nt-v2–100m-multi-species on mRNABench variant probes MRL-HL-Pair: Paired mean ribosome load and half life
mRNABench variant probes evaluation of nt-v2–100m-multi-species on Paired mean ribosome load and half life, scored with Pearson R.
Evaluation results
1 evaluation · 1 metric rows. Different protocols are not a single leaderboard.
Filter evaluations
Applied filters: All linked evaluations
| Tested configuration | Protocol and dataset | Finding | Evidence and details |
|---|---|---|---|
| Pipeline: nt-v2–100m-multi-species | Protocol: mRNABench variant probes MRL-HL-Pair: Paired mean ribosome load and half life Dataset subset: mRNABench MRL-HL-Pair (mRNABench split) | 0.516 ± 0.054 pearson_r correlation · higher Uncertainty: type: confidence_interval; confidence level: 0.95; reported half width: 0.054; aggregation: mean over ten random splits (table caption wording) Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · source checkedMethods, coverage and sourceFrozen transcript representations with task-specific linear probes, or named supervised/naive controls. Homology splits where possible; random splits for MRL-MPRA, MRL-HL-Pair and VEP. Reported mean over ten splits; Appendix C enumerates nine seeds. Table captions say ten random splits, while Methods specify homology splits where possible. This source ambiguity and the nine explicitly listed seeds are retained; exact split manifests remain unextracted. Appendix C uses micro-averaged multilabel metrics. Aggregation: Not reported mRNABench: A curated benchmark for mature mRNA property and function prediction · Table 6 (XML T3), data row 29, XML tr 31, column 3 (MRL-HL-Pair | Pearson R), model nt-v2–100m-multi-species |
Source checking is not independent reproduction. Release 2026-09-23-2b89723c6dd9.
Evaluation procedure
Frozen transcript representations with task-specific linear probes, or named supervised/naive controls. Homology splits where possible; random splits for MRL-MPRA, MRL-HL-Pair and VEP. Reported mean over ten splits; Appendix C enumerates nine seeds. Table captions say ten random splits, while Methods specify homology splits where possible. This source ambiguity and the nine explicitly listed seeds are retained; exact split manifests remain unextracted. Appendix C uses micro-averaged multilabel metrics.
- Pipeline
- nt-v2–100m-multi-species
- Protocol
- mRNABench variant probes MRL-HL-Pair: Paired mean ribosome load and half life
- Dataset subset
- mRNABench MRL-HL-Pair (mRNABench split)
- origin
- Author-reported evaluation
- configuration
- Not reported
- protocol id
- mrnabench-variants-2025-task-mrl-hl-pair
- metric implementation
- Pearson R
Metadata review: source checked. Unreported conditions prevent automatic comparisons.
Reproduction
- Split
- Not reported
- Adaptation
- Not reported
- Scoring implementation
- Pearson R
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.
15 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| attributes.adaptation Frozen representations averaged over tokens after chunking, followed by task-specific linear probes; RidgeCV for regression, logistic regression for classification. Appendix C. Context-only references | mRNABench: A curated benchmark for mature mRNA property and function prediction Table 6 (XML T3), data row 29, XML tr 31, column 3 (MRL-HL-Pair | Pearson R), model nt-v2–100m-multi-species Version: preprint archived 2025-07-08 | not individually reviewed No individual claim review recorded author reported Audit detailsField: Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
| attributes.comparison.metric_implementation Pearson R Context-only references | mRNABench: A curated benchmark for mature mRNA property and function prediction Table 6 (XML T3), data row 29, XML tr 31, column 3 (MRL-HL-Pair | Pearson R), model nt-v2–100m-multi-species Version: preprint archived 2025-07-08 | not individually reviewed No individual claim review recorded author reported Audit detailsField: Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
| attributes.comparison.protocol_id mrnabench-variants-2025-task-mrl-hl-pair Context-only references | mRNABench: A curated benchmark for mature mRNA property and function prediction Table 6 (XML T3), data row 29, XML tr 31, column 3 (MRL-HL-Pair | Pearson R), model nt-v2–100m-multi-species Version: preprint archived 2025-07-08 | not individually reviewed No individual claim review recorded author reported Audit detailsField: Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
| attributes.evidence_experiment_set_id mrnabench-2025-linear-probing-default-splits Context-only references | mRNABench: A curated benchmark for mature mRNA property and function prediction Table 6 (XML T3), data row 29, XML tr 31, column 3 (MRL-HL-Pair | Pearson R), model nt-v2–100m-multi-species Version: preprint archived 2025-07-08 | not individually reviewed No individual claim review recorded author reported Audit detailsField: Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
