{ "baseline": "main-r1", "candidate": "act-r1", "n_shared_queries": 38, "fixed_by_candidate": [], "broken_by_candidate": [ "q07", "q11", "q12", "q13", "q36" ], "discordant": 5, "net_queries": -5, "mcnemar_exact_p": 0.0625, "min_detectable_swing_queries": 6, "observed_run_to_run_drift_queries": 1, "noise_floor_queries": 6, "verdict": "no measurable difference", "baseline_aggregate": { "n_queries": 38, "n_scored": 35, "hit@5": 0.34285714285714286, "recall@5": 0.26947278911564626, "recall@10": 0.3333333333333333, "precision@5": 0.12000000000000001, "mrr@10": 0.2943197278911564, "nonsense_clean": "2/3", "superseded_outranks": "1/3", "latency_ms_p50": 1140.4, "latency_ms_p95": 1584.1, "latency_ms_max": 1627.6, "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": 0.0, "recall@5": 0.0, "recall@10": 0.0, "mrr@10": 0.0 }, "phrase": { "n": 7, "hit@5": 0.8571428571428571, "recall@5": 0.4902210884353741, "recall@10": 0.6666666666666666, "mrr@10": 0.5965986394557822 }, "superseded": { "n": 3, "hit@5": 0.0, "recall@5": 0.0, "recall@10": 0.3333333333333333, "mrr@10": 0.041666666666666664, "outranks": 1 } } }, "candidate_aggregate": { "n_queries": 38, "n_scored": 35, "hit@5": 0.22857142857142856, "recall@5": 0.19087301587301586, "recall@10": 0.24277210884353742, "precision@5": 0.07428571428571429, "mrr@10": 0.24154195011337865, "nonsense_clean": "2/3", "superseded_outranks": "0/3", "latency_ms_p50": 3208.8, "latency_ms_p95": 4851.9, "latency_ms_max": 5078.8, "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": 2.6666666666666665 }, "paraphrase": { "n": 13, "hit@5": 0.0, "recall@5": 0.0, "recall@10": 0.0, "mrr@10": 0.0 }, "phrase": { "n": 7, "hit@5": 0.2857142857142857, "recall@5": 0.09722222222222222, "recall@10": 0.3567176870748299, "mrr@10": 0.3505668934240363 }, "superseded": { "n": 3, "hit@5": 0.0, "recall@5": 0.0, "recall@10": 0.0, "mrr@10": 0.0, "outranks": 0 } } }, "repeat_variance": { "baseline": { "runs": 3, "hit@5_min": 0.34285714285714286, "hit@5_max": 0.34285714285714286, "spread_queries": 0 }, "candidate": { "runs": 3, "hit@5_min": 0.22857142857142856, "hit@5_max": 0.2571428571428571, "spread_queries": 1 } } }