Datasets
Long noncoding RNA sequences from RNAcentral with species labels.
Task
extremely long RNA species classification
Long-RNA species classification evaluates representation quality on an RNAcentral-derived seven-species dataset.
Sources
BiRNA-BERT allows efficient RNA language modeling with adaptive tokenization · Results: BiRNA-BERT significantly outperforms in extremely long sequence task; Table 2; cached text lines 37–40Overview
Metrics
F1 score; the reviewed task description does not establish the averaging convention.
Allowed inputs
Long RNA sequences.
Sources
BiRNA-BERT allows efficient RNA language modeling with adaptive tokenization · Results: BiRNA-BERT significantly outperforms in extremely long sequence task; Table 2; cached text lines 37–40Evaluation 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
BiRNA-BERT allows efficient RNA language modeling with adaptive tokenization · Results: BiRNA-BERT significantly outperforms in extremely long sequence task; Table 2; cached text lines 37–40limited source coverage · 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
1 evaluation · 1 result. Different protocols are not a single leaderboard.
Filter evaluations
Applied filters: All linked evaluations
| Tested configuration | Protocol and dataset | Finding | Evidence and details |
|---|---|---|---|
| Configuration: BiRNA-BERT | Task: extremely long RNA species classification Dataset: extremely long-sequence species classification | 0.804 F1 fraction · unknown Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceBiRNA-BERT: extremely long RNA species classification adaptive tokenization on full-length long RNA sequences Aggregation: Not reported BiRNA-BERT allows efficient RNA language modeling with adaptive tokenization · Table 2, BiRNA-BERT row, F1 Score 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
Long noncoding RNA sequences from RNAcentral with species labels. The long-sequence species-classification Results paragraph specifies the dataset and F1 comparisons but does not give a train/validation/test assignment rule. F1 score; the reviewed task description does not establish the averaging convention. RNA-FM and RiNALMo are compared under their sequence-length constraints. The species-classification paragraph does not specify RNAcentral overlap exclusion between its benchmark sequences and model pretraining. Structure-task deduplication elsewhere is not this task.
Sources
BiRNA-BERT allows efficient RNA language modeling with adaptive tokenization · Results: BiRNA-BERT significantly outperforms in extremely long sequence task; Table 2; cached text lines 37–40Recorded 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 and considerations
No source-reviewed explanatory claims are recorded here yet.
Limitations and conditions
- Comparator truncation is part of the published species-classification setting. Its task section and supplement do not establish split membership, related-sequence exclusion or task-specific fitting details.
Sources (2)
BiRNA-BERT allows efficient RNA language modeling with adaptive tokenization; birna journal Supplementary Information — pinned PDF · Results: BiRNA-BERT significantly outperforms in extremely long sequence task; Table 2; cached text lines 37–40 ; Supplementary Information task sections
Profile review details
Relevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged.
Stable record: reported-task-c40dac20d9af66Specifications
Inputs, training, access and other details
Explanatory profile: limited source coverage · Automated source review, 2026-09-16. Review applies to the cited claims; unresolved fields are listed below. Numerical results retain their own review status.
