Protocol

EVEE deconfounded ClinVar SNV pathogenicity AUROC (Pearce et al. 2026 Figure 1c)

Evidence concern: excluded from comparisons

The column labelled 'NTv3' in Figure 1b and 1c is not the method the Methods describe. The manuscript repository's plotting code (scripts/figure1/_heatmap_common.py at e5e4a43) renames 'NTv3 cosine dist' to 'NTv3' and drops 'NTv3 subref probe', whereas Methods 'Baseline methods' describe NTv3 650M layer-11 embeddings with L2-regularised logistic regression under 5-fold gene-holdout cross-validation. Figure 1d's NTv3 column is the supervised subref probe. The SNV and deconfounded NTv3 values are recorded as a zero-shot embedding distance.Interpretable variant effect prediction from genomic foundation model representations (EVEE), bioRxiv v4 · Figure 1b and 1c, column 'NTv3' (page 3); Methods 'Baseline methods', NTv3 (page 8); repository scripts/figure1/_heatmap_common.py RENAME_MAP and DROP_METHODS

AlphaMissense's 'Overall' cell in Figure 1b and 1c is its missense AUROC. The plotting code blanks AlphaMissense outside missense and copies the Missense value into the Overall row (scripts/figure1/_heatmap_common.py, am_ov_mask), so it is computed on a different, missense-only population from the other methods' Overall cells.Interpretable variant effect prediction from genomic foundation model representations (EVEE), bioRxiv v4 · Figure 1b and 1c, row 'Overall', column 'AlphaMissense' (page 3); repository scripts/figure1/_heatmap_common.py prepare()

AUROC for pathogenic versus benign on the deconfounded ClinVar SNV benchmark, all consequence types pooled (Overall row).

8 evaluations · 8 results

Overview

An explanatory profile has not yet been reviewed for this record.

Consult the linked sources for architecture or protocol details. Missing evidence is not evidence of a missing capability.

8 recorded evaluations, 8 metric rows. A comparison chart has not yet been validated for these results. The table retains the individual findings and their sources.

View coverage and remaining gaps across all benchmarks

Results

Results are available, but no reviewed comparison panel is linked in this release.

All evaluations

8 evaluations · 8 results. Different protocols are not a single leaderboard.

Protocol: EVEE deconfounded ClinVar SNV pathogenicity AUROC (Pearce et al. 2026 Figure 1c) · Dataset: EVEE deconfounded ClinVar SNV benchmark (158,616 variants)

Sorted by AUROC (Deconfounded ClinVar SNVs, all consequence types (Overall row)) (higher is better). The best value in each column is highlighted. Decimals are rounded for display; each value links to the printed value and its source.

Tested configuration	AUROC (Deconfounded ClinVar SNVs, all consequence types (Overall row))	AUROC (Deconfounded ClinVar SNVs, missense only (value plotted in the Overall row))
EVEE covariance probe on Evo 2 7B layer 27 (Pearce et al. 2026)Evaluation	0.977 (best in column)	Not reported
Evo 2 7B mean-pooled embedding probe (Pearce et al. 2026)Evaluation	0.967	Not reported
CADD v1.7 PHRED, pre-computed (Pearce et al. 2026)Evaluation	0.963	Not reported
GPN-MSA hg38 scores, pre-computed (Pearce et al. 2026)Evaluation	0.952	Not reported
Evo 2 7B loss-based zero-shot score (Pearce et al. 2026)Evaluation	0.929	Not reported
NTv3 cosine distance (Pearce et al. 2026 Figure 1b and 1c)Evaluation	0.71	Not reported
AlphaGenome all-folds composite score (Pearce et al. 2026)Evaluation	0.574	Not reported
AlphaMissense hg38, pre-computed (Pearce et al. 2026)Evaluation	Not reported	0.972

