SpliceAI (BEACON split)
The split of SpliceAI that the BEACON authors evaluated on, named in their Table 1. The upstream dataset release is not catalogued here, so no claim is made that this matches the original splits.
Subset and evaluation context
This record describes a particular subset or cohort used in an evaluation. Its results do not describe the full dataset.
Evaluation results
Release 2026-09-17-1a18ca2c038a · 17 evaluations · 17 metric rows. Different protocols are not a single leaderboard. Where several source tables report the same metric, the published comparisons above offer a pooled view that names what it does not hold constant.
| Metric and finding | Coverage and uncertainty | Evidence |
|---|---|---|
| BEACON-B on BEACON SPL: Splice site prediction Configuration: BEACON-BTask: BEACON SPL: Splice site predictionDataset subset: SpliceAI (BEACON split) BEACON harness, fixed downstream head per task. Train/validation/test 144,628/18,078/16,505; dataset SpliceAI. Author-reported evaluation · Evaluation metadata: source checked | ||
| 37.43(1.43)% top_k_accuracy Unit: percent · Direction: higher | Uncertainty: type: standard deviation; value: 1.43 Scored: Not reported · Eligible: Not reported | source checkedBEACON: Benchmark for Comprehensive RNA Tasks and Language Models (arXiv:2406.10391v2) · Table3,p.8,row(BEACON-B),column(SPL) Source checking is not independent reproduction. |
| BEACON-B512 on BEACON SPL: Splice site prediction Configuration: BEACON-B512Task: BEACON SPL: Splice site predictionDataset subset: SpliceAI (BEACON split) BEACON harness, fixed downstream head per task. Train/validation/test 144,628/18,078/16,505; dataset SpliceAI. Author-reported evaluation · Evaluation metadata: source checked | ||
| 37.24(1.09)% top_k_accuracy Unit: percent · Direction: higher | Uncertainty: type: standard deviation; value: 1.09 Scored: Not reported · Eligible: Not reported | source checkedBEACON: Benchmark for Comprehensive RNA Tasks and Language Models (arXiv:2406.10391v2) · Table3,p.8,row(BEACON-B512),column(SPL) Source checking is not independent reproduction. |
| CNN on BEACON SPL: Splice site prediction BEACON harness, fixed downstream head per task. Train/validation/test 144,628/18,078/16,505; dataset SpliceAI. Author-reported evaluation · Evaluation metadata: source checked | ||
| 8.43(0.38)% top_k_accuracy Unit: percent · Direction: higher | Uncertainty: type: standard deviation; value: 0.38 Scored: Not reported · Eligible: Not reported | source checkedBEACON: Benchmark for Comprehensive RNA Tasks and Language Models (arXiv:2406.10391v2) · Table3,p.8,row(CNN),column(SPL) Source checking is not independent reproduction. |
| LSTM on BEACON SPL: Splice site prediction BEACON harness, fixed downstream head per task. Train/validation/test 144,628/18,078/16,505; dataset SpliceAI. Author-reported evaluation · Evaluation metadata: source checked | ||
| 36.66(1.83)% top_k_accuracy Unit: percent · Direction: higher | Uncertainty: type: standard deviation; value: 1.83 Scored: Not reported · Eligible: Not reported | source checkedBEACON: Benchmark for Comprehensive RNA Tasks and Language Models (arXiv:2406.10391v2) · Table3,p.8,row(LSTM),column(SPL) Source checking is not independent reproduction. |
| ResNet on BEACON SPL: Splice site prediction BEACON harness, fixed downstream head per task. Train/validation/test 144,628/18,078/16,505; dataset SpliceAI. Author-reported evaluation · Evaluation metadata: source checked | ||
| 21.15(1.56)% top_k_accuracy Unit: percent · Direction: higher | Uncertainty: type: standard deviation; value: 1.56 Scored: Not reported · Eligible: Not reported | source checkedBEACON: Benchmark for Comprehensive RNA Tasks and Language Models (arXiv:2406.10391v2) · Table3,p.8,row(ResNet),column(SPL) Source checking is not independent reproduction. |
