search-reranker-irishgov-l5-k10-v2

5-layer bilingual reranker for the real Irish government serving path: RRF -> reranker over roughly top10 candidates.

This release is a strict follow-up to temsa/search-reranker-irishgov-l5-k10-v1. It keeps the same deployment shape but improves the broader gov test and the fresh unseen hard K=10 holdout.

Intended use

• Best use: direct CPU reranking of the RRF -> top10 candidate set.
• Recommended runtime profile: ONNX dynamic q8, max_length=140, threads=10.
• Not the best stage-1 prefilter for the older 80-candidate stress path; the public l6-fast -> broad cascade remains the better larger-pool fallback.

Why v2

Compared with v1, this release:

• keeps perfect bilingual office-holder ranking
• improves the broader gov finephrase test
• improves the fresh unseen hard K=10 holdout a03
• keeps the same CPU operating point for the deployed K=10 path

Key q8 benchmarks

Suite	Config	Overall MRR@10	Irish MRR@10	English MRR@10	Top-1	QPS
Office-holder bilingual	140, threads=8	1.0000	1.0000	1.0000	1.0000	74.09
Bilingual proxy	140, threads=8	0.8853	0.8482	0.9225	0.8100	26.82
Finephrase gov test	140, threads=8	1.0000	n/a	1.0000	1.0000	46.25
Hard gov K=10 holdout v1	140, threads=8	0.9815	n/a	0.9815	0.9630	49.37
Fresh unseen holdout a03	140, threads=8	1.0000	n/a	1.0000	1.0000	49.42

Comparison to previous and other public lines

Model	Suite	Config	Overall MRR@10	Top-1	QPS
search-reranker-irishgov-l5-k10-v1 q8	Finephrase gov test	140, threads=8	0.9762	0.9524	44.73
search-reranker-irishgov-l5-k10-v2 q8	Finephrase gov test	140, threads=8	1.0000	1.0000	46.25
search-reranker-irishgov-l5-k10-v1 q8	Fresh unseen holdout a03	140, threads=8	0.9630	0.9444	44.82
search-reranker-irishgov-l5-k10-v2 q8	Fresh unseen holdout a03	140, threads=8	1.0000	1.0000	49.42
search-reranker-broad-v1 q8	Fresh unseen holdout a03	160, threads=8	0.8759	0.8333	16.00
search-reranker-irishgov-l6-fast-v1 q8	Fresh unseen holdout a03	128, threads=8	0.9259	0.8889	52.65

Runtime note

Best measured proxy runtime for this release:

• q8 ONNX
• max_length=140
• threads=10
• proxy throughput = 28.27 qps
• average query latency = 35.37 ms
• p95 query latency = 40.81 ms

Artifacts

• Raw HF checkpoint: ./
• ONNX dynamic q8 artifact: onnx/model_quantized.onnx

Training provenance

• Base lineage: cross-encoder/mmarco-mMiniLMv2-L12-H384-v1
• Immediate parent: reranker_mmarco_mminilm_l5_irishgov_k10s5a
• Training mix: pairmix_k10_stage5_v1
• This run specifically re-aligned the model toward stronger short-length deployment while preserving the K=10 in-domain supervision.

Caveats

• This release is tuned for K=10 serving and should be evaluated that way.
• The old K=80 stress path is still a secondary evaluation axis, not the main promotion gate.

Portfolio comparison

Updated 2026-03-20 from local reranker reports only.

Use this section as the side-by-side public temsa reranker view. Cells are intentionally left out or summarized when the local report set does not contain a trustworthy non-quantized benchmark for the same public path.