All 8 result rows with coverage, uncertainty and sources

Filter evaluations

Tested model or methodProtocolDatasetEvaluation setupMetricEvidence origin

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configuration	Protocol and dataset	Finding	Evidence and details
Configuration: AlphaGenome all-folds composite score (Pearce et al. 2026)	Protocol: EVEE deconfounded ClinVar SNV pathogenicity AUROC (Pearce et al. 2026 Figure 1c) Dataset: EVEE deconfounded ClinVar SNV benchmark (158,616 variants)	0.574 AUROC (Deconfounded ClinVar SNVs, all consequence types (Overall row)) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons The column labelled 'NTv3' in Figure 1b and 1c is not the method the Methods describe. The manuscript repository's plotting code (scripts/figure1/_heatmap_common.py at e5e4a43) renames 'NTv3 cosine dist' to 'NTv3' and drops 'NTv3 subref probe', whereas Methods 'Baseline methods' describe NTv3 650M layer-11 embeddings with L2-regularised logistic regression under 5-fold gene-holdout cross-validation. Figure 1d's NTv3 column is the supervised subref probe. The SNV and deconfounded NTv3 values are recorded as a zero-shot embedding distance.Interpretable variant effect prediction from genomic foundation model representations (EVEE), bioRxiv v4 · Figure 1b and 1c, column 'NTv3' (page 3); Methods 'Baseline methods', NTv3 (page 8); repository scripts/figure1/_heatmap_common.py RENAME_MAP and DROP_METHODS AlphaMissense's 'Overall' cell in Figure 1b and 1c is its missense AUROC. The plotting code blanks AlphaMissense outside missense and copies the Missense value into the Overall row (scripts/figure1/_heatmap_common.py, am_ov_mask), so it is computed on a different, missense-only population from the other methods' Overall cells.Interpretable variant effect prediction from genomic foundation model representations (EVEE), bioRxiv v4 · Figure 1b and 1c, row 'Overall', column 'AlphaMissense' (page 3); repository scripts/figure1/_heatmap_common.py prepare() Methods, coverage and source AlphaGenome on the EVEE deconfounded ClinVar SNV benchmark (Pearce et al. 2026) gfm-guide-20261014-protocol-evee-deconfounded-snv-auroc Aggregation: Not reported Interpretable variant effect prediction from genomic foundation model representations (EVEE), bioRxiv v4; EVEE manuscript repository: figures/figure1/fig1c_deconf_heatmap.pdf; EVEE manuscript repository: scripts/figure1/_heatmap_common.py · Figure 1c (page 3, raster; matched to repository figures/figure1/fig1c_deconf_heatmap.pdf text layer), row 'Overall (n=158,616, 27.8%P)', column 'AlphaGenome'
Configuration: AlphaMissense hg38, pre-computed (Pearce et al. 2026)	Protocol: EVEE deconfounded ClinVar SNV pathogenicity AUROC (Pearce et al. 2026 Figure 1c) Dataset: EVEE deconfounded ClinVar SNV benchmark (158,616 variants)	0.972 AUROC (Deconfounded ClinVar SNVs, missense only (value plotted in the Overall row)) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons The column labelled 'NTv3' in Figure 1b and 1c is not the method the Methods describe. The manuscript repository's plotting code (scripts/figure1/_heatmap_common.py at e5e4a43) renames 'NTv3 cosine dist' to 'NTv3' and drops 'NTv3 subref probe', whereas Methods 'Baseline methods' describe NTv3 650M layer-11 embeddings with L2-regularised logistic regression under 5-fold gene-holdout cross-validation. Figure 1d's NTv3 column is the supervised subref probe. The SNV and deconfounded NTv3 values are recorded as a zero-shot embedding distance.Interpretable variant effect prediction from genomic foundation model representations (EVEE), bioRxiv v4 · Figure 1b and 1c, column 'NTv3' (page 3); Methods 'Baseline methods', NTv3 (page 8); repository scripts/figure1/_heatmap_common.py RENAME_MAP and