Task

Mean ribosome load from MPRA

Mean ribosome-load prediction includes a dedicated check of compositional generalization beyond the default split.

Sources

mRNABench: A curated benchmark for mature mRNA property and function prediction · Benchmarking Tasks; compositional generalization analysis; cached text lines 24, 26–27, 190–193; default-split results table caption and compositional-split results; matching task comparison table/ablation captions

2 evaluations · 2 results

Overview

Datasets

MRL-MPRA sequence/measurement dataset within mRNABench.

Metrics

Pearson correlation and the change between split conditions.

Allowed inputs

mRNA/UTR sequence representations.

Sources

Evaluation procedure diagram

How it worksComputational evaluation flow

Conceptual summary of the cited evaluation; exact task configuration and source version remain part of the protocol.

Sources

Source reviewed · Automated source review, 2026-09-16. All specifications and missing details

Results

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

All evaluations

2 evaluations · 2 results. Different protocols are not a single leaderboard.

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: RiNALMo	Task: Mean ribosome load from MPRA Dataset: mRNABench MRL-MPRA	0.74 Pearson R unitless · unknown Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source RiNALMo: Mean ribosome load from MPRA Linear probe; mean across ten random seeds. Aggregation: Not reported mRNABench: A curated benchmark for mature mRNA property and function prediction · Table 2, RiNALMo row, MRL MPRA column
Configuration: RNA-FM	Task: Mean ribosome load from MPRA Dataset: mRNABench MRL-MPRA	0.49 Pearson R unitless · unknown Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source RNA-FM: Mean ribosome load from MPRA Linear probe; mean across ten random seeds. Aggregation: Not reported mRNABench: A curated benchmark for mature mRNA property and function prediction · Table 2, RNA-FM row, MRL MPRA column

Source checking is not independent reproduction. Release 2026-09-29-06401fd5b220.

Methods and evaluation design

Procedure, tasks and evaluated configurations

How it works

Evaluation methodology

MRL-MPRA sequence/measurement dataset within mRNABench. The standard MRL-MPRA evaluation uses a naive random split. A separate compositional-generalization experiment holds out combinations of upstream AUG and Kozak features; neither should be described as the homology split used for other mRNABench tasks. Pearson correlation and the change between split conditions. Naive sequence-feature baseline, randomly initialized Naive Mamba, supervised CNN and multiple frozen foundation-model representations. The standard MRL-MPRA split is random. A separate compositional test holds out selected combinations of upstream AUG and Kozak features. Homology-based splits described for other benchmark tasks are not evidence of a homology-disjoint MRL-MPRA split.

Sources

Recorded evaluations

Each evaluation records what was tested and under which conditions.

Run instructions

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

A task describes a biological question. Choose a linked protocol to obtain concrete split and scoring instructions.

Strengths, limitations and unresolved questions

Strengths and limitations

Strengths supported by sources

No source-reviewed explanatory claims are recorded here yet.

Limitations and conditions

Compositional testing changes the feature combinations represented in training and testing.
Sources
mRNABench: A curated benchmark for mature mRNA property and function prediction · Benchmarking Tasks; compositional generalization analysis; cached text lines 24, 26–27, 190–193; default-split results table caption and compositional-split results; matching task comparison table/ablation captions

Profile review details

Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change.

Stable record: reported-task-57dc3dcdb67a81

Specifications

Inputs, training, access and other details

Explanatory profile: source reviewed · Automated source review, 2026-09-16. Review applies to the cited claims; unresolved fields are listed below. Numerical results retain their own review status.

