Held-out-clade classification asks how well sequence-based classification works when a defined taxonomic group is absent from training.
Explanatory profile: source reviewed · 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 |
|---|---|
| Entity type | Task guide; concrete protocol identities remain separate.SourcesBarcodeBERT: transformers for biodiversity analyses · Methods: dataset partition and 1-NN probing; Results: unseen-species genus prediction |
| Datasets | No single dataset is fixed by this guide. Select a linked protocol and its versioned data release. · Not applicableSourcesBarcodeBERT: transformers for biodiversity analyses · Methods: dataset partition and 1-NN probing; Results: unseen-species genus prediction |
| Organisms | No shared organism population is defined at this guide level. Record it for each selected dataset. · Not applicableSourcesBarcodeBERT: transformers for biodiversity analyses · Methods: dataset partition and 1-NN probing; Results: unseen-species genus prediction |
| Assays | No single measurement assay is fixed by this guide; the endpoint and assay belong to the selected protocol. · Not applicableSourcesBarcodeBERT: transformers for biodiversity analyses · Methods: dataset partition and 1-NN probing; Results: unseen-species genus prediction |
| Splits | No executable split is attached to this task identity. Use the selected protocol’s split manifest. · Not applicableSourcesBarcodeBERT: transformers for biodiversity analyses · Methods: dataset partition and 1-NN probing; Results: unseen-species genus prediction |
| Allowed inputs | Labelled reference sequences and a taxonomically held-out query set; exact rank and reference-library membership are protocol-specific.SourcesBarcodeBERT: transformers for biodiversity analyses · Methods: dataset partition and 1-NN probing; Results: unseen-species genus prediction |
| Adaptation | No common fitting regime is imposed here. Keep pretrained, frozen, probed, fine-tuned and conventional methods distinct where applicable. · Not applicableSourcesBarcodeBERT: transformers for biodiversity analyses · Methods: dataset partition and 1-NN probing; Results: unseen-species genus prediction |
| Metrics | Classification accuracy or other declared label metrics at the target rank; results at different taxonomic ranks are not interchangeable.SourcesBarcodeBERT: transformers for biodiversity analyses · Methods: dataset partition and 1-NN probing; Results: unseen-species genus prediction |
| Baselines | The BarcodeBERT protocol includes nearest-neighbour evaluation of sequence representations. A proposed alternative comparator is not a completed result.SourcesBarcodeBERT: transformers for biodiversity analyses · Methods: dataset partition and 1-NN probing; Results: unseen-species genus prediction |
Conceptual task guide. Dataset preparation, parameters and scoring must come from a separately identified protocol.
Specify both the taxonomic level that is withheld and the level that is predicted. BarcodeBERT’s unseen-species genus probe illustrates why these differ: species can be unseen while their genera remain represented. A benchmark must document which reference sequences and labels remain available before interpreting a result as taxonomic generalisation.
This is a task guide, not a single versioned benchmark protocol. The connected resources provide examples or concrete procedures. A candidate method or proposed control is not evidence that an evaluation has been completed.
Release 2026-09-17-d277315f7d76 · 0 evaluations · 0 metric rows. Different protocols are not a single leaderboard.
No evaluations linked in this release.
Last literature check: 2026-09-17. Primary-paper discovery and source inspection. Source-checked results are not independently reproduced experiments.
| Paper or primary resource | Version | Reference |
|---|---|---|
| BarcodeBERT: transformers for biodiversity analyses | journal full text in PMC | Read source DOI: 10.1093/bioadv/vbag054 |
broad task primary protocol linked
Reviewed named primary documentation and existing protocol records. Editorial task scope is distinguished from source-reported procedures. No model execution or new numerical result; a reviewed guide is not a complete runnable protocol.
Stable record: catalog-task-heldout-cladeApplicability is distinct from a completed evaluation.
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.