DROP_METHODS AlphaMissense's 'Overall' cell in Figure 1b and 1c is its missense AUROC. The plotting code blanks AlphaMissense outside missense and copies the Missense value into the Overall row (scripts/figure1/_heatmap_common.py, am_ov_mask), so it is computed on a different, missense-only population from the other methods' Overall cells.Interpretable variant effect prediction from genomic foundation model representations (EVEE), bioRxiv v4 · Figure 1b and 1c, row 'Overall', column 'AlphaMissense' (page 3); repository scripts/figure1/_heatmap_common.py prepare() Methods, coverage and source AlphaMissense on the EVEE deconfounded ClinVar SNV benchmark (Pearce et al. 2026) gfm-guide-20261014-protocol-evee-deconfounded-snv-auroc Aggregation: Not reported Interpretable variant effect prediction from genomic foundation model representations (EVEE), bioRxiv v4; EVEE manuscript repository: figures/figure1/fig1c_deconf_heatmap.pdf; EVEE manuscript repository: scripts/figure1/_heatmap_common.py · Figure 1c (page 3, raster; matched to repository figures/figure1/fig1c_deconf_heatmap.pdf text layer), row 'Overall (n=158,616, 27.8%P)', column 'AlphaMissense'
Configuration: CADD v1.7 PHRED, pre-computed (Pearce et al. 2026)	Protocol: EVEE deconfounded ClinVar SNV pathogenicity AUROC (Pearce et al. 2026 Figure 1c) Dataset: EVEE deconfounded ClinVar SNV benchmark (158,616 variants)	0.963 AUROC (Deconfounded ClinVar SNVs, all consequence types (Overall row)) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons The column labelled 'NTv3' in Figure 1b and 1c is not the method the Methods describe. The manuscript repository's plotting code (scripts/figure1/_heatmap_common.py at e5e4a43) renames 'NTv3 cosine dist' to 'NTv3' and drops 'NTv3 subref probe', whereas Methods 'Baseline methods' describe NTv3 650M layer-11 embeddings with L2-regularised logistic regression under 5-fold gene-holdout cross-validation. Figure 1d's NTv3 column is the supervised subref probe. The SNV and deconfounded NTv3 values are recorded as a zero-shot embedding distance.Interpretable variant effect prediction from genomic foundation model representations (EVEE), bioRxiv v4 · Figure 1b and 1c, column 'NTv3' (page 3); Methods 'Baseline methods', NTv3 (page 8); repository scripts/figure1/_heatmap_common.py RENAME_MAP and DROP_METHODS AlphaMissense's 'Overall' cell in Figure 1b and 1c is its missense AUROC. The plotting code blanks AlphaMissense outside missense and copies the Missense value into the Overall row (scripts/figure1/_heatmap_common.py, am_ov_mask), so it is computed on a different, missense-only population from the other methods' Overall cells.Interpretable variant effect prediction from genomic foundation model representations (EVEE), bioRxiv v4 · Figure 1b and 1c, row 'Overall', column 'AlphaMissense' (page 3); repository scripts/figure1/_heatmap_common.py prepare() Methods, coverage and source CADD v1.7 on the EVEE deconfounded ClinVar SNV benchmark (Pearce et al. 2026) gfm-guide-20261014-protocol-evee-deconfounded-snv-auroc Aggregation: Not reported Interpretable variant effect prediction from genomic foundation model representations (EVEE), bioRxiv v4; EVEE manuscript repository: figures/figure1/fig1c_deconf_heatmap.pdf; EVEE manuscript repository: scripts/figure1/_heatmap_common.py · Figure 1c (page 3, raster; matched to repository figures/figure1/fig1c_deconf_heatmap.pdf text layer), row 'Overall (n=158,616, 27.8%P)', column 'CADD v1.7'
