DNABERT-2 on Gene-MTEB genomic embedding benchmark HMPD-source: HMPD-source genomic embedding evaluation
Gene-MTEB genomic embedding benchmark evaluation of DNABERT-2 on HMPD-source genomic embedding evaluation, scored with accuracy.
Evaluation results
1 evaluation · 1 metric rows. Different protocols are not a single leaderboard.
Filter evaluations
Applied filters: All linked evaluations
| Tested configuration | Protocol and dataset | Finding | Evidence and details |
|---|---|---|---|
| Pipeline: DNABERT-2 | Protocol: Gene-MTEB genomic embedding benchmark HMPD-source: HMPD-source genomic embedding evaluation Dataset subset: HMPD-source Gene-MTEB data used in METAGENE-1 Table 3 (Gene-MTEB genomic embedding benchmark split) | 0.451 accuracy fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · source checkedMethods, coverage and sourceFrozen model last-hidden-state embeddings, mean pooled. Logistic regression for eight classification tasks and mini-batch k-means for eight clustering tasks. Source paper Section 5.3. Current official gene-mteb implementation corroborates task identities but its commit is not proven identical to the paper evaluator. Exact dataset release, split hash, scored counts and evaluator commit are unreported in the paper. Do not substitute current mutable HF main for the original split. Aggregation: Not reported METAGENE-1 v1: Gene-MTEB complete component tasks · Table 3 (S5.T3), row HMPD-source, column DNABERT-2; Section 5.3 paragraphs S5.SS3.p2.1 and S5.SS3.p3.1 |
Source checking is not independent reproduction. Release 2026-09-23-2b89723c6dd9.
Evaluation procedure
Frozen model last-hidden-state embeddings, mean pooled. Logistic regression for eight classification tasks and mini-batch k-means for eight clustering tasks. Source paper Section 5.3. Current official gene-mteb implementation corroborates task identities but its commit is not proven identical to the paper evaluator. Exact dataset release, split hash, scored counts and evaluator commit are unreported in the paper. Do not substitute current mutable HF main for the original split.
- Pipeline
- DNABERT-2
- Protocol
- Gene-MTEB genomic embedding benchmark HMPD-source: HMPD-source genomic embedding evaluation
- Dataset subset
- HMPD-source Gene-MTEB data used in METAGENE-1 Table 3 (Gene-MTEB genomic embedding benchmark split)
- origin
- Author-reported evaluation
- configuration
- Not reported
- protocol id
- metagene-gene-mteb-task-hmpd-source
- metric implementation
- accuracy
Metadata review: source checked. Unreported conditions prevent automatic comparisons.
Reproduction
- Split
- Not reported
- Adaptation
- Not reported
- Scoring implementation
- accuracy
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.
14 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| attributes.adaptation Frozen mean-pooled last-layer embeddings. Logistic regression is fitted on labelled training data for classification; mini-batch k-means is used for clustering. Context-only references | METAGENE-1 v1: Gene-MTEB complete component tasks Table 3 (S5.T3), row HMPD-source, column DNABERT-2; Section 5.3 paragraphs S5.SS3.p2.1 and S5.SS3.p3.1 Version: arXiv:2501.02045v1 | not individually reviewed No individual claim review recorded author reported Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| attributes.comparison.metric_implementation accuracy Context-only references | METAGENE-1 v1: Gene-MTEB complete component tasks Table 3 (S5.T3), row HMPD-source, column DNABERT-2; Section 5.3 paragraphs S5.SS3.p2.1 and S5.SS3.p3.1 Version: arXiv:2501.02045v1 | not individually reviewed No individual claim review recorded author reported Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| attributes.comparison.protocol_id metagene-gene-mteb-task-hmpd-source Context-only references | METAGENE-1 v1: Gene-MTEB complete component tasks Table 3 (S5.T3), row HMPD-source, column DNABERT-2; Section 5.3 paragraphs S5.SS3.p2.1 and S5.SS3.p3.1 Version: arXiv:2501.02045v1 | not individually reviewed No individual claim review recorded author reported Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| attributes.evidence_overlap Sixteen component tasks from a single paper experiment set. The 25 aggregate table cells are preserved in the review receipt and not republished as independent results. Context-only references | METAGENE-1 v1: Gene-MTEB complete component tasks Table 3 (S5.T3), row HMPD-source, column DNABERT-2; Section 5.3 paragraphs S5.SS3.p2.1 and S5.SS3.p3.1 Version: arXiv:2501.02045v1 | not individually reviewed No individual claim review recorded author reported Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| attributes.origin author_reported Context-only references | METAGENE-1 v1: Gene-MTEB complete component tasks Table 3 (S5.T3), row