Slow Triage
Exact reviewed source / 54 of 64

review/metrics.json

SHA-256 of original bytes
cf771971e57fd9dc9922802e08d9ee35dfdcad2023f3efa47f796d4510d5623e
{
  "synthetic": true,
  "claims": "Small fixed synthetic diagnostic only; no human time savings measured and no real-repository generalization established.",
  "fixtureManifestVerified": true,
  "referenceExactTextOverlap": [],
  "model": {
    "name": "Xenova/all-MiniLM-L6-v2",
    "revision": "751bff37182d3f1213fa05d7196b954e230abad9",
    "dtype": "q8",
    "dimensions": 384,
    "maxTokens": 256,
    "license": "Apache-2.0",
    "offline": true
  },
  "thresholds": {
    "minimumSimilarity": 0.4,
    "minimumMargin": 0.04,
    "duplicateSimilarity": 0.83
  },
  "classification": {
    "count": 40,
    "correct": 15,
    "accuracy": 0.375,
    "confusionMatrix": {
      "bug": {
        "bug": 1,
        "feature": 0,
        "documentation": 0,
        "question": 0,
        "unsure": 7,
        "rejected": 0
      },
      "feature": {
        "bug": 0,
        "feature": 1,
        "documentation": 0,
        "question": 0,
        "unsure": 7,
        "rejected": 0
      },
      "documentation": {
        "bug": 0,
        "feature": 0,
        "documentation": 4,
        "question": 0,
        "unsure": 4,
        "rejected": 0
      },
      "question": {
        "bug": 0,
        "feature": 0,
        "documentation": 0,
        "question": 2,
        "unsure": 6,
        "rejected": 0
      },
      "unsure": {
        "bug": 0,
        "feature": 0,
        "documentation": 0,
        "question": 0,
        "unsure": 7,
        "rejected": 1
      },
      "rejected": {
        "bug": 0,
        "feature": 0,
        "documentation": 0,
        "question": 0,
        "unsure": 0,
        "rejected": 0
      }
    },
    "perLabel": {
      "bug": {
        "support": 8,
        "precision": 1.0,
        "recall": 0.125,
        "f1": 0.2222222222222222
      },
      "feature": {
        "support": 8,
        "precision": 1.0,
        "recall": 0.125,
        "f1": 0.2222222222222222
      },
      "documentation": {
        "support": 8,
        "precision": 1.0,
        "recall": 0.5,
        "f1": 0.6666666666666666
      },
      "question": {
        "support": 8,
        "precision": 1.0,
        "recall": 0.25,
        "f1": 0.4
      },
      "unsure": {
        "support": 8,
        "precision": 0.22580645161290322,
        "recall": 0.875,
        "f1": 0.358974358974359
      }
    },
    "macroF1": 0.37401709401709404,
    "abstentionCount": 31,
    "abstentionRate": 0.775,
    "rejectedCount": 1,
    "coverage": 0.2,
    "accuracyAmongAnswered": 1.0
  },
  "rawTopLabelClassification": {
    "count": 40,
    "correct": 26,
    "accuracy": 0.65,
    "confusionMatrix": {
      "bug": {
        "bug": 6,
        "feature": 0,
        "documentation": 2,
        "question": 0,
        "unsure": 0,
        "rejected": 0
      },
      "feature": {
        "bug": 1,
        "feature": 5,
        "documentation": 1,
        "question": 1,
        "unsure": 0,
        "rejected": 0
      },
      "documentation": {
        "bug": 0,
        "feature": 0,
        "documentation": 8,
        "question": 0,
        "unsure": 0,
        "rejected": 0
      },
      "question": {
        "bug": 0,
        "feature": 0,
        "documentation": 1,
        "question": 7,
        "unsure": 0,
        "rejected": 0
      },
      "unsure": {
        "bug": 3,
        "feature": 3,
        "documentation": 1,
        "question": 0,
        "unsure": 0,
        "rejected": 1
      },
      "rejected": {
        "bug": 0,
        "feature": 0,
        "documentation": 0,
        "question": 0,
        "unsure": 0,
        "rejected": 0
      }
    },
    "perLabel": {
      "bug": {
        "support": 8,
        "precision": 0.6,
        "recall": 0.75,
        "f1": 0.6666666666666665
      },
      "feature": {
        "support": 8,
        "precision": 0.625,
        "recall": 0.625,
        "f1": 0.625
      },
      "documentation": {
        "support": 8,
        "precision": 0.6153846153846154,
