rewire.itbenchmarks
Result

0.403 Spearman rho

ESM2 OFS pseudo-perplexity · Spearman rho · ProteinGym substitutions

Tested pipeline
ESM2 OFS pseudo-perplexity
Task
protein variant fitness prediction
Dataset
ProteinGym substitutions
Procedure
authors’ zero-shot ESM2 OFS pseudo-perplexity evaluation; aggregate mean across ProteinGym substitution assays
Evaluation
ESM2 OFS pseudo-perplexity: protein variant fitness prediction
Coverage
scored: unreported; eligible: unreported
Uncertainty
Not reported
Evidence
Author-reported evaluation · source checkedPseudo-perplexity in One Fell Swoop for Protein Fitness Estimation · Published PDF page 6 (033014-6), Table I, ESM2: OFS PP row, Aggregate mean column

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

Reproduction

Split
aggregate across assays
Adaptation
Not reported
Scoring implementation
Not reported

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 2026-09-29-06401fd5b220
Property and statementOriginal source and locationReview and provenance
attributes.printed_value
0.403
Individual claims
Pseudo-perplexity in One Fell Swoop for Protein Fitness Estimation

Original source ↗

Published PDF page 6 (033014-6), Table I, ESM2: OFS PP row, Aggregate mean column

Version: PRX Life 2025 journal article
Retrieved: 2026-09-16T10:45:41.099916+00:00

source checked

independent ai table review · 2026-09-16T10:45:41.099916+00:00

author reported

Audit details

Publisher PDF retrieved through official APS harvest endpoint after direct download returned403. Table I is ProteinGym substitutions, not indels TableII. Last column aggregate mean0.403; separate function categories precede it. This verifies reported score, not experimental reproduction. Comparator rows in this table are sourced from ProteinGym; OFS PP is authors own method.

Field: attributes.printed_value

Claim: claim-b2-esm2-ofs-fitness-2025

Source artifact SHA-256: 085ef646f11b8e5335c4b3d86b15fb6c7bf5edf4a80a8b622753ac69d9991a67

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Extraction artifact SHA-256: 085ef646f11b8e5335c4b3d86b15fb6c7bf5edf4a80a8b622753ac69d9991a67

Extraction artifact

Sources and history

View linked audit checks and correction history

Release 2026-09-29-06401fd5b220 · Record review: source checked

1 source records and release historyDownload this release
Technical metadata and extraction receipts

Stable ID: b2-esm2-ofs-fitness-2025

areas
proteins-complexes
tasks
protein variant fitness prediction
printed value
0.403
numeric value
0.403
metric
Spearman rho
metric direction
unknown
unit
unitless
uncertainty
Not reported
source locator
Published PDF page 6 (033014-6), Table I, ESM2: OFS PP row, Aggregate mean column
review
method: independent_ai_table_review; reviewer: Codex omics research agent; independent source review, not human review; reviewed at: 2026-09-16T10:45:41.099916+00:00; notes: Publisher PDF retrieved through official APS harvest endpoint after direct download returned403. Table I is ProteinGym substitutions, not indels TableII. Last column aggregate mean0.403; separate function categories precede it. This verifies reported score, not experimental reproduction. Comparator rows in this table are sourced from ProteinGym; OFS PP is authors own method.; evidence: Headers: Activity(43), Binding(14), Expression(17), Organismal fitness(77), Stability(66), Aggregate mean. ESM2:OFS PP row:0.393,0.279,0.397,0.331,0.507,0.403. Verified publisher PDF layout extraction against web-rendered primary PDF table.; artifact sha256: 085ef646f11b8e5335c4b3d86b15fb6c7bf5edf4a80a8b622753ac69d9991a67; retrieval url: https://harvest.aps.org/v2/journals/articles/10.1103/zhx7-hcmm/fulltext
legacy id
b2-esm2-ofs-fitness-2025
legacy row
id: b2-esm2-ofs-fitness-2025; paper id: esm2-ofs-fitness-2025; domain id: proteins-complexes; task: protein variant fitness prediction; model: ESM2 OFS pseudo-perplexity; model version: not stated in table; dataset: ProteinGym substitutions; dataset version: Not reported; split: aggregate across assays; metric: Spearman rho; value: 0.403; unit: unitless; uncertainty: Not reported; protocol: authors’ zero-shot ESM2 OFS pseudo-perplexity evaluation; aggregate mean across ProteinGym substitution assays; source locator: Table I, ESM2: OFS PP row, Aggregate Mean Spearman correlation column; source url: https://journals.aps.org/prxlife/pdf/10.1103/zhx7-hcmm; evaluation origin: author_reported; reviewed utc: 2026-09-15T23:33:26Z
missing metadata
dataset version: not_reported_in_legacy_extract; uncertainty: not_reported_in_legacy_extract
Related records

Suggest a correction