HMPD-source, column DNABERT-2; Section 5.3 paragraphs S5.SS3.p2.1 and S5.SS3.p3.1 Version: arXiv:2501.02045v1 | not individually reviewed No individual claim review recorded author reported Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| attributes.protocol Frozen model last-hidden-state embeddings, mean pooled. Logistic regression for eight classification tasks and mini-batch k-means for eight clustering tasks. Source paper Section 5.3. Current official gene-mteb implementation corroborates task identities but its commit is not proven identical to the paper evaluator. Exact dataset release, split hash, scored counts and evaluator commit are unreported in the paper. Do not substitute current mutable HF main for the original split. Context-only references | METAGENE-1 v1: Gene-MTEB complete component tasks Table 3 (S5.T3), row HMPD-source, column DNABERT-2; Section 5.3 paragraphs S5.SS3.p2.1 and S5.SS3.p3.1 Version: arXiv:2501.02045v1 | not individually reviewed No individual claim review recorded author reported Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| attributes.published_score_reproduction false Context-only references | METAGENE-1 v1: Gene-MTEB complete component tasks Table 3 (S5.T3), row HMPD-source, column DNABERT-2; Section 5.3 paragraphs S5.SS3.p2.1 and S5.SS3.p3.1 Version: arXiv:2501.02045v1 | not individually reviewed No individual claim review recorded author reported Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| attributes.source_locator Table 3 (S5.T3), row HMPD-source, column DNABERT-2; Section 5.3 paragraphs S5.SS3.p2.1 and S5.SS3.p3.1 Context-only references | METAGENE-1 v1: Gene-MTEB complete component tasks Table 3 (S5.T3), row HMPD-source, column DNABERT-2; Section 5.3 paragraphs S5.SS3.p2.1 and S5.SS3.p3.1 Version: arXiv:2501.02045v1 | not individually reviewed No individual claim review recorded author reported Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| attributes.suite_complete false Context-only references | METAGENE-1 v1: Gene-MTEB complete component tasks Table 3 (S5.T3), row HMPD-source, column DNABERT-2; Section 5.3 paragraphs S5.SS3.p2.1 and S5.SS3.p3.1 Version: arXiv:2501.02045v1 | not individually reviewed No individual claim review recorded author reported Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| description Gene-MTEB genomic embedding benchmark evaluation of DNABERT-2 on HMPD-source genomic embedding evaluation, scored with accuracy. Context-only references | METAGENE-1 v1: Gene-MTEB complete component tasks Table 3 (S5.T3), row HMPD-source, column DNABERT-2; Section 5.3 paragraphs S5.SS3.p2.1 and S5.SS3.p3.1 Version: arXiv:2501.02045v1 | not individually reviewed No individual claim review recorded author reported Audit detailsField: 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 2026-09-23-2b89723c6dd9 · Record review: source checked
1 source records and release history
- METAGENE-1 v1: Gene-MTEB complete component tasks · Original source · arXiv:2501.02045v1
Technical metadata and extraction receipts
Stable ID: metagene-gene-mteb-evaluation-dnabert-2-hmpd-source
- areas
- dna-genomes
- tasks
- HMPD-source genomic embedding evaluation
- origin
- author_reported
- protocol
- Frozen model last-hidden-state embeddings, mean pooled. Logistic regression for eight classification tasks and mini-batch k-means for eight clustering tasks. Source paper Section 5.3. Current official gene-mteb implementation corroborates task identities but its commit is not proven identical to the paper evaluator. Exact dataset release, split hash, scored counts and evaluator commit are unreported in the paper. Do not substitute current mutable HF main for the original split.
- comparison
- protocol id: metagene-gene-mteb-task-hmpd-source; metric implementation: accuracy
- missing metadata
- checkpoint revision: unreported; seeds: unreported; budget: unreported; split manifest: unextracted
- source locator
- Table 3 (S5.T3), row HMPD-source, column DNABERT-2; Section 5.3 paragraphs S5.SS3.p2.1 and S5.SS3.p3.1
- adaptation
- Frozen mean-pooled last-layer embeddings. Logistic regression is fitted on labelled training data for classification; mini-batch k-means is used for clustering.
- evidence overlap
- Sixteen component tasks from a single paper experiment set. The 25 aggregate table cells are preserved in the review receipt and not republished as independent results.
- published score reproduction
- false
- suite complete
- false
Related records
- benchmark: Gene-MTEB genomic embedding benchmark HMPD-source: HMPD-source genomic embedding evaluation
- model: DNABERT-2
- dataset: HMPD-source Gene-MTEB data used in METAGENE-1 Table 3 (Gene-MTEB genomic embedding benchmark split)
- evaluation: DNABERT-2 · Gene-MTEB genomic embedding benchmark HMPD-source · accuracy