General bilingual rerankers

Repo	Primary role	Non-quantized path	Quantized path	Extra trustworthy signals
temsa/search-reranker-broad-v1	Broad final-stage reranker	ONNX fp32 l256: proxy 0.9490 / 2.08 qps	Sibling q8 l160: proxy 0.9458 / 8.41 qps	office 0.8056; hard-k10 0.9815; holdout-a03 0.8759
temsa/search-reranker-broad-v1-qint8	Broad CPU q8 sibling	See temsa/search-reranker-broad-v1	ONNX q8 l160: proxy 0.9458 / 8.41 qps	office 0.8056; hard-k10 0.9815; holdout-a03 0.8759
temsa/search-reranker-irishgov-l6-fast-v1	Fast stage-1 / cascade prefilter	PT l192: proxy 0.9192 / 7.99 qps	ONNX q8 l128: proxy 0.9218 / 27.25 qps	office 1.0000; holdout-a03 0.9259
temsa/search-reranker-irishgov-l6-fast-v2	Fast K=10 policy serving release	Same raw checkpoint family as v1; q8 with corrected temporal + office policy is the recommended path	ONNX q8 l160/t10: corrected holdout-v5 1.0000 / 47.68 qps	office-holdout-v3 1.0000; office-valid 1.0000; legacy-holdout-v4 0.9375
temsa/search-reranker-irishgov-l6-fast-v3	Fastest public K=10 serving profile	Same raw checkpoint family as v2; the value is the shorter recommended serving length on corrected gates	ONNX q8 l128/t10: corrected holdout-v5 1.0000 / 48.27 qps	office-holdout-v3 1.0000; office-valid 1.0000; legacy-holdout-v4 0.9444
temsa/search-reranker-irishgov-l6-fast-v4	Current best fast K=10 reranker	Margin-MSE style continuation over v3; q8 per-channel is the recommended deployed artifact	ONNX q8 per-channel l128/t10: corrected holdout-v5 1.0000 / 50.78 qps	office-holdout-v3 1.0000; office-valid 1.0000; legacy-holdout-v4 0.9444
temsa/search-reranker-irishgov-l6-fast-v5	Fast K=10 serving release with shorter broad-policy route	Same raw checkpoint family as v4; the value is a shorter broad-policy serving profile while keeping the office route unchanged	ONNX q8 per-channel gov_broad_v1 l104/t10: corrected holdout-v5 1.0000 / 55.77 qps	fresh-holdout-v6 0.8917; office-holdout-v3 1.0000; office-valid 1.0000
temsa/search-reranker-irishgov-l5-k10-v1	Fast K=10 direct reranker	PT l160: proxy 0.8800 / 1.32 qps	ONNX q8 l140: proxy 0.8872 / 28.72 qps	office 1.0000; hard-k10 0.9815; holdout-a03 0.9630
temsa/search-reranker-irishgov-l5-k10-v2	Current K=10 successor	PT l128: office 1.0000, finephrase 0.9405	ONNX q8 l140: proxy 0.8853 / 28.27 qps	office 1.0000; holdout-a03 1.0000

Policy rerankers

Repo	Primary role	Non-quantized path	Quantized path	Extra trustworthy signals
temsa/search-reranker-broad-policy-v1	Broad policy-tuned reranker	PT l224: policy-all 0.9270 / 7.94 qps	ONNX q8 l224: policy-all 0.9205 / 27.55 qps	office 0.9537; holdout-a04 0.9049
temsa/search-reranker-broad-policy-v3	Current broad policy successor	ONNX fp32 l224: policy-all 0.9259 / 15.75 qps	ONNX q8 reduce_range l224: policy-all 0.9268 / 30.12 qps	office 0.9676; holdout-v3 0.9286
temsa/search-reranker-broad-policy-v4	Current broad policy serving release	Same raw checkpoint family as v3; q8 gov_broad_v1 is the recommended path	ONNX q8 reduce_range + gov_broad_v1 l224: policy-all 0.9257 / 31.64 qps	office 0.9676; holdout-v3 0.9271; holdout-v4 0.9583
temsa/search-reranker-broad-policy-v5	Current broad policy serving release	Same raw checkpoint family as v4; q8 gov_broad_v1 is the recommended path	ONNX q8 reduce_range + gov_broad_v1 l224/t10: policy-all 0.9711 / 26.12 qps	office 1.0000; holdout-v3 1.0000; holdout-v4 1.0000
temsa/search-reranker-broad-policy-v6	Broad policy serving release with corrected temporal gate	Same raw checkpoint family as v5; q8 gov_broad_v1 + office_holder_v1 is the recommended path	ONNX q8 gov_broad_v1 l176/t10: corrected holdout-v5 0.8657 / 25.74 qps	office-l160 1.0000; legacy-holdout-v4 0.9444; legacy-policy-all 0.9167
temsa/search-reranker-broad-policy-v7	Broad policy serving release with stronger latest-turn and topic-specific news routing	Same raw checkpoint family as v6; q8 gov_broad_v1 + office_holder_v1 is the recommended path	ONNX q8 gov_broad_v1 l176/t10: fresh holdout-v6 0.9375 / 15.65 qps	office-l224 1.0000; office-holdout-v4 0.9659; corrected-holdout-v5 1.0000; legacy-policy-all 0.9196
temsa/search-reranker-broad-policy-v8	Broad policy serving-profile release with shorter broad and office routes	Same raw checkpoint family as v7; q8 gov_broad_v1 + office_holder_v1 is the recommended path	ONNX q8 gov_broad_v1 l160/t10: fresh holdout-v7 0.9500 / 29.85 qps	office-l208 1.0000; office-holdout-v3 1.0000; office-holdout-v4 0.9659; fresh-holdout-v6 0.9500
temsa/search-reranker-broad-policy-v9	Broad policy serving release with stronger year-specific change-history routing	Same raw checkpoint family as v8; q8 gov_broad_v1 + office_holder_v1 is the recommended path	ONNX q8 gov_broad_v1 l160/t10: gov.ie category-policy corrected 1.0000 / 26.01 qps	legacy-policy-all 0.9282; fresh-holdout-v6 0.9500; office-valid 1.0000; office-holdout-v4 0.9659

