{
  "case_sha256": "ba401b4ce611cf70ad252e3a4bbcd9dcde0700010b842767e77bd674a109da45",
  "demonstration_validation": {
    "exact_request_overlap": 0,
    "passed": 60,
    "total": 60
  },
  "executed_answers_replayed": 3944,
  "external_demonstrations_per_context": 30,
  "external_protocol_sha256": "589f554e1ca33a1ee484c0162d9e381dd0f3c0852ca1572e7d2729d89a339e51",
  "external_settings": {
    "gemini": {
      "candidateCount": 1,
      "maxOutputTokens": 65536,
      "temperature": 0,
      "thinkingConfig": {
        "includeThoughts": false,
        "thinkingLevel": "MEDIUM"
      }
    },
    "gemma": {
      "chat_template_kwargs": {
        "enable_thinking": true
      },
      "max_tokens": 12000,
      "skip_special_tokens": false,
      "temperature": 0
    }
  },
  "file_broker_sha256": "f2565cf789564f1792ac07546d23a1d4e8f4407db8ff3f062b297009026d4a04",
  "gemini_parameter_counts": "Not disclosed in the cited model cards; no size ratio assigned.",
  "gemma_model_card_parameters_approx": 30700000000,
  "gemma_parameter_ratio_approx": 19.887099523824844,
  "historical_external_failures": {
    "gemini-3.5-flash-lite": {
      "__failed__": 0,
      "blocked": 0,
      "empty": 0,
      "http": 0,
      "truncated": 0
    },
    "gemini-3.8-flash": {
      "__failed__": 0,
      "blocked": 0,
      "empty": 0,
      "http": 0,
      "truncated": 0
    },
    "gemma-4-31b-it": {
      "__failed__": 0,
      "blocked": 0,
      "empty": 0,
      "http": 0,
      "truncated": 0
    }
  },
  "independent_confirmation": false,
  "limitations": [
    "Adaptively reused developer-authored board with correlated scenario families.",
    "Fine-tuned specialist versus prompted generalists, not equal adaptation budgets.",
    "Same executor replay; original inference contexts and runtimes remain model-specific.",
    "No general-capability, statistical-equivalence, latency, energy or total-cost claim.",
    "External models were not evaluated on the private 100-query mailbox expansion.",
    "Only Gemini 3.5 Flash-Lite is measured here; other Flash-Lite versions are unmeasured."
  ],
  "lineage_selected_steps": {
    "broad": 500,
    "calendar_fields": 250,
    "file_refinement": 600,
    "joint_file_mail": 600,
    "literal_copy": 400
  },
  "local_demonstrations_per_request": 0,
  "models": [
    {
      "changed_from_historical": 0,
      "files": [
        735,
        746
      ],
      "key": "production",
      "model": "Tofazzol production Copy400",
      "scores": {
        "documents": [
          318,
          320
        ],
        "filenames": [
          155,
          160
        ],
        "media": [
          262,
          266
        ],
        "outlook": [
          217,
          240
        ]
      },
      "search": [
        952,
        986
      ],
      "unsafe_results": 0
    },
    {
      "changed_from_historical": 0,
      "files": [
        733,
        746
      ],
      "key": "g31",
      "model": "Gemma 4 31B",
      "scores": {
        "documents": [
          320,
          320
        ],
        "filenames": [
          158,
          160
        ],
        "media": [
          255,
          266
        ],
        "outlook": [
          240,
          240
        ]
      },
      "search": [
        973,
        986
      ],
      "unsafe_results": 0
    },
    {
      "changed_from_historical": 0,
      "files": [
        731,
        746
      ],
      "key": "f38",
      "model": "Gemini 3.8 Flash",
      "scores": {
        "documents": [
          319,
          320
        ],
        "filenames": [
          158,
          160
        ],
        "media": [
          254,
          266
        ],
        "outlook": [
          240,
          240
        ]
      },
      "search": [
        971,
        986
      ],
      "unsafe_results": 0
    },
    {
      "changed_from_historical": 0,
      "files": [
        697,
        746
      ],
      "key": "fl35",
      "model": "Gemini 3.5 Flash-Lite",
      "scores": {
        "documents": [
          310,
          320
        ],
        "filenames": [
          141,
          160
        ],
        "media": [
          246,
          266
        ],
        "outlook": [
          233,
          240
        ]
      },
      "search": [
        930,
        986
      ],
      "unsafe_results": 0
    }
  ],
  "native_mail_sha256": "815c744a6b0524be4b1da8cdea87ee84db05874f8da666a944cfaa778f8b7ee0",
  "new_inference": false,
  "paired": {
    "f38": {
      "all": {
        "both_fail": 3,
        "both_pass": 940,
        "production_gains": 12,
        "production_losses": 31
      },
      "email": {
        "both_fail": 0,
        "both_pass": 217,
        "production_gains": 0,
        "production_losses": 23
      },
      "files": {
        "both_fail": 3,
        "both_pass": 723,
        "production_gains": 12,
        "production_losses": 8
      }
    },
    "fl35": {
      "all": {
        "both_fail": 6,
        "both_pass": 902,
        "production_gains": 50,
        "production_losses": 28
      },
      "email": {
        "both_fail": 1,
        "both_pass": 211,
        "production_gains": 6,
        "production_losses": 22
      },
      "files": {
        "both_fail": 5,
        "both_pass": 691,
        "production_gains": 44,
        "production_losses": 6
      }
    },
    "g31": {
      "all": {
        "both_fail": 3,
        "both_pass": 942,
        "production_gains": 10,
        "production_losses": 31
      },
      "email": {
        "both_fail": 0,
        "both_pass": 217,
        "production_gains": 0,
        "production_losses": 23
      },
      "files": {
        "both_fail": 3,
        "both_pass": 725,
        "production_gains": 10,
        "production_losses": 8
      }
    }
  },
  "paper_date": "2026-11-08",
  "production_parameters": 1543714304,
  "production_storage_dtype": "BF16",
  "production_weight_bytes": 3087467144,
  "production_weights_sha256": "f69c89242cdf8de3662d89d09ed0d61441cfa908afb423886fd4574f550cf8d4",
  "protocol_sha256": "871d219e26c4416e35637ae1d5da24aaec0f569b538e632bd3e580e535244b51",
  "returned_model_versions": {
    "f38": {
      "gemini-3.8-flash": 1002
    },
    "fl35": {
      "gemini-3.5-flash-lite": 1002
    },
    "g31": {
      "not returned": 1002
    }
  },
  "schema": "tofazzol-specialist-paper-comparison-v1"
}