{ "model_name": "difficulty_model", "model_version": "difficulty_model_v2_baseline_001", "dataset_version": "2.0.0", "trained_at": "2026-05-22T05:33:07.506348+00:00", "seed": 20260520, "split_counts": { "train": 3912, "validation": 1033, "test": 875 }, "metrics": { "validation": { "mae": 0.3477, "r_squared": 0.5007, "per_bucket_mae": { "easy": 0.3051, "medium": 0.2958, "hard": 0.6525 } }, "test": { "mae": 0.3514, "r_squared": 0.4693, "per_bucket_mae": { "easy": 0.3241, "medium": 0.2903, "hard": 0.6728 } } }, "limitations": [ "Trained on synthetic data only.", "difficulty_score distribution may not reflect real-world difficulty.", "OrdinalEncoder assumes an ordering that may not be meaningful for subject/question_type.", "Per-bucket MAE depends on the quality of the difficulty string labels." ] }