Configuration: EVEE covariance probe on Evo 2 7B layer 27 (Pearce et al. 2026)	Protocol: EVEE deconfounded ClinVar SNV pathogenicity AUROC (Pearce et al. 2026 Figure 1c) Dataset: EVEE deconfounded ClinVar SNV benchmark (158,616 variants)	0.977 AUROC (Deconfounded ClinVar SNVs, all consequence types (Overall row)) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons The column labelled 'NTv3' in Figure 1b and 1c is not the method the Methods describe. The manuscript repository's plotting code (scripts/figure1/_heatmap_common.py at e5e4a43) renames 'NTv3 cosine dist' to 'NTv3' and drops 'NTv3 subref probe', whereas Methods 'Baseline methods' describe NTv3 650M layer-11 embeddings with L2-regularised logistic regression under 5-fold gene-holdout cross-validation. Figure 1d's NTv3 column is the supervised subref probe. The SNV and deconfounded NTv3 values are recorded as a zero-shot embedding distance.Interpretable variant effect prediction from genomic foundation model representations (EVEE), bioRxiv v4 · Figure 1b and 1c, column 'NTv3' (page 3); Methods 'Baseline methods', NTv3 (page 8); repository scripts/figure1/_heatmap_common.py RENAME_MAP and DROP_METHODS AlphaMissense's 'Overall' cell in Figure 1b and 1c is its missense AUROC. The plotting code blanks AlphaMissense outside missense and copies the Missense value into the Overall row (scripts/figure1/_heatmap_common.py, am_ov_mask), so it is computed on a different, missense-only population from the other methods' Overall cells.Interpretable variant effect prediction from genomic foundation model representations (EVEE), bioRxiv v4 · Figure 1b and 1c, row 'Overall', column 'AlphaMissense' (page 3); repository scripts/figure1/_heatmap_common.py prepare() Methods, coverage and source Evo2 Covariance on the EVEE deconfounded ClinVar SNV benchmark (Pearce et al. 2026) gfm-guide-20261014-protocol-evee-deconfounded-snv-auroc Aggregation: Not reported Interpretable variant effect prediction from genomic foundation model representations (EVEE), bioRxiv v4; EVEE manuscript repository: figures/figure1/fig1c_deconf_heatmap.pdf; EVEE manuscript repository: scripts/figure1/_heatmap_common.py · Figure 1c (page 3, raster; matched to repository figures/figure1/fig1c_deconf_heatmap.pdf text layer), row 'Overall (n=158,616, 27.8%P)', column 'Evo2 Covariance'
Configuration: Evo 2 7B loss-based zero-shot score (Pearce et al. 2026)	Protocol: EVEE deconfounded ClinVar SNV pathogenicity AUROC (Pearce et al. 2026 Figure 1c) Dataset: EVEE deconfounded ClinVar SNV benchmark (158,616 variants)	0.929 AUROC (Deconfounded ClinVar SNVs, all consequence types (Overall row)) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons The column labelled 'NTv3' in Figure 1b and 1c is not the method the Methods describe. The manuscript repository's plotting code (scripts/figure1/_heatmap_common.py at e5e4a43) renames 'NTv3 cosine dist' to 'NTv3' and drops 'NTv3 subref probe', whereas Methods 'Baseline methods' describe NTv3 650M layer-11 embeddings with L2-regularised logistic regression under 5-fold gene-holdout cross-validation. Figure 1d's NTv3 column is the supervised subref probe. The SNV and deconfounded NTv3 values are recorded as a zero-shot embedding distance.Interpretable variant effect prediction from genomic foundation model representations (EVEE), bioRxiv v4 · Figure 1b and 1c, column 'NTv3' (page 3); Methods 'Baseline methods', NTv3 (page 8); repository scripts/figure1/_heatmap_common.py RENAME_MAP and DROP_METHODS AlphaMissense's 'Overall' cell in Figure 1b and 1c is its missense AUROC. The plotting code blanks AlphaMissense outside missense and copies the Missense value into the Overall row (scripts/figure1/_heatmap_common.py, am_ov_mask), so it is computed on a different, missense-only population from the other methods' Overall cells.Interpretable variant effect prediction from genomic foundation model representations (EVEE), bioRxiv v4 · Figure 1b and 1c, row 'Overall', column 'AlphaMissense' (page 3); repository scripts/figure1/_heatmap_common.py