919
176
+ evalrx/contract/m2.py,sha256=a1_kwieH_00VXjfCgJ0yJe8hTXibnJAE-TN3dfhUkqc,13820
177
+ evalrx/contract/m3.py,sha256=Iz0GXdMb4AAtsRHHHM-Td3rsouRPqGLHGRGyJUwEfb8,7331
178
+ evalrx/contract/m4.py,sha256=uDx7sEBVsYNttRL4VYLoXw5HOBtY06kXuSqjconqTu0,5767
179
+ evalrx/contract/m5.py,sha256=uTpBGGP_7U-kpqwMqn9imiPfuP8R8pnQ-VpGbWrJgSc,14059
180
+ evalrx/contract/methodology.py,sha256=RNyPwVRnwuJTjmWOzXuBxDAJr9FSLA4ns3B91VyudgI,3201
181
+ evalrx/contract/pre_m1.py,sha256=rDeesSCfX3y-T4Wv8wlLbf9QVYVQc9Tpu0Hd60iqE60,2310
182
+ evalrx/contract/typescript.py,sha256=U50oGbCBUYHv6ENlhXRB3ovnfCkjHDTLZm0F0VEKw_E,5679
183
+ evalrx/core/__init__.py,sha256=cqfW11pq0lmsMM7QtVBhwhX0tCu6AJeGoZ6ZrMqhiyc,2094
184
+ evalrx/core/analyzer.py,sha256=zQsvutvwNsmxBZmj7To_SAZkzo-C0mz6R8V2iPLOK5E,7842
185
+ evalrx/core/capability.py,sha256=zeZwuv-t1z16ILuJd93IAhHJV7k0_pqf3-JsJnYNeuM,2174
186
+ evalrx/core/case.py,sha256=3TeVhCNYKKCm1TTB0tbEHwRGrzNWUn8p6dxsRE0_XGA,16802
187
+ evalrx/core/experiment.py,sha256=iyHMohu3z1ShQNB7Z8TQGVQ0Sp1A7cRByIbwCBi4eLM,3829
188
+ evalrx/core/model.py,sha256=UFUDeMxzma1UKV4x5JXLNIu8-J7uHfxkQbqyZvZwAvE,7858
189
+ evalrx/core/pipeline.py,sha256=vpvvmHCbbR7sLHu9WPbWztctSLQOFtIynHecXg4lV8o,1381
190
+ evalrx/core/registry.py,sha256=vxoq1fB77WY31B7SNfatOc1gO5XsIr3BH5mUO4tQlSM,4753
191
+ evalrx/core/result.py,sha256=i7MtO_sjMcu2c1e-olIZO1YEGRvj9z6Y-Oa_jqCCfiA,2363
192
+ evalrx/core/spec.py,sha256=83wZ8qa1iFs1P90naBVDxKgo2i1lQVRZWfPPosvhShM,8596
193
+ evalrx/core/tokentype.py,sha256=Cp6Yxsn9PK9Jg-ODataki3ydZyXNC9KVH5nx4K-S4gY,6466
194
+ evalrx/core/tool.py,sha256=STNsHN7sM6HmRD19j_HiGp4XMFvrquvevWoitdgFfAk,3279
195
+ evalrx/datasets/__init__.py,sha256=k5FpvidPkA625rArTRLjO6Fn-q4Ep3NEtKmKEPGuhg0,1029
196
+ evalrx/datasets/base.py,sha256=11sqvEvz46XaN2p-qt1O_BjrkgYwnExoO0IjsPSbNgI,2145
197
+ evalrx/datasets/gui_os.py,sha256=-UnYD_eOhigNKvznC0rKgT-Po-QkHJOIW1ijtE_WIzw,1905
198
+ evalrx/datasets/llm_qa.py,sha256=YLdhlR4weW7hIJrcGVH7R1xlJuA-PVRWI3YmyHlEIsc,2037
199
+ evalrx/datasets/pure_qa.py,sha256=dFptcymsTbU_tFr3DP3NOPRXvvltbW3QQml6ipAldLg,467
200
+ evalrx/datasets/vlm_qa.py,sha256=QJfJvwAyg0AYiV-gI7BeXBMJ-iMMnjg1Af4i0v9KGjw,26192
201
+ evalrx/datasets/web_search_qa.py,sha256=mz9cZWwr_zeowXc4VtgemCyoE-VRtyFFd6yfdmjhvUQ,1817
202
+ evalrx/eval_agent/__init__.py,sha256=-e1FGd-RIIrfmc5L8x_rTrDqA3sdQscklVkFGagMKY0,13273
203
+ evalrx/eval_agent/_tools.py,sha256=kERufR9sW6TkV8_r_Edh41LPxlnhuR-BNzgue1_3EPg,3107
204
+ evalrx/eval_agent/ab_runner.py,sha256=ICx2EdSZZE7sS5dmggdWzFKIoPmkaXfPxQZd8ywKDek,1746
205
