F1 of ADAR-GPT continual on liver editing sites
0.763 F1
Methods
- Tested configuration
- ADAR-GPT continual
- Task
- A-to-I RNA editing site prediction
- Dataset
- liver editing sites
- Procedure
- Curriculum plus 15% fine-tuning; 201-nt sequence windows; decision threshold 0.5
- Evaluation
- ADAR-GPT continual: A-to-I RNA editing site prediction
- Coverage
- Not reported scored / Not reported eligible
- Uncertainty
- Not yet extracted
- Evidence
- Author-reported evaluation · source checkedADAR-GPT: A continually fine-tuned language model for predicting A-to-I RNA editing sites · Table 2, Adar-GPT (continual) row, F1 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.
Reproduction
- Split
- 15% validation set
- Adaptation
- Not reported
- Scoring implementation
- Not reported
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.
1 evidence row matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Printed value 0.763 Individual claims | ADAR-GPT: A continually fine-tuned language model for predicting A-to-I RNA editing sites Table 2, Adar-GPT (continual) row, F1 column Version: version of record | source checked ["ai-assisted-source-review"] · 2026-09-16T10:41:06Z author reported Audit detailsAdar-GPT continual row; XML inline decimal reordered by parser, original text verified separately. Transcription verified; experimental claims not independently reproduced. Field: Claim: claim-lit-b4-005 Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record Extraction artifact SHA-256: |
Sources and history
Release 2026-11-21-c8bea25e5abb · Record review: source checked
1 source record and release history
- ADAR-GPT: A continually fine-tuned language model for predicting A-to-I RNA editing sites · Original source · version of record
Technical metadata and extraction receipts
Stable ID: lit-b4-005
- areas
- rna-transcriptomes
- tasks
- A-to-I RNA editing site prediction
- printed value
- 0.763
- numeric value
- 0.763
- metric
- f1-score
- metric direction
- unknown
- unit
- fraction
- source locator
- Table 2, Adar-GPT (continual) row, F1 column
- review
- method: ai-assisted-source-review; reviewer: codex; reviewed at: 2026-09-16T10:41:06Z; evidence: 0.763; artifact sha256: cc8c7eb928f246f1f347a8822f614cd3475381c35eef6d579032ce441580198e; retrieval url: https://www.ebi.ac.uk/europepmc/webservices/rest/PMC12798952/fullTextXML; method note: independent; table-level review; reviewer note: role: primary curator table review; note: Adar-GPT continual row; XML inline decimal reordered by parser, original text verified separately. Transcription verified; experimental claims not independently reproduced.
- legacy id
- lit-b4-005
- missing metadata
- dataset version: reason: unextracted; model version: reason: unextracted; uncertainty: reason: unextracted