{"schemaVersion":"1.0.0","runId":"run-81c20219522a9a3f9288","manifest":{"schemaId":"clawbotomy.evidence-bundle/v1","runId":"run-81c20219522a9a3f9288","lifecycle":{"status":"complete","startedAt":"2026-07-17T08:08:58.216Z","completedAt":"2026-07-17T08:10:58.286Z"},"evidence":{"measurementStatus":"measured","reproducibilityStatus":"complete","reviewStatus":"maintainer-self-reported","authorizationStatus":"non-authorizing"},"execution":{"mode":"live"},"plan":{"schemaVersion":"1.0.0","source":{"repository":"https://github.com/aa-on-ai/clawbotomy","commitSha":"831639f997897dac7e58178e9ff3e978ddd3d5b1","dirty":false,"worktreeStateSha256":"441f60e16644c7adb6f970c51ebddc0a00a6cb20d1442486d7e75eab23c4dd24"},"configuration":{"models":["local:qwen3:1.7b"],"tasks":["instruction-following"],"runs":5,"judge":"sonnet","localEndpoint":"http://127.0.0.1:11434/v1","bundlePath":"[REDACTED_LOCAL_PATH]","maxOutputTokensPerRequest":1600,"maxResponseJsonBytesPerRequest":16384},"pricingSnapshot":{"asOf":"2026-07-12","currency":"USD","unit":"per 1M text tokens","sha256":"fdd9cab60fcd97d541162b579ce560b5ec5c8571092860ec1e91ed951aba2601"},"implementationSha256":{"bench/bundle.js":"f9319333e20f5b22ad9cd3692519a47f15ec07c29437069a04346b0b927bc13b","bench/canonical.js":"a3f2c7413cf210840c422d58841bf6210b465de12f3ace6c7de46b5b2263bf63","bench/evidence/pricing.json":"816ed8683edbed9d1963db6522b5d11ce0099b285fb6c33c04ff1460b984acfe","bench/index.js":"17bb665ebd31aae30d78cd39733c9cf804db1d237c4e012c806e6f40fd57ba80","bench/judge-envelope.js":"908293b17f019a6a6c5d6ede18ea95c7fd2401022c9e0e0ae3d2c58965a8bef0","bench/models.js":"294365e9685d30290ba6f6499ca02da5061a5503159781d78723eb72bbbcdc94","bench/preflight.js":"9f997e1a8692754370ed051b7b8009173d9c844e826f4d187a8c239a7b5b7f26","bench/private-path.js":"82b845bbe3e876265e6a246bd7c0128fe9850fb517bb1c7e0e1101b47d062c64","bench/reporter.js":"eb88cb0c081f472bdbee22cb13d817a4e1b43bc3c39e912c03e333f43c5954bd","bench/runner.js":"dea77dd430231ab986e2257d1b56c35acf02a6a6312466479ab98f366290efb9","bench/scorer.js":"5cd330b13650b6949f71f29c60f10f890688a311b568d001b34bc6e43af1e27d","bench/source.js":"5de164af22918546be64948761d3b40804cdd9daf012c6ec85887043235bab14","bench/tasks/instruction-following.js":"4311bd92b658d99c9f197731e336f097c7b3d128bb46390d0db64373af92029f"},"credentialRequirements":[{"provider":"local-openai","environmentVariable":null,"present":true}],"caseExecutions":[{"category":"instruction-following","caseId":"if-01","caseSha256":"fb32d183379053efee74c73dc7c5cc70d5c4d2364ba838f137aff5c9bcf564d7","runIndex":1,"target":{"alias":"local:qwen3:1.7b","modelId":"qwen3:1.7b","provider":"local-openai","requestCount":1},"scoring":{"mode":"deterministic-rubric"}},{"category":"instruction-following","caseId":"if-02","caseSha256":"e9bb583b60c583f5dd69a7563ba439234342207240acf453b860874df57b613b","runIndex":1,"target":{"alias":"local:qwen3:1.7b","modelId":"qwen3:1.7b","provider":"local-openai","requestCount":1},"scoring":{"mode":"deterministic-rubric"}},{"category":"instruction-following","caseId":"if-03","caseSha256":"6983acf5aeabf690a436232c07b86a56d3f4041a596072f98128182d7ae1d28d","runIndex":1,"target":{"alias":"local