rewirebio.iobenchmarks
Result

R² of ESM-C on PRIME mutated RBD

-0.0162 R²

Methods

Tested configuration
ESM-C
Task
Mutated RBD binding prediction
Dataset
PRIME mutated RBD
Procedure
Frozen mean-pooled representation with downstream regression; position-stratified split.
Evaluation
ESM-C: Mutated RBD binding prediction
Coverage
Not reported scored / Not reported eligible
Uncertainty
± 0.01 (type not stated)
Evidence
Independent external evaluation · source checkedPRIME: An evaluation framework for protein representation inference and generalization in viral mutation space · Table 1, ESM-C 300M / Mean / not fine-tuned row, Position-Stratified Split Binding R² 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
position-stratified
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 2026-11-21-adc15377fab2
Property and statementOriginal source and locationReview and provenance
Printed value
-0.0162
Individual claims
PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space

Original source ↗

Table 1, ESM-C 300M / Mean / not fine-tuned row, Position-Stratified Split Binding R² column

Version: version of record
Retrieved: 2026-09-16T10:41:16.525183+00:00

source checked

["ai-assisted-source-review"] · 2026-09-16T10:41:16.526387+00:00

independent paper

Audit details

Resolved model row spans and Mean/CLS subrows in JATS: selected Mean, not fine-tuned (cross), Position-Stratified Split > Binding > R-squared. Central value agrees; uncertainty is retained in evidence. This verifies the central score at its source location, not every metadata field or an experimental reproduction.

Field: attributes.printed_value

Claim: claim-lit-022

Source artifact SHA-256: f6aac4c25dd93026f87ce9a2e327c95faf4c3014d7f9ae04bb11f208ce047971

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

Inspected artifact

Extraction artifact SHA-256: f6aac4c25dd93026f87ce9a2e327c95faf4c3014d7f9ae04bb11f208ce047971

Extraction artifact

Sources and history

Release 2026-11-21-adc15377fab2 · Record review: source checked

1 source record and release history

Superseded by ESM-C 300M Mean frozen ACE2 binding R² (position-stratified split)

Download this release (gzip)
Technical metadata and extraction receipts

Stable ID: lit-022

areas
proteins-complexes
tasks
Mutated RBD binding prediction
printed value
-0.0162
numeric value
-0.0162
metric
coefficient-of-determination
metric direction
unknown
unit
unitless
uncertainty
type: unresolved_spread; printed: ± 0.01; value: 0.01
source locator
Table 1, ESM-C 300M / Mean / not fine-tuned row, Position-Stratified Split Binding R² column
review
method: ai-assisted-source-review; reviewer: codex; reviewed at: 2026-09-16T10:41:16.526387+00:00; evidence: {"table_xml_id": "Tab1", "row_cells": ["Mean", "×", "0.7155 ± 0.07", "1.0075 ± 0.13", "0.6546 ± 0.04", "0.5830 ± 0.03", "-0.0162 ± 0.01", "1.7874 ± 0.02", "0.0647 ± 0.02", "1.0410 ± 0.01"], "selected_cell_zero_based": 6, "selected_cell_xml": "<td align=\"left\" colspan=\"1\" rowspan=\"1\">-0.0162 ± 0.01</td>", "caption": "Benchmarking PRIME across different model scales and validation regimes for mutated RBD binding and expression"}; artifact sha256: f6aac4c25dd93026f87ce9a2e327c95faf4c3014d7f9ae04bb11f208ce047971; retrieval url: https://www.ebi.ac.uk/europepmc/webservices/rest/PMC13425921/fullTextXML; method note: independent; table-level review; reviewer note: role: omics research agent; independent source-table review; not human review; note: Resolved model row spans and Mean/CLS subrows in JATS: selected Mean, not fine-tuned (cross), Position-Stratified Split > Binding > R-squared. Central value agrees; uncertainty is retained in evidence. This verifies the central score at its source location, not every metadata field or an experimental reproduction.
legacy id
lit-022
missing metadata
dataset version: reason: unextracted
Related records

Suggest a correction