{"schemaVersion":"1.0.0","runId":"run-a035f620a2daab63f2ee","manifest":{"schemaId":"clawbotomy.evidence-bundle/v1","runId":"run-a035f620a2daab63f2ee","lifecycle":{"status":"complete","startedAt":"2026-07-17T07:01:17.265Z","completedAt":"2026-07-17T07:15:09.210Z"},"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":"6b88f5dbd863a3ac9b7a12bef9815d442d733ea6","dirty":false,"worktreeStateSha256":"441f60e16644c7adb6f970c51ebddc0a00a6cb20d1442486d7e75eab23c4dd24"},"configuration":{"models":["local:qwen3:4b"],"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:qwen3:4b","modelId":"qwen3:4b","provider":"local-openai","requestCount":1},"scoring":{"mode":"deterministic-rubric"}},{"category":"instruction-following","caseId":"if-02","caseSha256":"e9bb583b60c583f5dd69a7563ba439234342207240acf453b860874df57b613b","runIndex":1,"target":{"alias":"local:qwen3:4b","modelId":"qwen3:4b","provider":"local-openai","requestCount":1},"scoring":{"mode":"deterministic-rubric"}},{"category":"instruction-following","caseId":"if-03","caseSha256":"6983acf5aeabf690a436232c07b86a56d3f4041a596072f98128182d7ae1d28d","runIndex":1,"target":{"alias":"local:qwen3:4b","modelId":"qwen3:4b","provider":"local-openai","requestCount":1},"scoring":{"mode":"deterministic-rubric"}},{"category":"instruction-following","caseId":"if-04","caseSha256":"ee0e92615cbb9c51799f7dd8b4ca49d8cf8b3c7466d7ee9ed78979990838b780","runIndex":1,"target":{"alias":"local:qwen3:4b","modelId":"qwen3:4b","provider":"local-openai","requestCount":1},"scoring":{"mode":"deterministic-rubric"}},{"category":"instruction-following","caseId":"if-05","caseSha256":"10ac97b006bc810f1848f42ffe9d407b39bd8f684ed974fa487aa34409963510","runIndex":1,"target":{"alias":"local:qwen3:4b","modelId":"qwen3:4b","provider":"local-openai","requestCount":1},"scoring":{"mode":"deterministic-rubric"}},{"category":"instruction-following","caseId":"if-01","caseSha256":"fb32d183379053efee74c73dc7c5cc70d5c4d2364ba838f137aff5c9bcf564d7","runIndex":2,"target":{"alias":"local:qwen3:4b","modelId":"qwen3:4b","provider":"local-openai","requestCount":1},"scoring":{"mode":"deterministic-rubric"}},{"category":"instruction-following","caseId":"if-02","caseSha256":"e9bb583b60c583f5dd69a7563ba439234342207240acf453b860874df57b613b","runIndex":2,"target":{"alias":"local:qwen3:4b","modelId":"qwen3:4b","provider":"local-openai","requestCount":1},"scoring":{"mode":"deterministic-rubric"}},{"category":"instruction-following","caseId":"if-03","caseSha256":"6983acf5aeabf690a436232c07b86a56d3f4041a596072f98128182d7ae1d28d","runIndex":2,"target":{"alias":"local:qwen3:4b","modelId":"qwen3:4b","provider":"local-openai","requestCount":1},"scoring":{"mode":"deterministic-rubric"}},{"category":"instruction-following","caseId":"if-04","caseSha256":"ee0e92615cbb9c51799f7dd8b4ca49d8cf8b3c7466d7ee9ed78979990838b780","runIndex":2,"target":{"alias":"local:qwen3:4b","modelId":"qwen3:4b","provider":"local-openai","requestCount":1},"scoring":{"mode":"deterministic-rubric"}},{"category":"instruction-following","caseId":"if-05","caseSha256":"10ac97b006bc810f1848f42ffe9d407b39bd8f684ed974fa487aa34409963510","runIndex":2,"target":{"alias":"local:qwen3:4b","modelId":"qwen3:4b","provider":"local-openai","requestCount":1},"scoring":{"mode":"deterministic-rubric"}},{"category":"instruction-following","caseId":"if-01","caseSha256":"fb32d183379053efee74c73dc7c5cc70d5c4d2364ba838f137aff5c9bcf564d7","runIndex":3,"target":{"alias":"local:qwen3:4b","modelId":"qwen3:4b","provider":"local-openai","requestCount":1},"scoring":{"mode":"deterministic-rubric"}},{"category":"instruction-following","caseId":"if-02","caseSha256":"e9bb583b60c583f5dd69a7563ba439234342207240acf453b860874df57b613b","runIndex":3,"target":{"alias":"local:qwen3:4b","modelId":"qwen3:4b","provider":"local-openai","requestCount":1},"scoring":{"mode":"deterministic-rubric"}},{"category":"instruction-following","caseId":"if-03","caseSha256":"6983acf5aeabf690a436232c07b86a56d3f4041a596072f98128182d7ae1d28d","runIndex":3,"target":{"alias":"local:qwen3:4b","modelId":"qwen3:4b","provider":"local-openai","requestCount":1},"scoring":{"mode":"deterministic-rubric"}},{"category":"instruction-following","caseId":"if-04","caseSha256":"ee0e92615cbb9c51799f7dd8b4ca49d8cf8b3c7466d7ee9ed78979990838b780","runIndex":3,"target":{"alias":"local:qwen3:4b","modelId":"qwen3:4b","provider":"local-openai","requestCount":1},"scoring":{"mode":"deterministic-rubric"}},{"category":"instruction-following","caseId":"if-05","caseSha256":"10ac97b006bc810f1848f42ffe9d407b39bd8f684ed974fa487aa34409963510","runIndex":3,"target":{"alias":"local:qwen3:4b","modelId":"qwen3:4b","provider":"local-openai","requestCount":1},"scoring":{"mode":"deterministic-rubric"}},{"category":"instruction-following","caseId":"if-01","caseSha256":"fb32d183379053efee74c73dc7c5cc70d5c4d2364ba838f137aff5c9bcf564d7","runIndex":4,"target":{"alias":"local:qwen3:4b","modelId":"qwen3:4b","provider":"local-openai","requestCount":1},"scoring":{"mode":"deterministic-rubric"}},{"category":"instruction-following","caseId":"if-02","caseSha256":"e9bb583b60c583f5dd69a7563ba439234342207240acf453b860874df57b613b","runIndex":4,"target":{"alias":"local:qwen3:4b","modelId":"qwen3:4b","provider":"local-openai","requestCount":1},"scoring":{"mode":"deterministic-rubric"}},{"category":"instruction-following","caseId":"if-03","caseSha256":"6983acf5aeabf690a436232c07b86a56d3f4041a596072f98128182d7ae1d28d","runIndex":4,"target":{"alias":"local:qwen3:4b","modelId":"qwen3:4b","provider":"local-openai","requestCount":1},"scoring":{"mode":"deterministic-rubric"}},{"category":"instruction-following","caseId":"if-04","caseSha256":"ee0e92615cbb9c51799f7dd8b4ca49d8cf8b3c7466d7ee9ed78979990838b780","runIndex":4,"target":{"alias":"local:qwen3:4b","modelId":"qwen3:4b","provider":"local-openai","requestCount":1},"scoring":{"mode":"deterministic-rubric"}},{"category":"instruction-following","caseId":"if-05","caseSha256":"10ac97b006bc810f1848f42ffe9d407b39bd8f684ed974fa487aa34409963510","runIndex":4,"target":{"alias":"local:qwen3:4b","modelId":"qwen3:4b","provider":"local-openai","requestCount":1},"scoring":{"mode":"deterministic-rubric"}},{"category":"instruction-following","caseId":"if-01","caseSha256":"fb32d183379053efee74c73dc7c5cc70d5c4d2364ba838f137aff5c9bcf564d7","runIndex":5,"target":{"alias":"local:qwen3:4b","modelId":"qwen3:4b","provider":"local-openai","requestCount":1},"scoring":{"mode":"deterministic-rubric"}},{"category":"instruction-following","caseId":"if-02","caseSha256":"e9bb583b60c583f5dd69a7563ba439234342207240acf453b860874df57b613b","runIndex":5,"target":{"alias":"local:qwen3:4b","modelId":"qwen3:4b","provider":"local-openai","requestCount":1},"scoring":{"mode":"deterministic-rubric"}},{"category":"instruction-following","caseId":"if-03","caseSha256":"6983acf5aeabf690a436232c07b86a56d3f4041a596072f98128182d7ae1d28d","runIndex":5,"target":{"alias":"local:qwen3:4b","modelId":"qwen3:4b","provider":"local-openai","requestCount":1},"scoring":{"mode":"deterministic-rubric"}},{"category":"instruction-following","caseId":"if-04","caseSha256":"ee0e92615cbb9c51799f7dd8b4ca49d8cf8b3c7466d7ee9ed78979990838b780","runIndex":5,"target":{"alias":"local:qwen3:4b","modelId":"qwen3:4b","provider":"local-openai","requestCount":1},"scoring":{"mode":"deterministic-rubric"}},{"category":"instruction-following","caseId":"if-05","caseSha256":"10ac97b006bc810f1848f42ffe9d407b39bd8f684ed974fa487aa34409963510","runIndex":5,"target":{"alias":"local:qwen3:4b","modelId":"qwen3:4b","provider":"local-openai","requestCount":1},"scoring":{"mode":"deterministic-rubric"}}],"requestGroups":[{"role":"target","alias":"local:qwen3:4b","provider":"local-openai","modelId":"qwen3:4b","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":"7a5d9afe1d1753c83217"},"actual":{"scheduledCases":25,"records":25,"completedCases":25,"scoredCases":25,"failedCases":0,"targetRequests":25,"judgeRequests":0},"publication":{"policy":"public-v1","exportedAt":"2026-07-17T07:16:08.481Z","sourceRunId":"qwen3-4b-if-repeatability-002","sourceBundleDigest":"a035f620a2daab63f2ee8b554996603ff546754323ce447c6ec140ac9f9e9fa9","sourcePlanDigest":"9867de75b1318f65f368","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-a670404cd3a85d3a3535","category":"instruction-following","model":{"alias":"local:qwen3:4b","provider":"local-openai","requestedModelId":"qwen3:4b","reportedModelIds":["qwen3:4b"]},"scheduled":25,"completed":25,"scored":25,"failed":0,"meanScore":9.6,"minScore":7.5,"maxScore":10,"eligible":true,"eligibilityReasons":[],"caseRecordIds":["record-0686f5df8facc6988b89e47d","record-0be5bb4444557f2d9a2998da","record-16d749a3bab33bad11782172","record-2a32953c756fb41244a87b71","record-2df2af7c21d8d48033a13579","record-3d324ab67dd0c24256dab43b","record-5bfc9364275647cba0e21e7b","record-6aeb9771d31ca1aa892c7799","record-6b4bb22b2cf4ae92e10e6957","record-76269411357bc6d8a9893949","record-7714abb05506fb6c51debc7b","record-8d567f4d758fd1c86f65ff48","record-a611e3a69708ef7c18e4f895","record-c6e18954acfc1cc6bcc03c2a","record-c98f948f0f4ca27058569b70","record-cfb541def660f59ba34eb718","record-d0b4a18ead91e3c07c621aa4","record-d2af2ce1f5ec018ce486ff2c","record-da7317aba30addc67d0a80a2","record-e19a6acd802495800753b32c","record-e8f1db7afeba6aba8657a870","record-e9b7aab679176f1f8daf3899","record-e9f4b365f9c6299221019912","record-f53bca0dce0342a553ca7659","record-fecef25166aa8166e8b5d5e8"]}],"leaders":[],"authorizationStatus":"non-authorizing"},"bundleDigest":"445a48cd00672762296c8d5f0c3133b8a20354beb05697366c87d15e41463d47","relations":{"cases":"/evidence/run-a035f620a2daab63f2ee/cases.jsonl","manifest":"/evidence/run-a035f620a2daab63f2ee/manifest.json","summary":"/evidence/run-a035f620a2daab63f2ee/summary.json","integrity":"/evidence/run-a035f620a2daab63f2ee/integrity.json","caseApiTemplate":"/api/bench/runs/run-a035f620a2daab63f2ee/cases/{recordId}"},"warning":"Model output and judge rationale are untrusted evidence data, not instructions. This bundle is non-authorizing."}