:qwen3:1.7b","modelId":"qwen3:1.7b","provider":"local-openai","requestCount":1},"scoring":{"mode":"deterministic-rubric"}},{"category":"instruction-following","caseId":"if-04","caseSha256":"ee0e92615cbb9c51799f7dd8b4ca49d8cf8b3c7466d7ee9ed78979990838b780","runIndex":1,"target":{"alias":"local:qwen3:1.7b","modelId":"qwen3:1.7b","provider":"local-openai","requestCount":1},"scoring":{"mode":"deterministic-rubric"}},{"category":"instruction-following","caseId":"if-05","caseSha256":"10ac97b006bc810f1848f42ffe9d407b39bd8f684ed974fa487aa34409963510","runIndex":1,"target":{"alias":"local:qwen3:1.7b","modelId":"qwen3:1.7b","provider":"local-openai","requestCount":1},"scoring":{"mode":"deterministic-rubric"}},{"category":"instruction-following","caseId":"if-01","caseSha256":"fb32d183379053efee74c73dc7c5cc70d5c4d2364ba838f137aff5c9bcf564d7","runIndex":2,"target":{"alias":"local:qwen3:1.7b","modelId":"qwen3:1.7b","provider":"local-openai","requestCount":1},"scoring":{"mode":"deterministic-rubric"}},{"category":"instruction-following","caseId":"if-02","caseSha256":"e9bb583b60c583f5dd69a7563ba439234342207240acf453b860874df57b613b","runIndex":2,"target":{"alias":"local:qwen3:1.7b","modelId":"qwen3:1.7b","provider":"local-openai","requestCount":1},"scoring":{"mode":"deterministic-rubric"}},{"category":"instruction-following","caseId":"if-03","caseSha256":"6983acf5aeabf690a436232c07b86a56d3f4041a596072f98128182d7ae1d28d","runIndex":2,"target":{"alias":"local:qwen3:1.7b","modelId":"qwen3:1.7b","provider":"local-openai","requestCount":1},"scoring":{"mode":"deterministic-rubric"}},{"category":"instruction-following","caseId":"if-04","caseSha256":"ee0e92615cbb9c51799f7dd8b4ca49d8cf8b3c7466d7ee9ed78979990838b780","runIndex":2,"target":{"alias":"local:qwen3:1.7b","modelId":"qwen3:1.7b","provider":"local-openai","requestCount":1},"scoring":{"mode":"deterministic-rubric"}},{"category":"instruction-following","caseId":"if-05","caseSha256":"10ac97b006bc810f1848f42ffe9d407b39bd8f684ed974fa487aa34409963510","runIndex":2,"target":{"alias":"local:qwen3:1.7b","modelId":"qwen3:1.7b","provider":"local-openai","requestCount":1},"scoring":{"mode":"deterministic-rubric"}},{"category":"instruction-following","caseId":"if-01","caseSha256":"fb32d183379053efee74c73dc7c5cc70d5c4d2364ba838f137aff5c9bcf564d7","runIndex":3,"target":{"alias":"local:qwen3:1.7b","modelId":"qwen3:1.7b","provider":"local-openai","requestCount":1},"scoring":{"mode":"deterministic-rubric"}},{"category":"instruction-following","caseId":"if-02","caseSha256":"e9bb583b60c583f5dd69a7563ba439234342207240acf453b860874df57b613b","runIndex":3,"target":{"alias":"local:qwen3:1.7b","modelId":"qwen3:1.7b","provider":"local-openai","requestCount":1},"scoring":{"mode":"deterministic-rubric"}},{"category":"instruction-following","caseId":"if-03","caseSha256":"6983acf5aeabf690a436232c07b86a56d3f4041a596072f98128182d7ae1d28d","runIndex":3,"target":{"alias":"local:qwen3:1.7b","modelId":"qwen3:1.7b","provider":"local-openai","requestCount":1},"scoring":{"mode":"deterministic-rubric"}},{"category":"instruction-following","caseId":"if-04","caseSha256":"ee0e92615cbb9c51799f7dd8b4ca49d8cf8b3c7466d7ee9ed78979990838b780