        "recall": 1.0,
        "f1": 0.761904761904762
      },
      "question": {
        "support": 8,
        "precision": 0.875,
        "recall": 0.875,
        "f1": 0.875
      },
      "unsure": {
        "support": 8,
        "precision": 0,
        "recall": 0.0,
        "f1": 0
      }
    },
    "macroF1": 0.5857142857142856,
    "abstentionCount": 0,
    "abstentionRate": 0.0,
    "rejectedCount": 1,
    "coverage": 0.975,
    "accuracyAmongAnswered": 0.6666666666666666
  },
  "keywordBaseline": {
    "count": 40,
    "correct": 24,
    "accuracy": 0.6,
    "confusionMatrix": {
      "bug": {
        "bug": 3,
        "feature": 0,
        "documentation": 0,
        "question": 0,
        "unsure": 5,
        "rejected": 0
      },
      "feature": {
        "bug": 0,
        "feature": 5,
        "documentation": 0,
        "question": 0,
        "unsure": 3,
        "rejected": 0
      },
      "documentation": {
        "bug": 0,
        "feature": 1,
        "documentation": 5,
        "question": 0,
        "unsure": 2,
        "rejected": 0
      },
      "question": {
        "bug": 0,
        "feature": 1,
        "documentation": 0,
        "question": 6,
        "unsure": 1,
        "rejected": 0
      },
      "unsure": {
        "bug": 0,
        "feature": 0,
        "documentation": 2,
        "question": 1,
        "unsure": 5,
        "rejected": 0
      },
      "rejected": {
        "bug": 0,
        "feature": 0,
        "documentation": 0,
        "question": 0,
        "unsure": 0,
        "rejected": 0
      }
    },
    "perLabel": {
      "bug": {
        "support": 8,
        "precision": 1.0,
        "recall": 0.375,
        "f1": 0.5454545454545454
      },
      "feature": {
        "support": 8,
        "precision": 0.7142857142857143,
        "recall": 0.625,
        "f1": 0.6666666666666666
      },
      "documentation": {
        "support": 8,
        "precision": 0.7142857142857143,
        "recall": 0.625,
        "f1": 0.6666666666666666
      },
      "question": {
        "support": 8,
        "precision": 0.8571428571428571,
        "recall": 0.75,
        "f1": 0.7999999999999999
      },
      "unsure": {
        "support": 8,
        "precision": 0.3125,
        "recall": 0.625,
        "f1": 0.4166666666666667
      }
    },
    "macroF1": 0.619090909090909,
    "abstentionCount": 16,
    "abstentionRate": 0.4,
    "rejectedCount": 0,
    "coverage": 0.6,
    "accuracyAmongAnswered": 0.7916666666666666
  },
  "classificationFailures": [
    {
      "fixtureId": "heldout-002",
      "title": "Search drops accented characters",
      "expected": "bug",
      "observed": "unsure",
      "rawSuggestedLabel": "bug",
      "similarity": 0.31691886865612806,
      "margin": 0.09499784081287282
    },
    {
      "fixtureId": "heldout-003",
      "title": "Next page returns the first page again",
      "expected": "bug",
      "observed": "unsure",
      "rawSuggestedLabel": "bug",
      "similarity": 0.3209102342294865,
      "margin": 0.08245770582829931
    },
    {
      "fixtureId": "heldout-004",
      "title": "Deleting a draft also removes the published copy",
      "expected": "bug",
      "observed": "unsure",
      "rawSuggestedLabel": "bug",
      "similarity": 0.22369145427902837,
      "margin": 0.019362608622608996
    },
    {
      "fixtureId": "heldout-005",
      "title": "Expired session gets an infinite redirect loop",
      "expected": "bug",
      "observed": "unsure",
      "rawSuggestedLabel": "documentation",
      "similarity": 0.20031679174045436,
      "margin": 0.004790127325585897
    },
    {
      "fixtureId": "heldout-006",
      "title": "A valid configuration is rejected after upgrading",
      "expected": "bug",
      "observed": "unsure",
      "rawSuggestedLabel": "documentation",
      "similarity": 0.38372008443491556,
      "margin": 0.07271489393168207
    },
    {
      "fixtureId": "heldout-007",
      "title": "Download produces a zero-byte archive",
      "expected": "bug",
      "observed": "unsure",
      "rawSuggestedLabel": "bug",
