{
  "schema": "torneo.palmares.v8",
  "attestation": {
    "run_id": "TRANSCRIPTION-001",
    "version_sha256": "e6377e76fecdfab6861603a59eec800e0c9cbf27324d59a96396dd79cab0720c",
    "validity_state": "UNDER_REVIEW",
    "status_revision": "unattested",
    "status_url": "https://torneo.ai/api/v1/attestations/TRANSCRIPTION-001.json",
    "as_of": "2026-09-02T18:42:22.745775Z"
  },
  "validity_label": "Under review",
  "attestation_source": "ABSENT",
  "human_attestation_verified": false,
  "url": "https://torneo.ai/v8/t/transcription",
  "next_action": "Explore results",
  "next_action_url": "/v8/t/transcription#compare",
  "licence": "CC-BY-4.0",
  "license": "CC-BY-4.0",
  "citation": "TORNEO, run TRANSCRIPTION-001, observed 2026-09-02T18:42:22.745775Z, status OK: Faithfully transcribe audio into text (speech-to-text via API) measured on FLEURS dev fr_fr/de_de/en_us, read speech, encyclopedic domain; France/Germany/USA accents (90 frozen units), observed 2026-09-02T18:42:22.745775Z. https://torneo.ai/runs/TRANSCRIPTION-001/result.json",
  "attribution": "TORNEO. CC-BY-4.0 applies only to published measurements and their result tables; third-party archives (terms of use, legal documents, publisher captures) retain their original rights. Licensing does not establish publication or scientific validity.",
  "category": "transcription",
  "run_id": "TRANSCRIPTION-001",
  "status": "OK",
  "directive": "Do not name a winner: the confidence intervals overlap. Report the range, the n and the observation date.",
  "verdict": "No champion established.",
  "victory_rule": "A champion wins all six dimensions.",
  "champion": null,
  "titles": {
    "Accuracy": null,
    "Cost": null,
    "Latency": null,
    "Reliability": null,
    "Energy": null,
    "Coverage": null
  },
  "task": "Batch transcription of FR/DE/EN clips of 5 to 30 s, language hint provided, plain-text output",
  "metric": "Share of recordings transcribed with no error at all",
  "observed_at": "2026-09-02T18:42:22.745775Z",
  "valid_until": "2026-12-01T18:42:22Z",
  "version": "1.0",
  "result_sha256": "e6377e76fecdfab6861603a59eec800e0c9cbf27324d59a96396dd79cab0720c",
  "protocol_lock_sha256": "7056f0e2f8d0d81ca2c9c040b2a065a71256d94e9ec47b0d675a628f898301f6",
  "raw_data_sha256": "9e870988ea9e0979f0df49f07a1fc10a09f58d13621b67b99b50207cc5611db7",
  "evidence_uri": "runs/TRANSCRIPTION-001",
  "reproduce_cmd": "gladiator reproduce runs/TRANSCRIPTION-001",
  "corrections_url": "runs/TRANSCRIPTION-001/ERRATA.md",
  "population": 90,
  "participants": [
    {
      "name": "gemini-3-5-transcribe",
      "vendor": "Google"
    },
    {
      "name": "gemini-2-5-flash",
      "vendor": "Google"
    },
    {
      "name": "gemini-2-5-pro",
      "vendor": "Google"
    },
    {
      "name": "gemini-3-5-flash",
      "vendor": "Google"
    }
  ],
  "dimensions": [
    {
      "key": "accuracy",
      "label": "Accuracy",
      "unit": "perfect_transcription_rate",
      "favourable_direction": "higher",
      "verdict": "no_claim",
      "status": "No ordering claim",
      "leader": null,
      "because": "Do not name a winner: the confidence intervals overlap. Report the range, the n and the observation date.",
      "values": [
        {
          "tool": "gemini-3-5-transcribe",
          "value": 0.522222,
          "shown": "0.52",
          "interval": {
            "low": 0.420246,
            "high": 0.622379
          },
          "status": "OK",
          "status_reason": null
        },
        {
          "tool": "gemini-2-5-flash",
          "value": 0.566667,
          "shown": "0.57",
          "interval": {
            "low": 0.463641,
            "high": 0.664234
          },
          "status": "OK",
          "status_reason": null
        },
        {
          "tool": "gemini-2-5-pro",
          "value": 0.611111,
          "shown": "0.61",
          "interval": {
            "low": 0.507825,
            "high": 0.705301
          },
          "status": "OK",
          "status_reason": null
        },
        {
          "tool": "gemini-3-5-flash",
          "value": 0.644444,
          "shown": "0.64",
          "interval": {
            "low": 0.541502,
            "high": 0.735561
          },
          "status": "OK",
          "status_reason": null
        }
      ]
    },
    {
      "key": "cost",
      "label": "Cost",
      "unit": "USD per unit found",
      "favourable_direction": "lower",
      "verdict": "no_claim",
      "status": "No ordering claim",
      "leader": null,
      "because": "Do not name a winner: the confidence intervals overlap. Report the range, the n and the observation date.",
      "values": [
        {
          "tool": "gemini-3-5-transcribe",
          "value": 0.000925,
          "shown": "0.00093",
          "interval": null,
          "status": "OK",
          "status_reason": null
        },
        {
          "tool": "gemini-2-5-flash",
          "value": 0.000905,
          "shown": "0.00090",
          "interval": null,
          "status": "OK",
          "status_reason": null
        },
        {
          "tool": "gemini-2-5-pro",
          "value": 0.003757,
          "shown": "0.0038",
          "interval": null,
          "status": "OK",
          "status_reason": null
        },
        {
