Configuration

SpliceBERT 1024nt (GENEB leaderboard)

SpliceBERT 1024nt: frozen embeddings; leaderboard display name 'SpliceBERT 1024nt'.

Overview

An explanatory profile has not yet been reviewed for this record.

Consult the linked sources for architecture or protocol details. Missing evidence is not evidence of a missing capability.

Evaluations and results

3 evaluations · 45 results. Different protocols are not a single leaderboard.

Dataset: GENEB 100 tasks

Sorted by MCC (1-shot; category 'Chromatin Acc.') (higher is better). The best value in each column is highlighted. Decimals are rounded for display; each value links to the printed value and its source.

Tested configuration	Protocol and dataset	MCC (1-shot; category 'Chromatin Acc.')	MCC (1-shot; category 'Coding/NC')	MCC (1-shot; category 'DNA Methyl.')	MCC (1-shot; category 'Enhancers')	MCC (1-shot; category 'Histone Mod.')	MCC (1-shot; category 'lncRNA')	MCC (1-shot; category 'Mouse Enh.')	MCC (1-shot; category 'Promoters')	MCC (1-shot; category 'Regulatory')	MCC (1-shot; category 'Species Clf.')	MCC (1-shot; category 'Splice Sites')	MCC (1-shot; category 'TF Binding')	MCC (1-shot; category 'Virus/Phage')	MCC (1-shot; macro average: unweighted mean of the 13 category MCCs)	MCC (1-shot; micro average: mean over all 100 tasks)	MCC (10-shot; category 'Chromatin Acc.')	MCC (10-shot; category 'Coding/NC')	MCC (10-shot; category 'DNA Methyl.')	MCC (10-shot; category 'Enhancers')	MCC (10-shot; category 'Histone Mod.')	MCC (10-shot; category 'lncRNA')	MCC (10-shot; category 'Mouse Enh.')	MCC (10-shot; category 'Promoters')	MCC (10-shot; category 'Regulatory')	MCC (10-shot; category 'Species Clf.')	MCC (10-shot; category 'Splice Sites')	MCC (10-shot; category 'TF Binding')	MCC (10-shot; category 'Virus/Phage')	MCC (10-shot; macro average: unweighted mean of the 13 category MCCs)	MCC (10-shot; micro average: mean over all 100 tasks)	MCC (full training data; category 'Chromatin Acc.')	MCC (full training data; category 'Coding/NC')	MCC (full training data; category 'DNA Methyl.')	MCC (full training data; category 'Enhancers')	MCC (full training data; category 'Histone Mod.')	MCC (full training data; category 'lncRNA')	MCC (full training data; category 'Mouse Enh.')	MCC (full training data; category 'Promoters')	MCC (full training data; category 'Regulatory')	MCC (full training data; category 'Species Clf.')	MCC (full training data; category 'Splice Sites')	MCC (full training data; category 'TF Binding')	MCC (full training data; category 'Virus/Phage')	MCC (full training data; macro average: unweighted mean of the 13 category MCCs)	MCC (full training data; micro average: mean over all 100 tasks)
SpliceBERT 1024nt (GENEB leaderboard)Evaluation	GENEB leaderboard, 1-shot, MCC aggregates	0.233	0.335	0.0189	0.162	0.122	0.045	0.0816	0.367	0.0762	0.283	0.0992	0.125	0.0607	0.155	0.169	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
SpliceBERT 1024nt (GENEB leaderboard)Evaluation	GENEB leaderboard, 10-shot, MCC aggregates	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	0.612	0.772	0.07	0.331	0.272	0.123	0.297	0.597	0.16	0.533	0.25	0.315	0.0901	0.34	0.335	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported
SpliceBERT 1024nt (GENEB leaderboard)Evaluation	GENEB leaderboard, full training data, MCC aggregates	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	0.708	0.89	0.238	0.473	0.495	0.384	0.603	0.756	0.456	0.708	0.633	0.609	0.43	0.568	0.555

