Datasets
bpRNA-1m similarity-filtered variants; the main task uses the standard TR0/VL0/TS0 benchmark.
Task
RNA secondary-structure prediction
RNA secondary-structure prediction uses a specified bpRNA benchmark version while distinguishing pretraining from supervised task data.
Sources
ERNIE-RNA: an RNA language model with structure-enhanced representations · Methods: Training dataset; RNA secondary structure dataset; cached text lines 71–72, 84–87; task metric definitions and corresponding results tableOverview
Metrics
Base-pairing F1 is used for secondary-structure model selection and evaluation; contact-map post-processing is shared across methods.
Allowed inputs
RNA sequence.
Sources
ERNIE-RNA: an RNA language model with structure-enhanced representations · Methods: Training dataset; RNA secondary structure dataset; cached text lines 71–72, 84–87; task metric definitions and corresponding results tableEvaluation 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
ERNIE-RNA: an RNA language model with structure-enhanced representations · Methods: Training dataset; RNA secondary structure dataset; cached text lines 71–72, 84–87; task metric definitions and corresponding results tablelimited 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: ERNIE-RNA | Task: RNA secondary-structure prediction Dataset: bpRNA-new | 0.575 binary F1 fraction · unknown Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceERNIE-RNA: RNA secondary-structure prediction zero-shot attention-derived base-pair prediction Aggregation: Not reported ERNIE-RNA: an RNA language model with structure-enhanced representations · Table 2, ERNIE-RNA zero-shot row, bpRNA-new F1-Score (binary) 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
bpRNA-1m similarity-filtered variants; the main task uses the standard TR0/VL0/TS0 benchmark. Base-pairing F1 is used for secondary-structure model selection and evaluation; contact-map post-processing is shared across methods. The partition is aligned with UFold and RNA-FM comparisons; UNI-RNA uses additional task-training data.
Sources
ERNIE-RNA: an RNA language model with structure-enhanced representations · Methods: Training dataset; RNA secondary structure dataset; cached text lines 71–72, 84–87; task metric definitions and corresponding results table; Methods: Training dataset; RNA secondary structure dataset; cached text lines 71–72, 84–87; task metric definitions and corresponding results table; Methods: Training dataset; RNA secondary structure dataset; cached text lines 71–72, 84–87; task metric definitions and corresponding results tableRecorded 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
- The different bpRNA similarity-filtered variants have different sequence memberships. Reporting a dataset family name alone is insufficient to identify the evaluated split.
Sources
ERNIE-RNA: an RNA language model with structure-enhanced representations · Methods: Training dataset; RNA secondary structure dataset; cached text lines 71–72, 84–87; task metric definitions and corresponding results table
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-a2bf7ddbc71d23Specifications
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 | bpRNA-1m similarity-filtered variants; the main task uses the standard TR0/VL0/TS0 benchmark.SourcesERNIE-RNA: an RNA language model with structure-enhanced representations · Methods: Training dataset; RNA secondary structure dataset; cached text lines 71–72, 84–87; task metric definitions and corresponding results table |
| Splits | TR0 is used for task training, VL0 for validation and TS0 for testing.SourcesERNIE-RNA: an RNA language model with structure-enhanced representations · Methods: Training dataset; RNA secondary structure dataset; cached text lines 71–72, 84–87; task metric definitions and corresponding results table |
