Result

0.419 ndcg

trec2020-pm-phase2-monot5rct ndcg (NDCG@30, Phase 2 evidence tiers, exponential gains {0,1,2,4,8}, mean over topics)

Tested configuration: TREC 2020 PM run monoT5rct (h2oloo)
Protocol: TREC 2020 PM Phase 2: evidence-tier-weighted ranking of retrieved abstracts
Dataset: TREC 2020 Precision Medicine: 40 cancer-gene-treatment topics over a 2019 MEDLINE baseline snapshot
Procedure: egfrnsclc-20261009-protocol-trec2020-pm-phase2-evidence
Evaluation: monoT5rct (h2oloo), TREC 2020 PM Phase 2
Coverage: Not reported scored / Not reported eligible
Uncertainty: Not reported by the source
Evidence: Independent external evaluation · source checkedOverview of the TREC 2020 Precision Medicine Track; NIST TREC Browser, Precision Medicine 2020 runs page · Overview Table 6 (PDF page 9), block 'exp-gains', row 2: team 'h2oloo', run 'monoT5rct'

A source-checked result verifies the numerical transcription, not every model or protocol detail. Evaluation metadata: source checked. Source checked does not mean independently reproduced.

Reproduction

Split: Single evaluation round (no training split)
Adaptation: Not reported
Scoring implementation: trec_eval and sample_eval (Phase 1); NDCG@30 (Phase 2)

No execution recipe has been verified for this exact configuration and evaluation. A benchmark's general instructions may use different inputs, splits or model settings.

Reproducing this published result requires matching its model configuration, data, split and scorer. Source checking or a successful smoke test does not establish score reproduction.

Evidence

Source checking verifies the cited claim or transcription. It does not establish independent reproduction.

Evidence table

Inspect claims, sources and review details

Trace each statement to its source and review. A context-only reference supports the record generally; it does not verify an individual field. Source checking does not reproduce an experiment.

One row per statement and cited source. Multiple citations are not independent evaluations. Shared locators are labelled explicitly.

2 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-10-09-ba02f2f4a36e
Property and statement	Original source and location	Review and provenance
Reported result 0.4193 Individual claims	NIST TREC Browser, Precision Medicine 2020 runs page Original source ↗ Overview Table 6 (PDF page 9), block 'exp-gains', row 2: team 'h2oloo', run 'monoT5rct' Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: usnistgov/trec-browser commit 75ec9339eac60126b1045e5858a5ac874ea54a51 Retrieved: 2026-10-09T20:41:00Z	source checked ["source-hash-verification","deterministic-table-parse","independent-cell-check"] · 2026-10-09 independent paper Audit details Extracted by deterministic parse of the PDF text layer (pdftotext -layout) of Tables 5 and 6, with table captions, metric sub-headers and five rows per block asserted; run names printed with spaces were matched to TREC browser run IDs with underscores. Independent review 2026-10-09: value and identity match the source. Field: `attributes.printed_value` Source artifact SHA-256: `910bdd0f56124a8aef1638808ba6cbb393d0483fc10013fec78f1d57803635ec` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact Extraction artifact SHA-256: `7951225ee5b517fac7bf5f5739c6a118182ce84a5c3f5ddd2284d85262c126c2` Extraction artifact
Reported result 0.4193 Individual claims	Overview of the TREC 2020 Precision Medicine Track Original source ↗ Overview Table 6 (PDF page 9), block 'exp-gains', row 2: team 'h2oloo', run 'monoT5rct' Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Proceedings of the Twenty-Ninth Text REtrieval Conference (TREC 2020), NIST Special Publication 1266; 10-page PDF Retrieved: 2026-10-09T20:41:38Z	source checked ["source-hash-verification","deterministic-table-parse","independent-cell-check"] · 2026-10-09 independent paper Audit details Extracted by deterministic parse of the PDF text layer (pdftotext -layout) of Tables 5 and 6, with table captions, metric sub-headers and five rows per block asserted; run names printed with spaces were matched to TREC browser run IDs with underscores. Independent review 2026-10-09: value and identity match the source. Field: `attributes.printed_value` Source artifact SHA-256: `7951225ee5b517fac7bf5f5739c6a118182ce84a5c3f5ddd2284d85262c126c2` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact Extraction artifact SHA-256: `7951225ee5b517fac7bf5f5739c6a118182ce84a5c3f5ddd2284d85262c126c2` Extraction artifact

All evidence (JSONL) (gzip)How to read the evidence

Sources and history

Release 2026-10-09-ba02f2f4a36e · Record review: source checked

2 source records and release history

Overview of the TREC 2020 Precision Medicine Track · Original source · Proceedings of the Twenty-Ninth Text REtrieval Conference (TREC 2020), NIST Special Publication 1266; 10-page PDF
NIST TREC Browser, Precision Medicine 2020 runs page · Original source · usnistgov/trec-browser commit 75ec9339eac60126b1045e5858a5ac874ea54a51

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: egfrnsclc-20261009-result-trec2020-pm-monot5rct-expgains

metric: ndcg
metric qualifier: NDCG@30, Phase 2 evidence tiers, exponential gains {0,1,2,4,8}, mean over topics
metric direction: higher
unit: unitless
printed value: 0.4193
numeric value: 0.4193
source locator: Overview Table 6 (PDF page 9), block 'exp-gains', row 2: team 'h2oloo', run 'monoT5rct'
review: method: source-hash-verification; deterministic-table-parse; independent-cell-check; method note: Read Tables 5 and 6 from the PDF text layer with a separate parser; checked value, block, row, team, run, metric, qualifier and the linked configuration and protocol. infNDCG and P@10 also match the TREC browser results page and every Table 5 value, R-prec included, matches the run's appendix PDF; Table 6 (NDCG@30) has no public cross-check.; reviewer: claude; reviewer note: Separate Claude review agent, independent of the extractor; no human review claimed; date: 2026-10-09; artifact sha256: 7951225ee5b517fac7bf5f5739c6a118182ce84a5c3f5ddd2284d85262c126c2; retrieval url: https://trec.nist.gov/pubs/trec29/papers/OVERVIEW.PM.pdf; note: Extracted by deterministic parse of the PDF text layer (pdftotext -layout) of Tables 5 and 6, with table captions, metric sub-headers and five rows per block asserted; run names printed with spaces were matched to TREC browser run IDs with underscores. Independent review 2026-10-09: value and identity match the source.
missing metadata: uncertainty: reason: unreported
scope note: Listed as one of the top five teams (best run per team) for this metric.

Related records

evaluation: monoT5rct (h2oloo), TREC 2020 PM Phase 2

Suggest a correction