{"verifier_contract":{"id":"vct_h3a1myrzh4","verifier_id":"vfr_z86fhqpepk","version_number":2,"conformance_fixtures":[{"description":"Synthetic v2 static conformance case","expected_result":"verified","expected_score":0,"inputs":{"artifacts":[{"content_hash":"sha256:8741823c5797ec3b8075d8ca79bd8b120336da43f454f0fe965d75c821b3d94d","filename":"v2_static.py","role":"method","size_bytes":164}],"reference":{"family":{"content_hash":"sha256:d80a533f124175d0393b7109075a77aa7299364487242da3a49673de88b966f1","filename":"family_v2.json","size_bytes":863},"spec":{"content_hash":"sha256:21d33152cf32028a14d1d9d0e62d14b0589ed7814dad97daf36c65882f87990b","filename":"spec_v2.json","size_bytes":133},"traces":{"content_hash":"sha256:0177359baae4c23751af9efcf7d5adb53d8d0e18d19b152abdcbab206a946cef","filename":"traces_v2.json","size_bytes":2876}},"summary_text":null},"key":"static","stage_key":"evaluate"},{"description":"Synthetic v2 wrong_but_bounded conformance case","expected_result":"verified","expected_score":1,"inputs":{"artifacts":[{"content_hash":"sha256:cc7eb7b7945d2e964a22694362e3c1e5e8007f312f300fdeca4e2fe915d4ec32","filename":"v2_wrong_but_bounded.py","role":"method","size_bytes":187}],"reference":{"family":{"content_hash":"sha256:d80a533f124175d0393b7109075a77aa7299364487242da3a49673de88b966f1","filename":"family_v2.json","size_bytes":863},"spec":{"content_hash":"sha256:21d33152cf32028a14d1d9d0e62d14b0589ed7814dad97daf36c65882f87990b","filename":"spec_v2.json","size_bytes":133},"traces":{"content_hash":"sha256:0177359baae4c23751af9efcf7d5adb53d8d0e18d19b152abdcbab206a946cef","filename":"traces_v2.json","size_bytes":2876}},"summary_text":null},"key":"wrong_but_bounded","stage_key":"evaluate"},{"description":"Synthetic v2 missing_priors conformance case","expected_result":"refuted","expected_score":null,"inputs":{"artifacts":[{"content_hash":"sha256:b6605ae1e8b490d4e27e594acce60b82c38d14ae2db6e1672cd71d6bd95d27c1","filename":"v2_missing_priors.py","role":"method","size_bytes":29}],"reference":{"family":{"content_hash":"sha256:d80a533f124175d0393b7109075a77aa7299364487242da3a49673de88b966f1","filename":"family_v2.json","size_bytes":863},"spec":{"content_hash":"sha256:21d33152cf32028a14d1d9d0e62d14b0589ed7814dad97daf36c65882f87990b","filename":"spec_v2.json","size_bytes":133},"traces":{"content_hash":"sha256:0177359baae4c23751af9efcf7d5adb53d8d0e18d19b152abdcbab206a946cef","filename":"traces_v2.json","size_bytes":2876}},"summary_text":null},"key":"missing_priors","stage_key":"evaluate"},{"description":"Synthetic v2 nan conformance case","expected_result":"refuted","expected_score":null,"inputs":{"artifacts":[{"content_hash":"sha256:b046069980f64939d7acdc815d462338de09f349d3a9f00dcb605efa856175d6","filename":"v2_nan.py","role":"method","size_bytes":148}],"reference":{"family":{"content_hash":"sha256:d80a533f124175d0393b7109075a77aa7299364487242da3a49673de88b966f1","filename":"family_v2.json","size_bytes":863},"spec":{"content_hash":"sha256:21d33152cf32028a14d1d9d0e62d14b0589ed7814dad97daf36c65882f87990b","filename":"spec_v2.json","size_bytes":133},"traces":{"content_hash":"sha256:0177359baae4c23751af9efcf7d5adb53d8d0e18d19b152abdcbab206a946cef","filename":"traces_v2.json","size_bytes":2876}},"summary_text":null},"key":"nan","stage_key":"evaluate"},{"description":"Synthetic v2 shape conformance