Data, procedure and scoring
Property	Description and evidence
Datasets	MRL-MPRA sequence/measurement dataset within mRNABench. Sources mRNABench: A curated benchmark for mature mRNA property and function prediction · Benchmarking Tasks; compositional generalization analysis; cached text lines 24, 26–27, 190–193; default-split results table caption and compositional-split results; matching task comparison table/ablation captions
Splits	The standard MRL-MPRA evaluation uses a naive random split. A separate compositional-generalization experiment holds out combinations of upstream AUG and Kozak features; neither should be described as the homology split used for other mRNABench tasks. Sources mRNABench: A curated benchmark for mature mRNA property and function prediction · Methods: Data Splitting Strategies; Appendix: Compositional Generalization
Metrics	Pearson correlation and the change between split conditions. Sources mRNABench: A curated benchmark for mature mRNA property and function prediction · Benchmarking Tasks; compositional generalization analysis; cached text lines 24, 26–27, 190–193; default-split results table caption and compositional-split results; matching task comparison table/ablation captions
Baselines	Naive sequence-feature baseline, randomly initialized Naive Mamba, supervised CNN and multiple frozen foundation-model representations. Sources mRNABench: A curated benchmark for mature mRNA property and function prediction · Benchmarking Tasks; compositional generalization analysis; cached text lines 24, 26–27, 190–193; default-split results table caption and compositional-split results; matching task comparison table/ablation captions
Leakage controls	The standard MRL-MPRA split is random. A separate compositional test holds out selected combinations of upstream AUG and Kozak features. Homology-based splits described for other benchmark tasks are not evidence of a homology-disjoint MRL-MPRA split. Sources mRNABench: A curated benchmark for mature mRNA property and function prediction · Methods: Data Splitting Strategies; Appendix: Compositional Generalization
Uncertainty	The default split results are averaged over ten random splits with 95% confidence intervals; the compositional split is reported separately. Sources mRNABench: A curated benchmark for mature mRNA property and function prediction · Benchmarking Tasks; compositional generalization analysis; cached text lines 24, 26–27, 190–193; default-split results table caption and compositional-split results; matching task comparison table/ablation captions
Entity type	Paper-specific computational evaluation protocol. Sources mRNABench: A curated benchmark for mature mRNA property and function prediction · Benchmarking Tasks; compositional generalization analysis; cached text lines 24, 26–27, 190–193; default-split results table caption and compositional-split results; matching task comparison table/ablation captions
Organisms	The MRL-MPRA task uses synthetic or designed 5′ UTR reporter libraries assayed in human cells. The reporter’s experimental host is distinct from a natural source organism for each synthetic UTR. Sources mRNABench: A curated benchmark for mature mRNA property and function prediction · Benchmarking Tasks: Local Tasks, MRL-MPRA
Assays	Massively parallel reporter measurements of mean ribosome load. Sources mRNABench: A curated benchmark for mature mRNA property and function prediction · Benchmarking Tasks; compositional generalization analysis; cached text lines 24, 26–27, 190–193; default-split results table caption and compositional-split results; matching task comparison table/ablation captions
Allowed inputs	mRNA/UTR sequence representations. Sources mRNABench: A curated benchmark for mature mRNA property and function prediction · Benchmarking Tasks; compositional generalization analysis; cached text lines 24, 26–27, 190–193; default-split results table caption and compositional-split results; matching task comparison table/ablation captions
Adaptation	Embedding-based supervised prediction under default and compositional split conditions. Sources mRNABench: A curated benchmark for mature mRNA property and function prediction · Benchmarking Tasks; compositional generalization analysis; cached text lines 24, 26–27, 190–193; default-split results table caption and compositional-split results; matching task comparison table/ablation captions

Evidence

Source checking verifies the cited claim or transcription. It does not establish independent reproduction.

Papers and result coverage

Last literature check: 2026-09-17. Primary-paper discovery and source inspection. Source-checked results are not independently reproduced experiments.

Paper or primary resource	Version	Reference
mRNABench: A curated benchmark for mature mRNA property and function prediction	preprint archived 2025-07-08	Read source DOI: 10.1101/2025.07.05.662870

Historical gaps recorded on 2026-09-17

The catalogue now holds 2 result rows for this benchmark. A note below about pending extraction describes the state on 2026-09-17 and may since have been answered by a later batch. The result rows and their sources are the current record.

Table 5 labels localization columns Pearson R while Table 2 labels them AUPRC; quarantine those metric identities pending reconciliation.
Appendix C claims ten splits but enumerates nine seeds. Record ten as reported, with discrepancy, not an inferred tenth seed.
Tables 5–6 uncertainties are 95% confidence intervals, not standard deviations.
Task/subtask pooling and transformed aggregate rankings must not be conflated with printed raw metrics.

Search and extraction details

primary comparison table screened

Searches

mRNABench PMC12265608

Evidence locations

Tables 1–2, 5–6
Appendix B: Mean Ribosome Load – MPRA
Appendix C: Linear Probing Experimental Setup
Appendix D

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.