| Property | Description and evidence |
|---|---|
| Datasets | Long noncoding RNA sequences from RNAcentral with species labels.SourcesBiRNA-BERT allows efficient RNA language modeling with adaptive tokenization · Results: BiRNA-BERT significantly outperforms in extremely long sequence task; Table 2; cached text lines 37–40 |
| Splits | The long-sequence species-classification Results paragraph specifies the dataset and F1 comparisons but does not give a train/validation/test assignment rule. · Not reported in inspected sourcesSourcesBiRNA-BERT allows efficient RNA language modeling with adaptive tokenization · Results: BiRNA-BERT significantly outperforms in extremely long sequence task; Table 2; cached text lines 37–40 |
| Metrics | F1 score; the reviewed task description does not establish the averaging convention.SourcesBiRNA-BERT allows efficient RNA language modeling with adaptive tokenization · Results: BiRNA-BERT significantly outperforms in extremely long sequence task; Table 2; cached text lines 37–40 |
| Baselines | RNA-FM and RiNALMo are compared under their sequence-length constraints.SourcesBiRNA-BERT allows efficient RNA language modeling with adaptive tokenization · Results: BiRNA-BERT significantly outperforms in extremely long sequence task; Table 2; cached text lines 37–40 |
| Leakage controls | The species-classification paragraph does not specify RNAcentral overlap exclusion between its benchmark sequences and model pretraining. Structure-task deduplication elsewhere is not this task. · Not reported in inspected sourcesSourcesBiRNA-BERT allows efficient RNA language modeling with adaptive tokenization · Results: BiRNA-BERT significantly outperforms in extremely long sequence task; Table 2; cached text lines 37–40 |
| Uncertainty | Table 2 reports one F1 score per model for long-sequence species classification. The corresponding main-text section and Supplementary Information do not define repeated runs, confidence intervals or a statistical comparison for this particular task. · Not reported in inspected sourcesSources (2)BiRNA-BERT allows efficient RNA language modeling with adaptive tokenization; birna journal Supplementary Information — pinned PDF · Results: extremely long sequence task and Table 2; Supplementary Information §§1–3 |
| Entity type | Paper-specific computational evaluation protocol.SourcesBiRNA-BERT allows efficient RNA language modeling with adaptive tokenization · Results: BiRNA-BERT significantly outperforms in extremely long sequence task; Table 2; cached text lines 37–40 |
| Organisms | Bos taurus, Gallus gallus, Gorilla gorilla, Homo sapiens, Mus musculus, Pan troglodytes and Rattus norvegicus.SourcesBiRNA-BERT allows efficient RNA language modeling with adaptive tokenization · Results: BiRNA-BERT significantly outperforms in extremely long sequence task; Table 2; cached text lines 37–40 |
| Assays | RNAcentral sequence/species annotations.SourcesBiRNA-BERT allows efficient RNA language modeling with adaptive tokenization · Results: BiRNA-BERT significantly outperforms in extremely long sequence task; Table 2; cached text lines 37–40 |
| Allowed inputs | Long RNA sequences.SourcesBiRNA-BERT allows efficient RNA language modeling with adaptive tokenization · Results: BiRNA-BERT significantly outperforms in extremely long sequence task; Table 2; cached text lines 37–40 |
| Adaptation | The long-sequence benchmark compares BiRNA-BERT, RiNALMo and RNA-FM, with comparator truncation stated. Its main-text description and Supplementary Information do not specify the classification head or whether each encoder is frozen or fine-tuned for this species task. · Not reported in inspected sourcesSources (2)BiRNA-BERT allows efficient RNA language modeling with adaptive tokenization; birna journal Supplementary Information — pinned PDF · Results: extremely long sequence task, Table 2; Supplementary Information §§1–3 |
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 |
|---|---|---|
| BiRNA-BERT allows efficient RNA language modeling with adaptive tokenization | journal full text in PMC | Read source DOI: 10.1038/s42003-025-08982-0 |
Historical gaps recorded on 2026-09-17
The catalogue now holds 1 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.
- No uncertainty in Table 2; exact long-sequence window/aggregation details remain tied to this paper's downstream classifiers.
- Species classification scores do not measure RNA-structure accuracy.
Search and extraction details
primary comparison table screened
Searches
- "PMC12635123"
Evidence locations
- Table 2
- Long sequence classification task
- Supplement task description
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.
