Model type
DNA state-space model; this record is the paper-specific evaluated configuration.
Configuration
Caduceus-Ph
This fine-tuned genomic model is evaluated on long-range DNA tasks in DNALongBench.
Sources
DNALongBench: A Benchmark Suite for Long-Range DNA Prediction Tasks · Proposed Dataset: DNALongBench (paragraph 3); Introduction (paragraph 5)How it worksEvaluated procedure (conceptual)
Conceptual input–method–output guide. Check the procedure text and linked evaluation for fitted components, additional inputs and exact settings.
Sources
DNALongBench: A Benchmark Suite for Long-Range DNA Prediction Tasks · Experiments/Benchmarking Results/The Expert Model achieves the highest scores on all tasks. (paragraph 1); Conclusion (paragraph 1)At a glance
Biological inputs
DNA windows for enhancer–gene, eQTL, chromatin organisation, activity or initiation tasks
Sources
DNALongBench: A Benchmark Suite for Long-Range DNA Prediction Tasks · Conclusion (paragraph 1); Abstract (paragraph 1)Outputs
Task-specific long-range genomic predictions
Sources
DNALongBench: A Benchmark Suite for Long-Range DNA Prediction Tasks · Introduction (paragraph 5); Proposed Dataset: DNALongBench (paragraph 1)limited source coverage · Automated source review, 2026-09-16. All specifications and missing details
Evaluations and results
Release 2026-09-17-d277315f7d76 · 1 evaluation · 1 metric row. Different protocols are not a single leaderboard.
| Metric and finding | Coverage and uncertainty | Evidence |
|---|---|---|
| Caduceus-Ph: Enhancer-target gene prediction Long-range ETGP benchmark; source table reports AUROC. Independent external evaluation · Evaluation metadata: needs review | ||
| 0.826 AUROC Unit: unitless · Direction: unknown | Uncertainty: not reported in legacy extract Scored: Not reported · Eligible: Not reported | source checkedDNALongBench: A Benchmark Suite for Long-Range DNA Prediction Tasks · Table 3, Caduceus-Ph row, ETGP column Source checking is not independent reproduction. |
How it works
How the evaluated method works
The DNA backbone is fine-tuned for task-specific outputs, with expert models and a CNN as separate controls.
Sources
DNALongBench: A Benchmark Suite for Long-Range DNA Prediction Tasks · Experiments/Benchmarking Results/The Expert Model achieves the highest scores on all tasks. (paragraph 1); Conclusion (paragraph 1)Underlying method and version boundaries
Caduceus exposes distinct Ph and PS configurations. The documented Ph-131k checkpoint uses 16 layers, width 256 and reverse-complement data augmentation; PS implements reverse-complement equivariance. These training choices are not interchangeable.
Sources
kuleshov-group/caduceus README.md · README.md; introduction, model description, pretrained-model and usage sections at pinned revisionWhat was evaluated
The linked evaluation record identifies Caduceus-Ph: Enhancer-target gene prediction. Its dataset, split, adaptation and evidence origin remain attached to the reported results.
Sources
DNALongBench: A Benchmark Suite for Long-Range DNA Prediction Tasks · The named evaluation’s methods and comparison table; exact preserved evaluation IDs: evaluation-lit-008Strengths and limitations
Strengths and considerations
- Tests genomic tasks that require information over long distances.
Sources
DNALongBench: A Benchmark Suite for Long-Range DNA Prediction Tasks · Proposed Dataset: DNALongBench (paragraph 3); Introduction (paragraph 4)
Limitations and conditions
- Nominal long input support does not prove effective long-range reasoning; specialist models outperform the tested foundation models in the reported benchmark.
Sources
DNALongBench: A Benchmark Suite for Long-Range DNA Prediction Tasks · Proposed Dataset: DNALongBench (paragraph 3); Introduction (paragraph 5)
Profile review details
Primary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction.
