Files
neuron/tools/retrieval-eval/comparison-semseed-vs-bm25lex.json
T
Tim Lingo 55f9ee3cb0 measure: BM25 lexical leg vs semseed baseline - net +2 (q10,q11), NOT-SHOWN
hit@5 68.6% -> 74.3%, phrase 71.4% -> 100%, MRR@10 0.461 -> 0.502, latency
p50 0.97x. Zero losses, zero run-to-run drift on both sides. 2 queries moved
against a 6-query noise floor: NO MEASURABLE DIFFERENCE by the harness's own
test (McNemar exact p=0.50). Unaddressable records in returned slots: 57 -> 0.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-07 15:55:42 -05:00

147 lines
3.2 KiB
JSON

{
"baseline": "semseed",
"candidate": "bm25lex",
"n_shared_queries": 38,
"fixed_by_candidate": [
"q10",
"q11"
],
"broken_by_candidate": [],
"discordant": 2,
"net_queries": 2,
"mcnemar_exact_p": 0.5,
"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": 0.6857142857142857,
"recall@5": 0.5213459159887731,
"recall@10": 0.6027048348476919,
"precision@5": 0.18285714285714294,
"mrr@10": 0.4608730158730158,
"nonsense_clean": "2/3",
"superseded_outranks": "2/3",
"latency_ms_p50": 1227.1,
"latency_ms_p95": 1692.6,
"latency_ms_max": 1710.4,
"errors": 0,
"by_category": {
"associative": {
"n": 6,
"hit@5": 0.6666666666666666,
"recall@5": 0.07342657342657344,
"recall@10": 0.24825174825174823,
"mrr@10": 0.20833333333333334
},
"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": 0.7142857142857143,
"recall@5": 0.40093537414965985,
"recall@10": 0.5150226757369615,
"mrr@10": 0.6507936507936508
},
"superseded": {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": 0.5536485340056769,
"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
}
}
},
"repeat_variance": {
"baseline": {
"runs": 2,
"hit@5_min": 0.6857142857142857,
"hit@5_max": 0.6857142857142857,
"spread_queries": 0
},
"candidate": {
"runs": 2,
"hit@5_min": 0.7428571428571429,
"hit@5_max": 0.7428571428571429,
"spread_queries": 0
}
}
}