      "similarity": 0.3654824885963447,
      "margin": 0.16743207989225148
    },
    {
      "fixtureId": "heldout-008",
      "title": "Retry button does not retry",
      "expected": "bug",
      "observed": "unsure",
      "rawSuggestedLabel": "bug",
      "similarity": 0.23744552364420712,
      "margin": 0.0548599137200812
    },
    {
      "fixtureId": "heldout-009",
      "title": "Let us pin favorite workspaces",
      "expected": "feature",
      "observed": "unsure",
      "rawSuggestedLabel": "feature",
      "similarity": 0.30298730957483455,
      "margin": 0.0809370624944632
    },
    {
      "fixtureId": "heldout-010",
      "title": "Provide a machine-readable command output option",
      "expected": "feature",
      "observed": "unsure",
      "rawSuggestedLabel": "documentation",
      "similarity": 0.15680882765931548,
      "margin": 0.003234162286219505
    },
    {
      "fixtureId": "heldout-011",
      "title": "Add a configurable retention period",
      "expected": "feature",
      "observed": "unsure",
      "rawSuggestedLabel": "feature",
      "similarity": 0.2704935731669698,
      "margin": 0.1348431633305376
    },
    {
      "fixtureId": "heldout-012",
      "title": "Support importing newline-delimited JSON",
      "expected": "feature",
      "observed": "unsure",
      "rawSuggestedLabel": "feature",
      "similarity": 0.258090359025198,
      "margin": 0.12696420655872892
    },
    {
      "fixtureId": "heldout-014",
      "title": "Request a read-only project role",
      "expected": "feature",
      "observed": "unsure",
      "rawSuggestedLabel": "question",
      "similarity": 0.1577232519718602,
      "margin": 0.0011212976622386739
    },
    {
      "fixtureId": "heldout-015",
      "title": "Offer an undo operation for archiving",
      "expected": "feature",
      "observed": "unsure",
      "rawSuggestedLabel": "feature",
      "similarity": 0.35220094685446207,
      "margin": 0.18254807618538396
    },
    {
      "fixtureId": "heldout-016",
      "title": "Allow sorting by last successful run",
      "expected": "feature",
      "observed": "unsure",
      "rawSuggestedLabel": "bug",
      "similarity": 0.183475057487055,
      "margin": 0.09443991962345641
    },
    {
      "fixtureId": "heldout-019",
      "title": "Explain the units of the timeout option",
      "expected": "documentation",
      "observed": "unsure",
      "rawSuggestedLabel": "documentation",
      "similarity": 0.24593982761064337,
      "margin": 0.028791182908548152
    },
    {
      "fixtureId": "heldout-020",
      "title": "Update the quickstart code sample",
      "expected": "documentation",
      "observed": "unsure",
      "rawSuggestedLabel": "documentation",
      "similarity": 0.33435597124685906,
      "margin": 0.16869413683050238
    },
    {
      "fixtureId": "heldout-022",
      "title": "The migration guide skips a rename",
      "expected": "documentation",
      "observed": "unsure",
      "rawSuggestedLabel": "documentation",
      "similarity": 0.30095196430970306,
      "margin": 0.03749232973938876
    },
    {
      "fixtureId": "heldout-024",
      "title": "Add a troubleshooting section to the manual",
      "expected": "documentation",
      "observed": "unsure",
      "rawSuggestedLabel": "documentation",
      "similarity": 0.3206273157851509,
      "margin": 0.01509125591616195
    },
    {
      "fixtureId": "heldout-026",
      "title": "Can existing jobs share one cache?",
      "expected": "question",
      "observed": "unsure",
      "rawSuggestedLabel": "question",
      "similarity": 0.14499380545436105,
      "margin": 0.04747730482587681
    },
    {
      "fixtureId": "heldout-027",
      "title": "What does the queued status mean?",
      "expected": "question",
      "observed": "unsure",
      "rawSuggestedLabel": "question",
      "similarity": 0.24506617054350713,
      "margin": 0.121169123828293
    },
    {
      "fixtureId": "heldout-028",
      "title": "Where can I find the logs?",
      "expected": "question",
      "observed": "unsure",
      "rawSuggestedLabel": "documentation",