prepare() Methods, coverage and source Evo2 Loss on the EVEE deconfounded ClinVar SNV benchmark (Pearce et al. 2026) gfm-guide-20261014-protocol-evee-deconfounded-snv-auroc Aggregation: Not reported Interpretable variant effect prediction from genomic foundation model representations (EVEE), bioRxiv v4; EVEE manuscript repository: figures/figure1/fig1c_deconf_heatmap.pdf; EVEE manuscript repository: scripts/figure1/_heatmap_common.py · Figure 1c (page 3, raster; matched to repository figures/figure1/fig1c_deconf_heatmap.pdf text layer), row 'Overall (n=158,616, 27.8%P)', column 'Evo2 Loss'
Configuration: Evo 2 7B mean-pooled embedding probe (Pearce et al. 2026)	Protocol: EVEE deconfounded ClinVar SNV pathogenicity AUROC (Pearce et al. 2026 Figure 1c) Dataset: EVEE deconfounded ClinVar SNV benchmark (158,616 variants)	0.967 AUROC (Deconfounded ClinVar SNVs, all consequence types (Overall row)) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons The column labelled 'NTv3' in Figure 1b and 1c is not the method the Methods describe. The manuscript repository's plotting code (scripts/figure1/_heatmap_common.py at e5e4a43) renames 'NTv3 cosine dist' to 'NTv3' and drops 'NTv3 subref probe', whereas Methods 'Baseline methods' describe NTv3 650M layer-11 embeddings with L2-regularised logistic regression under 5-fold gene-holdout cross-validation. Figure 1d's NTv3 column is the supervised subref probe. The SNV and deconfounded NTv3 values are recorded as a zero-shot embedding distance.Interpretable variant effect prediction from genomic foundation model representations (EVEE), bioRxiv v4 · Figure 1b and 1c, column 'NTv3' (page 3); Methods 'Baseline methods', NTv3 (page 8); repository scripts/figure1/_heatmap_common.py RENAME_MAP and DROP_METHODS AlphaMissense's 'Overall' cell in Figure 1b and 1c is its missense AUROC. The plotting code blanks AlphaMissense outside missense and copies the Missense value into the Overall row (scripts/figure1/_heatmap_common.py, am_ov_mask), so it is computed on a different, missense-only population from the other methods' Overall cells.Interpretable variant effect prediction from genomic foundation model representations (EVEE), bioRxiv v4 · Figure 1b and 1c, row 'Overall', column 'AlphaMissense' (page 3); repository scripts/figure1/_heatmap_common.py prepare() Methods, coverage and source Evo2 Mean on the EVEE deconfounded ClinVar SNV benchmark (Pearce et al. 2026) gfm-guide-20261014-protocol-evee-deconfounded-snv-auroc Aggregation: Not reported Interpretable variant effect prediction from genomic foundation model representations (EVEE), bioRxiv v4; EVEE manuscript repository: figures/figure1/fig1c_deconf_heatmap.pdf; EVEE manuscript repository: scripts/figure1/_heatmap_common.py · Figure 1c (page 3, raster; matched to repository figures/figure1/fig1c_deconf_heatmap.pdf text layer), row 'Overall (n=158,616, 27.8%P)', column 'Evo2 Mean'
Configuration: GPN-MSA hg38 scores, pre-computed (Pearce et al. 2026)	Protocol: EVEE deconfounded ClinVar SNV pathogenicity AUROC (Pearce et al. 2026 Figure 1c) Dataset: EVEE deconfounded ClinVar SNV benchmark (158,616 variants)	0.952 AUROC (Deconfounded ClinVar SNVs, all consequence types (Overall row)) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons The column labelled 'NTv3' in Figure 1b and 1c is not the method the Methods describe. The manuscript repository's plotting code (scripts/figure1/_heatmap_common.py at e5e4a43) renames 'NTv3 cosine dist' to 'NTv3' and drops 'NTv3 subref probe', whereas Methods 'Baseline methods' describe NTv3 650M layer-11 embeddings with L2-regularised logistic regression under 5-fold gene-holdout cross-validation. Figure 1d's NTv3 column is the supervised subref probe. The SNV and deconfounded NTv3 