Run ae27258 · Own gold set (private corpus)

Run ae27258 Own gold set (private corpus), recorded 26 June 2026, 13:53:20 UTC.

dirty tree · not cited
determinism ok
private corpus · not reproducible

Benchmark metrics
Metric	Value	Definition
Recall@5	0.5625	Mean over questions of \|evidence ∩ top-k\| / \|evidence\|.
nDCG@5	0.4788	With binary relevance.
MRR	0.4850	Mean of 1/rank of the first evidence session.
Precision@5	0.1214	Mean over questions of \|evidence ∩ top-k\| / k. It can't reach 1 when a question has fewer than k evidence sessions, so it is shown on receipts only.

Conditions
Queries	56
k	5
Strategy	tag
Gold path	benchmarks/recall-gold.json
Tests ran	555
Tests failed	0
Environment	Hardware, OS and Python version: not recorded for this run.
Ledger row	107

Raw row

{"ablation": null, "checks": {"determinism_ok": true, "index_validate_ok": true, "test_pass_rate": 1.0, "tests_failed": 0, "tests_ran": 555}, "commit": "ae27258", "committed": "2026-06-26T02:58:19Z", "corpus_fingerprint": "fb3b7f35cc6272499cb860aa9a12c41dc34c66d2ec83daee33ffab6ef0bc350b", "corpus_size": 209, "dirty": true, "gold_path": "benchmarks/recall-gold.json", "metrics": {"context_tokens_mean": 1494.267857142857, "latency_ms_mean": 0.017202375033775752, "latency_ms_p50": 0.01597949994902592, "mrr": 0.4850342637054822, "ndcg_at_k": 0.47877892341895706, "precision_at_k": 0.12142857142857144, "recall_at_k": 0.5625}, "mode": "eval", "num_queries": 56, "reliability": 82.5, "run": "2026-06-26T13:53:20Z", "schema": "agentware-bench/v1", "strategy": "tag", "subject": "chore(eval-corpus-pinning): learnings: bench-redact-committed-ledger-scrub, benchmark-pii-hygiene", "suite": null, "top_k": 5}

reliability is an internal composite health score (0–100), not a benchmark metric.