{ "schema_version": 1, "artifact": "embedding_dict.json", "distribution": "external_runtime_asset_not_tracked_by_git", "embedding_model": "embedding-3", "semantic_similarity_threshold": 0.85, "semantic_similarity_operation": "raw_dot_product_historical_implementation_on_approximately_unit_norm_vectors", "sha256": "df3c3dfd625f8205c278d9d7b22641cfbf351c886559abb1894c663bb657d067", "size_bytes": 548127946, "entry_count": 19644, "embedding_dimension": 2048, "non_finite_vector_count": 0, "inconsistent_dimension_count": 0, "blank_key_count": 1, "vector_l2_norm": { "minimum": 0.9999337429879811, "mean": 0.999999939836742, "median": 0.9999999995442519, "maximum": 1.000054469389027, "maximum_absolute_deviation_from_one": 0.0000662570120189 }, "frozen_at": "2026-08-22", "recommended_file_mode": "0444", "runtime_environment": { "ORIENTER_EMBEDDING_CACHE": "/absolute/path/to/embedding_dict.json", "ORIENTER_EMBEDDING_OFFLINE": "1", "ORIENTER_EMBEDDING_READONLY": "1" }, "notes": [ "Verify the SHA-256 before evaluation.", "Offline mode fails before an embedding API call when a required category is absent.", "The paper describes cosine similarity, while the historical evaluator uses a raw dot product. The cached vectors are approximately unit norm, so the operations are numerically close but not formally identical.", "The frozen artifact is unchanged from the historical evaluator cache; the single blank key is retained for byte identity and is not used by the validated evaluation paths." ] }