| attributes.evidence_overlap Same paper experiment set: mrnabench-2025-linear-probing-default-splits. Table 2 selects a best-overall variant per family from these measurements. Do not count the summary and per-variant tables as independent evidence. Context-only references | mRNABench: A curated benchmark for mature mRNA property and function prediction Table 6 (XML T3), data row 29, XML tr 31, column 3 (MRL-HL-Pair | Pearson R), model nt-v2–100m-multi-species Version: preprint archived 2025-07-08 | not individually reviewed No individual claim review recorded author reported Audit detailsField: Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
| attributes.origin author_reported Context-only references | mRNABench: A curated benchmark for mature mRNA property and function prediction Table 6 (XML T3), data row 29, XML tr 31, column 3 (MRL-HL-Pair | Pearson R), model nt-v2–100m-multi-species Version: preprint archived 2025-07-08 | not individually reviewed No individual claim review recorded author reported Audit detailsField: Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
| attributes.protocol Frozen transcript representations with task-specific linear probes, or named supervised/naive controls. Homology splits where possible; random splits for MRL-MPRA, MRL-HL-Pair and VEP. Reported mean over ten splits; Appendix C enumerates nine seeds. Table captions say ten random splits, while Methods specify homology splits where possible. This source ambiguity and the nine explicitly listed seeds are retained; exact split manifests remain unextracted. Appendix C uses micro-averaged multilabel metrics. Context-only references | mRNABench: A curated benchmark for mature mRNA property and function prediction Table 6 (XML T3), data row 29, XML tr 31, column 3 (MRL-HL-Pair | Pearson R), model nt-v2–100m-multi-species Version: preprint archived 2025-07-08 | not individually reviewed No individual claim review recorded author reported Audit detailsField: Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
| attributes.published_score_reproduction false Context-only references | mRNABench: A curated benchmark for mature mRNA property and function prediction Table 6 (XML T3), data row 29, XML tr 31, column 3 (MRL-HL-Pair | Pearson R), model nt-v2–100m-multi-species Version: preprint archived 2025-07-08 | not individually reviewed No individual claim review recorded author reported Audit detailsField: Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
| attributes.source_locator Table 6 (XML T3), data row 29, XML tr 31, column 3 (MRL-HL-Pair | Pearson R), model nt-v2–100m-multi-species Context-only references | mRNABench: A curated benchmark for mature mRNA property and function prediction Table 6 (XML T3), data row 29, XML tr 31, column 3 (MRL-HL-Pair | Pearson R), model nt-v2–100m-multi-species Version: preprint archived 2025-07-08 | not individually reviewed No individual claim review recorded author reported Audit detailsField: Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
| attributes.suite_complete false Context-only references | mRNABench: A curated benchmark for mature mRNA property and function prediction Table 6 (XML T3), data row 29, XML tr 31, column 3 (MRL-HL-Pair | Pearson R), model nt-v2–100m-multi-species Version: preprint archived 2025-07-08 | not individually reviewed No individual claim review recorded author reported Audit detailsField: Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
Sources and history
View linked audit checks and correction history
Release 2026-09-23-2b89723c6dd9 · Record review: source checked
1 source records and release history
- mRNABench: A curated benchmark for mature mRNA property and function prediction · Original source · preprint archived 2025-07-08
Technical metadata and extraction receipts
Stable ID: mrnabench-variants-2025-evaluation-nt-v2-100m-multi-species-mrl-hl-pair
- areas
- rna-transcriptomics
- tasks
- Paired mean ribosome load and half life
- origin
- author_reported
- protocol
- Frozen transcript representations with task-specific linear probes, or named supervised/naive controls. Homology splits where possible; random splits for MRL-MPRA, MRL-HL-Pair and VEP. Reported mean over ten splits; Appendix C enumerates nine seeds. Table captions say ten random splits, while Methods specify homology splits where possible. This source ambiguity and the nine explicitly listed seeds are retained; exact split manifests remain unextracted. Appendix C uses micro-averaged multilabel metrics.
- comparison
- protocol id: mrnabench-variants-2025-task-mrl-hl-pair; metric implementation: Pearson R
- missing metadata
- checkpoint revision: unreported; seeds: unreported; budget: unreported; split manifest: unextracted
- source locator
- Table 6 (XML T3), data row 29, XML tr 31, column 3 (MRL-HL-Pair | Pearson R), model nt-v2–100m-multi-species
- evidence experiment set id
- mrnabench-2025-linear-probing-default-splits
- adaptation
- Frozen representations averaged over tokens after chunking, followed by task-specific linear probes; RidgeCV for regression, logistic regression for classification. Appendix C.
- evidence overlap
- Same paper experiment set: mrnabench-2025-linear-probing-default-splits. Table 2 selects a best-overall variant per family from these measurements. Do not count the summary and per-variant tables as independent evidence.
- published score reproduction
- false
- suite complete
- false