{
  "schemaVersion": "kingy-document-three-pair-report/1.0.0",
  "metadata": {
    "schemaVersion": "kingy-document-three-pair-report/1.0.0",
    "studyId": "document-comparison-v24-20261018.1",
    "scopeDescription": "One shared Apple M4 Pro Mac, one separately frozen synthetic five-PDF/30-page English corpus,40 question clusters and three paired repetitions per workflow. Complete original answer deadlines are90seconds. Results describe these configured workflows only.",
    "limitations": [
      "40 unique question clusters repeated three times are not120independent questions or users.",
      "Synthetic selectable-text English PDFs on one shared M4 Pro system do not establish other hardware, models, OCR, private real-world documents or large libraries.",
      "The scorer is unchanged from v20: finite prospective aliases and source checks can leave unfamiliar wording unresolved; conservative lower bounds retain every unresolved outcome.",
      "Original failures and interruptions remain in evidence. Completion, strict method adherence, quality, installation/security and public-readback gates are separate.",
      "No overall winner, general hardware-upgrade, cost, speed or comparative privacy advantage is inferred.",
      "Review is AI-assisted, not human adjudication or independent hardware reproduction."
    ],
    "history": {
      "studyId": "document-comparison-v14-20261014.1",
      "href": "https://kingy.ai/wp-content/plugins/kingy-local-ai/app/documents/comparisons/document-comparison-v14-20261014.1/report.html"
    },
    "instrumentation": {
      "amended": false,
      "description": "V24 used the prospectively frozen preparation, bounded input-persistence and external one-shot System Events AXPress Send routes. Each native original used a distinct fresh conversation, the exact five PDF bytes and unchanged nine configuration groups. Source-bound fresh control runtimes, durable official logging, same-conversation first-user acceptance, original EOS/final-event evidence and both immutable90-second bounds were checked. Historical transport failures and repairs were preserved before this method/corpus freeze; no within-v24 transport or scientific-source amendment is asserted. Operator preparation and inter-original evidence-review pauses are outside per-query latency and do not establish setup speed, uninterrupted wall throughput or competitor reliability.",
      "evidenceIds": [
        "protocol",
        "freeze",
        "method-approval",
        "completion-eligibility",
        "session-provenance",
        "final-audit"
      ]
    },
    "repairedScorer": false,
    "engineeringRepair": true,
    "finalAudit": true,
    "artifacts": [
      {
        "id": "paired-results",
        "label": "Paired calculations and unresolved bounds (public derivative; original hash retained)",
        "sha256": "d15d9b827c7e0b0d0440afc6dd549168236c835549e2ad0111c13ba4cb89c3e1",
        "originalSha256": "d15d9b827c7e0b0d0440afc6dd549168236c835549e2ad0111c13ba4cb89c3e1",
        "privacyProjection": true,
        "role": "paired-results",
        "href": "evidence/paired-results.json",
        "bytes": 97901
      },
      {
        "id": "summaries",
        "label": "All six original-session summaries (public derivative; original hash retained)",
        "sha256": "6b19b267330e5b546c9b9949d6b3cc1830a3e34ad7978bf9ae82e60de365ae0d",
        "originalSha256": "af00e7c04884afbe97be021361d49d506c87e070259a7ebdb2d75010d98c6713",
        "privacyProjection": true,
        "role": "summaries",
        "href": "evidence/summaries.json",
        "bytes": 29191
      },
      {
        "id": "session-provenance",
        "label": "All six original-session provenance checks (public derivative; original hash retained)",
        "sha256": "50b47c705bbdc2f2e9e273fea7f0e7ec2bd9c78345f98434ec67fa1cd71cd83a",
        "originalSha256": "1cb76480dd3aad18603cbe872412e631078b105c6724b02d4db698c7377b349c",
        "privacyProjection": true,
        "role": "session-provenance",
        "href": "evidence/session-provenance.json",
        "bytes": 18918
      },
      {
        "id": "kingy-raw",
        "label": "All120 Kingy originals and frozen grades (public derivative; original hash retained)",
        "sha256": "ae1491ac449b06cb2c1731208b9fb6d0b397694eb005864a6cc456e020c9dfc2",
        "originalSha256": "cf85176126d315b58160d3cbb60d57f868afb6ed9e84b87cd85df86f5917b065",
        "privacyProjection": true,
        "role": "kingy-raw",
        "href": "evidence/kingy-raw.jsonl",
        "bytes": 342292
      },
      {
        "id": "native-raw",
        "label": "All120 normalized native originals and frozen grades (public derivative; original hash retained)",
        "sha256": "dce672a746eee02927bf2a61e7aedf06029fae8df6cde4a0bce6da30f1aa1b5f",
        "originalSha256": "f2e2baa5187b9a4cea5b8c3810381e0780e95bdb253558cb5f423ca3c5bc8424",
        "privacyProjection": true,
        "role": "native-raw",
        "href": "evidence/native-raw.jsonl",
        "bytes": 528191
      },
      {
        "id": "analysis-completion",
        "label": "Actual completed analysis and output hashes (public derivative; original hash retained)",
        "sha256": "aaadd02fde4486dc2720f43034bc95913a2f69e9fcfc8eedc3609cb549fb8e7d",
        "originalSha256": "aaadd02fde4486dc2720f43034bc95913a2f69e9fcfc8eedc3609cb549fb8e7d",
        "privacyProjection": true,
        "role": "analysis-completion",
        "href": "evidence/analysis-completion.json",
        "bytes": 1172
      },
      {
        "id": "protocol",
        "label": "Frozen prospective comparison protocol (public derivative; original hash retained)",
        "sha256": "d7b8c8a8559ed76925cd0257b023f59d152d6c29bec0d9e49229ddbed5bae0bc",
        "originalSha256": "d7b8c8a8559ed76925cd0257b023f59d152d6c29bec0d9e49229ddbed5bae0bc",
        "privacyProjection": true,
        "role": "protocol",
        "href": "evidence/protocol.md",
        "bytes": 18248
      },
      {
        "id": "scoring",
        "label": "Unchanged common atomic rubric1.5.0 (public derivative; original hash retained)",
        "sha256": "2d0b2201a894bb663f5f71a6c2464bcf7d53138b84b83de153ed9bf18f553259",
        "originalSha256": "2d0b2201a894bb663f5f71a6c2464bcf7d53138b84b83de153ed9bf18f553259",
        "privacyProjection": true,
        "role": "scoring",
        "href": "evidence/scoring.md",
        "bytes": 7235
      },
      {
        "id": "freeze",
        "label": "Complete approved study freeze (public derivative; original hash retained)",
        "sha256": "74b9864d7e01ebcd5775b5ec0fadc6a3bb4283428513d2991fc47ff5ea275c7f",
        "originalSha256": "f968a685190b843d121167b1031130e79a8daaf5a86da13effef37cb7af45936",
        "privacyProjection": true,
        "role": "freeze",
        "href": "evidence/freeze.json",
        "bytes": 8352
      },
      {
        "id": "method-freeze",
        "label": "Approved method/source freeze (public derivative; original hash retained)",
        "sha256": "b182ad917d590521c622e93e447de296481d9f6db98261ccccf7d6f8303580b2",