+ evalrx/eval_agent/checkpoint.py,sha256=x61kwWLaPkfbAXvijRcc5kd7Yw2081Dj1KsL79m1gNU,1864
206
+ evalrx/eval_agent/cli_agent.py,sha256=6_Is5bAMiad-i4LDhJtUS8mfP_k-NzKj7lv5d9lcs6w,1938
207
+ evalrx/eval_agent/cli_skills.py,sha256=B22zuOcIvIjuSGRbjocyWBRHfIZUad-F_0KUSOXLOVs,199
208
+ evalrx/eval_agent/evolution.py,sha256=rNuRqbTka0py5cfhtYzhuY7jGbLwBcpWh50_pX3RriI,14548
209
+ evalrx/eval_agent/git_manager.py,sha256=iHzRhybvSpDfu1crY-Is62VZqCua3dEk8o1Bv0JPhGs,8065
210
+ evalrx/eval_agent/hypothesis.py,sha256=nrwzOx4hPh959kbu3BdPC-o8KQR9IEB4NoZvyO-8mW0,7484
211
+ evalrx/eval_agent/label_quarantine.py,sha256=Z7OHiPeqoQuijCaP8A22IWh_aZvcOYrMDBN3DUjROgc,8957
212
+ evalrx/eval_agent/legacy.py,sha256=o5CBHn5Ci34l4V4MvXypEGCBe81Mq7mKC8slVAEgnaM,24579
213
+ evalrx/eval_agent/log_schema.py,sha256=oDSVZZWY1FFdXEKHHp1uLNn-sPVRm0nA-BKBxCqp9GE,21421
214
+ evalrx/eval_agent/loop.py,sha256=B8Kgczm4maFMPNjZP1horAatJAOukAnGw7_o__KsLFI,104651
215
+ evalrx/eval_agent/loop_reports.py,sha256=p9O9c7fQ6IqqPna2qzwnOs33M4NoCGfEX9BvXRmXEv4,6391
216
+ evalrx/eval_agent/model_instrumentation.py,sha256=aMdd2WEwiZ2IlBx13_LrGfQ3Yq9RR_KLM8tAPIN-Mbg,13532
217
+ evalrx/eval_agent/narration.py,sha256=drPLKkHGxmpwKl6-SKy-HSPC8eKkUxS0Op1tYuRV4AU,8240
218
+ evalrx/eval_agent/nl_runner.py,sha256=N3u32C2yvaajywMFR5VZTEEzrxrTbNkSPmhNVdjoS-E,15030
219
+ evalrx/eval_agent/orchestrator.py,sha256=Jk2NZoim36PLEOj6ebUsUz3Cs-hf18zrrmhlGnTBrKc,2288
220
+ evalrx/eval_agent/preregister.py,sha256=wWN1mi3gIQp-nflEwlYKUvE1RefqVkWITKU6PPnmj04,3363
221
+ evalrx/eval_agent/report.py,sha256=q3JX4sGVUZelDt0acHlJlEuBwpikwq_Lsi4d-oQjXS4,2266
222
+ evalrx/eval_agent/run_context.py,sha256=oefxzPC1itdsbSvEGiezmOhU88rZrruSu7id1kxoogM,15408
223
+ evalrx/eval_agent/run_log.schema.json,sha256=yC3kIRbTjlI9x67fQ-JmsYSietF__dQFJhwlQkmSLaQ,27097
224
+ evalrx/eval_agent/run_logger_v2.py,sha256=D-oQTjPFGRcMB6f3q-o6YuWP5mLQGT09F0ANWzC8eFY,81118
225
+ evalrx/eval_agent/run_metadata.py,sha256=hshpWRvOjlHwagXflN6moAq0y1DPZGe2NNiUuaxkEro,8523
226
+ evalrx/eval_agent/store.py,sha256=In6kxvOeAw5s0FESS34KsfHmwMAP-vTg1KqbrRFo4-o,8865
227
+ evalrx/eval_agent/agentic/__init__.py,sha256=jRoUIrlJuRiUWN3d6BDmI50XtR2bD01b5DsV1UPSN_M,1160
228
+ evalrx/eval_agent/agentic/actions.py,sha256=eiDl84j_h4UEJveTWmBrHZrLQ0Ic-xUvKqKylYXPvCA,7673
229
+ evalrx/eval_agent/agentic/board.py,sha256=3rJGVrdCjpl-SQJ3hcTJXzC20HeECVPlk3sNRWx7lCE,4153
230
+ evalrx/eval_agent/agentic/loop.py,sha256=WskteAwSgnDmRhyYByP0lppUdG_k4Rx8zX7ZNnZp_w0,7688
231
+ evalrx/eval_agent/agentic/tools.py,sha256=4DUumzaJVxp0sa4ppKhAW4IxZGhJebTMDWlIzQJuoEE,21774
