{
  "example_type": "OBSERVED_TRANSFORMATION_EXAMPLE",
  "not_a_normative_schema": true,
  "not_adoption_evidence": true,
  "model": "openai/whisper-large-v3",
  "source_page_url": "https://huggingface.co/openai/whisper-large-v3",
  "source_api_url": "https://huggingface.co/api/models/openai/whisper-large-v3",
  "source_observed_at_utc": "2026-07-12T14:25:44Z",
  "free2aitools_record_url": "https://free2aitools.com/model/openai/whisper-large-v3",
  "free2aitools_api_url": "https://free2aitools.com/api/v1/entity/hf-model--openai--whisper-large-v3",
  "free2aitools_observed_at_utc": "2026-07-12T14:25:47Z",
  "example_generated_at_utc": "2026-07-12T14:30:30Z",
  "observation_note": "The Hugging Face source and the Free2AITools record were observed independently, in separate requests at different times; the Hugging Face downloads metric may vary between observations.",
  "source_excerpt": {
    "id": "openai/whisper-large-v3",
    "author": "openai",
    "lastModified": "2024-08-12T10:20:10.000Z",
    "likes": 5935,
    "downloads": 5963543,
    "pipeline_tag": "automatic-speech-recognition",
    "cardData_license": "apache-2.0",
    "config_architectures_0": "WhisperForConditionalGeneration",
    "safetensors_total_parameter_count": 1543490560
  },
  "normalized_excerpt": {
    "id": "hf-model--openai--whisper-large-v3",
    "name": "whisper-large-v3",
    "author": "openai",
    "license": "Apache-2.0",
    "pipeline_tag": "automatic-speech-recognition",
    "specs": { "params_billions": 1.54, "context_length": 448, "architecture": "WhisperForConditionalGeneration" },
    "stats": { "downloads": 6143734, "stars": 0, "forks": 0, "last_modified": "2026-07-11T08:45:48.461Z" },
    "fni": { "score": 39.6, "factors": { "semantic": null, "authority": 59.7, "popularity": 75, "recency": 24.8, "quality": 65 } },
    "source_url": "https://huggingface.co/openai/whisper-large-v3"
  },
  "classification_vocabulary": ["SOURCE_RETAINED", "NORMALIZED", "DERIVED", "ESTIMATED", "SOURCE_UNAVAILABLE", "DROPPED_BY_CURRENT_PIPELINE", "KNOWN_DEFECT"],
  "classifications_used_in_this_example": ["SOURCE_RETAINED", "NORMALIZED", "DERIVED", "SOURCE_UNAVAILABLE", "DROPPED_BY_CURRENT_PIPELINE", "KNOWN_DEFECT"],
  "field_mappings": [
    { "field": "id / slug", "source": "modelId = openai/whisper-large-v3", "served": "hf-model--openai--whisper-large-v3", "classification": "NORMALIZED" },
    { "field": "author", "source": "author = openai", "served": "openai", "classification": "SOURCE_RETAINED" },
    { "field": "license", "source": "cardData.license = apache-2.0", "served": "Apache-2.0", "classification": "NORMALIZED" },
    { "field": "pipeline_tag", "source": "automatic-speech-recognition", "served": "automatic-speech-recognition", "classification": "SOURCE_RETAINED" },
    { "field": "specs.params_billions", "source": "safetensors.total = 1543490560 (source-reported parameter count, not file bytes)", "served": 1.54, "classification": "NORMALIZED" },
    { "field": "specs.architecture", "source": "config.architectures[0]", "served": "WhisperForConditionalGeneration", "classification": "SOURCE_RETAINED" },
    { "field": "specs.context_length", "source": "(not in source API response)", "served": 448, "classification": "DERIVED" },
    { "field": "specs.vocab_size / num_layers / hidden_size", "source": "config.* (not in source API response)", "served": null, "classification": "SOURCE_UNAVAILABLE" },
    { "field": "category", "source": "(derived from tags / pipeline_tag)", "served": "vision-multimedia", "classification": "KNOWN_DEFECT", "note": "a known classification defect on this record (an ASR model classified as vision-multimedia)" },
    { "field": "specs.can_run_local", "source": "(derived heuristic)", "served": false, "classification": "KNOWN_DEFECT", "note": "a coarse derived heuristic that may be misleading across hardware, runtime and model-format contexts" },
    { "field": "stats.downloads", "source": "downloads = 5963543 (a periodic snapshot of the HuggingFace-reported figure)", "served": 6143734, "classification": "SOURCE_RETAINED" },
    { "field": "stats.stars / forks", "source": "(HuggingFace has no stars/forks)", "served": 0, "classification": "KNOWN_DEFECT" },
    { "field": "likes", "source": "likes = 5935", "served": "(not exposed as a served field after projection)", "classification": "DROPPED_BY_CURRENT_PIPELINE", "note": "The source likes value is not exposed as a served field after projection. Its upstream popularity signal contributes to the Authority calculation before that field is dropped from the served projection." },
    { "field": "stats.last_modified", "source": "lastModified = 2024-08-12T10:20:10Z", "served": "2026-07-11T08:45:48.461Z", "classification": "KNOWN_DEFECT" },
    { "field": "primary_language", "source": "language tags (~100)", "served": null, "classification": "DROPPED_BY_CURRENT_PIPELINE" },
    { "field": "fni.factors.semantic", "source": "(genuine query-time semantic/ANN scoring not provided)", "served": null, "classification": "NORMALIZED" },
    { "field": "fni.factors.authority", "source": "log-compressed likes proxy", "served": 59.7, "classification": "DERIVED" }
  ],
  "known_limitations": [
    { "audit_ref": "G1", "status": "OPEN_AT_OBSERVATION_TIME", "summary": "A single canonical ID may currently resolve to inconsistent duplicate records across the entity and compare surfaces." },
    { "audit_ref": "G3", "status": "OPEN_AT_OBSERVATION_TIME", "summary": "The served last_modified currently reflects Free2AITools projection/harvest timing rather than reliably preserving the upstream source last-modified value." },
    { "audit_ref": "G4", "status": "OPEN_AT_OBSERVATION_TIME", "summary": "Hugging Face likes are not exposed as a served field, and stars/forks may be served as 0 where null would be more honest." },
    { "audit_ref": "G5", "status": "OPEN_AT_OBSERVATION_TIME", "summary": "The published SDK has known nullability and percentile-type drift." },
    { "audit_ref": "G6", "status": "OPEN_AT_OBSERVATION_TIME", "summary": "Some search fields currently use 0 where entity surfaces use null." },
    { "audit_ref": "G7", "status": "OPEN_AT_OBSERVATION_TIME", "summary": "Some context, VRAM, local-run, category or architecture values may be derived or estimated rather than directly reported." },
    { "audit_ref": "G14", "status": "OPEN_AT_OBSERVATION_TIME", "summary": "Parameter-count source selection and confidence are not yet represented publicly." }
  ]
}