Stable record: reported-model-a7cfacf25d97adSpecifications
Inputs, training, access and other details
Explanatory profile: limited source coverage · Automated source review, 2026-09-16. Review applies to the cited claims; unresolved fields are listed below. Numerical results retain their own review status.
| Property | Description and evidence |
|---|---|
| Model type | DNA state-space model; this record is the paper-specific evaluated configuration.Sourceskuleshov-group/caduceus README.md · README.md model description |
| Architecture / procedure | The DNA backbone is fine-tuned for task-specific outputs, with expert models and a CNN as separate controls.SourcesDNALongBench: A Benchmark Suite for Long-Range DNA Prediction Tasks · Experiments/Benchmarking Results/The Expert Model achieves the highest scores on all tasks. (paragraph 1); Conclusion (paragraph 1) |
| Biological inputs | DNA windows for enhancer–gene, eQTL, chromatin organisation, activity or initiation tasksSourcesDNALongBench: A Benchmark Suite for Long-Range DNA Prediction Tasks · Conclusion (paragraph 1); Abstract (paragraph 1) |
| Outputs | Task-specific long-range genomic predictionsSourcesDNALongBench: A Benchmark Suite for Long-Range DNA Prediction Tasks · Introduction (paragraph 5); Proposed Dataset: DNALongBench (paragraph 1) |
| Parameters | An aggregate parameter total for this exact evaluated configuration is not established by the inspected sources. · Not reported in inspected sourcesSources (2)DNALongBench: A Benchmark Suite for Long-Range DNA Prediction Tasks; kuleshov-group/caduceus README.md · Complete primary text and named comparison table; inspected for aggregate parameter count (component sizes are not added without an exact configuration); README.md at pinned repository revision |
| Known versions / configuration | Caduceus-Ph is the comparison-table label; that label does not specify an immutable weight revision. · Not reported in inspected sourcesSourcesDNALongBench: A Benchmark Suite for Long-Range DNA Prediction Tasks · Model identification in the comparison table and corresponding Methods; immutable checkpoint revision is not supplied by the table label. |
| Training data / fitting | Task-specific fine-tuning on the DNALongBench splits, separate from original genome pretraining.SourcesDNALongBench: A Benchmark Suite for Long-Range DNA Prediction Tasks · Proposed Dataset: DNALongBench (paragraph 4); Proposed Dataset: DNALongBench/3D Chromatin Contact Map Prediction (paragraph 1) |
| Context limits | A maximum input/context length for this exact evaluated configuration is not established by the inspected sources. · Not reported in inspected sourcesSources (2)DNALongBench: A Benchmark Suite for Long-Range DNA Prediction Tasks; kuleshov-group/caduceus README.md · Complete primary text and named comparison table; inspected for explicit maximum input length (dataset lengths and family-wide limits are not substituted); README.md at pinned repository revision |
| Access | Official upstream implementation and usage documentation: https://github.com/kuleshov-group/caduceus/blob/0060a6d8079b6a040fc55d505e15972a327b70a6/README.md. This pinned documentation revision is not automatically the evaluated weight revision.Sourceskuleshov-group/caduceus README.md · README.md; installation, model download and usage instructions |
| Code licence | Apache 2.0 (upstream repository code at the cited revision; this does not establish every dependency or historical checkpoint licence).Sourceskuleshov-group/caduceus LICENSE · LICENSE; complete licence text |
| Weights licence | The inspected model-access documentation does not explicitly identify terms for this exact evaluated checkpoint or fitted head; repository code terms are shown separately. · Not reported in inspected sourcesSourceskuleshov-group/caduceus README.md · README.md; checkpoint/access documentation and licence scope |
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.