232
+ evalrx/eval_agent/prompts/__init__.py,sha256=Kj7hpdtJDKD4bsf_q6wH6Ho5eqOuIVt8OiaHRHGeYWE,61
233
+ evalrx/eval_agent/prompts/agentic.py,sha256=9DI64alEyhJAWHFZZXivB53qZ0CowL8_VD5xxbTPR_U,1690
234
+ evalrx/eval_agent/prompts/case_discovery.py,sha256=cmK5p1HpqQv2OTwWRHdgBF1tVxFB82RgeHKGa7Z7AHo,496
235
+ evalrx/eval_agent/prompts/diagnosis.py,sha256=DByRkiPcBtEurFR91xwtSEmq1e8v7KUBxGn9O9Dnzuo,6285
236
+ evalrx/eval_agent/prompts/experiment_writer.py,sha256=3tIC08x1_CbZz_pX-azEyCQreyzAQr29y9zkP0SGMVk,7675
237
+ evalrx/eval_agent/prompts/explore_step.py,sha256=LWvCk-oexjR39sRbi4dZ7JveU5FCOPBXSb1aVkAr7hc,1897
238
+ evalrx/eval_agent/prompts/fix_agent.py,sha256=xf54o0qE2V4Rvy-KAtccO5a56x67vLaZoAqdMssriUk,13357
239
+ evalrx/eval_agent/prompts/hypothesis_tester.py,sha256=wvKPBG_TfGs-IhncuXI8PT61QTEu0_cvL0_uhLgI6_c,542
240
+ evalrx/eval_agent/prompts/nl_runner.py,sha256=nsBqe1AhDefH3ElFXJBlc8CH5y1-TaY9wBOMlkIdPEY,1674
241
+ evalrx/eval_agent/prompts/probe_agent.py,sha256=zZgxRZDlTpBTD1AcX53JbBSIUB1QnN-sYCR7GKe5NNo,1008
242
+ evalrx/eval_agent/prompts/probe_candidate_generator.py,sha256=VKUG2M8hdigD39KHgrwHSaiU6dMpNHK_RhKVJu5WAl4,546
243
+ evalrx/eval_agent/prompts/probe_generator.py,sha256=v5W5yYJXbxGrvSd-zd2OG1t_5whW0jcB9Xvsmit6tMY,1353
244
+ evalrx/eval_agent/prompts/whitebox_probe_generator.py,sha256=ZCXERn6YLiNMG420TDEdcIoUyBpziFGy_2F1xaEw_W0,1711
245
+ evalrx/eval_agent/stages/__init__.py,sha256=olN7o76bSSWEt8-roTt4z1H5eCGQmUfmUJ5BVoOQX9s,3437
246
+ evalrx/eval_agent/stages/case_discovery.py,sha256=MrBXIuW44YfQGUHDMeJhleu6X7GPbKoNV_aJwGLa5Ws,11676
247
+ evalrx/eval_agent/stages/diagnosis.py,sha256=ly6hmA5pzgoNrZ_Jz7NSHh3Jb86YNP5D8v7D9ivOBGY,46068
248
+ evalrx/eval_agent/stages/experiment_writer.py,sha256=QSYnkD09TV8Kvi_tM9fo-RBHiHlGcVPlRV5lu_GPkl0,64777
249
+ evalrx/eval_agent/stages/fix_agent.py,sha256=gaPRS532x4R9_3jkGgz1MhpuAlToZYaP45GFp25DpzY,184289
250
+ evalrx/eval_agent/stages/fix_internals.py,sha256=EtuoVNy8UutCXnVJJ9__-eCis0HzzLk6VvrjclM10d0,22007
251
+ evalrx/eval_agent/stages/fix_pipeline.py,sha256=etRH236n_0_C_G0JltSsuDqb06M588Ir-ho4h5lwq-A,32087
252
+ evalrx/eval_agent/stages/fix_tiers.py,sha256=MbT8OK6h9Dlx3IcdoHqa8vz3UMj8GDXxkF-IrJQm6t4,7967
253
+ evalrx/eval_agent/stages/fix_tools.py,sha256=CAdYXyaVN1jyP_cHY7vpj8MRynInxyXLoWV3vqBkybQ,42645
254
+ evalrx/eval_agent/stages/hypothesis_tester.py,sha256=LsBzyeU1CjEHJr0ZW2JTBwbLS9Eu1j7hn5MC8gG7SQA,47471
255
+ evalrx/eval_agent/stages/probe.py,sha256=f0ENvUNL0SNTo87yvRHwyDlIBB06VMQm4C-x5mcgBA8,22597
256
+ evalrx/eval_agent/stages/probe_agent.py,sha256=ZGG-jZi5BssphYDRpLrbE8ngOzaFTFyIQqiZQaM571U,47839