| Metrics | Base-pairing F1 is used for secondary-structure model selection and evaluation; contact-map post-processing is shared across methods.SourcesERNIE-RNA: an RNA language model with structure-enhanced representations · Methods: Training dataset; RNA secondary structure dataset; cached text lines 71–72, 84–87; task metric definitions and corresponding results table |
| Baselines | The partition is aligned with UFold and RNA-FM comparisons; UNI-RNA uses additional task-training data.SourcesERNIE-RNA: an RNA language model with structure-enhanced representations · Methods: Training dataset; RNA secondary structure dataset; cached text lines 71–72, 84–87; task metric definitions and corresponding results table |
| Leakage controls | The bpRNA benchmark variants apply explicit sequence-similarity filtering, including the 80% variant used for TR0/VL0/TS0. The cited dataset Methods do not give a cross-corpus exclusion audit against RNAcentral pretraining.SourcesERNIE-RNA: an RNA language model with structure-enhanced representations · Methods: Training dataset and RNA secondary structure dataset; cached paragraphs 71–72,84–87 |
| Uncertainty | The cited text-accessible evaluation sections give no confidence-interval, resampling or repeat-run error-bar specification. Image-only tables and uninspected supplements are outside this absence claim. · Not reported in inspected sourcesSourcesERNIE-RNA: an RNA language model with structure-enhanced representations · Methods: Training dataset; RNA secondary structure dataset; cached text lines 71–72, 84–87; task metric definitions and corresponding results table |
| Entity type | Paper-specific computational evaluation protocol.SourcesERNIE-RNA: an RNA language model with structure-enhanced representations · Methods: Training dataset; RNA secondary structure dataset; cached text lines 71–72, 84–87; task metric definitions and corresponding results table |
| Organisms | The secondary-structure task is defined by bpRNA sequences and RNA-family collections. Its downstream-dataset Methods describe similarity filtering and partition membership, but do not tabulate the evaluated sequences by organism. · Not reported in inspected sourcesSourcesERNIE-RNA: an RNA language model with structure-enhanced representations · Methods: RNA secondary structure datasets; bpRNA-1m and ArchiveII |
| Assays | Reference RNA secondary structures.SourcesERNIE-RNA: an RNA language model with structure-enhanced representations · Methods: Training dataset; RNA secondary structure dataset; cached text lines 71–72, 84–87; task metric definitions and corresponding results table |
| Allowed inputs | RNA sequence.SourcesERNIE-RNA: an RNA language model with structure-enhanced representations · Methods: Training dataset; RNA secondary structure dataset; cached text lines 71–72, 84–87; task metric definitions and corresponding results table |
| Adaptation | Supervised structure-task training on TR0, validation on VL0 and testing on TS0.SourcesERNIE-RNA: an RNA language model with structure-enhanced representations · Methods: Training dataset; RNA secondary structure dataset; cached text lines 71–72, 84–87; task metric definitions and corresponding results table |
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. Dated primary-source discovery and protocol/table screening. Source checking does not mean experimental reproduction. Only separately extracted and independently reviewed numeric batches are publishable.
| Paper or primary resource | Version | Reference |
|---|---|---|
| ERNIE-RNA: an RNA language model with structure-enhanced representations | journal full text in PMC | Read source |
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.
- complete numerical transcription and independent cell review: Full primary artifact and table inventory preserved; no new numeric row is published from this audit alone.
- exact checkpoint hashes and per-method scored denominators: Table labels alone do not establish these fields; do not infer checkpoint or scored count from model name or dataset size.