        "originalSha256": "c3cfa47c1e7a30832d0fdad78774ff5543a1851f5d679389b9ce097540d51709",
        "privacyProjection": true,
        "href": "evidence/method-freeze.json",
        "bytes": 8453
      },
      {
        "id": "measurement-integrity",
        "label": "All240 stopped originals sealed before grading (public derivative; original hash retained)",
        "sha256": "30205ab52d00ed8564dc789e750082c959894b9f3408acfcf924b6fe869f7c5d",
        "originalSha256": "55c6073e5e88de4fefd694d2dc91ea9b2d2e0f6ffd8fad90d654cca6546cbf00",
        "privacyProjection": true,
        "href": "evidence/measurement-integrity.json",
        "bytes": 141058
      },
      {
        "id": "qualification-decision",
        "label": "Actual release decision and all gates (public derivative; original hash retained)",
        "sha256": "0be7f29e838cb0ec9c75744d2b25d2765bb2db4e650a8c6baed72cc161570e69",
        "originalSha256": "0be7f29e838cb0ec9c75744d2b25d2765bb2db4e650a8c6baed72cc161570e69",
        "privacyProjection": true,
        "role": "qualification-decision",
        "href": "evidence/qualification-decision.json",
        "bytes": 4778
      },
      {
        "id": "fresh-failures",
        "label": "All actual failed or unresolved Kingy originals (public derivative; original hash retained)",
        "sha256": "58a04b49f62702527f2139d88f4107617cc200a0a98aedb7e433f04033da8fbd",
        "originalSha256": "58a04b49f62702527f2139d88f4107617cc200a0a98aedb7e433f04033da8fbd",
        "privacyProjection": true,
        "href": "evidence/fresh-failures.json",
        "bytes": 320
      },
      {
        "id": "final-audit",
        "label": "Actual independent final source and scoring audit (public derivative; original hash retained)",
        "sha256": "07798964c26d6b9126a2fa7134e9d680ab76a6b8ca3f64d332943d59bf94e468",
        "originalSha256": "f9d6f762dd963af631c2146a59457d7231554828520e8b1b89de3decde6a1b00",
        "privacyProjection": true,
        "role": "final-audit",
        "href": "evidence/final-audit.json",
        "bytes": 12352
      },
      {
        "id": "final-audit-notes",
        "label": "Actual independent every-case review notes (public derivative; original hash retained)",
        "sha256": "6ce3f17a5d2e6342cc41d1b8910e34764508a1438a2e1db359de911a8513bbc0",
        "originalSha256": "6ce3f17a5d2e6342cc41d1b8910e34764508a1438a2e1db359de911a8513bbc0",
        "privacyProjection": true,
        "href": "evidence/final-audit-notes.md",
        "bytes": 2589
      },
      {
        "id": "completion-eligibility",
        "label": "Actual original completion and strict-method eligibility (public derivative; original hash retained)",
        "sha256": "9e2f90f98029af814a6848c9f5fe791ae91eb67b03fd31684c7e066d74f074fb",
        "originalSha256": "6af7ef7f761ebd31edc268b61231385d1ba9758325f380ea7d1fe4481107f5c1",
        "privacyProjection": true,
        "role": "completion-eligibility",
        "href": "evidence/completion-eligibility.json",
        "bytes": 1549528
      },
      {
        "id": "installation",
        "label": "Actual fresh package/selftest/security outcome (public derivative; original hash retained)",
        "sha256": "9f40b29e451739967c274b108282c41eead19fc96079f01e3e5b9a1162c36133",
        "originalSha256": "b56fd88145a9930020da961d8dfa129067323b93e51619776d4cfe3a4809080f",
        "privacyProjection": true,
        "role": "installation",
        "href": "evidence/installation.json",
        "bytes": 2035
      },
      {
        "id": "selftest-raw",
        "label": "All four actual public selftest originals (public derivative; original hash retained)",
        "sha256": "f632028c6eaadf63e8fad8bee89a998d3be12c9d154c4aee0c5c8a5bf6c36663",
        "originalSha256": "42710fd8d31110dd9846cdc83fe64bc5680443375ae4af5b36f8c52692225670",
        "privacyProjection": true,
        "role": "selftest-raw",
        "href": "evidence/selftest-raw.jsonl",
        "bytes": 5720
      },
      {
        "id": "selftest-summary",
        "label": "Actual four-selftest summary (public derivative; original hash retained)",
        "sha256": "4022ddb4e18b2bbd5ec5e2cee5174eaf371b76428d7ed8c21ebd6638cba542fa",
        "originalSha256": "4022ddb4e18b2bbd5ec5e2cee5174eaf371b76428d7ed8c21ebd6638cba542fa",
        "privacyProjection": true,
        "role": "selftest-summary",
        "href": "evidence/selftest-summary.json",
        "bytes": 1376
      },
      {
        "id": "network-checks",
        "label": "Actual authentication and declared egress checks (public derivative; original hash retained)",
        "sha256": "77f7a86eb014d334417ba7d0525d0b676a5a0af3359faf3c2fcb31f7b8714560",
        "originalSha256": "77f7a86eb014d334417ba7d0525d0b676a5a0af3359faf3c2fcb31f7b8714560",
        "privacyProjection": true,
        "href": "evidence/network-checks.json",
        "bytes": 639
      },
      {
        "id": "report-narrative",
        "label": "Actual reviewed publication narrative and evidence bindings (public derivative; original hash retained)",
        "sha256": "c9167107f3da61ef5b156e8a77997dde330cd4bcc0ed28f8646f57e091197a95",
        "originalSha256": "c9167107f3da61ef5b156e8a77997dde330cd4bcc0ed28f8646f57e091197a95",
        "privacyProjection": true,
        "role": "report-narrative",
        "href": "evidence/report-narrative.json",
        "bytes": 4949
      },
      {
        "id": "candidate-changes",
        "label": "Actual r7 engineering changes and retained development evidence (public derivative; original hash retained)",
        "sha256": "9824855623ea294fd9d6bb2feeaf900f3d7ffe1b42ff0de99ec58056e49a8989",
        "originalSha256": "9824855623ea294fd9d6bb2feeaf900f3d7ffe1b42ff0de99ec58056e49a8989",
        "privacyProjection": true,
        "href": "evidence/candidate-changes.json",
        "bytes": 3475
      },
      {
        "id": "history-preservation",
        "label": "Preserved v23 and previous evidence hashes (public derivative; original hash retained)",
        "sha256": "506f2326a6f3e9eb76e4f9eeec7ebf88a658052d5cb2ad9f7f5878f456d54f55",
        "originalSha256": "ad82a8122acc46f4e0e0d693a98ac215331b492349eb8f76ae87230490ea51dc",
        "privacyProjection": true,
        "href": "evidence/history-preservation.json",
        "bytes": 1800
      },
      {
        "id": "kingy-settings",
        "label": "Actual current-study kingy settings (public derivative; original hash retained)",
        "sha256": "00f086449f790bea02b4e829ddafad49ffed4c0ce891375c9b85c9d085153a97",
        "originalSha256": "00f086449f790bea02b4e829ddafad49ffed4c0ce891375c9b85c9d085153a97",
        "privacyProjection": true,
        "role": "kingy-settings",
        "href": "evidence/kingy-settings.json",
        "bytes": 2237
      },
      {
        "id": "native-settings",
        "label": "Actual current-study native settings (public derivative; original hash retained)",
        "sha256": "59271fba82e95ad0ad55e082673da4112cbccd86596ef926259f0bbc0ab5f188",
        "originalSha256": "59271fba82e95ad0ad55e082673da4112cbccd86596ef926259f0bbc0ab5f188",
