{ "baseline": "hybrid-semantic", "candidate": "assoc-leg", "n_shared_queries": 38, "fixed_by_candidate": [ "q27", "q28", "q29", "q31" ], "broken_by_candidate": [], "discordant": 4, "net_queries": 4, "mcnemar_exact_p": 0.125, "min_detectable_swing_queries": 6, "observed_run_to_run_drift_queries": 0, "noise_floor_queries": 6, "verdict": "no measurable difference", "baseline_aggregate": { "n_queries": 38, "n_scored": 35, "hit@5": 0.5142857142857142, "recall@5": 0.4409013605442177, "recall@10": 0.5047619047619047, "precision@5": 0.15428571428571433, "mrr@10": 0.38746031746031745, "nonsense_clean": "2/3", "superseded_outranks": "2/3", "latency_ms_p50": 1219.7, "latency_ms_p95": 1667.1, "latency_ms_max": 1720.2, "errors": 0, "by_category": { "associative": { "n": 6, "hit@5": 0.0, "recall@5": 0.0, "recall@10": 0.0, "mrr@10": 0.0 }, "exact_rare": { "n": 6, "hit@5": 1.0, "recall@5": 1.0, "recall@10": 1.0, "mrr@10": 1.0 }, "nonsense": { "n": 3, "clean": 2, "avg_false_positives": 3.3333333333333335 }, "paraphrase": { "n": 13, "hit@5": 0.38461538461538464, "recall@5": 0.38461538461538464, "recall@10": 0.38461538461538464, "mrr@10": 0.17307692307692307 }, "phrase": { "n": 7, "hit@5": 0.8571428571428571, "recall@5": 0.4902210884353741, "recall@10": 0.6666666666666666, "mrr@10": 0.6634920634920636 }, "superseded": { "n": 3, "hit@5": 0.3333333333333333, "recall@5": 0.3333333333333333, "recall@10": 0.6666666666666666, "mrr@10": 0.2222222222222222, "outranks": 2 } } }, "candidate_aggregate": { "n_queries": 38, "n_scored": 35, "hit@5": 0.6285714285714286, "recall@5": 0.45309194773480493, "recall@10": 0.5405733155733157, "precision@5": 0.17714285714285719, "mrr@10": 0.42650793650793645, "nonsense_clean": "2/3", "superseded_outranks": "2/3", "latency_ms_p50": 1228.5, "latency_ms_p95": 1681.8, "latency_ms_max": 1718.6, "errors": 0, "by_category": { "associative": { "n": 6, "hit@5": 0.6666666666666666, "recall@5": 0.07342657342657342, "recall@10": 0.24825174825174826, "mrr@10": 0.22777777777777777 }, "exact_rare": { "n": 6, "hit@5": 1.0, "recall@5": 1.0, "recall@10": 1.0, "mrr@10": 1.0 }, "nonsense": { "n": 3, "clean": 2, "avg_false_positives": 3.3333333333333335 }, "paraphrase": { "n": 13, "hit@5": 0.38461538461538464, "recall@5": 0.38461538461538464, "recall@10": 0.38461538461538464, "mrr@10": 0.17307692307692307 }, "phrase": { "n": 7, "hit@5": 0.8571428571428571, "recall@5": 0.4882369614512472, "recall@10": 0.6329365079365079, "mrr@10": 0.6634920634920636 }, "superseded": { "n": 3, "hit@5": 0.3333333333333333, "recall@5": 0.3333333333333333, "recall@10": 0.6666666666666666, "mrr@10": 0.2222222222222222, "outranks": 2 } } }, "repeat_variance": { "baseline": { "runs": 2, "hit@5_min": 0.5142857142857142, "hit@5_max": 0.5142857142857142, "spread_queries": 0 } } }