22 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Diagram caption Conceptual input–method–output guide. Check the procedure text and linked evaluation for fitted components, additional inputs and exact settings. Individual claims | DNALongBench: A Benchmark Suite for Long-Range DNA Prediction Tasks Experiments/Benchmarking Results/The Expert Model achieves the highest scores on all tasks. (paragraph 1); Conclusion (paragraph 1) Version: PMC11741265.1 | source checked automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Diagram steps ["DNA windows for enhancer–gene, eQTL, chromatin organisation, activity or initiation tasks","Caduceus-Ph","Task-specific long-range genomic predictions"] Individual claims | DNALongBench: A Benchmark Suite for Long-Range DNA Prediction Tasks Experiments/Benchmarking Results/The Expert Model achieves the highest scores on all tasks. (paragraph 1); Conclusion (paragraph 1) Version: PMC11741265.1 | source checked automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Diagram title Evaluated procedure (conceptual) Individual claims | DNALongBench: A Benchmark Suite for Long-Range DNA Prediction Tasks Experiments/Benchmarking Results/The Expert Model achieves the highest scores on all tasks. (paragraph 1); Conclusion (paragraph 1) Version: PMC11741265.1 | source checked automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Model type DNA state-space model; this record is the paper-specific evaluated configuration. Individual claims | kuleshov-group/caduceus README.md README.md model description Version: 0060a6d8079b6a040fc55d505e15972a327b70a6 | source checked automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Architecture / procedure The DNA backbone is fine-tuned for task-specific outputs, with expert models and a CNN as separate controls. Individual claims | DNALongBench: A Benchmark Suite for Long-Range DNA Prediction Tasks Experiments/Benchmarking Results/The Expert Model achieves the highest scores on all tasks. (paragraph 1); Conclusion (paragraph 1) Version: PMC11741265.1 | source checked automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Weights licence The inspected model-access documentation does not explicitly identify terms for this exact evaluated checkpoint or fitted head; repository code terms are shown separately. Individual claims | kuleshov-group/caduceus README.md README.md; checkpoint/access documentation and licence scope Version: 0060a6d8079b6a040fc55d505e15972a327b70a6 | unreported automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Biological inputs DNA windows for enhancer–gene, eQTL, chromatin organisation, activity or initiation tasks Individual claims | DNALongBench: A Benchmark Suite for Long-Range DNA Prediction Tasks Conclusion (paragraph 1); Abstract (paragraph 1) Version: PMC11741265.1 | source checked automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Outputs Task-specific long-range genomic predictions Individual claims | DNALongBench: A Benchmark Suite for Long-Range DNA Prediction Tasks Introduction (paragraph 5); Proposed Dataset: DNALongBench (paragraph 1) Version: PMC11741265.1 | source checked automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Parameters An aggregate parameter total for this exact evaluated configuration is not established by the inspected sources. Individual claims | DNALongBench: A Benchmark Suite for Long-Range DNA Prediction Tasks Complete primary text and named comparison table; inspected for aggregate parameter count (component sizes are not added without an exact configuration); README.md at pinned repository revision Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: PMC11741265.1 | unreported automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Parameters An aggregate parameter total for this exact evaluated configuration is not established by the inspected sources. Individual claims | kuleshov-group/caduceus README.md Complete primary text and named comparison table; inspected for aggregate parameter count (component sizes are not added without an exact configuration); README.md at pinned repository revision Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 0060a6d8079b6a040fc55d505e15972a327b70a6 | unreported automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
Sources and history
Release 2026-09-17-d277315f7d76 · Record review: needs review
3 source records and release history
- DNALongBench: A Benchmark Suite for Long-Range DNA Prediction Tasks · Original source · PMC11741265.1
- kuleshov-group/caduceus README.md · Original source · 0060a6d8079b6a040fc55d505e15972a327b70a6
- kuleshov-group/caduceus LICENSE · Original source · 0060a6d8079b6a040fc55d505e15972a327b70a6
Technical metadata and extraction receipts
Stable ID: reported-model-a7cfacf25d97ad
- areas
- dna-genomes
- entity level
- method
- version
- Not reported
- reported name
- Caduceus-Ph
- historical missing metadata
- version: not_reported_in_legacy_extract; checkpoint revision: not_reported_in_legacy_extract; training data: not_reported_in_legacy_extract; licence: not_reported_in_legacy_extract
- metadata review scope
- historical_missing_metadata preserves the original discovery state. Current descriptive evidence and missingness are recorded in profile.facts; numerical-result review is separate.
- legacy kinds
- model
- entity classification
- review date: 2026-09-17; rationale: This source-scoped entry preserves the method/configuration actually named in an evaluation. It is neither a global family identity nor proof of an immutable checkpoint; the linked evaluation retains adaptation, fitting and scoring details.; source ids: dnalongbench-2025; evidence-reported-base-caduceus-readme-md; source locator: Experiments/Benchmarking Results/The Expert Model achieves the highest scores on all tasks. (paragraph 1); Conclusion (paragraph 1) | README.md model description | Proposed Dataset: DNALongBench (paragraph 3); Introduction (paragraph 5); ambiguities: Configuration means the source-labelled evaluated identity. It does not establish missing checkpoint hashes, default settings or equivalence to same-named records in other papers.