Result

0.317 average-precision

znabu2026-splicetransformer-ap average-precision

Tested configuration: SpliceTransformer (Znabu et al. 2026)
Protocol: MFASS splice-disrupting variant detection, all 27,733 labelled SNVs (Znabu et al. 2026)
Dataset: MFASS v2 eligible assay cohort
Procedure: splicing-follow-up-20261009-protocol-znabu2026-mfass-full-cohort
Evaluation: SpliceTransformer on all labelled MFASS SNVs
Coverage: Not reported scored / Not reported eligible
Uncertainty: 95% CI 0.285 to 0.352
Evidence: Independent external evaluation · source checkedA Reproducible MFASS Benchmark of Splice-Disruption Predictors Reveals a Shared Exon-Interior Blind Spot · Section 4 'Results' table (page 3), row 'SpliceTransformer', columns 'AP' and 'AP 95% CI'

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: None (whole labelled cohort)
Adaptation: None; published weights
Scoring implementation: AUROC and average precision

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.

1 evidence row matching the loaded filters

Claims, original sources and review scope · Release 2026-10-10-6e93f504adfc
Property and statement	Original source and location	Review and provenance
Reported result 0.317 Individual claims	A Reproducible MFASS Benchmark of Splice-Disruption Predictors Reveals a Shared Exon-Interior Blind Spot Original source ↗ Section 4 'Results' table (page 3), row 'SpliceTransformer', columns 'AP' and 'AP 95% CI' Version: bioRxiv 2026.07.21.739871 v1, posted 2026-07-26; full-text PDF Retrieved: 2026-10-09T20:52:21Z	source checked ["source-hash-verification","deterministic-table-parse","independent-cell-check"] · 2026-10-09 independent paper Audit details Deterministic parse of the pinned PDF text layer (pdftotext -layout) with the header line and five row labels asserted by regular expression. Independent review 2026-10-09: value and identity match the source. Field: `attributes.printed_value` Source artifact SHA-256: `52a2d1ccfd99ef62f847b323030acdb7d881ae75b6c9dda8805884a2e7727552` Hash scope: SHA-256 of the PDF as served. The PDF ModDate is 2026-10-09 21:52:24 BST; a re-download at review on 2026-10-09 returned identical bytes. bioRxiv can re-stamp the PDF on later downloads, so if the hash stops matching, compare the text layer. Inspected artifact Extraction artifact SHA-256: `52a2d1ccfd99ef62f847b323030acdb7d881ae75b6c9dda8805884a2e7727552` Extraction artifact

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

Sources and history

Release 2026-10-10-6e93f504adfc · Record review: source checked

1 source records and release history

A Reproducible MFASS Benchmark of Splice-Disruption Predictors Reveals a Shared Exon-Interior Blind Spot · Original source · bioRxiv 2026.07.21.739871 v1, posted 2026-07-26; full-text PDF

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: splicing-follow-up-20261009-result-znabu2026-splicetransformer-ap

metric: average-precision
metric direction: higher
unit: unitless
printed value: 0.317
numeric value: 0.317
source locator: Section 4 'Results' table (page 3), row 'SpliceTransformer', columns 'AP' and 'AP 95% CI'
review: method: source-hash-verification; deterministic-table-parse; independent-cell-check; method note: Re-downloaded the preprint PDF; it matched the pinned SHA-256. Read the Section 4 results table from the text layer (pdftotext -layout) with a separate parser written for this review; the extractor's scripts were not imported or run. Checked row label, printed value, numeric value, interval, metric, qualifier, unit, direction and the linked evaluation's configuration, protocol and dataset.; reviewer: claude; reviewer note: Separate Claude review agent, independent of the extractor; no human review claimed; date: 2026-10-09; artifact sha256: 52a2d1ccfd99ef62f847b323030acdb7d881ae75b6c9dda8805884a2e7727552; retrieval url: https://www.biorxiv.org/content/biorxiv/early/2026/07/26/2026.07.21.739871.full.pdf; note: Deterministic parse of the pinned PDF text layer (pdftotext -layout) with the header line and five row labels asserted by regular expression. Independent review 2026-10-09: value and identity match the source.
uncertainty: type: confidence_interval; printed: [0.285, 0.352]; lower: 0.285; upper: 0.352; level: 0.95; method: bootstrap; resamples: 1000; source column: AP 95% CI

Related records

evaluation: SpliceTransformer on all labelled MFASS SNVs

Suggest a correction