17 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-09-29-06401fd5b220
Property and statement	Original source and location	Review and provenance
Diagram caption Conceptual summary of the cited evaluation; exact task configuration and source version remain part of the protocol. Individual claims	mRNABench: A curated benchmark for mature mRNA property and function prediction Original source ↗ Benchmarking Tasks; compositional generalization analysis; cached text lines 24, 26–27, 190–193; default-split results table caption and compositional-split results; matching task comparison table/ablation captions; Methods: Data Splitting Strategies; Appendix: Compositional Generalization Version: preprint archived 2025-07-08 Retrieved: 2026-09-16T10:41:16.497221+00:00	source checked automated source review · 2026-09-16 Audit details Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: `attributes.profile.diagram.caption` Source artifact SHA-256: `79f6264ee883535203c63a313547e7c57baa85585f76b42f8d899eb17fb7e600` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Diagram steps Input: mRNA/UTR sequence representations. Evaluation: The standard MRL-MPRA evaluation uses a naive random split. A separate compositional-generalization experiment holds out combinations of upstream AUG and Kozak features; neither should be described as the homology split used for other mRNABench tasks. Readout: Pearson correlation and the change between split conditions. Individual claims	mRNABench: A curated benchmark for mature mRNA property and function prediction Original source ↗ Benchmarking Tasks; compositional generalization analysis; cached text lines 24, 26–27, 190–193; default-split results table caption and compositional-split results; matching task comparison table/ablation captions; Methods: Data Splitting Strategies; Appendix: Compositional Generalization Version: preprint archived 2025-07-08 Retrieved: 2026-09-16T10:41:16.497221+00:00	source checked automated source review · 2026-09-16 Audit details Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: `attributes.profile.diagram.steps` Source artifact SHA-256: `79f6264ee883535203c63a313547e7c57baa85585f76b42f8d899eb17fb7e600` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Diagram title Computational evaluation flow Individual claims	mRNABench: A curated benchmark for mature mRNA property and function prediction Original source ↗ Benchmarking Tasks; compositional generalization analysis; cached text lines 24, 26–27, 190–193; default-split results table caption and compositional-split results; matching task comparison table/ablation captions; Methods: Data Splitting Strategies; Appendix: Compositional Generalization Version: preprint archived 2025-07-08 Retrieved: 2026-09-16T10:41:16.497221+00:00	source checked automated source review · 2026-09-16 Audit details Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: `attributes.profile.diagram.title` Source artifact SHA-256: `79f6264ee883535203c63a313547e7c57baa85585f76b42f8d899eb17fb7e600` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Datasets MRL-MPRA sequence/measurement dataset within mRNABench. Individual claims	mRNABench: A curated benchmark for mature mRNA property and function prediction Original source ↗ Benchmarking Tasks; compositional generalization analysis; cached text lines 24, 26–27, 190–193; default-split results table caption and compositional-split results; matching task comparison table/ablation captions Version: preprint archived 2025-07-08 Retrieved: 2026-09-16T10:41:16.497221+00:00	source checked automated source review · 2026-09-16 Audit details Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: `attributes.profile.facts.0.value` Source artifact SHA-256: `79f6264ee883535203c63a313547e7c57baa85585f76b42f8d899eb17fb7e600` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Splits The standard MRL-MPRA evaluation uses a naive random split. A separate compositional-generalization experiment holds out combinations of upstream AUG and Kozak features; neither should be described as the homology split used for other mRNABench tasks. Individual claims	mRNABench: A curated benchmark for mature mRNA property and function prediction Original source ↗ Methods: Data Splitting Strategies; Appendix: Compositional Generalization Version: preprint archived 2025-07-08 Retrieved: 2026-09-16T10:41:16.497221+00:00	source checked automated source review · 2026-09-16 Audit details Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: `attributes.profile.facts.1.value` Source artifact SHA-256: `79f6264ee883535203c63a313547e7c57baa85585f76b42f8d899eb17fb7e600` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Adaptation Embedding-based supervised prediction under default and compositional split conditions. Individual claims	mRNABench: A curated benchmark for mature mRNA property and function prediction Original source ↗ Benchmarking Tasks; compositional generalization analysis; cached text lines 24, 26–27, 190–193; default-split results table caption and compositional-split results; matching task comparison table/ablation captions Version: preprint archived 2025-07-08 Retrieved: 2026-09-16T10:41:16.497221+00:00	source checked automated source review · 2026-09-16 Audit details Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: `attributes.profile.facts.10.value` Source artifact SHA-256: `79f6264ee883535203c63a313547e7c57baa85585f76b42f8d899eb17fb7e600` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Metrics Pearson correlation and the change between split conditions. Individual claims	mRNABench: A curated benchmark for mature mRNA property and function prediction Original source ↗ Benchmarking Tasks; compositional generalization analysis; cached text lines 24, 26–27, 190–193; default-split results table caption and compositional-split results; matching task comparison table/ablation captions Version: preprint archived 2025-07-08 Retrieved: 2026-09-16T10:41:16.497221+00:00	source checked automated source review · 2026-09-16 Audit details Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: `attributes.profile.facts.2.value` Source artifact SHA-256: `79f6264ee883535203c63a313547e7c57baa85585f76b42f8d899eb17fb7e600` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Baselines Naive sequence-feature baseline, randomly initialized Naive Mamba, supervised CNN and multiple frozen foundation-model representations. Individual claims	mRNABench: A curated benchmark for mature mRNA property and function prediction Original source ↗ Benchmarking Tasks; compositional generalization analysis; cached text lines 24, 26–27, 190–193; default-split results table caption and compositional-split results; matching task comparison table/ablation captions Version: preprint archived 2025-07-08 Retrieved: 2026-09-16T10:41:16.497221+00:00	source checked automated source review · 2026-09-16 Audit details Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: `attributes.profile.facts.3.value` Source artifact SHA-256: `79f6264ee883535203c63a313547e7c57baa85585f76b42f8d899eb17fb7e600` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Leakage controls The standard MRL-MPRA split is random. A separate compositional test holds out selected combinations of upstream AUG and Kozak features. Homology-based splits described for other benchmark tasks are not evidence of a homology-disjoint MRL-MPRA split. Individual claims	mRNABench: A curated benchmark for mature mRNA property and function prediction Original source ↗ Methods: Data Splitting Strategies; Appendix: Compositional Generalization Version: preprint archived 2025-07-08 Retrieved: 2026-09-16T10:41:16.497221+00:00	source checked automated source review · 2026-09-16 Audit details Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: `attributes.profile.facts.4.value` Source artifact SHA-256: `79f6264ee883535203c63a313547e7c57baa85585f76b42f8d899eb17fb7e600` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Uncertainty The default split results are averaged over ten random splits with 95% confidence intervals; the compositional split is reported separately. Individual claims	mRNABench: A curated benchmark for mature mRNA property and function prediction Original source ↗ Benchmarking Tasks; compositional generalization analysis; cached text lines 24, 26–27, 190–193; default-split results table caption and compositional-split results; matching task comparison table/ablation captions Version: preprint archived 2025-07-08 Retrieved: 2026-09-16T10:41:16.497221+00:00	source checked automated source review · 2026-09-16 Audit details Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: `attributes.profile.facts.5.value` Source artifact SHA-256: `79f6264ee883535203c63a313547e7c57baa85585f76b42f8d899eb17fb7e600` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact

