Files
neuron/tools/retrieval-eval/cmp-bm25-vs-claim24.json
T
Tim Lingo 21d3516426 measure: claim-24 unfloored semantic leg vs bm25lex baseline - net +0, NOT-SHOWN
gains q14,q25 (gold at global cosine rank 1, previously discarded by the 0.60
floor); losses q15,q28 (the semantic leg was EMPTY on those queries under the
floor, so filling it turns a 2-leg rotation into a 3-leg one and halves the
associative leg's share of the top 5). Guards held: exact_rare 6/6, phrase 7/7,
nonsense 2/3, superseded 2/3 outranks. recall@10 61.8->65.4pp, latency 0.99x.
Baseline reproduced from source (results-bm25base-rerun.json is byte-identical
to the committed results-bm25lex.json), candidate deterministic across 2 runs.
2026-08-07 16:33:50 -05:00

150 lines
3.2 KiB
JSON

{
"baseline": "bm25lex",
"candidate": "claim24",
"n_shared_queries": 38,
"fixed_by_candidate": [
"q14",
"q25"
],
"broken_by_candidate": [
"q15",
"q28"
],
"discordant": 4,
"net_queries": 0,
"mcnemar_exact_p": 1.0,
"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": 0.7428571428571429,
"recall@5": 0.5536485340056769,
"recall@10": 0.6175677497106068,
"precision@5": 0.20000000000000007,
"mrr@10": 0.5021428571428571,
"nonsense_clean": "2/3",
"superseded_outranks": "2/3",
"latency_ms_p50": 1184.4,
"latency_ms_p95": 1620.0,
"latency_ms_max": 1655.4,
"errors": 0,
"by_category": {
"associative": {
"n": 6,
"hit@5": 0.6666666666666666,
"recall@5": 0.08857808857808858,
"recall@10": 0.23310023310023312,
"mrr@10": 0.25
},
"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": 0.6153846153846154,
"recall@5": 0.6153846153846154,
"recall@10": 0.6153846153846154,
"mrr@10": 0.2846153846153846
},
"phrase": {
"n": 7,
"hit@5": 1.0,
"recall@5": 0.5494614512471656,
"recall@10": 0.6023242630385487,
"mrr@10": 0.8214285714285714
},
"superseded": {
"n": 3,
"hit@5": 0.3333333333333333,
"recall@5": 0.3333333333333333,
"recall@10": 0.6666666666666666,
"mrr@10": 0.20833333333333334,
"outranks": 2
}
}
},
"candidate_aggregate": {
"n_queries": 38,
"n_scored": 35,
"hit@5": 0.7428571428571429,
"recall@5": 0.5768475572047,
"recall@10": 0.6537440733869305,
"precision@5": 0.19428571428571437,
"mrr@10": 0.5021428571428572,
"nonsense_clean": "2/3",
"superseded_outranks": "2/3",
"latency_ms_p50": 1173.7,
"latency_ms_p95": 1623.0,
"latency_ms_max": 1647.9,
"errors": 0,
"by_category": {
"associative": {
"n": 6,
"hit@5": 0.5,
"recall@5": 0.07575757575757576,
"recall@10": 0.12121212121212122,
"mrr@10": 0.22916666666666666
},
"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": 0.6923076923076923,
"recall@5": 0.6923076923076923,
"recall@10": 0.7692307692307693,
"mrr@10": 0.29423076923076924
},
"phrase": {
"n": 7,
"hit@5": 1.0,
"recall@5": 0.5335884353741497,
"recall@10": 0.5933956916099773,
"mrr@10": 0.8214285714285714
},
"superseded": {
"n": 3,
"hit@5": 0.3333333333333333,
"recall@5": 0.3333333333333333,
"recall@10": 0.6666666666666666,
"mrr@10": 0.20833333333333334,
"outranks": 2
}
}
},
"repeat_variance": {
"baseline": {
"runs": 3,
"hit@5_min": 0.7428571428571429,
"hit@5_max": 0.7428571428571429,
"spread_queries": 0
},
"candidate": {
"runs": 2,
"hit@5_min": 0.7428571428571429,
"hit@5_max": 0.7428571428571429,
"spread_queries": 0
}
}
}