257
+ evalrx/eval_agent/stages/probe_candidate_generator.py,sha256=A6qYrU1m1ViQs_XrF4rIi9jeDiI3DeHjn4C47kk97uM,5570
258
+ evalrx/eval_agent/stages/probe_generator.py,sha256=KctIz4kNgnNxGVP2QwHcggpZkn9AvRckGSERjlS0MCA,12803
259
+ evalrx/eval_agent/stages/probe_search_agent.py,sha256=WqemodLbfGK77yXYs1spvr5blgTmFyOKbM1sWVL8uHE,4450
260
+ evalrx/eval_agent/stages/protocol.py,sha256=gtXO871XpsPvJwfD0QB6aFBiHNk8nLUR53i9Be8YD_8,4601
261
+ evalrx/eval_agent/stages/repair_catalog.py,sha256=7GSwksPf01S-duzDs55Y3XW4140_WLzMAaud_JBk--Y,11971
262
+ evalrx/eval_agent/stages/surgery.py,sha256=YrsHwY3rxocLTHFZSqbW-2TSRT3TMcYQqsWZXkt-9zw,22980
263
+ evalrx/eval_agent/stages/whitebox_probe_generator.py,sha256=_bh5XG6ShcuNJH6Y7DExCCM666PsPsJNSrK-RfiQwyQ,14104
264
+ evalrx/models/__init__.py,sha256=0SIFkv7nfWJqRH1kU25pJtGgfr63iOa6lZrHdte3JAw,5904
265
+ evalrx/models/_discover.py,sha256=Tnyjrc5c2DiE7cAd1VQDfCYdJPMTfSCRfrAm2PHQZHw,4295
266
+ evalrx/models/agent.py,sha256=0JqsN7OJgnVTQQuXZX2Bx6KdtqY80RXVVbJ4cMIfWjg,15171
267
+ evalrx/models/base.py,sha256=4sUYHC1l_MG8Wcu7vW9D2j3-VHDBtTK3AMMJRtfpgT4,777
268
+ evalrx/models/compose.py,sha256=h9JTZFLTSJGGYPalscufNLJWIqqVmPHwtBOdBQ64yqU,2631
269
+ evalrx/models/inference.py,sha256=njTjhlzVx3S9qpLmzTy92dKqKFPj3Jmp0i4ZIeoaq9Q,3419
270
+ evalrx/models/toolcodec.py,sha256=KDF490mGR_UxIfy03Tegw_Ih8ivUHCQFXvVB2RP8EQY,5778
271
+ evalrx/models/backends/__init__.py,sha256=UogjEUFoF-k2pTp0-QRve2N-L746nG0dpro-aQQ3tEM,1571
272
+ evalrx/models/backends/api.py,sha256=yFypbxhjwUNk3t8PYq4HIQ02oeSirjL0IWvN9ZY0VDE,7253
273
+ evalrx/models/backends/base.py,sha256=SFQ6qvzg0qhY94IH7dgKz0zGgFOjFF0NuMGBdC_vlnY,2546
274
+ evalrx/models/backends/gemini_compat.py,sha256=cA3eSonUs5oQwDzugKdJx_MBTgbYSZ9_P7F4hOcCtVg,25157
275
+ evalrx/models/backends/hf_local.py,sha256=CLeMchpPtdPe2J-_90vDKBUe0puG89-AVfD3nEwfoUs,96064
276
+ evalrx/models/backends/openai_compat.py,sha256=iKJqOMUz37-NqzUJb1HJ2IVOgJexJSl5E2ueI5xiQ6M,11386
277
+ evalrx/models/backends/vllm_offline.py,sha256=NrvNZ9Rr0MikkbV-GrPbmRoFnLdjadAmMOdXrNb1JHo,5036
278
+ evalrx/models/blackbox/__init__.py,sha256=AUlmaewF4C1LeeIZKx_YwcOEg9ylX9NTVwRlPMGHlZI,152
279
+ evalrx/models/blackbox/agent.py,sha256=0u6wzH-imiwpb_8bVnizfAc04IfdJLJP07ggZ_PAHMM,920
280
+ evalrx/models/blackbox/base.py,sha256=cYcD851XwZiO9mLzBUoVRgjqaUdpin9YsY-J1KxE-X0,986
281
+ evalrx/models/blackbox/gemini.py,sha256=yKC-cvKxabn83u3Wm08IXm-5zCA_o9f_BjC3ZZMkkVQ,10943
282
+ evalrx/models/blackbox/llm_api.py,sha256=OL-93SIux1a-7y_XgaWQxitje4OhuqD0aPXGu8dr2Ys,443
