RMSE (RBD expression; Position-stratified split holding out whole mutated positions; the CLS token embedding, frozen) of ESM-C 600M, the CLS token embedding, not fine-tuned (PRIME) on SARS-CoV-2 RBD mutant binding and expression measurements
1.0823 ± 0.01 RMSE (RBD expression; Position-stratified split holding out whole mutated positions; the CLS token embedding, frozen)
Methods
- Tested configuration
- ESM-C 600M, the CLS token embedding, not fine-tuned (PRIME)
- Protocol
- PRIME RBD expression regression, Position-stratified split holding out whole mutated positions, RMSE
- Dataset
- SARS-CoV-2 RBD mutant binding and expression measurements
- Procedure
- PRIME RBD expression regression, Position-stratified split holding out whole mutated positions, RMSE
- Evaluation
- ESM-C 600M CLS frozen: RBD expression RMSE, Position-stratified split holding out whole mutated positions
- Coverage
- Not reported scored / Not reported eligible
- Uncertainty
- SD 0.01
- Evidence
- Author-reported evaluation · source checkedPRIME: An evaluation framework for protein representation inference and generalization in viral mutation space · Table 1, row 'ESM-C 600M' / 'CLS' / '×', columns 'Position-Stratified Split' / 'Expression' / 'RMSE'
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
- Position-stratified split holding out whole mutated positions
- Adaptation
- Supervised regression head on the representations
- Scoring implementation
- RMSE
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
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Reported result 1.0823 ± 0.01 Individual claims | PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space Table 1, row 'ESM-C 600M' / 'CLS' / '×', columns 'Position-Stratified Split' / 'Expression' / 'RMSE' Version: Version of record, BMC Genomics 2026 (PMC13425921 JATS full text) | source checked ["source-hash-verification","deterministic-table-parse","independent-cell-check"] · 2026-10-11 author reported Audit detailsExtraction: Parsed the pinned Europe PMC JATS XML with extract_prime.py (table-wrap grid with rowspan and colspan expanded, three header rows asserted); row and column labels asserted. Table 1, row 'ESM-C 600M' / 'CLS' / '×', columns 'Position-Stratified Split' / 'Expression' / 'RMSE' Independent review 2026-10-11: value, locator, metric, unit, direction and linked configuration and protocol checked; corrections from the review applied by the extractor as listed in review.md. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record Extraction artifact SHA-256: |
Sources and history
Release 2026-10-22-1b7cf027e4f6 · Record review: source checked
1 source record and release history
- PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space · Original source · Version of record, BMC Genomics 2026 (PMC13425921 JATS full text)
Technical metadata and extraction receipts
Stable ID: lit-protein-20261011-prime-result-position-stratified-expression-rmse-esm-c-600m-cls-frozen
- metric
- root-mean-squared-error
- metric direction
- lower
- unit
- unit-unreported
- printed value
- 1.0823 ± 0.01
- source locator
- Table 1, row 'ESM-C 600M' / 'CLS' / '×', columns 'Position-Stratified Split' / 'Expression' / 'RMSE'
- review
- method: source-hash-verification; deterministic-table-parse; independent-cell-check; method note: Reviewer re-retrieved the Europe PMC JATS XML and matched its SHA-256; an independent JATS table-grid parse compared all 168 results (printed and numeric values and spreads) with 0 mismatches; a hand sample of 40 values covering every column matched.; reviewer: claude; reviewer note: Claude review agent reviewer-ps-1, independent of the extractor lit-protein-structure; no human review claimed; date: 2026-10-11; artifact sha256: f6aac4c25dd93026f87ce9a2e327c95faf4c3014d7f9ae04bb11f208ce047971; retrieval url: https://www.ebi.ac.uk/europepmc/webservices/rest/PMC13425921/fullTextXML; note: Extraction: Parsed the pinned Europe PMC JATS XML with extract_prime.py (table-wrap grid with rowspan and colspan expanded, three header rows asserted); row and column labels asserted. Table 1, row 'ESM-C 600M' / 'CLS' / '×', columns 'Position-Stratified Split' / 'Expression' / 'RMSE' Independent review 2026-10-11: value, locator, metric, unit, direction and linked configuration and protocol checked; corrections from the review applied by the extractor as listed in review.md.
- numeric value
- 1.0823
- metric qualifier
- RBD expression; Position-stratified split holding out whole mutated positions; the CLS token embedding, frozen
- uncertainty
- type: standard_deviation; value: 0.01; printed: 1.0823 ± 0.01; scope: Standard deviation across random seeds (Table 1 footnote: 'with ± values representing the standard deviation across random seeds seen in Supplementary Table 6'). Table 1 uses five folds (Fig. 1C) and the Methods name three seeds, and the article does not say which of the two the spread is taken over, so no sample count is recorded.
- printed value basis
- Mean plus or minus standard deviation as printed