{ "release_version": "3.1.0-multisource-balanced", "random_seed": 42, "test_size": 0.2, "splitter": "GroupShuffleSplit", "group_key_priority": [ "derived_from", "normalized_hash", "id" ], "classifier": { "type": "sklearn.linear_model.LogisticRegression", "solver": "lbfgs", "C": 4.0, "max_iter": 3000, "class_weight": "balanced" }, "preparation": { "confidence_threshold": 0.65, "target_per_task": 800, "max_per_task": 2000, "accepted_label_methods": [ "source_fixed", "human_override" ], "augmentation": "deterministic lexical variants" }, "features": { "input_size": 1544, "word_bigram_bins": 1024, "character_trigram_bins": 512, "numeric_features": 8, "hash": "FNV-1a 32-bit over JavaScript UTF-16 code units" }, "labels": { "task": [ "general_chat", "writing", "translation", "summarization", "research", "coding", "mathematics", "document_analysis", "high_stakes" ], "complexity": [ "low", "medium", "high" ] }, "reference_environment": { "python": "3.13.5", "numpy": "2.3.5", "scikit-learn": "1.8.0", "regex": "2026.5.9", "onnx_opset": 13, "onnx_ir_version": 8 } }