283
+ evalrx/models/blackbox/vlm_api.py,sha256=VZZqcfSeo8aENPLZsDGoVRbMFDLGQqwLGrclbJR2VhY,404
284
+ evalrx/models/paper_methods/__init__.py,sha256=69S7uOO7mNFxsIwChgLIebxVPelSMjY7HEBj8vT_E1U,311
285
+ evalrx/models/paper_methods/aad.py,sha256=Kpee8JeSLV40gwF6CnXbxkOCDFp_3Z5U2q-sPKcvaVo,2034
286
+ evalrx/models/paper_methods/ifcd.py,sha256=wVT45knZ82I1UhnettSaHeP9vxZvcTh3hUo38Vldowc,9128
287
+ evalrx/models/paper_methods/pai.py,sha256=UXGTQ1NzXmzzHpWJEiV5QYYt4EaNl_J6zFSeCXew_cM,7039
288
+ evalrx/models/paper_methods/tcd.py,sha256=iN6ffaL28dIUafgauSLnDZDP6_Un8HDqAfXoeSqTar8,9671
289
+ evalrx/models/paper_methods/vcd.py,sha256=tj2WLj3BVLM00qT3GitbdjfaMGiMp2NrYmjasWATThA,1694
290
+ evalrx/models/paper_methods/vicrop.py,sha256=y49jL6w-ZHcO27-OpT2XYbJxOhMSxMsaTfysvKfah1I,5915
291
+ evalrx/models/tools/__init__.py,sha256=rY0jBaFMICvoKafdWzHJC7kOC7v90pI-UzFRb-4CVkM,1017
292
+ evalrx/models/tools/perception.py,sha256=PTQfIVH1gDGjIdWZES27l2o753ikTK_lCG0ANAfH-u4,11116
293
+ evalrx/models/tools/visual.py,sha256=CHtgCPIbyf3QyqwfO-qDHaXXyAGz7BY0U5TjKFwVVnE,6298
294
+ evalrx/models/whitebox/__init__.py,sha256=vybx5GZEVJAsDjpaoswcpIDsGCGxqLqbxvrwJH2JtvY,1244
295
+ evalrx/models/whitebox/agent.py,sha256=KPts4fcMiYs5Txl_O7A7ilbScXSOGnnPy0VmliN-DBE,1004
296
+ evalrx/models/whitebox/base.py,sha256=pRSGImeLMP1dN6DJ_d9XFLzpEaDQ-ojynW6FqHLckU0,747
297
+ evalrx/models/whitebox/qwen.py,sha256=0kG2xNJOKBBj5ufvb9TLldSjs0xgRj4LJGffJv0_3BI,2412
298
+ evalrx/models/whitebox/qwen2_5_omni.py,sha256=9naB84B4-BSzaFMZjHxFDfiAqm7o7OFrhXVvdZ69sMI,1042
299
+ evalrx/models/whitebox/qwen2_audio.py,sha256=SsM_-ab1tEhzCe65DKHXfIBLl597ir8yNfAEgfcvdtw,814
300
+ evalrx/models/whitebox/qwen_omni.py,sha256=s_OHN1sUapNeY7WLm395yFkCJVqnPFuobALTg9deukg,1960
301
+ evalrx/models/whitebox/qwen_vl.py,sha256=qsQ2N62-SxWRQKoXDv6t9ktp6QnDIJ5_JhBEKn8Jxgg,2386
302
+ evalrx/observability/__init__.py,sha256=kJwtD8c36wqJwlFsEkp5iFQ4GceaMAm9l-b-Y0WDjNk,505
303
+ evalrx/observability/envelope.py,sha256=fRc_cf9-429PNnNzuJ6s116fZn9hbEfUEk06e2_5NY8,4683
304
+ evalrx/observability/outbox.py,sha256=lL_3_ZkqdtkjP_5kx9ailTsb9WnBbL2-s3lRsHlAggQ,4569
305
+ evalrx/observability/tracer.py,sha256=jUshB_Z9bIvT7Be4etq-71GDA8RdiHmlAPRzfZehjKs,35390
306
+ evalrx/reporting/__init__.py,sha256=fzYxG3d2jcJ_ueh8cq_OUTnr0DZkW9f7DewugvTho9A,748
307
+ evalrx/reporting/case_study.py,sha256=G6hqA6Q_rquNu4zAATOhu_6AvjJx-qCMI0OTw5CHrVE,42198
308
+ evalrx/reporting/compiler.py,sha256=w5cU0p1cuDVjvDSEDLvpUTg9iqalTRQ098TGpSunyGI,23572
309
+ evalrx/reporting/dynamic.py,sha256=-_XKY9rvK6iiD9_Lb6GlyUmfpB87wKOvQBSSm7bLdmE,91618