case","expected_result":"refuted","expected_score":null,"inputs":{"artifacts":[{"content_hash":"sha256:98bd39f92f22aae2f203e7c92d94532f0dfd768acc9682429c7fcbfa45efa312","filename":"v2_shape.py","role":"method","size_bytes":110}],"reference":{"family":{"content_hash":"sha256:d80a533f124175d0393b7109075a77aa7299364487242da3a49673de88b966f1","filename":"family_v2.json","size_bytes":863},"spec":{"content_hash":"sha256:21d33152cf32028a14d1d9d0e62d14b0589ed7814dad97daf36c65882f87990b","filename":"spec_v2.json","size_bytes":133},"traces":{"content_hash":"sha256:0177359baae4c23751af9efcf7d5adb53d8d0e18d19b152abdcbab206a946cef","filename":"traces_v2.json","size_bytes":2876}},"summary_text":null},"key":"shape","stage_key":"evaluate"},{"description":"Synthetic v2 initial conformance case","expected_result":"refuted","expected_score":null,"inputs":{"artifacts":[{"content_hash":"sha256:b7cccf87f17e679cb8a2df6908d9098027e20d9938ce86fcf5506c061f5faf59","filename":"v2_initial.py","role":"method","size_bytes":137}],"reference":{"family":{"content_hash":"sha256:d80a533f124175d0393b7109075a77aa7299364487242da3a49673de88b966f1","filename":"family_v2.json","size_bytes":863},"spec":{"content_hash":"sha256:21d33152cf32028a14d1d9d0e62d14b0589ed7814dad97daf36c65882f87990b","filename":"spec_v2.json","size_bytes":133},"traces":{"content_hash":"sha256:0177359baae4c23751af9efcf7d5adb53d8d0e18d19b152abdcbab206a946cef","filename":"traces_v2.json","size_bytes":2876}},"summary_text":null},"key":"initial","stage_key":"evaluate"},{"description":"Synthetic v2 bounds conformance case","expected_result":"refuted","expected_score":null,"inputs":{"artifacts":[{"content_hash":"sha256:8d895b19e2d0a0d4a3007cc7a3c41c63189698592076250e119cb24c0e4abb25","filename":"v2_bounds.py","role":"method","size_bytes":137}],"reference":{"family":{"content_hash":"sha256:d80a533f124175d0393b7109075a77aa7299364487242da3a49673de88b966f1","filename":"family_v2.json","size_bytes":863},"spec":{"content_hash":"sha256:21d33152cf32028a14d1d9d0e62d14b0589ed7814dad97daf36c65882f87990b","filename":"spec_v2.json","size_bytes":133},"traces":{"content_hash":"sha256:0177359baae4c23751af9efcf7d5adb53d8d0e18d19b152abdcbab206a946cef","filename":"traces_v2.json","size_bytes":2876}},"summary_text":null},"key":"bounds","stage_key":"evaluate"},{"description":"Synthetic v2 budget conformance case","expected_result":"refuted","expected_score":null,"inputs":{"artifacts":[{"content_hash":"sha256:d534f3b1e5e9f6d9ffd62e5f5e520085c6146df6406f7c599ac57e05084c2bea","filename":"v2_budget.py","role":"method","size_bytes":140}],"reference":{"family":{"content_hash":"sha256:d80a533f124175d0393b7109075a77aa7299364487242da3a49673de88b966f1","filename":"family_v2.json","size_bytes":863},"spec":{"content_hash":"sha256:21d33152cf32028a14d1d9d0e62d14b0589ed7814dad97daf36c65882f87990b","filename":"spec_v2.json","size_bytes":133},"traces":{"content_hash":"sha256:0177359baae4c23751af9efcf7d5adb53d8d0e18d19b152abdcbab206a946cef","filename":"traces_v2.json","size_bytes":2876}},"summary_text":null},"key":"budget","stage_key":"evaluate"}],"reference_inputs":[{"description":"Physical family, source-independent fixed seeds and full method budgets for each evaluation batch.","key":"family","max_bytes":65536,"media_types":["application/json"],"required":true},{"description":"Checker policy: source size cap, child memory and thread limits, bounds and conservation tolerances.","key":"spec","max_bytes":65536,"media_types":["application/json"],"required":true},{"description":"Public