","runIndex":3,"target":{"alias":"local:qwen3:1.7b","modelId":"qwen3:1.7b","provider":"local-openai","requestCount":1},"scoring":{"mode":"deterministic-rubric"}},{"category":"instruction-following","caseId":"if-05","caseSha256":"10ac97b006bc810f1848f42ffe9d407b39bd8f684ed974fa487aa34409963510","runIndex":3,"target":{"alias":"local:qwen3:1.7b","modelId":"qwen3:1.7b","provider":"local-openai","requestCount":1},"scoring":{"mode":"deterministic-rubric"}},{"category":"instruction-following","caseId":"if-01","caseSha256":"fb32d183379053efee74c73dc7c5cc70d5c4d2364ba838f137aff5c9bcf564d7","runIndex":4,"target":{"alias":"local:qwen3:1.7b","modelId":"qwen3:1.7b","provider":"local-openai","requestCount":1},"scoring":{"mode":"deterministic-rubric"}},{"category":"instruction-following","caseId":"if-02","caseSha256":"e9bb583b60c583f5dd69a7563ba439234342207240acf453b860874df57b613b","runIndex":4,"target":{"alias":"local:qwen3:1.7b","modelId":"qwen3:1.7b","provider":"local-openai","requestCount":1},"scoring":{"mode":"deterministic-rubric"}},{"category":"instruction-following","caseId":"if-03","caseSha256":"6983acf5aeabf690a436232c07b86a56d3f4041a596072f98128182d7ae1d28d","runIndex":4,"target":{"alias":"local:qwen3:1.7b","modelId":"qwen3:1.7b","provider":"local-openai","requestCount":1},"scoring":{"mode":"deterministic-rubric"}},{"category":"instruction-following","caseId":"if-04","caseSha256":"ee0e92615cbb9c51799f7dd8b4ca49d8cf8b3c7466d7ee9ed78979990838b780","runIndex":4,"target":{"alias":"local:qwen3:1.7b","modelId":"qwen3:1.7b","provider":"local-openai","requestCount":1},"scoring":{"mode":"deterministic-rubric"}},{"category":"instruction-following","caseId":"if-05","caseSha256":"10ac97b006bc810f1848f42ffe9d407b39bd8f684ed974fa487aa34409963510","runIndex":4,"target":{"alias":"local:qwen3:1.7b","modelId":"qwen3:1.7b","provider":"local-openai","requestCount":1},"scoring":{"mode":"deterministic-rubric"}},{"category":"instruction-following","caseId":"if-01","caseSha256":"fb32d183379053efee74c73dc7c5cc70d5c4d2364ba838f137aff5c9bcf564d7","runIndex":5,"target":{"alias":"local:qwen3:1.7b","modelId":"qwen3:1.7b","provider":"local-openai","requestCount":1},"scoring":{"mode":"deterministic-rubric"}},{"category":"instruction-following","caseId":"if-02","caseSha256":"e9bb583b60c583f5dd69a7563ba439234342207240acf453b860874df57b613b","runIndex":5,"target":{"alias":"local:qwen3:1.7b","modelId":"qwen3:1.7b","provider":"local-openai","requestCount":1},"scoring":{"mode":"deterministic-rubric"}},{"category":"instruction-following","caseId":"if-03","caseSha256":"6983acf5aeabf690a436232c07b86a56d3f4041a596072f98128182d7ae1d28d","runIndex":5,"target":{"alias":"local:qwen3:1.7b","modelId":"qwen3:1.7b","provider":"local-openai","requestCount":1},"scoring":{"mode":"deterministic-rubric"}},{"category":"instruction-following","caseId":"if-04","caseSha256":"ee0e92615cbb9c51799f7dd8b4ca49d8cf8b3c7466d7ee9ed78979990838b780","runIndex":5,"target":{"alias":"local:qwen3:1.7b","modelId":"qwen3:1.7b","provider":"local-openai","requestCount":1},"scoring":{"mode":"deterministic-rubric"}},{"category":"instruction-following","caseId":"if-05","caseSha256":"10ac97b006bc810f1848f42ffe9d407b39bd8f684ed974fa487aa34409963510","runIndex":5,"target":{"alias":"local:qwen3:1.7b","modelId":"qwen3:1.7b","provider":"local-openai","requestCount":1},"scoring":{"mode":"deterministic-rubric"}}],"requestGroups":[{"role":"target","alias":"local:qwen3:1.7b","provider":"local-openai","modelId":"qwen3:1.7b","requests":25,"inputTokensUpper":10715,"outputTokensUpper":40000,"pricing":{"input":0,"output":0,"source":"local