310
+ evalrx/reporting/html_report.py,sha256=KDLiQ-QvrhJXP0darzYpTEz6VDBW44a-wfDZNuOuRlc,121047
311
+ evalrx/reporting/langfuse_exporter.py,sha256=JCCIgvx2Eu4jhWYZ14c4Yth2-Ksb5vGNG3x_V1r4Q6M,1083
312
+ evalrx/reporting/langfuse_source.py,sha256=N9xo1fGa26o_cxrxFGVl8Pvmh0Fpo_21Jkg348PvqDc,6578
313
+ evalrx/reporting/model.py,sha256=jfD6DueYl4Cd_eiEGPXuCNWyaCbXUv7xLMZwBQEv3FE,4773
314
+ evalrx/reporting/run_events.py,sha256=OEMEjkR0gARbAT6g9kUk18hPibRFX4WVd8rkMaxpycU,7128
315
+ evalrx/reporting/server.py,sha256=D7QZzV8y3JF2V8AVQSdqYw4Oh-URvbpEPpZE5oUbUfU,24150
316
+ evalrx/reporting/stages.py,sha256=YH9DGat2rPw2B1HJ9Xu3oiE7Yvx6pv7LMJz6P-nln5Y,2273
317
+ evalrx/reporting/static_export.py,sha256=y5qtAU-TFGPxnuxmXecYO_TY3KIxpLWGjlYfyAJTO2c,6141
318
+ evalrx/reporting/web_dist/index.html,sha256=EKmbParQFygBGnlzRzCFNtavMU0_bAwJI4cD9jT1mZs,1995243
319
+ evalrx/stats/__init__.py,sha256=MmkpDvPbP97cXnldVF3B6ZKcusJjrYHb1ZAoUQQx-Uk,1410
320
+ evalrx/stats/api.py,sha256=rhDsDBCYReQmHIRN-GfGVAGFO4zKUX5_g0qIbwptAK0,8635
321
+ evalrx/stats/bootstrap.py,sha256=EXwEn7M5ZIWYytNGy5s3dy-ptPrIhiLVv0aju6j5cKU,3442
322
+ evalrx/stats/ebh.py,sha256=FBY_u1EbZK24Z0XyZEWggcTlQj88kRiKgpSveujh-IM,958
323
+ evalrx/stats/evalue.py,sha256=Yz4m92z11qYcOcRrrptBIh2ce-tiGDpxH-jvZS-nhJo,4172
324
+ evalrx/stats/friedman.py,sha256=nJls3WQiUen8VoXaQ4v6LBvv-hmQ0vgRdrOE8t6Zu6Y,4691
325
+ evalrx/stats/mcnemar.py,sha256=CWZfiqzxTSslb89u0AZkc7lAz421MDsXjUKFJq6W7Os,1625
326
+ evalrx/stats/multiplicity.py,sha256=rszVJbuJed1gxHibeNPC8vmpCQk6LuGu-Oo7ED7pwFc,5778
327
+ evalrx/stats/subset_sampling.py,sha256=KpNHP0XNWD6lg_NYPjYOFa7bGoyrZEB8ZFfn_ylkD5g,1782
328
+ evalrx/viz/__init__.py,sha256=-oS5dBK4VTrK2l1FprIU1O2OQ_Z8Wc3klvh1msvbtfc,294
329
+ evalrx/viz/labels.py,sha256=8fx93Ia8N3w_fRp1GfGgIhMlIzmYTRaHgGQkekBTjyw,2886
330
+ evalrx/viz/prompts.py,sha256=8hPZUHrZ0rNbENSlMH-sMz0TgZ0ITnb35o85zZ_crnA,1767
331
+ evalrx/viz/renderer.py,sha256=CTwhF9B_SzccHXHWdQX-qppKkYuTY4Z3gg6rRWVP0QI,26404
332
+ evalrx/viz/schema.py,sha256=j0IHoVVbbIOEB7_kHZxVujyjKC_6JjZh7R7uoXhtEG4,724
333
+ evalrx/viz/style.py,sha256=528Y4zQAIqthPhJDbTGC7FiMmzi4CFuh1giSXS5EFI4,4789
334
+ evalrx-0.1.2.dist-info/licenses/LICENSE,sha256=ogEPNDSH0_dhiv_lT3ifVIdgIzHAqNA_SemnxUfPBJk,7048
335
+ evalrx-0.1.2.dist-info/METADATA,sha256=DE8PJTDbD0_fZTUm9fcImBnpc9d7hwDwkF9BxAlWkxA,25880
336
+ evalrx-0.1.2.dist-info/WHEEL,sha256=YVMoNqKzERt-wjUZwJ33xBGAwnFl-4cqbYkTtWa4itE,91
337
+ evalrx-0.1.2.dist-info/entry_points.txt,sha256=CnZiyipSEH5oy1ynveMBRAEmHZ7SdV4NTrjB_OJxH2k,85
338