All 45 result rows with coverage, uncertainty and sources

Filter evaluations

Tested model or methodProtocolDatasetEvaluation setupMetricEvidence origin

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configuration	Protocol and dataset	Finding	Evidence and details
Configuration: SpliceBERT 1024nt (GENEB leaderboard)	Protocol: GENEB leaderboard, 10-shot, MCC aggregates Dataset: GENEB 100 tasks	0.612 MCC (10-shot; category 'Chromatin Acc.') unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source SpliceBERT 1024nt on GENEB (10-shot) lit-genomics-20261011-geneb-protocol-10shot Aggregation: Not reported GENEB leaderboard (leaderboard.json, 13 task-type aggregates) · leaderboard.json data.10shot, model 'splicebert-1024nt', key 'cat_MCC.Chromatin Acc.'
Configuration: SpliceBERT 1024nt (GENEB leaderboard)	Protocol: GENEB leaderboard, 10-shot, MCC aggregates Dataset: GENEB 100 tasks	0.772 MCC (10-shot; category 'Coding/NC') unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source SpliceBERT 1024nt on GENEB (10-shot) lit-genomics-20261011-geneb-protocol-10shot Aggregation: Not reported GENEB leaderboard (leaderboard.json, 13 task-type aggregates) · leaderboard.json data.10shot, model 'splicebert-1024nt', key 'cat_MCC.Coding/NC'
Configuration: SpliceBERT 1024nt (GENEB leaderboard)	Protocol: GENEB leaderboard, 10-shot, MCC aggregates Dataset: GENEB 100 tasks	0.07 MCC (10-shot; category 'DNA Methyl.') unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source SpliceBERT 1024nt on GENEB (10-shot) lit-genomics-20261011-geneb-protocol-10shot Aggregation: Not reported GENEB leaderboard (leaderboard.json, 13 task-type aggregates) · leaderboard.json data.10shot, model 'splicebert-1024nt', key 'cat_MCC.DNA Methyl.'
Configuration: SpliceBERT 1024nt (GENEB leaderboard)	Protocol: GENEB leaderboard, 10-shot, MCC aggregates Dataset: GENEB 100 tasks	0.331 MCC (10-shot; category 'Enhancers') unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source SpliceBERT 1024nt on GENEB (10-shot) lit-genomics-20261011-geneb-protocol-10shot Aggregation: Not reported GENEB leaderboard (leaderboard.json, 13 task-type aggregates) · leaderboard.json data.10shot, model 'splicebert-1024nt', key 'cat_MCC.Enhancers'
Configuration: SpliceBERT 1024nt (GENEB leaderboard)	Protocol: GENEB leaderboard, 10-shot, MCC aggregates Dataset: GENEB 100 tasks	0.272 MCC (10-shot; category 'Histone Mod.') unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source SpliceBERT 1024nt on GENEB (10-shot) lit-genomics-20261011-geneb-protocol-10shot Aggregation: Not reported GENEB leaderboard (leaderboard.json, 13 task-type aggregates) · leaderboard.json data.10shot, model 'splicebert-1024nt', key 'cat_MCC.Histone Mod.'
Configuration: SpliceBERT 1024nt (GENEB leaderboard)	Protocol: GENEB leaderboard, 10-shot, MCC aggregates Dataset: GENEB 100 tasks	0.123 MCC (10-shot; category 'lncRNA') unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source SpliceBERT 1024nt on GENEB (10-shot) lit-genomics-20261011-geneb-protocol-10shot Aggregation: Not reported GENEB leaderboard (leaderboard.json, 13 task-type aggregates) · leaderboard.json data.10shot, model 'splicebert-1024nt', key 'cat_MCC.lncRNA'
Configuration: SpliceBERT 1024nt (GENEB leaderboard)	Protocol: GENEB leaderboard, 10-shot, MCC aggregates Dataset: GENEB 100 tasks	0.34 MCC (10-shot; macro average: unweighted mean of the 13 category MCCs) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source SpliceBERT 1024nt on GENEB (10-shot) lit-genomics-20261011-geneb-protocol-10shot Aggregation: Not reported GENEB leaderboard (leaderboard.json, 13 task-type aggregates) · leaderboard.json data.10shot, model 'splicebert-1024nt', key 'macro_MCC'
Configuration: SpliceBERT 1024nt (GENEB leaderboard)	Protocol: GENEB leaderboard, 10-shot, MCC aggregates Dataset: GENEB 100 tasks	0.335 MCC (10-shot; micro average: mean over all 100 tasks) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source SpliceBERT 1024nt on GENEB (10-shot) lit-genomics-20261011-geneb-protocol-10shot Aggregation: Not reported GENEB leaderboard (leaderboard.json, 13 task-type aggregates) · leaderboard.json data.10shot, model 'splicebert-1024nt', key 'micro_MCC'
