{ "verified_by": "verify_zero_overlap_dataset.py", "data_dir": "V2_dpskw\\data\\zero_overlap", "train": { "split": "train", "episodes": 1200, "distinct_queries": 48, "candidate_counts": [ 24 ], "unknown_episodes": 199, "unknown_share_pct": 16.58, "episodes_whose_query_lexically_matches_its_own_target": 0, "episodes_with_a_lexical_distractor": 528, "distractor_share_pct": 44.0, "problems": 0, "problem_examples": [] }, "eval": { "split": "eval", "episodes": 300, "distinct_queries": 24, "candidate_counts": [ 24 ], "unknown_episodes": 50, "unknown_share_pct": 16.67, "episodes_whose_query_lexically_matches_its_own_target": 0, "episodes_with_a_lexical_distractor": 150, "distractor_share_pct": 50.0, "problems": 0, "problem_examples": [] }, "split_disjointness": { "shared_query_strings": [], "disjoint": true }, "checks": { "no_query_overlaps_its_own_target": true, "no_structural_problems": true, "splits_disjoint": true }, "all_checks_passed": true }