        "privacyProjection": true,
        "role": "native-settings",
        "href": "evidence/native-settings.json",
        "bytes": 5280
      },
      {
        "id": "native-runtime",
        "label": "Actual current-study native runtime (public derivative; original hash retained)",
        "sha256": "a3cc8b82ce1135e9daf17e17d4d4fcf061edd0ab3827946a580e701102eb17a3",
        "originalSha256": "a3cc8b82ce1135e9daf17e17d4d4fcf061edd0ab3827946a580e701102eb17a3",
        "privacyProjection": true,
        "role": "native-runtime",
        "href": "evidence/native-runtime.json",
        "bytes": 2069
      },
      {
        "id": "native-rag",
        "label": "Actual current-study native rag (public derivative; original hash retained)",
        "sha256": "879a81063ac8a97ab8200fd1105b86997bcb0580610ec40cf31df3a05b9be62b",
        "originalSha256": "879a81063ac8a97ab8200fd1105b86997bcb0580610ec40cf31df3a05b9be62b",
        "privacyProjection": true,
        "role": "native-rag",
        "href": "evidence/native-rag.json",
        "bytes": 2006
      },
      {
        "id": "control-provenance",
        "label": "Actual current-study control provenance (public derivative; original hash retained)",
        "sha256": "2dc6b1bfd6318c305732912d9c991530b69b74e95ff562795826e3705a154986",
        "originalSha256": "2dc6b1bfd6318c305732912d9c991530b69b74e95ff562795826e3705a154986",
        "privacyProjection": true,
        "role": "control-provenance",
        "href": "evidence/control-provenance.json",
        "bytes": 5134
      },
      {
        "id": "method-approval",
        "label": "Independent exact method/source approval (public derivative; original hash retained)",
        "sha256": "51736a986d11bf5cb49d83dd38317a2844759f93e6d666ff2a3ebbabdb3cec03",
        "originalSha256": "975b8f91179494e6420d50e116b9011b795aef4a7e863fff006d5c72f537107c",
        "privacyProjection": true,
        "href": "evidence/method-approval.json",
        "bytes": 37954
      },
      {
        "id": "scorer-validation",
        "label": "Independent current candidate engineering approval (public derivative; original hash retained)",
        "sha256": "0ce1522d447de753efef208ad3a5160f78e0b1000134cf2c6838c4c59f174f79",
        "originalSha256": "0ce1522d447de753efef208ad3a5160f78e0b1000134cf2c6838c4c59f174f79",
        "privacyProjection": true,
        "href": "evidence/scorer-validation.json",
        "bytes": 7664
      },
      {
        "id": "corpus-freeze",
        "label": "Separate author exact frozen corpus hashes (public derivative; original hash retained)",
        "sha256": "e9edf878c8a1392cc50c4b09f2575f4a5583b30c5264dbc7bbccf2dde79d7164",
        "originalSha256": "9f71a39abecdfe1990fd1d130a408767265341362d72c96a51d5448d351f6867",
        "privacyProjection": true,
        "href": "evidence/corpus-freeze.json",
        "bytes": 5386
      },
      {
        "id": "corpus-review",
        "label": "Independent every-item corpus approval (public derivative; original hash retained)",
        "sha256": "6e5da968f07e168e903b04226975b20a878a17b70d6ba6e85c2c13716761fd98",
        "originalSha256": "0b6e285a595f6003470e0f21e812733dd70e31c2cbe0d81eb9f35f9a9d4aa017",
        "privacyProjection": true,
        "href": "evidence/corpus-review.json",
        "bytes": 9538
      },
      {
        "id": "history-manifest",
        "label": "Original immutable1.4 manifest (public derivative; original hash retained)",
        "sha256": "fc28d7f64e75a37768586ded40807195f55aac7d1337d27ecf7a700fbd63a4e6",
        "originalSha256": "fc28d7f64e75a37768586ded40807195f55aac7d1337d27ecf7a700fbd63a4e6",
        "privacyProjection": true,
        "role": "history-manifest",
        "href": "evidence/history-manifest.json",
        "bytes": 3822
      },
      {
        "id": "v15-history-manifest",
        "label": "Preserved1.5.0 manifest (public derivative; original hash retained)",
        "sha256": "f62295ede008d7312b9dc967d7c7394fd552a3736558b04286f69b075827ed5e",
        "originalSha256": "f62295ede008d7312b9dc967d7c7394fd552a3736558b04286f69b075827ed5e",
        "privacyProjection": true,
        "href": "evidence/v15-history-manifest.json",
        "bytes": 4793
      },
      {
        "id": "v19-history-manifest",
        "label": "Preserved v19 manifest (public derivative; original hash retained)",
        "sha256": "2c9bc99ccffb4fa0d68053a0a0c8766808efc9e92901aeb36effba824d3357fd",
        "originalSha256": "2c9bc99ccffb4fa0d68053a0a0c8766808efc9e92901aeb36effba824d3357fd",
        "privacyProjection": true,
        "href": "evidence/v19-history-manifest.json",
        "bytes": 19702
      },
      {
        "id": "v20-history-manifest",
        "label": "Preserved v20 manifest (public derivative; original hash retained)",
        "sha256": "295bafdb79648533f3cfade9aa23380dfedf633bfb8640c02a30bbc90abf8b62",
        "originalSha256": "295bafdb79648533f3cfade9aa23380dfedf633bfb8640c02a30bbc90abf8b62",
        "privacyProjection": true,
        "href": "evidence/v20-history-manifest.json",
        "bytes": 58789
      },
      {
        "id": "v21-history-manifest",
        "label": "Preserved v21 incomplete manifest (public derivative; original hash retained)",
        "sha256": "dca7d395feadfc268ad8afca66ffc25407f1dde5c23a85ac9786c00be5ad977d",
        "originalSha256": "dca7d395feadfc268ad8afca66ffc25407f1dde5c23a85ac9786c00be5ad977d",
        "privacyProjection": true,
        "href": "evidence/v21-history-manifest.json",
        "bytes": 751
      },
      {
        "id": "v22-history-manifest",
        "label": "Preserved v22 incomplete manifest (public derivative; original hash retained)",
        "sha256": "159912e9acb016fcc4ccb8073258250c5864155c804e5c9794310577b44c3b94",
        "originalSha256": "159912e9acb016fcc4ccb8073258250c5864155c804e5c9794310577b44c3b94",
        "privacyProjection": true,
        "href": "evidence/v22-history-manifest.json",
        "bytes": 857
      },
      {
        "id": "v23-history-manifest",
        "label": "Preserved v23 incomplete manifest (public derivative; original hash retained)",
        "sha256": "5d8b38c4e3c50d3dadc6cbd59200790bfd5fbd21d8b57d2e80a1cfcfb5b776bc",
        "originalSha256": "5d8b38c4e3c50d3dadc6cbd59200790bfd5fbd21d8b57d2e80a1cfcfb5b776bc",
        "privacyProjection": true,
        "href": "evidence/v23-history-manifest.json",
        "bytes": 857
      },
      {
        "id": "projection-review",
        "label": "Actual independent exact public derivative approval (public derivative; original hash retained)",
        "sha256": "09a42bfc92c806938818ea5af987495e33aaacb944e2dd40102acf5026ad4ca7",
        "originalSha256": "09a42bfc92c806938818ea5af987495e33aaacb944e2dd40102acf5026ad4ca7",
        "privacyProjection": true,
        "role": "projection-review",
        "href": "evidence/projection-review.json",
        "bytes": 15105
      },
      {
        "id": "projection-lineage",
        "role": "projection-lineage",
        "label": "Exact original/public derivative hashes and path-only transformations",