Configuration: SpliceBERT 1024nt (GENEB leaderboard)	Protocol: GENEB leaderboard, 10-shot, MCC aggregates Dataset: GENEB 100 tasks	0.297 MCC (10-shot; category 'Mouse Enh.') unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source SpliceBERT 1024nt on GENEB (10-shot) lit-genomics-20261011-geneb-protocol-10shot Aggregation: Not reported GENEB leaderboard (leaderboard.json, 13 task-type aggregates) · leaderboard.json data.10shot, model 'splicebert-1024nt', key 'cat_MCC.Mouse Enh.'
Configuration: SpliceBERT 1024nt (GENEB leaderboard)	Protocol: GENEB leaderboard, 10-shot, MCC aggregates Dataset: GENEB 100 tasks	0.597 MCC (10-shot; category 'Promoters') unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source SpliceBERT 1024nt on GENEB (10-shot) lit-genomics-20261011-geneb-protocol-10shot Aggregation: Not reported GENEB leaderboard (leaderboard.json, 13 task-type aggregates) · leaderboard.json data.10shot, model 'splicebert-1024nt', key 'cat_MCC.Promoters'
Configuration: SpliceBERT 1024nt (GENEB leaderboard)	Protocol: GENEB leaderboard, 10-shot, MCC aggregates Dataset: GENEB 100 tasks	0.16 MCC (10-shot; category 'Regulatory') unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source SpliceBERT 1024nt on GENEB (10-shot) lit-genomics-20261011-geneb-protocol-10shot Aggregation: Not reported GENEB leaderboard (leaderboard.json, 13 task-type aggregates) · leaderboard.json data.10shot, model 'splicebert-1024nt', key 'cat_MCC.Regulatory'
Configuration: SpliceBERT 1024nt (GENEB leaderboard)	Protocol: GENEB leaderboard, 10-shot, MCC aggregates Dataset: GENEB 100 tasks	0.533 MCC (10-shot; category 'Species Clf.') unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source SpliceBERT 1024nt on GENEB (10-shot) lit-genomics-20261011-geneb-protocol-10shot Aggregation: Not reported GENEB leaderboard (leaderboard.json, 13 task-type aggregates) · leaderboard.json data.10shot, model 'splicebert-1024nt', key 'cat_MCC.Species Clf.'
Configuration: SpliceBERT 1024nt (GENEB leaderboard)	Protocol: GENEB leaderboard, 10-shot, MCC aggregates Dataset: GENEB 100 tasks	0.25 MCC (10-shot; category 'Splice Sites') unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source SpliceBERT 1024nt on GENEB (10-shot) lit-genomics-20261011-geneb-protocol-10shot Aggregation: Not reported GENEB leaderboard (leaderboard.json, 13 task-type aggregates) · leaderboard.json data.10shot, model 'splicebert-1024nt', key 'cat_MCC.Splice Sites'
Configuration: SpliceBERT 1024nt (GENEB leaderboard)	Protocol: GENEB leaderboard, 10-shot, MCC aggregates Dataset: GENEB 100 tasks	0.315 MCC (10-shot; category 'TF Binding') unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source SpliceBERT 1024nt on GENEB (10-shot) lit-genomics-20261011-geneb-protocol-10shot Aggregation: Not reported GENEB leaderboard (leaderboard.json, 13 task-type aggregates) · leaderboard.json data.10shot, model 'splicebert-1024nt', key 'cat_MCC.TF Binding'
Configuration: SpliceBERT 1024nt (GENEB leaderboard)	Protocol: GENEB leaderboard, 10-shot, MCC aggregates Dataset: GENEB 100 tasks	0.0901 MCC (10-shot; category 'Virus/Phage') unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source SpliceBERT 1024nt on GENEB (10-shot) lit-genomics-20261011-geneb-protocol-10shot Aggregation: Not reported GENEB leaderboard (leaderboard.json, 13 task-type aggregates) · leaderboard.json data.10shot, model 'splicebert-1024nt', key 'cat_MCC.Virus/Phage'
Configuration: SpliceBERT 1024nt (GENEB leaderboard)	Protocol: GENEB leaderboard, 1-shot, MCC aggregates Dataset: GENEB 100 tasks	0.233 MCC (1-shot; category 'Chromatin Acc.') unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source SpliceBERT 1024nt on GENEB (1-shot) lit-genomics-20261011-geneb-protocol-1shot Aggregation: Not reported GENEB leaderboard (leaderboard.json, 13 task-type aggregates) · leaderboard.json data.1shot, model 'splicebert-1024nt', key 'cat_MCC.Chromatin Acc.'
Configuration: SpliceBERT 1024nt (GENEB leaderboard)	Protocol: GENEB leaderboard, 1-shot, MCC aggregates Dataset: GENEB 100 tasks	0.335 MCC (1-shot; category 'Coding/NC') unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source SpliceBERT 1024nt on GENEB (1-shot) lit-genomics-20261011-geneb-protocol-1shot Aggregation: Not reported GENEB leaderboard (leaderboard.json, 13 task-type aggregates) · leaderboard.json data.1shot, model 'splicebert-1024nt', key 'cat_MCC.Coding/NC'