| RNA-FM on BEACON SPL: Splice site prediction Configuration: RNA-FMTask: BEACON SPL: Splice site predictionDataset subset: SpliceAI (BEACON split) BEACON harness, fixed downstream head per task. Train/validation/test 144,628/18,078/16,505; dataset SpliceAI. Author-reported evaluation · Evaluation metadata: source checked | ||
| 34.84(0.87)% top_k_accuracy Unit: percent · Direction: higher | Uncertainty: type: standard deviation; value: 0.87 Scored: Not reported · Eligible: Not reported | source checkedBEACON: Benchmark for Comprehensive RNA Tasks and Language Models (arXiv:2406.10391v2) · Table3,p.8,row(RNA-FM),column(SPL) Source checking is not independent reproduction. |
| RNA-MSM on BEACON SPL: Splice site prediction Configuration: RNA-MSMTask: BEACON SPL: Splice site predictionDataset subset: SpliceAI (BEACON split) BEACON harness, fixed downstream head per task. Train/validation/test 144,628/18,078/16,505; dataset SpliceAI. Author-reported evaluation · Evaluation metadata: source checked | ||
| 38.33(0.76)% top_k_accuracy Unit: percent · Direction: higher | Uncertainty: type: standard deviation; value: 0.76 Scored: Not reported · Eligible: Not reported | source checkedBEACON: Benchmark for Comprehensive RNA Tasks and Language Models (arXiv:2406.10391v2) · Table3,p.8,row(RNA-MSM),column(SPL) Source checking is not independent reproduction. |
| RNABERT on BEACON SPL: Splice site prediction Configuration: RNABERTTask: BEACON SPL: Splice site predictionDataset subset: SpliceAI (BEACON split) BEACON harness, fixed downstream head per task. Train/validation/test 144,628/18,078/16,505; dataset SpliceAI. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.18(0.18)% top_k_accuracy Unit: percent · Direction: higher | Uncertainty: type: standard deviation; value: 0.18 Scored: Not reported · Eligible: Not reported | source checkedBEACON: Benchmark for Comprehensive RNA Tasks and Language Models (arXiv:2406.10391v2) · Table3,p.8,row(RNABERT),column(SPL) Source checking is not independent reproduction. |
| Splice-H510 on BEACON SPL: Splice site prediction Configuration: Splice-H510Task: BEACON SPL: Splice site predictionDataset subset: SpliceAI (BEACON split) BEACON harness, fixed downstream head per task. Train/validation/test 144,628/18,078/16,505; dataset SpliceAI. Author-reported evaluation · Evaluation metadata: source checked | ||
| 44.80(1.93)% top_k_accuracy Unit: percent · Direction: higher | Uncertainty: type: standard deviation; value: 1.93 Scored: Not reported · Eligible: Not reported | source checkedBEACON: Benchmark for Comprehensive RNA Tasks and Language Models (arXiv:2406.10391v2) · Table3,p.8,row(Splice-H510),column(SPL) Source checking is not independent reproduction. |
| Splice-MS1024 on BEACON SPL: Splice site prediction Configuration: Splice-MS1024Task: BEACON SPL: Splice site predictionDataset subset: SpliceAI (BEACON split) BEACON harness, fixed downstream head per task. Train/validation/test 144,628/18,078/16,505; dataset SpliceAI. Author-reported evaluation · Evaluation metadata: source checked | ||
| 48.52(0.49)% top_k_accuracy Unit: percent · Direction: higher | Uncertainty: type: standard deviation; value: 0.49 Scored: Not reported · Eligible: Not reported | source checkedBEACON: Benchmark for Comprehensive RNA Tasks and Language Models (arXiv:2406.10391v2) · Table3,p.8,row(Splice-MS1024),column(SPL) Source checking is not independent reproduction. |