      "similarity": 0.21972172315457267,
      "margin": 0.010762111635235272
    },
    {
      "fixtureId": "heldout-030",
      "title": "Which setting limits concurrent workers?",
      "expected": "question",
      "observed": "unsure",
      "rawSuggestedLabel": "question",
      "similarity": 0.24336263306485956,
      "margin": 0.0056780048828297125
    },
    {
      "fixtureId": "heldout-031",
      "title": "Does deleting a local copy affect the server?",
      "expected": "question",
      "observed": "unsure",
      "rawSuggestedLabel": "question",
      "similarity": 0.13517322815819105,
      "margin": 0.06361004243122156
    },
    {
      "fixtureId": "heldout-032",
      "title": "How can I cancel a running export?",
      "expected": "question",
      "observed": "unsure",
      "rawSuggestedLabel": "question",
      "similarity": 0.33059763098099393,
      "margin": 0.03460661000095605
    },
    {
      "fixtureId": "heldout-040",
      "title": "",
      "expected": "unsure",
      "observed": "rejected",
      "rawSuggestedLabel": null,
      "similarity": null,
      "margin": null
    }
  ],
  "rejectedInputs": [
    {
      "fixtureId": "heldout-040",
      "id": 1040,
      "error": "Every issue needs a title of 1\u2013300 characters."
    }
  ],
  "duplicates": {
    "items": 28,
    "trueUniquePairs": 8,
    "predictedUniquePairs": 8,
    "truePositivePairs": 7,
    "precision": 0.875,
    "recall": 0.875,
    "f1": 0.875,
    "falsePositivePairs": [
      [
        2000,
        3006
      ]
    ],
    "missedPairs": [
      [
        2008,
        2009
      ]
    ],
    "top1PositiveAnchors": 16,
    "top1Correct": 15,
    "top1Recall": 0.9375,
    "top1Details": [
      {
        "id": 2000,
        "nearestCandidateId": 3006,
        "similarity": 0.8467967829217281,
        "correct": false
      },
      {
        "id": 2001,
        "nearestCandidateId": 2000,
        "similarity": 0.8418473852003064,
        "correct": true
      },
      {
        "id": 2002,
        "nearestCandidateId": 2003,
        "similarity": 0.8772852109564382,
        "correct": true
      },
      {
        "id": 2003,
        "nearestCandidateId": 2002,
        "similarity": 0.8772852109564382,
        "correct": true
      },
      {
        "id": 2004,
        "nearestCandidateId": 2005,
        "similarity": 0.8968869256682411,
        "correct": true
      },
      {
        "id": 2005,
        "nearestCandidateId": 2004,
        "similarity": 0.8968869256682411,
        "correct": true
      },
      {
        "id": 2006,
        "nearestCandidateId": 2007,
        "similarity": 0.85970670731982,
        "correct": true
      },
      {
        "id": 2007,
        "nearestCandidateId": 2006,
        "similarity": 0.85970670731982,
        "correct": true
      },
      {
        "id": 2008,
        "nearestCandidateId": 2009,
        "similarity": 0.7246551750429989,
        "correct": true
      },
      {
        "id": 2009,
        "nearestCandidateId": 2008,
        "similarity": 0.7246551750429989,
        "correct": true
      },
      {
        "id": 2010,
        "nearestCandidateId": 2011,
        "similarity": 0.8888269888733635,
        "correct": true
      },
      {
        "id": 2011,
        "nearestCandidateId": 2010,
        "similarity": 0.8888269888733635,
        "correct": true
      },
      {
        "id": 2012,
        "nearestCandidateId": 2013,
        "similarity": 1,
        "correct": true
      },
      {
        "id": 2013,
        "nearestCandidateId": 2012,
        "similarity": 1,
        "correct": true
      },
      {
        "id": 2014,
        "nearestCandidateId": 2015,
        "similarity": 1,
        "correct": true
      },
      {
        "id": 2015,
        "nearestCandidateId": 2014,
        "similarity": 1,
        "correct": true
      }
    ],
    "invalidCandidates": [],
    "threshold": 0.83,
    "interpretation": "Threshold suggestions point to an earlier item; nearest-candidate retrieval is across all other items. Scores are cosine similarity, not probabilities or proof."