Configuration: SpliceBERT 1024nt (GENEB leaderboard)	Protocol: GENEB leaderboard, 1-shot, MCC aggregates Dataset: GENEB 100 tasks	0.0189 MCC (1-shot; category 'DNA Methyl.') unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source SpliceBERT 1024nt on GENEB (1-shot) lit-genomics-20261011-geneb-protocol-1shot Aggregation: Not reported GENEB leaderboard (leaderboard.json, 13 task-type aggregates) · leaderboard.json data.1shot, model 'splicebert-1024nt', key 'cat_MCC.DNA Methyl.'
Configuration: SpliceBERT 1024nt (GENEB leaderboard)	Protocol: GENEB leaderboard, 1-shot, MCC aggregates Dataset: GENEB 100 tasks	0.162 MCC (1-shot; category 'Enhancers') unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source SpliceBERT 1024nt on GENEB (1-shot) lit-genomics-20261011-geneb-protocol-1shot Aggregation: Not reported GENEB leaderboard (leaderboard.json, 13 task-type aggregates) · leaderboard.json data.1shot, model 'splicebert-1024nt', key 'cat_MCC.Enhancers'
Configuration: SpliceBERT 1024nt (GENEB leaderboard)	Protocol: GENEB leaderboard, 1-shot, MCC aggregates Dataset: GENEB 100 tasks	0.122 MCC (1-shot; category 'Histone Mod.') unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source SpliceBERT 1024nt on GENEB (1-shot) lit-genomics-20261011-geneb-protocol-1shot Aggregation: Not reported GENEB leaderboard (leaderboard.json, 13 task-type aggregates) · leaderboard.json data.1shot, model 'splicebert-1024nt', key 'cat_MCC.Histone Mod.'
Configuration: SpliceBERT 1024nt (GENEB leaderboard)	Protocol: GENEB leaderboard, 1-shot, MCC aggregates Dataset: GENEB 100 tasks	0.045 MCC (1-shot; category 'lncRNA') unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source SpliceBERT 1024nt on GENEB (1-shot) lit-genomics-20261011-geneb-protocol-1shot Aggregation: Not reported GENEB leaderboard (leaderboard.json, 13 task-type aggregates) · leaderboard.json data.1shot, model 'splicebert-1024nt', key 'cat_MCC.lncRNA'
Configuration: SpliceBERT 1024nt (GENEB leaderboard)	Protocol: GENEB leaderboard, 1-shot, MCC aggregates Dataset: GENEB 100 tasks	0.155 MCC (1-shot; macro average: unweighted mean of the 13 category MCCs) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source SpliceBERT 1024nt on GENEB (1-shot) lit-genomics-20261011-geneb-protocol-1shot Aggregation: Not reported GENEB leaderboard (leaderboard.json, 13 task-type aggregates) · leaderboard.json data.1shot, model 'splicebert-1024nt', key 'macro_MCC'
Configuration: SpliceBERT 1024nt (GENEB leaderboard)	Protocol: GENEB leaderboard, 1-shot, MCC aggregates Dataset: GENEB 100 tasks	0.169 MCC (1-shot; micro average: mean over all 100 tasks) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source SpliceBERT 1024nt on GENEB (1-shot) lit-genomics-20261011-geneb-protocol-1shot Aggregation: Not reported GENEB leaderboard (leaderboard.json, 13 task-type aggregates) · leaderboard.json data.1shot, model 'splicebert-1024nt', key 'micro_MCC'
Configuration: SpliceBERT 1024nt (GENEB leaderboard)	Protocol: GENEB leaderboard, 1-shot, MCC aggregates Dataset: GENEB 100 tasks	0.0816 MCC (1-shot; category 'Mouse Enh.') unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source SpliceBERT 1024nt on GENEB (1-shot) lit-genomics-20261011-geneb-protocol-1shot Aggregation: Not reported GENEB leaderboard (leaderboard.json, 13 task-type aggregates) · leaderboard.json data.1shot, model 'splicebert-1024nt', key 'cat_MCC.Mouse Enh.'
Configuration: SpliceBERT 1024nt (GENEB leaderboard)	Protocol: GENEB leaderboard, 1-shot, MCC aggregates Dataset: GENEB 100 tasks	0.367 MCC (1-shot; category 'Promoters') unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Evaluation origin not reported · Source checked Methods, coverage and source SpliceBERT 1024nt on GENEB (1-shot) lit-genomics-20261011-geneb-protocol-1shot Aggregation: Not reported GENEB leaderboard (leaderboard.json, 13 task-type aggregates) · leaderboard.json data.1shot, model 'splicebert-1024nt', key 'cat_MCC.Promoters'