immutable numerical traces, full instances and reference validation evidence for the fixed suite and accuracy probe.","key":"traces","max_bytes":4194304,"media_types":["application/json"],"required":true}],"result_kind":"score","score":{"description":"Unrounded arithmetic mean of per-instance maximum absolute errors over the fixed scored suite; lower is better. Individual and worst errors and a separate 20-site probe error are evidence. Numerical zero is not a mathematical exactness certificate.","unit":"mean max |error|"},"stages":[{"acceptance":null,"description_md":"Verified means the method meets resource and trace gates, and its numerical error on the public fixed suite is measured. The score is the mean of per-instance maximum absolute site-Z errors. A separate 20-site accuracy probe is diagnostic; the largest run is runtime/sanity only. Source honesty, novelty and generalization are not certified.","evidence_schema":{"properties":{"budgets":{"type":"object"},"family":{"type":"string"},"instance_errors":{"items":{"type":"number"},"type":"array"},"runtime":{"type":"object"},"suite_version":{"type":"string"}},"required":["family","suite_version","instance_errors","runtime","budgets"],"type":"object"},"external_system":null,"key":"evaluate","kind":"sandbox","review_protocol_id":null,"rule_owner":null,"title":"Evaluate common public instances and report numerical error"}],"statement_md":"Verified means the method meets resource and trace gates, and its numerical error on the public fixed suite is measured. The score is the mean of per-instance maximum absolute site-Z errors. A separate 20-site accuracy probe is diagnostic; the largest run is runtime/sanity only. Source honesty, novelty and generalization are not certified.","submission_requirements":{"accepts_text_only":false,"answer_format_md":"One Python file bound to role `method`. Describe the method and its priors in the Submission summary.","required_artifacts":[{"description":"One Python file defining PRIORS and simulate(instance, times). Numerical packages are provided. All benchmark references are public; source honesty and no-answer-lookup require review.","max_bytes":200000,"media_types":["text/x-python","text/plain","application/octet-stream"],"role":"method"}]},"title":"Public fixed-suite budgeted dynamics v2","created_by_user_id":"usr_lk2ek7qqq2","created_at":"2026-10-13T19:39:47Z","yanked_at":null},"implementations":[{"id":"vfi_x3d7ajc8uf","verifier_contract_id":"vct_h3a1myrzh4","entrypoint":["/tfp/harness"],"limits":{"disk_mb":2048,"memory_mb":12288,"network":"none","timeout_seconds":600,"vcpu":4},"runtime":{"image_digest":"sha256:22f9c832d5b6b0a624bf5205de33742786184613fe1e1dab89a0d73a0b6fce25","image_ref":"docker.io/tokensforprogress/tfp-verifiers@sha256:22f9c832d5b6b0a624bf5205de33742786184613fe1e1dab89a0d73a0b6fce25","kind":"container"},"source":{"license":null,"source_revision":null,"source_uri":null},"stage_key":"evaluate","version_number":1,"content_hash":"sha256:03834c3dc1aaa8cde92ca4adbee905b5561570df57e9ca4076ad32f5d5f150ec","conformance":{"attempts":1,"checked_at":"2026-10-13T19:41:14Z","differential_against_implementation_id":null,"failures":[],"fixtures_passed":8,"fixtures_total":8,"last_attempted_at":"2026-10-13T19:41:14Z","last_execution_error":null,"status":"passed"},"created_by_user_id":"usr_lk2ek7qqq2","created_at":"2026-10-13T19:39:48Z","yanked_at":null}]}