        "sha256": "428f337c40ec5fae63f95de48ae87e5194cf5045f457d0d9ec92989e17c2586f",
        "href": "evidence/projection-lineage.json",
        "bytes": 4891323
      },
      {
        "id": "study-materials",
        "label": "Exact frozen method/source and seven-input audit bundle",
        "sha256": "adc0042ccdc978952a6d78a2bf5bcfce4fb4d4e4c2ef8ff7cd7ca6b13f435af4",
        "href": "evidence/study-materials.zip",
        "bytes": 310526
      }
    ],
    "projectionReviewRequiredBeforePublication": true,
    "projectionReviewApproved": true
  },
  "analysisCompletedAt": "2026-10-18T17:50:30.012401+00:00",
  "uniqueQuestionClusters": 40,
  "repetitions": 3,
  "attemptsPerWorkflow": 120,
  "summaries": {
    "A1": {
      "attempts": 40,
      "answer_correctness": {
        "passed": 30,
        "total": 30,
        "unresolved": 0,
        "lower": 1,
        "upper": 1
      },
      "supported_answer_success": {
        "passed": 30,
        "total": 30,
        "unresolved": 0,
        "lower": 1,
        "upper": 1
      },
      "abstention_accuracy": {
        "passed": 10,
        "total": 10,
        "unresolved": 0,
        "lower": 1,
        "upper": 1
      },
      "citation_precision": {
        "passed": 35,
        "total": 35,
        "unresolved": 0,
        "lower": 1,
        "upper": 1
      },
      "unresolved_questions": 0,
      "explicit_page_citations": 35,
      "uniquely_quote_mapped_citations": 0,
      "all_semantic_judgments_resolved": true,
      "qualified": true,
      "complete_planned_ids": true,
      "thresholds": {
        "supported_answer_success": 0.9,
        "citation_precision": 0.95,
        "abstention_accuracy": 0.9
      },
      "thresholds_passed_on_lower_bounds": {
        "supported_answer_success": true,
        "citation_precision": true,
        "abstention_accuracy": true
      },
      "latency": {
        "n": 40,
        "unavailable": 0,
        "p50": 5.103510208500666,
        "p95": 10.89339574999758,
        "max": 11.25245904098847,
        "errors_retained": 0,
        "timeouts_retained": 0,
        "boundary": null
      },
      "answer_model_request_count": 89,
      "original_session_receipt": {
        "original_summary": {
          "executor_version": "kingy-comparison-session/1.0.0",
          "system": "A",
          "repetition": 1,
          "status": "complete",
          "qualificationGranted": false,
          "complete_query_deadline_seconds": 90,
          "generation_seed": 271828,
          "client_offline_profile": "offline.sb",
          "client_offline_profile_sha256": "e5462ef1daae3785012cb8e4fa05b89105bf4ac4d98be9580a8c357365a4f54f",
          "timing_boundary": "runner.ask entry through its complete returned answer, source resolution and sufficiency check; excludes prior PDF import/index, cold start, warmup and later grading.",
          "cache_policy": "cache_prompt false; no claim that OS file caches were flushed.",
          "freeze_sha256": "f968a685190b843d121167b1031130e79a8daaf5a86da13effef37cb7af45936",
          "schedule_sha256": "d4a89e088855354ce486d7989bebb27c01836110279d1ddc1745abd2b9d449e6",
          "questions_sha256": "b00b40659e59072dd38b6327aa5a1f14da82ba9fc4a3d0f99396a17f0bd274be",
          "executor_sha256": "0313919e7c3f11d8238c5afad191d2bd8b92de63c13cea691c56f360096d2527",
          "runner_sha256": "3bcc03ffef818fa7fb6062ae17f20aa09d2fcc25fc9d57572c77ec35bc1ef02b",
          "model_sha256": "7485fe6f11af29433bc51cab58009521f205840f5b4ae3a32fa7f92e8534fdf5",
          "corpus_pdf_sha256": {
            "briar-quay-listening.pdf": "763eadc38b9947a4bb5134d7a5c5baf8e35bab68cf267e3f0b96adb29598dcbb",
            "kestrel-reach-loans.pdf": "c8407ae49d56cea5fbfe200b3ea6f8b4f6d6d237dfca7c8eb5e3fc3458be5641",
            "larkspur-seed-dispatch.pdf": "444fbb28dc1510635f7f0cfaeb876fadf217b915e5d49428d993d53ab09c62a2",
            "morrow-vale-textiles.pdf": "1e32270cc8f6f5822964e8bc486c4dac0e1ac8428eca064d0a93b9dff7d09acc",
            "tamarind-ridge-visitors.pdf": "7cd78484d127c379022d2f746f44ef03a162398b91379fede3ceb4ef56b67bba"
          },
          "planned_question_ids": [
            "V24-Q07",
            "V24-Q33",
            "V24-Q05",
            "V24-Q39",
            "V24-Q36",
            "V24-Q29",
            "V24-Q16",
            "V24-Q13",
            "V24-Q28",
            "V24-Q22",
            "V24-Q09",
            "V24-Q35",
            "V24-Q26",
            "V24-Q14",
            "V24-Q25",
            "V24-Q21",
            "V24-Q04",
            "V24-Q02",
            "V24-Q24",
            "V24-Q38",
            "V24-Q01",
            "V24-Q40",
            "V24-Q37",
            "V24-Q34",
            "V24-Q20",
            "V24-Q31",
            "V24-Q10",
            "V24-Q30",
            "V24-Q08",
            "V24-Q11",
            "V24-Q17",
            "V24-Q23",
            "V24-Q18",
            "V24-Q32",
            "V24-Q15",
            "V24-Q03",
            "V24-Q12",
            "V24-Q19",
            "V24-Q27",
            "V24-Q06"
          ],
          "session_order": [
            "A1",
            "B1",
            "B2",
            "A2",
            "A3",
            "B3"
          ],
          "artifact_verification_seconds": 6.569331916005467,
          "runtime": {
            "name": "llama.cpp",
            "binary_sha256": "51afbf4ea6485b9ada19e99af97181f12baca42ef704b1e291c26a9ac0644eae",
            "version": {
              "exit_code": 0
            }
          },
          "task_owned_server_pid": 37950,
          "cold_process_to_health_seconds": 2.3175289999926463,
          "ready_model_identity": {
            "models": [
              {
                "name": "kingy-qwen3-4b",
                "model": "kingy-qwen3-4b",
                "modified_at": "",
                "size": "",
                "digest": "",
                "type": "model",
                "description": "",
                "tags": [
                  ""
                ],
                "capabilities": [
                  "completion"
                ],
                "parameters": "",
                "details": {
                  "parent_model": "",
                  "format": "gguf",
                  "family": "",
                  "families": [
                    ""
                  ],
                  "parameter_size": "",
                  "quantization_level": ""
                }
              }
            ],
            "object": "list",
            "data": [
              {
                "id": "kingy-qwen3-4b",
                "aliases": [
                  "kingy-qwen3-4b"
                ],
                "tags": [],
                "object": "model",
                "architecture": {
                  "input_modalities": [
                    "text"
                  ],
                  "output_modalities": [
                    "text"
                  ]
                },
                "created": 1792337910,
                "owned_by": "llamacpp",