| Splice-MS510 on BEACON SPL: Splice site prediction Configuration: Splice-MS510Task: BEACON SPL: Splice site predictionDataset subset: SpliceAI (BEACON split) BEACON harness, fixed downstream head per task. Train/validation/test 144,628/18,078/16,505; dataset SpliceAI. Author-reported evaluation · Evaluation metadata: source checked | ||
| 50.55(0.49)% top_k_accuracy Unit: percent · Direction: higher | Uncertainty: type: standard deviation; value: 0.49 Scored: Not reported · Eligible: Not reported | source checkedBEACON: Benchmark for Comprehensive RNA Tasks and Language Models (arXiv:2406.10391v2) · Table3,p.8,row(Splice-MS510),column(SPL) Source checking is not independent reproduction. |
| UTR-LM-MRL on BEACON SPL: Splice site prediction Configuration: UTR-LM-MRLTask: BEACON SPL: Splice site predictionDataset subset: SpliceAI (BEACON split) BEACON harness, fixed downstream head per task. Train/validation/test 144,628/18,078/16,505; dataset SpliceAI. Author-reported evaluation · Evaluation metadata: source checked | ||
| 36.20(1.84)% top_k_accuracy Unit: percent · Direction: higher | Uncertainty: type: standard deviation; value: 1.84 Scored: Not reported · Eligible: Not reported | source checkedBEACON: Benchmark for Comprehensive RNA Tasks and Language Models (arXiv:2406.10391v2) · Table3,p.8,row(UTR-LM-MRL),column(SPL) Source checking is not independent reproduction. |
| UTR-LM-TE&EL on BEACON SPL: Splice site prediction Configuration: UTR-LM-TE&ELTask: BEACON SPL: Splice site predictionDataset subset: SpliceAI (BEACON split) BEACON harness, fixed downstream head per task. Train/validation/test 144,628/18,078/16,505; dataset SpliceAI. Author-reported evaluation · Evaluation metadata: source checked | ||
| 37.35(5.48)% top_k_accuracy Unit: percent · Direction: higher | Uncertainty: type: standard deviation; value: 5.48 Scored: Not reported · Eligible: Not reported | source checkedBEACON: Benchmark for Comprehensive RNA Tasks and Language Models (arXiv:2406.10391v2) · Table3,p.8,row(UTR-LM-TE&EL),column(SPL) Source checking is not independent reproduction. |
| UTRBERT-3mer on BEACON SPL: Splice site prediction Configuration: UTRBERT-3merTask: BEACON SPL: Splice site predictionDataset subset: SpliceAI (BEACON split) BEACON harness, fixed downstream head per task. Train/validation/test 144,628/18,078/16,505; dataset SpliceAI. Author-reported evaluation · Evaluation metadata: source checked | ||
| 44.24(0.53)% top_k_accuracy Unit: percent · Direction: higher | Uncertainty: type: standard deviation; value: 0.53 Scored: Not reported · Eligible: Not reported | source checkedBEACON: Benchmark for Comprehensive RNA Tasks and Language Models (arXiv:2406.10391v2) · Table3,p.8,row(UTRBERT-3mer),column(SPL) Source checking is not independent reproduction. |
| UTRBERT-4mer on BEACON SPL: Splice site prediction Configuration: UTRBERT-4merTask: BEACON SPL: Splice site predictionDataset subset: SpliceAI (BEACON split) BEACON harness, fixed downstream head per task. Train/validation/test 144,628/18,078/16,505; dataset SpliceAI. Author-reported evaluation · Evaluation metadata: source checked | ||
| 42.04(0.53)% top_k_accuracy Unit: percent · Direction: higher | Uncertainty: type: standard deviation; value: 0.53 Scored: Not reported · Eligible: Not reported | source checkedBEACON: Benchmark for Comprehensive RNA Tasks and Language Models (arXiv:2406.10391v2) · Table3,p.8,row(UTRBERT-4mer),column(SPL) Source checking is not independent reproduction. |
| UTRBERT-5mer on BEACON SPL: Splice site prediction Configuration: UTRBERT-5merTask: BEACON SPL: Splice site predictionDataset subset: SpliceAI (BEACON split) BEACON harness, fixed downstream head per task. Train/validation/test 144,628/18,078/16,505; dataset SpliceAI. Author-reported evaluation · Evaluation metadata: source checked | ||
