GENEB leaderboard
Frozen-embedding probing benchmark of genomic foundation models over 100 tasks in 13 categories, with full-data, 10-shot and 1-shot regimes.
Results are recorded on the linked protocols, tasks or configurations listed below. Their settings and evaluations are kept separate.
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.
Results on linked records
This benchmark has no results of its own in this release. 3 linked records have results. They are not assigned to the underlying benchmark: each record keeps its own settings and evaluations, and its scores are on its own page.
- GENEB leaderboard, 10-shot, MCC aggregates Protocol · part of this benchmark · 41 evaluations · 615 results
- GENEB leaderboard, 1-shot, MCC aggregates Protocol · part of this benchmark · 41 evaluations · 615 results
- GENEB leaderboard, full training data, MCC aggregates Protocol · part of this benchmark · 41 evaluations · 615 results
Methods and evaluation design
Procedure, tasks and evaluated configurations
Evaluation design
Benchmarks bring together tasks and protocols. A task describes the biological question; a protocol defines a particular test.
Benchmarks
These source-backed links do not make different protocols or scores interchangeable.
Baseline coverage
Reference methods help show what a model adds beyond simple controls. We track a null control and a conventional method for each protocol.
0 of 6 active baseline roles have published Rewire measurements in this release. Measurements on a selected protocol do not establish coverage of an entire suite.
Baseline status by linked protocol
- GENEB leaderboard, 10-shot, MCC aggregates · 0/2 roles measured
- GENEB leaderboard, 1-shot, MCC aggregates · 0/2 roles measured
- GENEB leaderboard, full training data, MCC aggregates · 0/2 roles measured
Protocol coverage CSV (gzip) · Model evaluation matrix (gzip) · Source table (gzip) · Release and checksums (gzip)
Coverage is derived from release 2026-10-22-1b7cf027e4f6. Source citations describe the original records; they do not validate an unreviewed baseline proposal. No results have been generated by this audit.
Run instructions
No runnable recipe has been reviewed for this benchmark. Dataset access, model requirements, licences and compute requirements must be checked against its sources before execution.
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.
4 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Relationship: part of discovery-benchmark-geneb Individual claims | GENEB: Why Genomic Models Are Hard to Compare Both records describe the GENEB suite in the darlednik/GENEB repository at commit 9642d481e40c0af23995dcd162b779613f789f97: src-discovery-darlednik-geneb is README.md and lit-genomics-20261011-geneb-source-leaderboard is leaderboard/leaderboard.json at the same commit. The leaderboard record is the suite's published aggregate, not a separate benchmark. Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 2606.04525v1 | source checked ["scope-review"] · 2026-10-14 Audit detailsAccepted in the independent review of 2026-10-14. See docs/reviews/2026-10-14-gfm-guide-evidence-review.md. Field: Claim: identity-20261014-db5569641cdee680b5a9 Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
| Relationship: part of discovery-benchmark-geneb Individual claims | GENEB leaderboard (leaderboard.json, 13 task-type aggregates) Both records describe the GENEB suite in the darlednik/GENEB repository at commit 9642d481e40c0af23995dcd162b779613f789f97: src-discovery-darlednik-geneb is README.md and lit-genomics-20261011-geneb-source-leaderboard is leaderboard/leaderboard.json at the same commit. The leaderboard record is the suite's published aggregate, not a separate benchmark. Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Git commit 9642d481e40c0af23995dcd162b779613f789f97 (repository pushed 2026-08-22) | source checked ["scope-review"] · 2026-10-14 Audit detailsAccepted in the independent review of 2026-10-14. See docs/reviews/2026-10-14-gfm-guide-evidence-review.md. Field: Claim: identity-20261014-db5569641cdee680b5a9 Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Relationship: part of discovery-benchmark-geneb Individual claims | darlednik/GENEB / README.md Both records describe the GENEB suite in the darlednik/GENEB repository at commit 9642d481e40c0af23995dcd162b779613f789f97: src-discovery-darlednik-geneb is README.md and lit-genomics-20261011-geneb-source-leaderboard is leaderboard/leaderboard.json at the same commit. The leaderboard record is the suite's published aggregate, not a separate benchmark. Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Git commit 9642d481e40c0af23995dcd162b779613f789f97 | source checked ["scope-review"] · 2026-10-14 Audit detailsAccepted in the independent review of 2026-10-14. See docs/reviews/2026-10-14-gfm-guide-evidence-review.md. Field: Claim: identity-20261014-db5569641cdee680b5a9 Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Relationship: part of discovery-benchmark-geneb Individual claims | darlednik/GENEB official source Both records describe the GENEB suite in the darlednik/GENEB repository at commit 9642d481e40c0af23995dcd162b779613f789f97: src-discovery-darlednik-geneb is README.md and lit-genomics-20261011-geneb-source-leaderboard is leaderboard/leaderboard.json at the same commit. The leaderboard record is the suite's published aggregate, not a separate benchmark. Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 9642d481e40c0af23995dcd162b779613f789f97 | source checked ["scope-review"] · 2026-10-14 Audit detailsAccepted in the independent review of 2026-10-14. See docs/reviews/2026-10-14-gfm-guide-evidence-review.md. Field: Claim: identity-20261014-db5569641cdee680b5a9 Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
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)
Technical metadata and extraction receipts
Stable ID: lit-genomics-20261011-geneb-benchmark-geneb
- areas
- dna-genomes
- contexts
- research
- entity level
- suite
- version
- Leaderboard at commit 9642d481e40c
- task
- Genomic sequence classification from frozen embeddings
- scope note
- MCC aggregates only: micro average over all 100 tasks, macro average (unweighted mean of the 13 category MCCs), and per category.
- source locator
- leaderboard/README.md (Evaluation table: logistic-regression probe on frozen embeddings, max_iter=1000; Macro = mean of the 13 category scores); leaderboard.json
Related records
- part of: GENEB
- subject: GENEB leaderboard: part of GENEB
- part of: GENEB leaderboard, 10-shot, MCC aggregates
- part of: GENEB leaderboard, 1-shot, MCC aggregates
- part of: GENEB leaderboard, full training data, MCC aggregates