Result

Recall (maximum delta score classification after legacy-tool pre-filtering (threshold not restated for this dataset)) of SpliceAI (Fortier et al. 2026) on Extended ClinVar benchmark (58,064 variants)

0.791 Recall (maximum delta score classification after legacy-tool pre-filtering (threshold not restated for this dataset))

Methods

Tested configuration: SpliceAI (Fortier et al. 2026)
Protocol: Splice-altering variant classification, Extended ClinVar benchmark (58,064 variants) (Fortier et al. Table 6)
Dataset: Extended ClinVar benchmark (58,064 variants)
Procedure: Splice-altering variant classification, Extended ClinVar benchmark (58,064 variants) (Fortier et al. Table 6)
Evaluation: SpliceAI on the Extended ClinVar benchmark (58,064 variants)
Coverage: Not reported scored / Not reported eligible
Uncertainty: Not reported by the source
Evidence: Independent external evaluation · source checkedAnalyzing the performance of deep learning splice prediction algorithms (Fortier, Rudy and Scherer, PLOS One 2026) · Table 6, row 'SpliceAI', column 'Sensitivity'

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: Whole set
Adaptation: maximum delta score classification after legacy-tool pre-filtering (threshold not restated for this dataset)
Scoring implementation: Sensitivity, specificity, F1 = 2TP/(2TP+FP+FN), balanced accuracy = mean of sensitivity and specificity (Equations 1 to 4)

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 2026-10-22-1b7cf027e4f6
Property and statement	Original source and location	Review and provenance
Reported result 0.791 Individual claims	Analyzing the performance of deep learning splice prediction algorithms (Fortier, Rudy and Scherer, PLOS One 2026) Original source ↗ Table 6, row 'SpliceAI', column 'Sensitivity' Version: PLOS One 21(5):e0348885, published 2026-05-13; PMC13170886 full-text XML Retrieved: 2026-10-11T21:37:04Z	source checked ["source-hash-verification","independent-cell-check","automated-source-review"] · 2026-10-12 independent paper Audit details Checked by reviewer-scnv against the pinned source; verdict in docs/reviews/use-cases/splicing-cnv-use-cases-2026-10-12.md and in this batch's review.md. Field: `attributes.printed_value` Source artifact SHA-256: `dffe74cee7782cbdfdbc9423cf00f0a846b3d720b90b10e9732d6f768c485176` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact Extraction artifact SHA-256: `dffe74cee7782cbdfdbc9423cf00f0a846b3d720b90b10e9732d6f768c485176` Extraction artifact

How to read the evidence

Sources and history

Release 2026-10-22-1b7cf027e4f6 · Record review: source checked

1 source record and release history

Analyzing the performance of deep learning splice prediction algorithms (Fortier, Rudy and Scherer, PLOS One 2026) · Original source · PLOS One 21(5):e0348885, published 2026-05-13; PMC13170886 full-text XML

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: rna-splicing-20261011-fortier2026-result-extended-clinvar-spliceai-recall

metric: recall
metric direction: higher
unit: fraction
printed value: 0.791
source locator: Table 6, row 'SpliceAI', column 'Sensitivity'
review: method: source-hash-verification; independent-cell-check; automated-source-review; reviewer: claude; reviewer note: Independent Claude review agent reviewer-scnv; did not extract this batch; no human review claimed; date: 2026-10-12; artifact sha256: dffe74cee7782cbdfdbc9423cf00f0a846b3d720b90b10e9732d6f768c485176; retrieval url: https://www.ebi.ac.uk/europepmc/webservices/rest/PMC13170886/fullTextXML; method note: Parsed the pinned PMC13170886 article XML (table-wrap elements) with a stdlib reader; caption, header row and the four row labels asserted for each table; printed cell text kept exactly.; note: Checked by reviewer-scnv against the pinned source; verdict in docs/reviews/use-cases/splicing-cnv-use-cases-2026-10-12.md and in this batch's review.md.
numeric value: 0.791
metric qualifier: maximum delta score classification after legacy-tool pre-filtering (threshold not restated for this dataset)
missing metadata: uncertainty: reason: unreported

Related records

evaluation: SpliceAI on the Extended ClinVar benchmark (58,064 variants)

Suggest a correction