                "meta": {
                  "vocab_type": 2,
                  "n_vocab": 151936,
                  "n_ctx": 8192,
                  "n_ctx_train": 40960,
                  "n_embd": 2560,
                  "n_params": 4022468096,
                  "size": 2491323904,
                  "ftype": "Q4_K - Medium"
                }
              }
            ]
          },
          "warmup_model_request_count": 1,
          "warmup_seconds": 0.09381187500548549,
          "parse_seconds": 0.04358345799846575,
          "index_seconds": 0.0021135840070201084,
          "loaded_pdf_pages": 30,
          "retained_attempts": 40,
          "planned_attempts": 40,
          "unexecuted_question_ids": [],
          "unexecuted_attempt_count": 0,
          "model_request_count": 89,
          "session_total_model_request_count": 90,
          "attempt_errors": 0,
          "timeouts": 0,
          "session_wall_seconds": 240.02825091600243,
          "frozen_inputs_unchanged": true
        },
        "integrity_issues": [],
        "source_sha256": {
          "session-plan.json": "f5fc825a828fdc46bc30b6eaf729cb99d425425b81c279289cc105c176431c3a",
          "session-summary.json": "9182044e8bf4e86551d5f3c362b84fabf6d8baac58bdb56fb5429c40132ad9fe",
          "attempts.jsonl": "a197628b5a666146bdb09ad2763f8325a38cf1d9c7b12eadc30408f8218d5dd6"
        },
        "complete_40_original_rows": true
      },
      "provenance_verified": true
    },
    "A2": {
      "attempts": 40,
      "answer_correctness": {
        "passed": 30,
        "total": 30,
        "unresolved": 0,
        "lower": 1,
        "upper": 1
      },
      "supported_answer_success": {
        "passed": 30,
        "total": 30,
        "unresolved": 0,
        "lower": 1,
        "upper": 1
      },
      "abstention_accuracy": {
        "passed": 10,
        "total": 10,
        "unresolved": 0,
        "lower": 1,
        "upper": 1
      },
      "citation_precision": {
        "passed": 35,
        "total": 35,
        "unresolved": 0,
        "lower": 1,
        "upper": 1
      },
      "unresolved_questions": 0,
      "explicit_page_citations": 35,
      "uniquely_quote_mapped_citations": 0,
      "all_semantic_judgments_resolved": true,
      "qualified": true,
      "complete_planned_ids": true,
      "thresholds": {
        "supported_answer_success": 0.9,
        "citation_precision": 0.95,
        "abstention_accuracy": 0.9
      },
      "thresholds_passed_on_lower_bounds": {
        "supported_answer_success": true,
        "citation_precision": true,
        "abstention_accuracy": true
      },
      "latency": {
        "n": 40,
        "unavailable": 0,
        "p50": 4.956697499495931,
        "p95": 10.339400832992396,
        "max": 10.659548584008007,
        "errors_retained": 0,
        "timeouts_retained": 0,
        "boundary": null
      },
      "answer_model_request_count": 89,
      "original_session_receipt": {
        "original_summary": {
          "executor_version": "kingy-comparison-session/1.0.0",
          "system": "A",
          "repetition": 2,
          "status": "complete",
          "qualificationGranted": false,
          "complete_query_deadline_seconds": 90,
          "generation_seed": 271828,
          "client_offline_profile": "offline.sb",
          "client_offline_profile_sha256": "e5462ef1daae3785012cb8e4fa05b89105bf4ac4d98be9580a8c357365a4f54f",
          "timing_boundary": "runner.ask entry through its complete returned answer, source resolution and sufficiency check; excludes prior PDF import/index, cold start, warmup and later grading.",
          "cache_policy": "cache_prompt false; no claim that OS file caches were flushed.",
          "freeze_sha256": "f968a685190b843d121167b1031130e79a8daaf5a86da13effef37cb7af45936",
          "schedule_sha256": "d4a89e088855354ce486d7989bebb27c01836110279d1ddc1745abd2b9d449e6",
          "questions_sha256": "b00b40659e59072dd38b6327aa5a1f14da82ba9fc4a3d0f99396a17f0bd274be",
          "executor_sha256": "0313919e7c3f11d8238c5afad191d2bd8b92de63c13cea691c56f360096d2527",
          "runner_sha256": "3bcc03ffef818fa7fb6062ae17f20aa09d2fcc25fc9d57572c77ec35bc1ef02b",
          "model_sha256": "7485fe6f11af29433bc51cab58009521f205840f5b4ae3a32fa7f92e8534fdf5",
          "corpus_pdf_sha256": {
            "briar-quay-listening.pdf": "763eadc38b9947a4bb5134d7a5c5baf8e35bab68cf267e3f0b96adb29598dcbb",
            "kestrel-reach-loans.pdf": "c8407ae49d56cea5fbfe200b3ea6f8b4f6d6d237dfca7c8eb5e3fc3458be5641",
            "larkspur-seed-dispatch.pdf": "444fbb28dc1510635f7f0cfaeb876fadf217b915e5d49428d993d53ab09c62a2",
            "morrow-vale-textiles.pdf": "1e32270cc8f6f5822964e8bc486c4dac0e1ac8428eca064d0a93b9dff7d09acc",
            "tamarind-ridge-visitors.pdf": "7cd78484d127c379022d2f746f44ef03a162398b91379fede3ceb4ef56b67bba"
          },
          "planned_question_ids": [
            "V24-Q23",
            "V24-Q30",
            "V24-Q02",
            "V24-Q07",
            "V24-Q40",
            "V24-Q20",
            "V24-Q28",
            "V24-Q27",
            "V24-Q01",
            "V24-Q12",
            "V24-Q24",
            "V24-Q26",
            "V24-Q22",
            "V24-Q31",
            "V24-Q19",
            "V24-Q32",
            "V24-Q06",
            "V24-Q36",
            "V24-Q03",
            "V24-Q04",
            "V24-Q35",
            "V24-Q15",
            "V24-Q16",
            "V24-Q11",
            "V24-Q29",
            "V24-Q18",
            "V24-Q09",
            "V24-Q17",
            "V24-Q14",
            "V24-Q21",
            "V24-Q05",
            "V24-Q10",
            "V24-Q39",
            "V24-Q08",
            "V24-Q25",
            "V24-Q34",
            "V24-Q38",
            "V24-Q13",
            "V24-Q37",
            "V24-Q33"
          ],
          "session_order": [
            "A1",
            "B1",
            "B2",
            "A2",
            "A3",
            "B3"
          ],
          "artifact_verification_seconds": 6.299513874997501,
          "runtime": {
            "name": "llama.cpp",
            "binary_sha256": "51afbf4ea6485b9ada19e99af97181f12baca42ef704b1e291c26a9ac0644eae",
            "version": {
              "exit_code": 0
            }
          },
          "task_owned_server_pid": 67872,
          "cold_process_to_health_seconds": 2.0424199590052012,
          "ready_model_identity": {
            "models": [
              {
                "name": "kingy-qwen3-4b",
                "model": "kingy-qwen3-4b",
                "modified_at": "",
                "size": "",
                "digest": "",
                "type": "model",
                "description": "",
                "tags": [
                  ""
                ],
                "capabilities": [
                  "completion"
                ],
                "parameters": "",
                "details": {
                  "parent_model": "",
                  "format": "gguf",
                  "family": "",
                  "families": [