  },
  "timingMs": {
    "modelLoadMs": 125.48320000000001,
    "referenceEmbeddingMs": 49.205917,
    "classificationWallMs": 105.320741,
    "duplicateWallMs": 76.24322299999994,
    "warmRepeatWallMs": 107.59672
  },
  "processPeakRssKiB": 261600,
  "nodeVersion": "v24.19.0",
  "realVectorEvidence": {
    "count": 2,
    "dimensions": 384,
    "finite": true,
    "firstSixPerVector": [
      [
        -0.0038394939620047808,
        -0.05189432203769684,
        0.02111446112394333,
        -0.043545182794332504,
        0.08614278584718704,
        -0.09509851038455963
      ],
      [
        0.03972547873854637,
        0.033752620220184326,
        0.030181316658854485,
        0.04185470938682556,
        -0.013174621388316154,
        -0.08983414620161057
      ]
    ],
    "vectorsDiffer": true
  },
  "warmRepeatPredictionsIdentical": true,
  "sourceFreeze": {
    "frozenAtUtc": "2026-10-19T22:35:20.411012+00:00",
    "files": {
      "package.json": "d738b7a364bd3d70a97046719ac87077601dd8b0d39f548d7ca2eb22795368c2",
      "package-lock.json": "cee984f4133cc4df05633d618327db162be4335c94ee44f8ca10557bfc8518f8",
      "src/core.mjs": "0090c8143ae3a4fe53194a564457d99983025f5dc7b009ef9e4f28f902709a9b",
      "src/model.mjs": "7273332e105fcb43cd9c5bbe378fa63138d05da897cfb948f010e09a8f6c2351",
      "src/server.mjs": "13832e0dfbca254cd346da388c9bb2077248251258927b74627c6e3d8b36231a",
      "src/workflow.mjs": "a5771dab8a7f234b55e475b4fd1eb72e441bef91d846f7367c60079cd9532697",
      "data/reference.json": "249505ab8a46972bc515e4427f8738a4314446488efd8499bbf2f4cc360b70d4",
      "scripts/triage.mjs": "91a6856d2a53d9f6212a4430dcdf9018d9a2c3a279d85389bc2da49788b1433d",
      "models/Xenova/all-MiniLM-L6-v2/onnx/model_quantized.onnx": "afdb6f1a0e45b715d0bb9b11772f032c399babd23bfc31fed1c170afc848bdb1",
      "models/Xenova/all-MiniLM-L6-v2/config.json": "7135149f7cffa1a573466c6e4d8423ed73b62fd2332c575bf738a0d033f70df7",
      "models/Xenova/all-MiniLM-L6-v2/tokenizer_config.json": "9261e7d79b44c8195c1cada2b453e55b00aeb81e907a6664974b4d7776172ab3"
    }
  }
}
← review/heldout_duplicates.jsonreview/network_guard.mjs →