rewire.it
result · source checked

0.49 Pearson R

RNA-FM · Pearson R · mRNABench MRL-MPRA

Tested model
RNA-FM
Task or benchmark
Mean ribosome load from MPRA
Dataset
mRNABench MRL-MPRA
Procedure
Linear probe; mean across ten random seeds.
Evaluation
RNA-FM: Mean ribosome load from MPRA
Evidence
Independent external evaluation · source checkedmRNABench: A curated benchmark for mature mRNA property and function prediction · Table 2, RNA-FM row, MRL MPRA 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.

Evaluation results

Release 2026-09-16-d74d282221a9 · 1 evaluation · 1 metric row. Different protocols are not a single leaderboard.

Results grouped by the exact reported evaluation
Metric and findingCoverage and uncertaintyEvidence
RNA-FM: Mean ribosome load from MPRA

Linear probe; mean across ten random seeds.

Independent external evaluation · Evaluation metadata: needs review

0.49 Pearson R

Unit: unitless · Direction: unknown

Uncertainty: not reported in legacy extract

Scored: Not reported · Eligible: Not reported

source checkedmRNABench: A curated benchmark for mature mRNA property and function prediction · Table 2, RNA-FM row, MRL MPRA column

Source checking is not independent reproduction.

Sources and history

Release 2026-09-16-d74d282221a9 · Record review: source checked

Download this release
Technical metadata and extraction receipts

Stable ID: lit-010

areas
rna-transcriptomes
tasks
Mean ribosome load from MPRA
printed value
0.49
numeric value
0.49
metric
Pearson R
metric direction
unknown
unit
unitless
uncertainty
Not reported
source locator
Table 2, RNA-FM row, MRL MPRA column
review
method: independent_ai_table_review; reviewer: Codex omics research agent; independent source-table review, not human review; reviewed at: 2026-09-16T10:41:16.500211+00:00; notes: MRL MPRA is the second task under Local and uses R. Caption specifies mean over ten random seeds and selected best model per family, not a fully identified checkpoint. This verifies the central score at its source location, not every metadata field or an experimental reproduction.; evidence: {"table_xml_id": "T9", "row_cells": ["RNA-FM", "25.7", "0.49", "35.0", "74.3", "67.0", "0.47", "0.29", "0.49", "32.2", "32.2"], "selected_cell_zero_based": 2, "selected_cell_xml": "<td align=\"right\" valign=\"top\" rowspan=\"1\" colspan=\"1\">0.49</td>", "caption": "Linear probe results. Mean of metric over ten random seeds reported. Best model per model family reported, see Appendix D for selected models. Best model for each dataset is and best foundation model is underlined. Models not significantly worse under Wilcoxon signed-rank test at p=0.05 are bolded."}; artifact sha256: 79f6264ee883535203c63a313547e7c57baa85585f76b42f8d899eb17fb7e600; retrieval url: https://www.ebi.ac.uk/europepmc/webservices/rest/PMC12265608/fullTextXML
legacy id
lit-010
legacy row
id: lit-010; paper id: mrnabench-2025; domain id: rna-transcriptomes; task: Mean ribosome load from MPRA; model: RNA-FM; model version: Not reported; dataset: mRNABench MRL-MPRA; dataset version: Not reported; split: Not reported; metric: Pearson R; value: 0.49; unit: unitless; uncertainty: Not reported; protocol: Linear probe; mean across ten random seeds.; source locator: Table 2, RNA-FM row, MRL MPRA column; source url: https://pmc.ncbi.nlm.nih.gov/articles/PMC12265608/; evaluation origin: independent_paper; reviewed utc: 2026-09-15T23:25:00Z
missing metadata
model version: not_reported_in_legacy_extract; dataset version: not_reported_in_legacy_extract; split: not_reported_in_legacy_extract; uncertainty: not_reported_in_legacy_extract
Related records

Suggest a correction