values are recorded as a zero-shot embedding distance.Interpretable variant effect prediction from genomic foundation model representations (EVEE), bioRxiv v4 · Figure 1b and 1c, column 'NTv3' (page 3); Methods 'Baseline methods', NTv3 (page 8); repository scripts/figure1/_heatmap_common.py RENAME_MAP and DROP_METHODS AlphaMissense's 'Overall' cell in Figure 1b and 1c is its missense AUROC. The plotting code blanks AlphaMissense outside missense and copies the Missense value into the Overall row (scripts/figure1/_heatmap_common.py, am_ov_mask), so it is computed on a different, missense-only population from the other methods' Overall cells.Interpretable variant effect prediction from genomic foundation model representations (EVEE), bioRxiv v4 · Figure 1b and 1c, row 'Overall', column 'AlphaMissense' (page 3); repository scripts/figure1/_heatmap_common.py prepare() Methods, coverage and source GPN-MSA on the EVEE deconfounded ClinVar SNV benchmark (Pearce et al. 2026) gfm-guide-20261014-protocol-evee-deconfounded-snv-auroc Aggregation: Not reported Interpretable variant effect prediction from genomic foundation model representations (EVEE), bioRxiv v4; EVEE manuscript repository: figures/figure1/fig1c_deconf_heatmap.pdf; EVEE manuscript repository: scripts/figure1/_heatmap_common.py · Figure 1c (page 3, raster; matched to repository figures/figure1/fig1c_deconf_heatmap.pdf text layer), row 'Overall (n=158,616, 27.8%P)', column 'GPN-MSA'
Configuration: NTv3 cosine distance (Pearce et al. 2026 Figure 1b and 1c)	Protocol: EVEE deconfounded ClinVar SNV pathogenicity AUROC (Pearce et al. 2026 Figure 1c) Dataset: EVEE deconfounded ClinVar SNV benchmark (158,616 variants)	0.71 AUROC (Deconfounded ClinVar SNVs, all consequence types (Overall row)) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons The column labelled 'NTv3' in Figure 1b and 1c is not the method the Methods describe. The manuscript repository's plotting code (scripts/figure1/_heatmap_common.py at e5e4a43) renames 'NTv3 cosine dist' to 'NTv3' and drops 'NTv3 subref probe', whereas Methods 'Baseline methods' describe NTv3 650M layer-11 embeddings with L2-regularised logistic regression under 5-fold gene-holdout cross-validation. Figure 1d's NTv3 column is the supervised subref probe. The SNV and deconfounded NTv3 values are recorded as a zero-shot embedding distance.Interpretable variant effect prediction from genomic foundation model representations (EVEE), bioRxiv v4 · Figure 1b and 1c, column 'NTv3' (page 3); Methods 'Baseline methods', NTv3 (page 8); repository scripts/figure1/_heatmap_common.py RENAME_MAP and DROP_METHODS AlphaMissense's 'Overall' cell in Figure 1b and 1c is its missense AUROC. The plotting code blanks AlphaMissense outside missense and copies the Missense value into the Overall row (scripts/figure1/_heatmap_common.py, am_ov_mask), so it is computed on a different, missense-only population from the other methods' Overall cells.Interpretable variant effect prediction from genomic foundation model representations (EVEE), bioRxiv v4 · Figure 1b and 1c, row 'Overall', column 'AlphaMissense' (page 3); repository scripts/figure1/_heatmap_common.py prepare() Methods, coverage and source NTv3 on the EVEE deconfounded ClinVar SNV benchmark (Pearce et al. 2026) gfm-guide-20261014-protocol-evee-deconfounded-snv-auroc Aggregation: Not reported Interpretable variant effect prediction from genomic foundation model representations (EVEE), bioRxiv v4; EVEE manuscript repository: figures/figure1/fig1c_deconf_heatmap.pdf; EVEE manuscript repository: scripts/figure1/_heatmap_common.py · Figure 1c (page 3, raster; matched to repository figures/figure1/fig1c_deconf_heatmap.pdf text layer), row 'Overall (n=158,616, 27.8%P)', column 'NTv3'