Dynamic q8 CPU at K=20

These rows use the current local K=20 benchmark harness:

• proxy_k20: policy=none
• broad_policy_k20: policy=gov_broad_v1
• office_holder_k20: policy=office_holder_v1
• fixed threads=10, batch_size=32

Repo	Broad len	Office len	Proxy K=20	Broad-policy K=20	Office-holder K=20	Notes
temsa/search-reranker-broad-v1	160	160	0.9458 / 6.93 qps	0.9437 / 9.10 qps	0.6073 / 8.23 qps	broad baseline
temsa/search-reranker-broad-v1-qint8	160	160	0.9458 / 6.65 qps	0.9437 / 6.62 qps	0.6073 / 5.91 qps	q8 sibling repo
temsa/search-reranker-broad-policy-v1	224	224	0.9414 / 7.20 qps	0.9125 / 11.32 qps	0.6966 / 6.49 qps	first policy model
temsa/search-reranker-broad-policy-v2	224	224	0.9414 / 6.44 qps	0.9125 / 9.40 qps	0.6966 / 7.75 qps	office-policy serving fix era
temsa/search-reranker-broad-policy-v3	224	224	0.9364 / 7.38 qps	0.9250 / 12.20 qps	0.7451 / 7.15 qps	custom CPU continuation
temsa/search-reranker-broad-policy-v4	224	224	0.9364 / 7.16 qps	0.9250 / 11.40 qps	0.7451 / 6.90 qps	gov_broad_v1 serving route
temsa/search-reranker-broad-policy-v5	224	224	0.9364 / 7.00 qps	0.9250 / 12.35 qps	0.7451 / 6.47 qps	stronger serving release
temsa/search-reranker-broad-policy-v6	176	160	0.9433 / 8.09 qps	0.9250 / 9.97 qps	0.7186 / 9.77 qps	corrected temporal gate
temsa/search-reranker-broad-policy-v7	176	224	0.9433 / 7.91 qps	0.9250 / 12.11 qps	0.7451 / 7.49 qps	stronger latest-turn routing
temsa/search-reranker-broad-policy-v8	160	208	0.9371 / 9.49 qps	0.9250 / 11.21 qps	0.7527 / 7.01 qps	current broad fallback
temsa/search-reranker-broad-policy-v9	160	208	0.9371 / 8.97 qps	0.9250 / 11.56 qps	0.7527 / 6.62 qps	current broad fallback + change-history fix
temsa/search-reranker-irishgov-l5-k10-v1	140	140	0.8872 / 15.56 qps	0.8938 / 21.68 qps	0.6751 / 21.01 qps	fast K=10 direct
temsa/search-reranker-irishgov-l5-k10-v2	140	140	0.8853 / 18.06 qps	0.8854 / 18.87 qps	0.6327 / 17.93 qps	fast K=10 successor
temsa/search-reranker-irishgov-l6-fast-v1	128	128	0.9286 / 18.70 qps	0.9042 / 17.65 qps	0.6934 / 20.36 qps	fast stage-1 v1
temsa/search-reranker-irishgov-l6-fast-v2	128	128	0.9286 / 18.59 qps	0.9042 / 19.67 qps	0.6934 / 19.30 qps	fast stage-1 v2
temsa/search-reranker-irishgov-l6-fast-v3	128	128	0.9286 / 18.48 qps	0.9042 / 18.60 qps	0.6934 / 19.30 qps	shorter serving profile
temsa/search-reranker-irishgov-l6-fast-v4	128	128	0.9184 / 17.66 qps	0.9008 / 21.83 qps	0.7197 / 17.31 qps	margin-MSE per-channel
temsa/search-reranker-irishgov-l6-fast-v5	104	128	0.8987 / 20.85 qps	0.9133 / 20.29 qps	0.7197 / 15.45 qps	current fast route

Intentional gaps:

• search-reranker-broad-v1: the local reports include strong fp32 ONNX proxy and office data, but not a matching fp32 in-domain finephrase / hard-K10 / holdout-A03 set, so those are not claimed here.
• search-reranker-irishgov-l5-k10-v2: the local non-quantized reports are trustworthy for office / finephrase / hard-K10, but not for the same proxy runtime shape as the shipped q8 path.
• search-reranker-irishgov-l6-fast-v1: the local non-quantized reports cover proxy and office, but not the fresh holdout-A03 slice used for the q8 K=10 comparison.