                    ""
                  ],
                  "parameter_size": "",
                  "quantization_level": ""
                }
              }
            ],
            "object": "list",
            "data": [
              {
                "id": "kingy-qwen3-4b",
                "aliases": [
                  "kingy-qwen3-4b"
                ],
                "tags": [],
                "object": "model",
                "architecture": {
                  "input_modalities": [
                    "text"
                  ],
                  "output_modalities": [
                    "text"
                  ]
                },
                "created": 1792342965,
                "owned_by": "llamacpp",
                "meta": {
                  "vocab_type": 2,
                  "n_vocab": 151936,
                  "n_ctx": 8192,
                  "n_ctx_train": 40960,
                  "n_embd": 2560,
                  "n_params": 4022468096,
                  "size": 2491323904,
                  "ftype": "Q4_K - Medium"
                }
              }
            ]
          },
          "warmup_model_request_count": 1,
          "warmup_seconds": 0.08162187499692664,
          "parse_seconds": 0.027941499996813945,
          "index_seconds": 0.0011765000090235844,
          "loaded_pdf_pages": 30,
          "retained_attempts": 40,
          "planned_attempts": 40,
          "unexecuted_question_ids": [],
          "unexecuted_attempt_count": 0,
          "model_request_count": 89,
          "session_total_model_request_count": 90,
          "attempt_errors": 0,
          "timeouts": 0,
          "session_wall_seconds": 230.79314120899653,
          "frozen_inputs_unchanged": true
        },
        "integrity_issues": [],
        "source_sha256": {
          "session-plan.json": "610b15116b19ec7a2956c163285ebc784fc6244ba99c5a859b28410a0ccda242",
          "session-summary.json": "462f8775cd5dee86753cde89f513ac261f6b64b273a53bcf3e917da34c31027d",
          "attempts.jsonl": "ce0d9fcc97fd001a74ecf03159e2f7d6d2e529be267fde25d0682c7387aaeb3b"
        },
        "complete_40_original_rows": true
      },
      "provenance_verified": true
    },
    "A3": {
      "attempts": 40,
      "answer_correctness": {
        "passed": 30,
        "total": 30,
        "unresolved": 0,
        "lower": 1,
        "upper": 1
      },
      "supported_answer_success": {
        "passed": 30,
        "total": 30,
        "unresolved": 0,
        "lower": 1,
        "upper": 1
      },
      "abstention_accuracy": {
        "passed": 10,
        "total": 10,
        "unresolved": 0,
        "lower": 1,
        "upper": 1
      },
      "citation_precision": {
        "passed": 35,
        "total": 35,
        "unresolved": 0,
        "lower": 1,
        "upper": 1
      },
      "unresolved_questions": 0,
      "explicit_page_citations": 35,
      "uniquely_quote_mapped_citations": 0,
      "all_semantic_judgments_resolved": true,
      "qualified": true,
      "complete_planned_ids": true,
      "thresholds": {
        "supported_answer_success": 0.9,
        "citation_precision": 0.95,
        "abstention_accuracy": 0.9
      },
      "thresholds_passed_on_lower_bounds": {
        "supported_answer_success": true,
        "citation_precision": true,
        "abstention_accuracy": true
      },
      "latency": {
        "n": 40,
        "unavailable": 0,
        "p50": 4.90504999949917,
        "p95": 10.300472667004215,
        "max": 10.594951999999466,
        "errors_retained": 0,
        "timeouts_retained": 0,
        "boundary": null
      },
      "answer_model_request_count": 89,
      "original_session_receipt": {
        "original_summary": {
          "executor_version": "kingy-comparison-session/1.0.0",
          "system": "A",
          "repetition": 3,
          "status": "complete",
          "qualificationGranted": false,
          "complete_query_deadline_seconds": 90,
          "generation_seed": 271828,
          "client_offline_profile": "offline.sb",
          "client_offline_profile_sha256": "e5462ef1daae3785012cb8e4fa05b89105bf4ac4d98be9580a8c357365a4f54f",
          "timing_boundary": "runner.ask entry through its complete returned answer, source resolution and sufficiency check; excludes prior PDF import/index, cold start, warmup and later grading.",
          "cache_policy": "cache_prompt false; no claim that OS file caches were flushed.",
          "freeze_sha256": "f968a685190b843d121167b1031130e79a8daaf5a86da13effef37cb7af45936",
          "schedule_sha256": "d4a89e088855354ce486d7989bebb27c01836110279d1ddc1745abd2b9d449e6",
          "questions_sha256": "b00b40659e59072dd38b6327aa5a1f14da82ba9fc4a3d0f99396a17f0bd274be",
          "executor_sha256": "0313919e7c3f11d8238c5afad191d2bd8b92de63c13cea691c56f360096d2527",
          "runner_sha256": "3bcc03ffef818fa7fb6062ae17f20aa09d2fcc25fc9d57572c77ec35bc1ef02b",
          "model_sha256": "7485fe6f11af29433bc51cab58009521f205840f5b4ae3a32fa7f92e8534fdf5",
          "corpus_pdf_sha256": {
            "briar-quay-listening.pdf": "763eadc38b9947a4bb5134d7a5c5baf8e35bab68cf267e3f0b96adb29598dcbb",
            "kestrel-reach-loans.pdf": "c8407ae49d56cea5fbfe200b3ea6f8b4f6d6d237dfca7c8eb5e3fc3458be5641",
            "larkspur-seed-dispatch.pdf": "444fbb28dc1510635f7f0cfaeb876fadf217b915e5d49428d993d53ab09c62a2",
            "morrow-vale-textiles.pdf": "1e32270cc8f6f5822964e8bc486c4dac0e1ac8428eca064d0a93b9dff7d09acc",
            "tamarind-ridge-visitors.pdf": "7cd78484d127c379022d2f746f44ef03a162398b91379fede3ceb4ef56b67bba"
          },
          "planned_question_ids": [
            "V24-Q18",
            "V24-Q16",
            "V24-Q06",
            "V24-Q05",
            "V24-Q37",
            "V24-Q23",
            "V24-Q28",
            "V24-Q04",
            "V24-Q26",
            "V24-Q22",
            "V24-Q34",
            "V24-Q32",
            "V24-Q13",
            "V24-Q35",
            "V24-Q07",
            "V24-Q20",
            "V24-Q24",
            "V24-Q29",
            "V24-Q02",
            "V24-Q14",
            "V24-Q39",
            "V24-Q38",
            "V24-Q09",
            "V24-Q36",
            "V24-Q17",
            "V24-Q01",
            "V24-Q25",
            "V24-Q11",
            "V24-Q19",
            "V24-Q30",
            "V24-Q03",
            "V24-Q27",
            "V24-Q10",
            "V24-Q12",
            "V24-Q15",
            "V24-Q33",
            "V24-Q08",
            "V24-Q21",
            "V24-Q40",
            "V24-Q31"
          ],
          "session_order": [
            "A1",
            "B1",
            "B2",
            "A2",
            "A3",
            "B3"
          ],
          "artifact_verification_seconds": 5.4561507500038715,
          "runtime": {
            "name": "llama.cpp",
            "binary_sha256": "51afbf4ea6485b9ada19e99af97181f12baca42ef704b1e291c26a9ac0644eae",
            "version": {
              "exit_code": 0
            }
          },
          "task_owned_server_pid": 68338,
          "cold_process_to_health_seconds": 2.0720122500060825,
          "ready_model_identity": {
            "models": [
              {
                "name": "kingy-qwen3-4b",
                "model": "kingy-qwen3-4b",
                "modified_at": "",
                "size": "",
                "digest": "",
                "type": "model",
                "description": "",
                "tags": [
                  ""
                ],
                "capabilities": [
                  "completion"
                ],
                "parameters": "",
                "details": {
                  "parent_model": "",
                  "format": "gguf",
                  "family": "",
                  "families": [
                    ""
                  ],
                  "parameter_size": "",
                  "quantization_level": ""
                }
              }
            ],
            "object": "list",
            "data": [
              {
                "id": "kingy-qwen3-4b",
                "aliases": [
                  "kingy-qwen3-4b"
                ],
                "tags": [],
                "object": "model",
                "architecture": {
                  "input_modalities": [
                    "text"
                  ],
                  "output_modalities": [
                    "text"
                  ]
                },
                "created": 1792343227,
                "owned_by": "llamacpp",
                "meta": {
                  "vocab_type": 2,
                  "n_vocab": 151936,
                  "n_ctx": 8192,
                  "n_ctx_train": 40960,
                  "n_embd": 2560,
                  "n_params": 4022468096,
                  "size": 2491323904,
                  "ftype": "Q4_K - Medium"
                }
              }
            ]
          },
          "warmup_model_request_count": 1,
          "warmup_seconds": 0.08258416601165663,
          "parse_seconds": 0.03061837499262765,
          "index_seconds": 0.001151499993284233,
          "loaded_pdf_pages": 30,
          "retained_attempts": 40,
          "planned_attempts": 40,
          "unexecuted_question_ids": [],
          "unexecuted_attempt_count": 0,
          "model_request_count": 89,
          "session_total_model_request_count": 90,
          "attempt_errors": 0,
          "timeouts": 0,
          "session_wall_seconds": 229.9553237499931,
          "frozen_inputs_unchanged": true
        },
        "integrity_issues": [],
        "source_sha256": {
          "session-plan.json": "dddba1bf17e178438af98589f4077a4d0195f9a0a021637e02a6285e2876b157",
          "session-summary.json": "7b3e6818aed4aa8fd37e556692684eb3a36dd156781d2fdf095537d9ae8f1972",
          "attempts.jsonl": "9419ea1ea016d945c22800b7a8d4a567bc512a6d6c01cf3da871cbd309aeab23"
        },
        "complete_40_original_rows": true
      },
      "provenance_verified": true
    },
    "B1": {
      "attempts": 40,
      "answer_correctness": {
        "passed": 29,
        "total": 30,
        "unresolved": 1,
        "lower": 0.9666666666666667,
        "upper": 1
      },
      "supported_answer_success": {
        "passed": 27,
        "total": 30,
        "unresolved": 1,
        "lower": 0.9,
        "upper": 0.9333333333333333
      },
      "abstention_accuracy": {
        "passed": 10,
        "total": 10,
        "unresolved": 0,
        "lower": 1,
        "upper": 1
      },
      "citation_precision": {
        "passed": 31,
        "total": 35,
        "unresolved": 2,
        "lower": 0.8857142857142857,
        "upper": 0.9428571428571428
      },
      "unresolved_questions": 3,
      "explicit_page_citations": 0,
      "uniquely_quote_mapped_citations": 31,
      "all_semantic_judgments_resolved": false,
      "qualified": false,
      "complete_planned_ids": true,
      "thresholds": {
        "supported_answer_success": 0.9,
        "citation_precision": 0.95,
        "abstention_accuracy": 0.9
      },
      "thresholds_passed_on_lower_bounds": {
        "supported_answer_success": true,
        "citation_precision": false,
        "abstention_accuracy": true
      },
      "latency": {
        "n": 40,
        "unavailable": 0,
        "p50": 7.5634999999999994,
        "p95": 9.129,
        "max": 9.472,
        "errors_retained": 0,
        "timeouts_retained": 0,
        "boundary": "Native app submission to documented logger final-answer event; includes native preprocessing/retrieval/embedding/inference; excludes later title generation and automation/export."
      },
      "answer_model_request_count": 40,
      "original_session_receipt": {
        "logger": {
          "path": "[redacted metadata reference; sha256 606c13a5529551ade4a17c96a5ffcfb53297059ff8f302d8eeae79ffff4b09fa]",
          "sha256": "e31304eabeb5f47cec7ae67cbd6d987b351136bf116f45f76375c6ee51cff292",
          "parsed_events": 82,
          "malformed_lines": []
        },
        "integrity_issues": [],
        "source_sha256": {
          "omittedPrivateInventory": true,
          "entryCount": 3,
          "originalInventorySha256": "159251026054a6e537f0e78a60190c0ef592a1c2f16bb83ddabfeea7a58c12ea"
        },
        "retained_manifest_rows": 40,
        "unmanifested_pending_attempt": false,
        "complete_40_original_manifest_rows": true,
        "original_files_modified_by_analysis": false
      },
      "provenance_verified": true
    },
    "B2": {
      "attempts": 40,
      "answer_correctness": {
        "passed": 29,
        "total": 30,
        "unresolved": 1,
        "lower": 0.9666666666666667,
        "upper": 1
      },
      "supported_answer_success": {
        "passed": 27,
        "total": 30,
        "unresolved": 1,
        "lower": 0.9,
        "upper": 0.9333333333333333
      },
      "abstention_accuracy": {
        "passed": 10,
        "total": 10,
        "unresolved": 0,
        "lower": 1,
        "upper": 1
      },
      "citation_precision": {
        "passed": 31,
        "total": 35,
        "unresolved": 2,
        "lower": 0.8857142857142857,
        "upper": 0.9428571428571428
      },
      "unresolved_questions": 3,
      "explicit_page_citations": 0,
      "uniquely_quote_mapped_citations": 31,
      "all_semantic_judgments_resolved": false,
      "qualified": false,
      "complete_planned_ids": true,
      "thresholds": {
        "supported_answer_success": 0.9,
        "citation_precision": 0.95,
        "abstention_accuracy": 0.9
      },
      "thresholds_passed_on_lower_bounds": {
        "supported_answer_success": true,
        "citation_precision": false,
        "abstention_accuracy": true
      },
      "latency": {
        "n": 40,
        "unavailable": 0,
        "p50": 7.3045,
        "p95": 9.232,
        "max": 9.39,
        "errors_retained": 0,
        "timeouts_retained": 0,
        "boundary": "Native app submission to documented logger final-answer event; includes native preprocessing/retrieval/embedding/inference; excludes later title generation and automation/export."