| 39.19(0.37)% top_k_accuracy Unit: percent · Direction: higher | Uncertainty: type: standard deviation; value: 0.37 Scored: Not reported · Eligible: Not reported | source checkedBEACON: Benchmark for Comprehensive RNA Tasks and Language Models (arXiv:2406.10391v2) · Table3,p.8,row(UTRBERT-5mer),column(SPL) Source checking is not independent reproduction. |
| UTRBERT-6mer on BEACON SPL: Splice site prediction Configuration: UTRBERT-6merTask: BEACON SPL: Splice site predictionDataset subset: SpliceAI (BEACON split) BEACON harness, fixed downstream head per task. Train/validation/test 144,628/18,078/16,505; dataset SpliceAI. Author-reported evaluation · Evaluation metadata: source checked | ||
| 38.58(2.72)% top_k_accuracy Unit: percent · Direction: higher | Uncertainty: type: standard deviation; value: 2.72 Scored: Not reported · Eligible: Not reported | source checkedBEACON: Benchmark for Comprehensive RNA Tasks and Language Models (arXiv:2406.10391v2) · Table3,p.8,row(UTRBERT-6mer),column(SPL) Source checking is not 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.
3 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| attributes.source_locator Table1,p.6,column(Source/Venue) Context-only references | BEACON: Benchmark for Comprehensive RNA Tasks and Language Models (arXiv:2406.10391v2) Table1,p.6,column(Source/Venue) Version: v2, 12 December 2024 | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| description The split of SpliceAI that the BEACON authors evaluated on, named in their Table 1. The upstream dataset release is not catalogued here, so no claim is made that this matches the original splits. Context-only references | BEACON: Benchmark for Comprehensive RNA Tasks and Language Models (arXiv:2406.10391v2) Table1,p.6,column(Source/Venue) Version: v2, 12 December 2024 | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| name SpliceAI (BEACON split) Context-only references | BEACON: Benchmark for Comprehensive RNA Tasks and Language Models (arXiv:2406.10391v2) Table1,p.6,column(Source/Venue) Version: v2, 12 December 2024 | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
Sources and history
Release 2026-09-17-1a18ca2c038a · Record review: source checked
1 source records and release history
- BEACON: Benchmark for Comprehensive RNA Tasks and Language Models (arXiv:2406.10391v2) · Original source · v2, 12 December 2024
Technical metadata and extraction receipts
Stable ID: beacon-dataset-spliceai
- areas
- rna-transcriptomes
- source locator
- Table1,p.6,column(Source/Venue)
- missing metadata
- version: unreported; url: unextracted
Related records
- dataset: BEACON-B on BEACON SPL: Splice site prediction
- dataset: BEACON-B512 on BEACON SPL: Splice site prediction
- dataset: CNN on BEACON SPL: Splice site prediction
- dataset: LSTM on BEACON SPL: Splice site prediction
- dataset: ResNet on BEACON SPL: Splice site prediction
- dataset: RNA-FM on BEACON SPL: Splice site prediction
- dataset: RNA-MSM on BEACON SPL: Splice site prediction
- dataset: RNABERT on BEACON SPL: Splice site prediction
- dataset: Splice-H510 on BEACON SPL: Splice site prediction
- dataset: Splice-MS1024 on BEACON SPL: Splice site prediction
- dataset: Splice-MS510 on BEACON SPL: Splice site prediction
- dataset: UTR-LM-MRL on BEACON SPL: Splice site prediction
- dataset: UTR-LM-TE&EL on BEACON SPL: Splice site prediction
- dataset: UTRBERT-3mer on BEACON SPL: Splice site prediction
- dataset: UTRBERT-4mer on BEACON SPL: Splice site prediction
- dataset: UTRBERT-5mer on BEACON SPL: Splice site prediction
- dataset: UTRBERT-6mer on BEACON SPL: Splice site prediction