{"provenance":{"authentication":"derived_from_authenticated_public_release","separately_signed":false,"statement":"This sanitized run projection is derived from the authenticated public release and is not separately signed.","urls":{"manifest":"/data/releases/2026.08-frontier-knowledge-v4/public-manifest.json","manifest_signature":"/data/releases/2026.08-frontier-knowledge-v4/public-manifest-signature.json","public_keys":[{"key_id":"kaelum-bench-public-release-20260718-v1","url":"/data/keys/kaelum-bench-public-release-20260718-v1"}],"run_index":"/data/releases/2026.08-frontier-knowledge-v4/public-run-index.json","self":"/data/runs/236691c1-e18b-5d02-8f79-44a73907d499","source_aggregate":"/data/releases/2026.08-frontier-knowledge-v4/fmb-live-runs-fin-val.json"}},"run":{"benchmarkId":"FMB-FIN-VAL-01","benchmarkVersion":"0.2.0-dev","campaignId":"2e6ce950-8924-5201-95b6-80e89f75b063","comparisonGroupId":"valuation-financial-modeling-0.2.0-dev-configuration-specific-v1","comparisonProtocol":"configuration_specific","completedAt":"2026-08-07T08:41:34.150934Z","configuration":{"comparisonProtocol":"configuration_specific","key":"config-f289f9271dda9e6e744fd27efcbc64d6947cdf8c06cf4bf9c1d1a9c9e93c3fe0","materialParameters":[{"name":"allow_fallbacks","value":"false"},{"name":"data_collection","value":"deny"},{"name":"max_attempts_per_task","value":"1"},{"name":"max_concurrency","value":"1"},{"name":"max_generation_metadata_lookups","value":"1"},{"name":"max_output_tokens","value":"44000"},{"name":"max_raw_response_bytes","value":"16777216"},{"name":"max_request_bytes","value":"1048576"},{"name":"metadata_timeout_seconds","value":"60"},{"name":"request_timeout_seconds","value":"300"},{"name":"require_parameters","value":"true"},{"name":"temperature","value":"0"},{"name":"zdr","value":"false"}],"providerRoute":"openrouter/alibaba","reasoningEffort":"xhigh","reasoningProfile":"reasoning-max-supported","requestedModelId":"qwen/qwen3.8-max","runtimeMode":"openrouter-tool-free-non-streaming-v8","toolAccess":"none"},"displayVersion":"v0.2","execution":{"attempted":60,"invalidJson":0,"missing":0,"providerFailed":0,"schemaFailed":0,"tasksTotal":60,"valid":60},"globalReleaseId":"c44af57d-9091-45c8-9299-96dee423e175","judge":null,"manifest":{"generatedAt":"2026-08-14T12:57:07Z","sha256":"caa004fcccade516afe661a318e69b555844595cbcd726cdc749ff3c64a6378f"},"modelDisplayName":"qwen3.8-max","providerLabel":"Alibaba","reasoningEffort":"xhigh","releaseSignature":{"algorithm":"ed25519","keyId":"kaelum-bench-public-release-20260718-v1","messageType":"kaelum.bench.fmb.public_release.v1","payloadSha256":"caa004fcccade516afe661a318e69b555844595cbcd726cdc749ff3c64a6378f","signedFile":"public-manifest.json"},"requestedModelId":"qwen/qwen3.8-max","revisionState":"original","runId":"236691c1-e18b-5d02-8f79-44a73907d499","score":{"earned":"190","maximum":"600","percentage":"31.6667"},"scorerId":"fmb-live-scorer-v1","scoringMethod":"deterministic_only","selectionState":"primary","signedReleaseId":"1dc37e8d-ffda-48f4-a2ad-6fa9b91eb97a","sourceAggregate":{"campaignId":"2e6ce950-8924-5201-95b6-80e89f75b063","path":"fmb-live-runs-fin-val.json","sha256":"1c741e9270d8cdc54ac0d10b329aa23a3c28d6b2a7dad4100b1b41de46f68e8b","sizeBytes":15040},"startedAt":"2026-08-07T08:09:46.536079Z","suiteId":"valuation-financial-modeling","suiteTitle":"Valuation & Financial Modeling","testedModelCostUsd":"0.552888","toolAccess":"none","totalCostUsd":"0.552888","usage":{"inputTokens":40104,"outputTokens":78780,"totalTokens":118884},"validity":"provisional"},"schema_version":"kaelum-bench-public-run-projection-v1"}