      },
      "answer_model_request_count": 40,
      "original_session_receipt": {
        "logger": {
          "path": "[redacted metadata reference; sha256 1702dd93a276f6db64cebaf10430315171a74fce6e1bdbbf97f452dc96759609]",
          "sha256": "4033104897fa021a70b1d76eb1f119c9841a275509a52825ceea0298af322e5b",
          "parsed_events": 82,
          "malformed_lines": []
        },
        "integrity_issues": [],
        "source_sha256": {
          "omittedPrivateInventory": true,
          "entryCount": 3,
          "originalInventorySha256": "a8a199740d39275b312f19343e578c37005d22fe6b02c6e568c7a045666941db"
        },
        "retained_manifest_rows": 40,
        "unmanifested_pending_attempt": false,
        "complete_40_original_manifest_rows": true,
        "original_files_modified_by_analysis": false
      },
      "provenance_verified": true
    },
    "B3": {
      "attempts": 40,
      "answer_correctness": {
        "passed": 29,
        "total": 30,
        "unresolved": 1,
        "lower": 0.9666666666666667,
        "upper": 1
      },
      "supported_answer_success": {
        "passed": 27,
        "total": 30,
        "unresolved": 1,
        "lower": 0.9,
        "upper": 0.9333333333333333
      },
      "abstention_accuracy": {
        "passed": 10,
        "total": 10,
        "unresolved": 0,
        "lower": 1,
        "upper": 1
      },
      "citation_precision": {
        "passed": 31,
        "total": 35,
        "unresolved": 2,
        "lower": 0.8857142857142857,
        "upper": 0.9428571428571428
      },
      "unresolved_questions": 3,
      "explicit_page_citations": 0,
      "uniquely_quote_mapped_citations": 31,
      "all_semantic_judgments_resolved": false,
      "qualified": false,
      "complete_planned_ids": true,
      "thresholds": {
        "supported_answer_success": 0.9,
        "citation_precision": 0.95,
        "abstention_accuracy": 0.9
      },
      "thresholds_passed_on_lower_bounds": {
        "supported_answer_success": true,
        "citation_precision": false,
        "abstention_accuracy": true
      },
      "latency": {
        "n": 40,
        "unavailable": 0,
        "p50": 7.375,
        "p95": 9.015,
        "max": 9.447,
        "errors_retained": 0,
        "timeouts_retained": 0,
        "boundary": "Native app submission to documented logger final-answer event; includes native preprocessing/retrieval/embedding/inference; excludes later title generation and automation/export."
      },
      "answer_model_request_count": 40,
      "original_session_receipt": {
        "logger": {
          "path": "[redacted metadata reference; sha256 475bee461295598cf84f4cf42210cd16b18231c142cb5fd627bff90bd5b511a0]",
          "sha256": "8fd4e9249c9a6390245fb18bcf6b954325bc75c146ed111fccd7e960516761c6",
          "parsed_events": 82,
          "malformed_lines": []
        },
        "integrity_issues": [],
        "source_sha256": {
          "omittedPrivateInventory": true,
          "entryCount": 3,
          "originalInventorySha256": "1a53aa2a6a14a314e480b274f087c5ede9716324585ff549d5dfcb6bd4d0acec"
        },
        "retained_manifest_rows": 40,
        "unmanifested_pending_attempt": false,
        "complete_40_original_manifest_rows": true,
        "original_files_modified_by_analysis": false
      },
      "provenance_verified": true
    }
  },
  "pairedEffects": {
    "complete_question_success": {
      "unique_questions": 40,
      "effect_bounds_A_minus_B": [
        0.05,
        0.075
      ],
      "cluster_bootstrap_95pct_sensitivity_envelope": [
        0,
        0.175
      ],
      "bootstrap_draws": 10000,
      "usable_bootstrap_draws": 10000,
      "interpretation": "Paired whole-question case-resampling sensitivity on this fixed corpus; not a p-value, population confidence claim or independent-repeat sample."
    },
    "supported_answer_success": {
      "unique_questions": 30,
      "effect_bounds_A_minus_B": [
        0.06666666666666667,
        0.1
      ],
      "cluster_bootstrap_95pct_sensitivity_envelope": [
        0,
        0.23333333333333334
      ],
      "bootstrap_draws": 10000,
      "usable_bootstrap_draws": 10000,
      "interpretation": "Paired whole-question case-resampling sensitivity on this fixed corpus; not a p-value, population confidence claim or independent-repeat sample."
    },
    "canonical_fact_correctness": {
      "unique_questions": 30,
      "effect_bounds_A_minus_B": [
        0,
        0.03333333333333333
      ],
      "cluster_bootstrap_95pct_sensitivity_envelope": [
        0,
        0.1
      ],
      "bootstrap_draws": 10000,
      "usable_bootstrap_draws": 10000,
      "interpretation": "Paired whole-question case-resampling sensitivity on this fixed corpus; not a p-value, population confidence claim or independent-repeat sample."
    },
    "correct_abstention": {
      "unique_questions": 10,
      "effect_bounds_A_minus_B": [
        0,
        0
      ],
      "cluster_bootstrap_95pct_sensitivity_envelope": [
        0,
        0
      ],
      "bootstrap_draws": 10000,
      "usable_bootstrap_draws": 10000,
      "interpretation": "Paired whole-question case-resampling sensitivity on this fixed corpus; not a p-value, population confidence claim or independent-repeat sample."
    },
    "emitted_citation_precision": {
      "unique_questions": 40,
      "effect_bounds_A_minus_B": [
        0.05714285714285716,
        0.11428571428571432
      ],
      "cluster_bootstrap_95pct_sensitivity_envelope": [
        0,
        0.2727272727272727
      ],
      "bootstrap_draws": 10000,
      "usable_bootstrap_draws": 10000,
      "interpretation": "Paired whole-question case-resampling sensitivity on this fixed corpus; not a p-value, population confidence claim or independent-repeat sample."
    }
  },
  "automaticWinner": null
}