All evidence (CSV)All evidence (JSONL)How to read the evidence

Sources and history

View linked audit checks and correction history

Release 2026-09-29-06401fd5b220 · Record review: needs review

2 source records and release history

mRNABench: A curated benchmark for mature mRNA property and function prediction · Original source · preprint archived 2025-07-08
mRNABench: A curated benchmark for mature mRNA property and function prediction · Original source · preprint archived 2025-07-08

Download this release

Technical metadata and extraction receipts

Stable ID: reported-task-57dc3dcdb67a81

areas: rna-transcriptomes
tasks: Mean ribosome load from MPRA
entity level: task
version: Not reported
task: Mean ribosome load from MPRA
scope note: Paper-specific evaluation task; protocol completeness requires further extraction.
benchmark research: review date: 2026-09-17; status: primary_comparison_table_screened; primary sources: expansion-p3-mrnabench-2025; inspected locators: Tables 1–2, 5–6; Appendix B: Mean Ribosome Load – MPRA; Appendix C: Linear Probing Experimental Setup; Appendix D; searched queries: mRNABench PMC12265608; gaps: Table 5 labels localization columns Pearson R while Table 2 labels them AUPRC; quarantine those metric identities pending reconciliation.; Appendix C claims ten splits but enumerates nine seeds. Record ten as reported, with discrepancy, not an inferred tenth seed.; Tables 5–6 uncertainties are 95% confidence intervals, not standard deviations.; Task/subtask pooling and transformed aggregate rankings must not be conflated with printed raw metrics.; claim scope: Primary-paper discovery and source inspection. Source-checked results are not independently reproduced experiments.
historical missing metadata: protocol version: not_reported_in_legacy_extract; split: not_reported_in_legacy_extract
metadata review scope: historical_missing_metadata preserves the original discovery state. Current descriptive evidence and missingness are recorded in profile.facts; numerical-result review is separate.
legacy kinds: benchmark
entity classification: review date: 2026-09-17; rationale: This source-scoped record identifies the biological prediction task and holds its paper context. Preserve the existing task identity; exact split, model adaptation and scoring remain in linked evaluations or separate protocol records.; source ids: mrnabench-2025; source locator: Benchmarking Tasks; compositional generalization analysis; cached text lines 24, 26–27, 190–193; default-split results table caption and compositional-split results; matching task comparison table/ablation captions; ambiguities: A paper- or suite-specific task may constrain some inputs or metrics; that alone does not make it interchangeable with a complete versioned protocol. No protocol equivalence is inferred.; Some legacy profile Entity type facts use the generic phrase computational evaluation protocol. That boilerplate is not sufficient to establish a single fixed protocol identity or to merge this task with another protocol record.

Related records

dataset: mRNABench MRL-MPRA
benchmark: RiNALMo: Mean ribosome load from MPRA
benchmark: RNA-FM: Mean ribosome load from MPRA

Suggest a correction