+ evalrx-0.1.2.dist-info/top_level.txt,sha256=39LaClxelCxkFG_CorGPhxCallMaU5__VrFa7oaAO0E,7
339
+ evalrx-0.1.2.dist-info/RECORD,,
@@ -0,0 +1,5 @@
1
+ Wheel-Version: 1.0
2
+ Generator: setuptools (84.0.0)
3
+ Root-Is-Purelib: true
4
+ Tag: py3-none-any
5
+
@@ -0,0 +1,3 @@
1
+ [console_scripts]
2
+ evalrx = evalrx.cli:main
3
+ evalrx-explore = evalrx.analysis.cli:main
@@ -0,0 +1,121 @@
1
+ Creative Commons Legal Code
2
+
3
+ CC0 1.0 Universal
4
+
5
+ CREATIVE COMMONS CORPORATION IS NOT A LAW FIRM AND DOES NOT PROVIDE
6
+ LEGAL SERVICES. DISTRIBUTION OF THIS DOCUMENT DOES NOT CREATE AN
7
+ ATTORNEY-CLIENT RELATIONSHIP. CREATIVE COMMONS PROVIDES THIS
8
+ INFORMATION ON AN "AS-IS" BASIS. CREATIVE COMMONS MAKES NO WARRANTIES
9
+ REGARDING THE USE OF THIS DOCUMENT OR THE INFORMATION OR WORKS
10
+ PROVIDED HEREUNDER, AND DISCLAIMS LIABILITY FOR DAMAGES RESULTING FROM
11
+ THE USE OF THIS DOCUMENT OR THE INFORMATION OR WORKS PROVIDED
12
+ HEREUNDER.
13
+
14
+ Statement of Purpose
15
+
16
+ The laws of most jurisdictions throughout the world automatically confer
17
+ exclusive Copyright and Related Rights (defined below) upon the creator
18
+ and subsequent owner(s) (each and all, an "owner") of an original work of
19
+ authorship and/or a database (each, a "Work").
20
+
21
+ Certain owners wish to permanently relinquish those rights to a Work for
22
+ the purpose of contributing to a commons of creative, cultural and
23
+ scientific works ("Commons") that the public can reliably and without fear
24
+ of later claims of infringement build upon, modify, incorporate in other
25
+ works, reuse and redistribute as freely as possible in any form whatsoever
26
+ and for any purposes, including without limitation commercial purposes.
27
+ These owners may contribute to the Commons to promote the ideal of a free
28
+ culture and the further production of creative, cultural and scientific
29
+ works, or to gain reputation or greater distribution for their Work in
30
+ part through the use and efforts of others.
31
+
32
+ For these and/or other purposes and motivations, and without any
33
+ expectation of additional consideration or compensation, the person
34
+ associating CC0 with a Work (the "Affirmer"), to the extent that he or she
35
+ is an owner of Copyright and Related Rights in the Work, voluntarily
36
+ elects to apply CC0 to the Work and publicly distribute the Work under its
37
+ terms, with knowledge of his or her Copyright and Related Rights in the
38
+ Work and the meaning and intended legal effect of CC0 on those rights.