Search and extraction details
primary comparison tables located
Searches
- ERNIE-RNA: an RNA language model with structure-enhanced representations 10.1038/s41467-025-64972-0
Evidence locations
- Table 1; XML table Tab1
- Table 2; XML table Tab2
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
| 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 | ERNIE-RNA: an RNA language model with structure-enhanced representations Methods: Training dataset; RNA secondary structure dataset; cached text lines 71–72, 84–87; task metric definitions and corresponding results table 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
| ERNIE-RNA: an RNA language model with structure-enhanced representations Methods: Training dataset; RNA secondary structure dataset; cached text lines 71–72, 84–87; task metric definitions and corresponding results table 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 | ERNIE-RNA: an RNA language model with structure-enhanced representations Methods: Training dataset; RNA secondary structure dataset; cached text lines 71–72, 84–87; task metric definitions and corresponding results table 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 bpRNA-1m similarity-filtered variants; the main task uses the standard TR0/VL0/TS0 benchmark. Individual claims | ERNIE-RNA: an RNA language model with structure-enhanced representations Methods: Training dataset; RNA secondary structure dataset; cached text lines 71–72, 84–87; task metric definitions and corresponding results table 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 TR0 is used for task training, VL0 for validation and TS0 for testing. Individual claims | ERNIE-RNA: an RNA language model with structure-enhanced representations Methods: Training dataset; RNA secondary structure dataset; cached text lines 71–72, 84–87; task metric definitions and corresponding results table 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 |
| Adaptation Supervised structure-task training on TR0, validation on VL0 and testing on TS0. Individual claims | ERNIE-RNA: an RNA language model with structure-enhanced representations Methods: Training dataset; RNA secondary structure dataset; cached text lines 71–72, 84–87; task metric definitions and corresponding results table 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 |
| Metrics Base-pairing F1 is used for secondary-structure model selection and evaluation; contact-map post-processing is shared across methods. Individual claims | ERNIE-RNA: an RNA language model with structure-enhanced representations Methods: Training dataset; RNA secondary structure dataset; cached text lines 71–72, 84–87; task metric definitions and corresponding results table 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 The partition is aligned with UFold and RNA-FM comparisons; UNI-RNA uses additional task-training data. Individual claims | ERNIE-RNA: an RNA language model with structure-enhanced representations Methods: Training dataset; RNA secondary structure dataset; cached text lines 71–72, 84–87; task metric definitions and corresponding results table 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 bpRNA benchmark variants apply explicit sequence-similarity filtering, including the 80% variant used for TR0/VL0/TS0. The cited dataset Methods do not give a cross-corpus exclusion audit against RNAcentral pretraining. Individual claims | ERNIE-RNA: an RNA language model with structure-enhanced representations Methods: Training dataset and RNA secondary structure dataset; cached paragraphs 71–72,84–87 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 |
| Uncertainty The cited text-accessible evaluation sections give no confidence-interval, resampling or repeat-run error-bar specification. Image-only tables and uninspected supplements are outside this absence claim. Individual claims | ERNIE-RNA: an RNA language model with structure-enhanced representations Methods: Training dataset; RNA secondary structure dataset; cached text lines 71–72, 84–87; task metric definitions and corresponding results table 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
2 source records and release history
- ERNIE-RNA: an RNA language model with structure-enhanced representations · Original source · journal full text in PMC
- ERNIE-RNA: an RNA language model with structure-enhanced representations · Original source · journal full text in PMC
Technical metadata and extraction receipts
Stable ID: reported-task-a2bf7ddbc71d23
- areas
- rna-transcriptomes
- tasks
- RNA secondary-structure prediction
- entity level
- task
- version
- Not reported
- task
- RNA secondary-structure prediction
- scope note
- Paper-specific evaluation task; protocol completeness requires further extraction.
- benchmark research
- review date: 2026-09-17; status: primary_comparison_tables_located; primary sources: evidence-expansion-ernie-rna-2025-0bd1d4b3; inspected locators: Table 1; XML table Tab1; Table 2; XML table Tab2; searched queries: ERNIE-RNA: an RNA language model with structure-enhanced representations 10.1038/s41467-025-64972-0; gaps: complete numerical transcription and independent cell review: Full primary artifact and table inventory preserved; no new numeric row is published from this audit alone.; exact checkpoint hashes and per-method scored denominators: Table labels alone do not establish these fields; do not infer checkpoint or scored count from model name or dataset size.; claim scope: Dated primary-source discovery and protocol/table screening. Source checking does not mean experimental reproduction. Only separately extracted and independently reviewed numeric batches are publishable.
- 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: ernie-rna-2025; source locator: Methods: Training dataset; RNA secondary structure dataset; cached text lines 71–72, 84–87; task metric definitions and corresponding results table; 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: bpRNA-new
- benchmark: ERNIE-RNA: RNA secondary-structure prediction