17 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Diagram caption Conceptual task guide. Dataset preparation, parameters and scoring must come from a separately identified protocol. Individual claims | BarcodeBERT: transformers for biodiversity analyses Methods: dataset partition and 1-NN probing; Results: unseen-species genus prediction Version: journal full text in PMC | source checked automated source review · 2026-09-16 Audit detailsReviewed named primary documentation and existing protocol records. Editorial task scope is distinguished from source-reported procedures. No model execution or new numerical result; a reviewed guide is not a complete runnable protocol. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Diagram steps ["Choose held-out and predicted ranks","Construct reference and query sets","Apply the declared classifier or probe","Score at the specified taxonomic rank"] Individual claims | BarcodeBERT: transformers for biodiversity analyses Methods: dataset partition and 1-NN probing; Results: unseen-species genus prediction Version: journal full text in PMC | source checked automated source review · 2026-09-16 Audit detailsReviewed named primary documentation and existing protocol records. Editorial task scope is distinguished from source-reported procedures. No model execution or new numerical result; a reviewed guide is not a complete runnable protocol. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Diagram title Conceptual evaluation workflow Individual claims | BarcodeBERT: transformers for biodiversity analyses Methods: dataset partition and 1-NN probing; Results: unseen-species genus prediction Version: journal full text in PMC | source checked automated source review · 2026-09-16 Audit detailsReviewed named primary documentation and existing protocol records. Editorial task scope is distinguished from source-reported procedures. No model execution or new numerical result; a reviewed guide is not a complete runnable protocol. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Entity type Task guide; concrete protocol identities remain separate. Individual claims | BarcodeBERT: transformers for biodiversity analyses Methods: dataset partition and 1-NN probing; Results: unseen-species genus prediction Version: journal full text in PMC | source checked automated source review · 2026-09-16 Audit detailsReviewed named primary documentation and existing protocol records. Editorial task scope is distinguished from source-reported procedures. No model execution or new numerical result; a reviewed guide is not a complete runnable protocol. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Datasets No single dataset is fixed by this guide. Select a linked protocol and its versioned data release. Individual claims | BarcodeBERT: transformers for biodiversity analyses Methods: dataset partition and 1-NN probing; Results: unseen-species genus prediction Version: journal full text in PMC | inapplicable automated source review · 2026-09-16 Audit detailsReviewed named primary documentation and existing protocol records. Editorial task scope is distinguished from source-reported procedures. No model execution or new numerical result; a reviewed guide is not a complete runnable protocol. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Organisms No shared organism population is defined at this guide level. Record it for each selected dataset. Individual claims | BarcodeBERT: transformers for biodiversity analyses Methods: dataset partition and 1-NN probing; Results: unseen-species genus prediction Version: journal full text in PMC | inapplicable automated source review · 2026-09-16 Audit detailsReviewed named primary documentation and existing protocol records. Editorial task scope is distinguished from source-reported procedures. No model execution or new numerical result; a reviewed guide is not a complete runnable protocol. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Assays No single measurement assay is fixed by this guide; the endpoint and assay belong to the selected protocol. Individual claims | BarcodeBERT: transformers for biodiversity analyses Methods: dataset partition and 1-NN probing; Results: unseen-species genus prediction Version: journal full text in PMC | inapplicable automated source review · 2026-09-16 Audit detailsReviewed named primary documentation and existing protocol records. Editorial task scope is distinguished from source-reported procedures. No model execution or new numerical result; a reviewed guide is not a complete runnable protocol. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Splits No executable split is attached to this task identity. Use the selected protocol’s split manifest. Individual claims | BarcodeBERT: transformers for biodiversity analyses Methods: dataset partition and 1-NN probing; Results: unseen-species genus prediction Version: journal full text in PMC | inapplicable automated source review · 2026-09-16 Audit detailsReviewed named primary documentation and existing protocol records. Editorial task scope is distinguished from source-reported procedures. No model execution or new numerical result; a reviewed guide is not a complete runnable protocol. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Allowed inputs Labelled reference sequences and a taxonomically held-out query set; exact rank and reference-library membership are protocol-specific. Individual claims | BarcodeBERT: transformers for biodiversity analyses Methods: dataset partition and 1-NN probing; Results: unseen-species genus prediction Version: journal full text in PMC | source checked automated source review · 2026-09-16 Audit detailsReviewed named primary documentation and existing protocol records. Editorial task scope is distinguished from source-reported procedures. No model execution or new numerical result; a reviewed guide is not a complete runnable protocol. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Adaptation No common fitting regime is imposed here. Keep pretrained, frozen, probed, fine-tuned and conventional methods distinct where applicable. Individual claims | BarcodeBERT: transformers for biodiversity analyses Methods: dataset partition and 1-NN probing; Results: unseen-species genus prediction Version: journal full text in PMC | inapplicable automated source review · 2026-09-16 Audit detailsReviewed named primary documentation and existing protocol records. Editorial task scope is distinguished from source-reported procedures. No model execution or new numerical result; a reviewed guide is not a complete runnable protocol. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
Release 2026-09-17-d277315f7d76 · Record review: discovered
Stable ID: catalog-task-heldout-clade