20 evidence rows matching the loaded filters
| 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 | BiRNA-BERT allows efficient RNA language modeling with adaptive tokenization Results: BiRNA-BERT significantly outperforms in extremely long sequence task; Table 2; cached text lines 37–40 Version: journal full text in PMC | source checked automated source review · 2026-09-16 Audit detailsRelevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
Diagram steps
| BiRNA-BERT allows efficient RNA language modeling with adaptive tokenization Results: BiRNA-BERT significantly outperforms in extremely long sequence task; Table 2; cached text lines 37–40 Version: journal full text in PMC | source checked automated source review · 2026-09-16 Audit detailsRelevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Diagram title Computational evaluation flow Individual claims | BiRNA-BERT allows efficient RNA language modeling with adaptive tokenization Results: BiRNA-BERT significantly outperforms in extremely long sequence task; Table 2; cached text lines 37–40 Version: journal full text in PMC | source checked automated source review · 2026-09-16 Audit detailsRelevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Datasets Long noncoding RNA sequences from RNAcentral with species labels. Individual claims | BiRNA-BERT allows efficient RNA language modeling with adaptive tokenization Results: BiRNA-BERT significantly outperforms in extremely long sequence task; Table 2; cached text lines 37–40 Version: journal full text in PMC | source checked automated source review · 2026-09-16 Audit detailsRelevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Splits The long-sequence species-classification Results paragraph specifies the dataset and F1 comparisons but does not give a train/validation/test assignment rule. Individual claims | BiRNA-BERT allows efficient RNA language modeling with adaptive tokenization Results: BiRNA-BERT significantly outperforms in extremely long sequence task; Table 2; cached text lines 37–40 Version: journal full text in PMC | unreported automated source review · 2026-09-16 Audit detailsRelevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Adaptation The long-sequence benchmark compares BiRNA-BERT, RiNALMo and RNA-FM, with comparator truncation stated. Its main-text description and Supplementary Information do not specify the classification head or whether each encoder is frozen or fine-tuned for this species task. Individual claims | BiRNA-BERT allows efficient RNA language modeling with adaptive tokenization Results: extremely long sequence task, Table 2; Supplementary Information §§1–3 Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: journal full text in PMC | unreported automated source review · 2026-09-16 Audit detailsRelevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Adaptation The long-sequence benchmark compares BiRNA-BERT, RiNALMo and RNA-FM, with comparator truncation stated. Its main-text description and Supplementary Information do not specify the classification head or whether each encoder is frozen or fine-tuned for this species task. Individual claims | birna journal Supplementary Information — pinned PDF Results: extremely long sequence task, Table 2; Supplementary Information §§1–3 Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Published supplementary PDF 42003_2025_8982_MOESM2_ESM.pdf; sha256:7897d4dcf456d1f22b0631beabf7c5fd8678d0b8765cd40325195eb5addf4493 | unreported automated source review · 2026-09-16 Audit detailsRelevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record Archive member: 42003_2025_8982_MOESM2_ESM.pdf |
| Metrics F1 score; the reviewed task description does not establish the averaging convention. Individual claims | BiRNA-BERT allows efficient RNA language modeling with adaptive tokenization Results: BiRNA-BERT significantly outperforms in extremely long sequence task; Table 2; cached text lines 37–40 Version: journal full text in PMC | source checked automated source review · 2026-09-16 Audit detailsRelevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Baselines RNA-FM and RiNALMo are compared under their sequence-length constraints. Individual claims | BiRNA-BERT allows efficient RNA language modeling with adaptive tokenization Results: BiRNA-BERT significantly outperforms in extremely long sequence task; Table 2; cached text lines 37–40 Version: journal full text in PMC | source checked automated source review · 2026-09-16 Audit detailsRelevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Leakage controls The species-classification paragraph does not specify RNAcentral overlap exclusion between its benchmark sequences and model pretraining. Structure-task deduplication elsewhere is not this task. Individual claims | BiRNA-BERT allows efficient RNA language modeling with adaptive tokenization Results: BiRNA-BERT significantly outperforms in extremely long sequence task; Table 2; cached text lines 37–40 Version: journal full text in PMC | unreported automated source review · 2026-09-16 Audit detailsRelevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
Sources and history
View linked audit checks and correction history
Release 2026-09-29-06401fd5b220 · Record review: needs review
3 source records and release history
- BiRNA-BERT allows efficient RNA language modeling with adaptive tokenization · Original source · journal full text in PMC
- BiRNA-BERT allows efficient RNA language modeling with adaptive tokenization · Original source · journal full text in PMC
- birna journal Supplementary Information — pinned PDF · Original source · Published supplementary PDF 42003_2025_8982_MOESM2_ESM.pdf; sha256:7897d4dcf456d1f22b0631beabf7c5fd8678d0b8765cd40325195eb5addf4493
Technical metadata and extraction receipts
Stable ID: reported-task-c40dac20d9af66
- areas
- rna-transcriptomes
- tasks
- extremely long RNA species classification
- entity level
- task
- version
- Not reported
- task
- extremely long RNA species classification
- 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-birna-bert-2025; inspected locators: Table 2; Long sequence classification task; Supplement task description; searched queries: "PMC12635123"; gaps: No uncertainty in Table 2; exact long-sequence window/aggregation details remain tied to this paper's downstream classifiers.; Species classification scores do not measure RNA-structure accuracy.; 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
- 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: birna-bert-2025; source locator: Results: BiRNA-BERT significantly outperforms in extremely long sequence task; Table 2; cached text lines 37–40; 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.