Source checking is not independent reproduction. Release 2026-10-22-1b7cf027e4f6.

Methods and evaluation design

Procedure, tasks and evaluated configurations

Recorded evaluations

Each evaluation records what was tested and under which conditions.

Baseline coverage

Reference methods help show what a model adds beyond simple controls. We track a null control and a conventional method for each protocol.

0 of 2 active baseline roles have published Rewire measurements in this release. Measurements on a selected protocol do not establish coverage of an entire suite.

No execution recipe linked to this protocol. Recipe availability does not establish a completed evaluation.

Author-reported evaluations: 3
External evaluations: 5

Literature evidence is not a Rewire measurement. Executed but unpublished runs and private review status are not included.

Null control

Proposed control: requires review

Select a task-valid null control after reviewing inputs and metric

Protocol-specific applicability, permitted inputs, access, split, evaluator and execution requirements need review before implementation or execution.

This is a suggested selection rule, not a validated method or a measured score.

Conventional reference

Proposed control: requires review

Select an upstream conventional reference after reviewing the full protocol

Protocol-specific applicability, permitted inputs, access, split, evaluator and execution requirements need review before implementation or execution.

This is a suggested selection rule, not a validated method or a measured score.

Protocol coverage CSV (gzip) · Model evaluation matrix (gzip) · Source table (gzip) · Release and checksums (gzip)

Coverage is derived from release 2026-10-22-1b7cf027e4f6. Source citations describe the original records; they do not validate an unreviewed baseline proposal. No results have been generated by this audit.

Run instructions

No runnable recipe has been reviewed for this protocol. Dataset access, model requirements, licences and compute requirements must be checked against its sources before execution.

Strengths, limitations and unresolved questions

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.

0 evidence rows 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

No evidence rows match these filters. Choose another scope or clear the search.

How to read the evidence

Sources and history

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

3 source records and release history

Interpretable variant effect prediction from genomic foundation model representations (EVEE), bioRxiv v4 · Original source · bioRxiv v4, posted 2026-07-11 (v1 posted 2026-04-11)
EVEE manuscript repository: figures/figure1/fig1c_deconf_heatmap.pdf · Original source · goodfire-ai/evee-manuscript commit e5e4a43d60bb217819144c09ab509ed44f49cd5f
EVEE manuscript repository: scripts/figure1/_heatmap_common.py · Original source · goodfire-ai/evee-manuscript commit e5e4a43d60bb217819144c09ab509ed44f49cd5f

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: gfm-guide-20261014-protocol-evee-deconfounded-snv-auroc

areas: dna-genomes
contexts: research
protocol: Each method's score on the 158,616 deconfounded ClinVar SNVs, AUROC for P/LP versus B/LB. Supervised probes use gene-holdout cross-validation; CADD, AlphaMissense, GPN-MSA and AlphaGenome use pre-computed or zero-shot scores.
version: bioRxiv v4 Figure 1c
metric: auroc
limitations: Developer-reported: the authors built EVEE and three of them co-authored Evo 2.; One value per method; no confidence interval is printed in Figure 1c.; AlphaMissense's Overall cell is its missense-only AUROC (see the source concern).; The NTv3 column is a zero-shot cosine distance, not the probe described in Methods (see the source concern).
source locator: Figure 1c (page 3); Methods 'Deconfounded benchmark' (page 9)

Related records

Suggest a correction