39
+
40
+ 1. Copyright and Related Rights. A Work made available under CC0 may be
41
+ protected by copyright and related or neighboring rights ("Copyright and
42
+ Related Rights"). Copyright and Related Rights include, but are not
43
+ limited to, the following:
44
+
45
+ i. the right to reproduce, adapt, distribute, perform, display,
46
+ communicate, and translate a Work;
47
+ ii. moral rights retained by the original author(s) and/or performer(s);
48
+ iii. publicity and privacy rights pertaining to a person's image or
49
+ likeness depicted in a Work;
50
+ iv. rights protecting against unfair competition in regards to a Work,
51
+ subject to the limitations in paragraph 4(a), below;
52
+ v. rights protecting the extraction, dissemination, use and reuse of data
53
+ in a Work;
54
+ vi. database rights (such as those arising under Directive 96/9/EC of the
55
+ European Parliament and of the Council of 11 March 1996 on the legal
56
+ protection of databases, and under any national implementation
57
+ thereof, including any amended or successor version of such
58
+ directive); and
59
+ vii. other similar, equivalent or corresponding rights throughout the
60
+ world based on applicable law or treaty, and any national
61
+ implementations thereof.
62
+
63
+ 2. Waiver. To the greatest extent permitted by, but not in contravention
64
+ of, applicable law, Affirmer hereby overtly, fully, permanently,
65
+ irrevocably and unconditionally waives, abandons, and surrenders all of
66
+ Affirmer's Copyright and Related Rights and associated claims and causes
67
+ of action, whether now known or unknown (including existing as well as
68
+ future claims and causes of action), in the Work (i) in all territories
69
+ worldwide, (ii) for the maximum duration provided by applicable law or
70
+ treaty (including future time extensions), (iii) in any current or future
71
+ medium and for any number of copies, and (iv) for any purpose whatsoever,
72
+ including without limitation commercial, advertising or promotional
73
+ purposes (the "Waiver"). Affirmer makes the Waiver for the benefit of each
74
+ member of the public at large and to the detriment of Affirmer's heirs and
75
+ successors, fully intending that such Waiver shall not be subject to
76
+ revocation, rescission, cancellation, termination, or any other legal or
77
+ equitable action to disrupt the quiet enjoyment of the Work by the public
78
+ as contemplated by Affirmer's express Statement of Purpose.
79
+
80
+ 3. Public License Fallback. Should any part of the Waiver for any reason
81
+ be judged legally invalid or ineffective under applicable law, then the
82
+ Waiver shall be preserved to the maximum extent permitted taking into
83
+ account Affirmer's express Statement of Purpose. In addition, to the
84
+ extent the Waiver is so judged Affirmer hereby grants to each affected
85
+ person a royalty-free, non transferable, non sublicensable, non exclusive,
86
+ irrevocable and unconditional license to exercise Affirmer's Copyright and
87
+ Related Rights in the Work (i) in all territories worldwide, (ii) for the
88
+ maximum duration provided by applicable law or treaty (including future
89
+ time extensions), (iii) in any current or future medium and for any number
90
+ of copies, and (iv) for any purpose whatsoever, including without
91
+ limitation commercial, advertising or promotional purposes (the
92
+ "License"). The License shall be deemed effective as of the date CC0 was
93
+ applied by Affirmer to the Work. Should any part of the License for any
94
+ reason be judged legally invalid or ineffective under applicable law, such
95
+ partial invalidity or ineffectiveness shall not invalidate the remainder
96
+ of the License, and in such case Affirmer hereby affirms that he or she
97
+ will not (i) exercise any of his or her remaining Copyright and Related
98
+ Rights in the Work or (ii) assert any associated claims and causes of
99
+ action with respect to the Work, in either case contrary to Affirmer's
100
+ express Statement of Purpose.
101
+
102
+ 4. Limitations and Disclaimers.
103
+
104
+ a. No trademark or patent rights held by Affirmer are waived, abandoned,
105
+ surrendered, licensed or otherwise affected by this document.
106
+ b. Affirmer offers the Work as-is and makes no representations or
107
+ warranties of any kind concerning the Work, express, implied,
108
+ statutory or otherwise, including without limitation warranties of
109
+ title, merchantability, fitness for a particular purpose, non
110
+ infringement, or the absence of latent or other defects, accuracy, or
111
+ the present or absence of errors, whether or not discoverable, all to
112
+ the greatest extent permissible under applicable law.
113
+ c. Affirmer disclaims responsibility for clearing rights of other persons
114
+ that may apply to the Work or any use thereof, including without
115
+ limitation any person's Copyright and Related Rights in the Work.
116
+ Further, Affirmer disclaims responsibility for obtaining any necessary
117
+ consents, permissions or other rights required for any use of the
118
+ Work.
119
+ d. Affirmer understands and acknowledges that Creative Commons is not a
120
+ party to this document and has no duty or obligation with respect to
121
+ this CC0 or use of the Work.
@@ -0,0 +1 @@
1
+ evalrx