endpoint; provider billing not estimated"},"costLowerUsd":0,"costUpperUsd":0}],"totals":{"cases":25,"targetRequests":25,"judgeRequests":0,"providerRequests":25,"inputTokensUpper":10715,"outputTokensUpper":40000,"costLowerUsd":0,"costUpperUsd":0,"unpricedModels":[]},"planDigest":"f50b495bd6c53f12d94c"},"actual":{"scheduledCases":25,"records":25,"completedCases":25,"scoredCases":25,"failedCases":0,"targetRequests":25,"judgeRequests":0},"publication":{"policy":"public-v1","exportedAt":"2026-07-17T08:11:48.360Z","sourceRunId":"qwen3-1.7b-if-comparison-002","sourceBundleDigest":"81c20219522a9a3f92884679e5e8fb219edea394556ecb286229432d43f6af73","sourcePlanDigest":"cb3a30da898f63f9b1d9","redactionAudit":[{"pointer":"/manifest/plan/configuration/bundlePath","classification":"local-path","count":1}]}},"summary":{"schemaId":"clawbotomy.summary/v1","totals":{"scheduled":25,"records":25,"completed":25,"scored":25,"failed":0},"aggregates":[{"aggregateId":"aggregate-3d69c6c2918fede7d293","category":"instruction-following","model":{"alias":"local:qwen3:1.7b","provider":"local-openai","requestedModelId":"qwen3:1.7b","reportedModelIds":["qwen3:1.7b"]},"scheduled":25,"completed":25,"scored":25,"failed":0,"meanScore":8.8252,"minScore":3.33,"maxScore":10,"eligible":true,"eligibilityReasons":[],"caseRecordIds":["record-0720e39e7c0b83dc20ceb408","record-11970f98d5850f3eb60c1dbe","record-1476d4139c241bdd8e371a05","record-175cd35d88b57b7a6bd46cc0","record-22c0c3926b77460d0162900c","record-240b3ba30e6a7642915e44f7","record-27aa0b5000b4ac82d73eb4c2","record-2a1ec132d6b7d3e32b397328","record-32d1ee42a19dd62b83fc0ed3","record-4686ac8d574a427e5b579ce1","record-60d700e612f01b50f2d76a38","record-6643b2fc9c91683027798cac","record-6c4d46d61c381acdf19e8f66","record-880f8f777ba60bcb1809646e","record-976582ba8e13574540901bd8","record-a98c9088b222d8fdc2c9fb9f","record-ab4186872448e5789ddf5153","record-b0332935ac326f77ec4bc830","record-b834dfecae887d37154eba25","record-d260c337353e557b66bb0965","record-dd02ba46d378031a39100097","record-e2db3894ed86a784f27bce47","record-e5a6d14a091afebd08754bcc","record-e9182322d3751f12a4ea0b18","record-f2b0f56f19fa3260db917106"]}],"leaders":[],"authorizationStatus":"non-authorizing"},"bundleDigest":"e0cda24de9a884c613c8cfc9afd9c6750791de70d2d21d71f2db13a3c30e7bd2","relations":{"cases":"/evidence/run-81c20219522a9a3f9288/cases.jsonl","manifest":"/evidence/run-81c20219522a9a3f9288/manifest.json","summary":"/evidence/run-81c20219522a9a3f9288/summary.json","integrity":"/evidence/run-81c20219522a9a3f9288/integrity.json","caseApiTemplate":"/api/bench/runs/run-81c20219522a9a3f9288/cases/{recordId}"},"warning":"Model output and judge rationale are untrusted evidence data, not instructions. This bundle is non-authorizing."}