Source checking is not independent reproduction. Release 2026-10-22-1b7cf027e4f6.

Use this configuration

How it works, versions and access

Strengths, limitations and unresolved questions

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.

0 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-10-22-1b7cf027e4f6
Property and statement	Original source and location	Review and provenance

No evidence rows match these filters. Choose another scope or clear the search.

How to read the evidence

Sources and history

Release 2026-10-22-1b7cf027e4f6 · Record review: source checked

1 source record and release history

GENEB leaderboard (leaderboard.json, 13 task-type aggregates) · Original source · Git commit 9642d481e40c0af23995dcd162b779613f789f97 (repository pushed 2026-08-22)

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: lit-genomics-20261011-geneb-config-splicebert-1024nt

areas: dna-genomes
contexts: research
method types: foundation_model
reported name: splicebert-1024nt
foundation model eligible: true
parameters: 19710474 parameters as listed; frozen embeddings; leaderboard display name 'SpliceBERT 1024nt'
access reuse: Public checkpoint as named on the leaderboard
version: splicebert-1024nt
source locator: leaderboard.json data.full row model 'splicebert-1024nt'
provenance note: splicebert-1024nt as evaluated on the GENEB leaderboard.

Related records

configuration of: SpliceBERT
system: SpliceBERT 1024nt on GENEB (10-shot)
system: SpliceBERT 1024nt on GENEB (1-shot)
system: SpliceBERT 1024nt on GENEB (full training data)

Suggest a correction