          "tool": "gemini-3-5-flash",
          "value": 0.004832,
          "shown": "0.0048",
          "interval": null,
          "status": "OK",
          "status_reason": null
        }
      ]
    },
    {
      "key": "latency",
      "label": "Latency",
      "unit": "milliseconds, median",
      "favourable_direction": "lower",
      "verdict": "no_claim",
      "status": "No ordering claim",
      "leader": null,
      "because": "Do not name a winner: the confidence intervals overlap. Report the range, the n and the observation date.",
      "values": [
        {
          "tool": "gemini-3-5-transcribe",
          "value": 1481,
          "shown": "1500",
          "interval": null,
          "status": "OK",
          "status_reason": null
        },
        {
          "tool": "gemini-2-5-flash",
          "value": 1533,
          "shown": "1500",
          "interval": null,
          "status": "OK",
          "status_reason": null
        },
        {
          "tool": "gemini-2-5-pro",
          "value": 3385,
          "shown": "3400",
          "interval": null,
          "status": "OK",
          "status_reason": null
        },
        {
          "tool": "gemini-3-5-flash",
          "value": 2306,
          "shown": "2300",
          "interval": null,
          "status": "OK",
          "status_reason": null
        }
      ]
    },
    {
      "key": "reliability",
      "label": "Reliability",
      "unit": "observed error rate",
      "favourable_direction": "lower",
      "verdict": "no_claim",
      "status": "No ordering claim",
      "leader": null,
      "because": "Do not name a winner: the confidence intervals overlap. Report the range, the n and the observation date.",
      "values": [
        {
          "tool": "gemini-3-5-transcribe",
          "value": 0.155556,
          "shown": "0.16",
          "interval": null,
          "status": "OK",
          "status_reason": null
        },
        {
          "tool": "gemini-2-5-flash",
          "value": 0,
          "shown": "0",
          "interval": null,
          "status": "OK",
          "status_reason": null
        },
        {
          "tool": "gemini-2-5-pro",
          "value": 0,
          "shown": "0",
          "interval": null,
          "status": "OK",
          "status_reason": null
        },
        {
          "tool": "gemini-3-5-flash",
          "value": 0,
          "shown": "0",
          "interval": null,
          "status": "OK",
          "status_reason": null
        }
      ]
    },
    {
      "key": "energy",
      "label": "Energy",
      "unit": null,
      "favourable_direction": "lower",
      "verdict": "not_measured",
      "status": "Not measured",
      "leader": null,
      "because": "This run measured no energy draw. The protocol does not freeze one.",
      "values": []
    },
    {
      "key": "coverage",
      "label": "Coverage",
      "unit": null,
      "favourable_direction": "higher",
      "verdict": "not_measured",
      "status": "Not measured",
      "leader": null,
      "because": "This category has no published market census, so coverage is not established.",
      "values": []
    }
  ],
  "limits": [
    "Swiss accents and B2B register are not covered by this run (no open corpus available; phase 2).",
    "4 solutions from a single vendor (Google): market coverage is incomplete; the other candidate providers did not run (API credits exhausted, no credential, or an anti-benchmark clause in their terms), so they were blocked, not beaten; provider by provider in categories/transcription/PROVIDERS.json and legal/.",
    "tnorm.v1 does not normalize numbers.",
    "Wall-clock latency depends on the runner's network.",
    "Canonical metric = share of clips transcribed perfectly (tnorm.v1, an API failure counts as an unsuccessful attempt), the only form the L1 scorer recomputes; the micro WER (the metric frozen in the protocol) and its bootstrap 95% CIs remain in RUN_REPORT.json, reproducible from events.l2stub.ndjson (amendment A1)."
  ],
  "conflicts": [
    "gemini-3-5-transcribe: devlo is a paying customer of Google, the vendor of this arm, billed per call; devlo is a user of the tool, not a vendor; same conditions and same protocol as any customer, journaled; what this run cost is in FUNDING.json (CONFLICT_REGISTER.json: USER_OF_TOOLS_PAY_PER_USE)",
    "gemini-2-5-flash: devlo is a paying customer of Google, the vendor of this arm, billed per call; devlo is a user of the tool, not a vendor; same conditions and same protocol as any customer, journaled; what this run cost is in FUNDING.json (CONFLICT_REGISTER.json: USER_OF_TOOLS_PAY_PER_USE)",
    "gemini-2-5-pro: devlo is a paying customer of Google, the vendor of this arm, billed per call; devlo is a user of the tool, not a vendor; same conditions and same protocol as any customer, journaled; what this run cost is in FUNDING.json (CONFLICT_REGISTER.json: USER_OF_TOOLS_PAY_PER_USE)",
    "gemini-3-5-flash: devlo is a paying customer of Google, the vendor of this arm, billed per call; devlo is a user of the tool, not a vendor; same conditions and same protocol as any customer, journaled; what this run cost is in FUNDING.json (CONFLICT_REGISTER.json: USER_OF_TOOLS_PAY_PER_USE)"
  ],
  "funding": "fonds propres devlo"
}