Model type
Reference-index taxonomic classifier; this record is the paper-specific evaluated configuration.
Configuration
Kraken2
Kraken 2 is the reference-database taxonomic classifier used in this metagenomic comparison.
Sources
ICCTax: a hierarchical taxonomic classifier for metagenomic sequences on a large language model · 3 Experiments/3.2 Experiments on ICCTax performance/3.2.2 Performance on the complete dataset (paragraph 1); Abstract (paragraph 1)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
ICCTax: a hierarchical taxonomic classifier for metagenomic sequences on a large language model · 2 Methods/2.2 Complementary-view based hierarchical metric learning (paragraph 1); 3 Experiments/3.6 Taxonomic profiling on real metagenomic data (paragraph 1)At a glance
Biological inputs
Metagenomic reads or contigs and a taxonomic reference database
Sources
ICCTax: a hierarchical taxonomic classifier for metagenomic sequences on a large language model · 3 Experiments/3.6 Taxonomic profiling on real metagenomic data (paragraph 1); 3 Experiments/3.2 Experiments on ICCTax performance/3.2.2 Performance on the complete dataset (paragraph 1)Outputs
Taxonomic assignments
Sources
ICCTax: a hierarchical taxonomic classifier for metagenomic sequences on a large language model · 2 Methods/2.3 Compactness loss (paragraph 7); 2 Methods/2.3 Compactness loss (paragraph 2)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 |
|---|---|---|
| Kraken2: Hierarchical metagenomic taxonomy classification Configuration: Kraken2Task: Hierarchical metagenomic taxonomy classificationDataset: ICCTax Complete dataset Macro average precision at genus rank on Complete dataset. Independent external evaluation · Evaluation metadata: needs review | ||
| 70.56 Genus macro AveP Unit: % · Direction: unknown | Uncertainty: not reported in legacy extract Scored: Not reported · Eligible: Not reported | source checkedICCTax: a hierarchical taxonomic classifier for metagenomic sequences on a large language model · Table 2, Kraken2 row, Genus column Source checking is not independent reproduction. |
How it works
How the evaluated method works
Sequence evidence is matched against a taxonomic reference index to assign reads or contigs. Database construction and the chosen confidence/settings remain part of the evaluated configuration.
Sources
ICCTax: a hierarchical taxonomic classifier for metagenomic sequences on a large language model · 2 Methods/2.2 Complementary-view based hierarchical metric learning (paragraph 1); 3 Experiments/3.6 Taxonomic profiling on real metagenomic data (paragraph 1)Underlying method and version boundaries
Kraken 2 classifies sequences against a taxonomic reference index. The software version and the database used to construct that index are distinct reproducibility requirements.
Sources
DerrickWood/kraken2 README.md · README.md; introduction, model description, pretrained-model and usage sections at pinned revisionWhat was evaluated
The linked evaluation record identifies Kraken2: Hierarchical metagenomic taxonomy classification. Its dataset, split, adaptation and evidence origin remain attached to the reported results.
Sources
ICCTax: a hierarchical taxonomic classifier for metagenomic sequences on a large language model · The named evaluation’s methods and comparison table; exact preserved evaluation IDs: evaluation-lit-b3-036Strengths and limitations
Strengths and considerations
- Provides an established reference-based comparator for learned or alignment-based taxonomic methods.
Sources
ICCTax: a hierarchical taxonomic classifier for metagenomic sequences on a large language model · 3 Experiments/3.2 Experiments on ICCTax performance/3.2.2 Performance on the complete dataset (paragraph 1); 3 Experiments/3.2 Experiments on ICCTax performance (paragraph 1)
Limitations and conditions
- Unrepresented organisms and reference contamination can alter assignments; results are specific to the database and query distribution.
Sources
ICCTax: a hierarchical taxonomic classifier for metagenomic sequences on a large language model · 3 Experiments/3.2 Experiments on ICCTax performance/3.2.2 Performance on the complete dataset (paragraph 1); 2 Methods/2.2 Complementary-view based hierarchical metric learning (paragraph 3)
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-8861b9ad9b9c9bSpecifications
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 | Reference-index taxonomic classifier; this record is the paper-specific evaluated configuration.SourcesDerrickWood/kraken2 README.md · README.md model description |
| Architecture / procedure | Sequence evidence is matched against a taxonomic reference index to assign reads or contigs. Database construction and the chosen confidence/settings remain part of the evaluated configuration.SourcesICCTax: a hierarchical taxonomic classifier for metagenomic sequences on a large language model · 2 Methods/2.2 Complementary-view based hierarchical metric learning (paragraph 1); 3 Experiments/3.6 Taxonomic profiling on real metagenomic data (paragraph 1) |
| Biological inputs | Metagenomic reads or contigs and a taxonomic reference databaseSourcesICCTax: a hierarchical taxonomic classifier for metagenomic sequences on a large language model · 3 Experiments/3.6 Taxonomic profiling on real metagenomic data (paragraph 1); 3 Experiments/3.2 Experiments on ICCTax performance/3.2.2 Performance on the complete dataset (paragraph 1) |
| Outputs | Taxonomic assignmentsSourcesICCTax: a hierarchical taxonomic classifier for metagenomic sequences on a large language model · 2 Methods/2.3 Compactness loss (paragraph 7); 2 Methods/2.3 Compactness loss (paragraph 2) |
| Parameters | Not applicable as a neural model size. · Not applicableSourcesICCTax: a hierarchical taxonomic classifier for metagenomic sequences on a large language model · 2 Methods/2.1 HyenaDNA (paragraph 6); 2 Methods/2.1 HyenaDNA (paragraph 5) |
| Known versions / configuration | Kraken2 is the comparison-table label; that label does not specify an immutable weight revision. · Not reported in inspected sourcesSourcesICCTax: a hierarchical taxonomic classifier for metagenomic sequences on a large language model · Model identification in the comparison table and corresponding Methods; immutable checkpoint revision is not supplied by the table label. |
| Training data / fitting | Reference-index construction rather than foundation-model pretraining.SourcesICCTax: a hierarchical taxonomic classifier for metagenomic sequences on a large language model · 3 Experiments/3.2 Experiments on ICCTax performance/3.2.2 Performance on the complete dataset (paragraph 1); 3 Experiments/3.1 Datasets (paragraph 1) |
| Context limits | Not applicable to a pretrained sequence-token window; read/contig lengths and the reference-database or comparison configuration determine the analysed input. · Not applicableSourcesICCTax: a hierarchical taxonomic classifier for metagenomic sequences on a large language model · Table vbaf257-T1 (paragraph 1); 3 Experiments/3.2 Experiments on ICCTax performance/3.2.2 Performance on the complete dataset (paragraph 1) |
| Access | Official upstream implementation and usage documentation: https://github.com/DerrickWood/kraken2/blob/8c190b1b668825935dbf6dee5f969227dc8269bb/README.md. This pinned documentation revision is not automatically the evaluated weight revision.SourcesDerrickWood/kraken2 README.md · README.md; installation, model download and usage instructions |
| Code licence | MIT (upstream repository code at the cited revision; this does not establish every dependency or historical checkpoint licence).SourcesDerrickWood/kraken2 LICENSE · LICENSE; complete licence text |
| Weights licence | Not applicable: uses a reference index rather than a pretrained neural checkpoint. · Not applicableSourcesICCTax: a hierarchical taxonomic classifier for metagenomic sequences on a large language model · 2 Methods/2.1 HyenaDNA (paragraph 6); 2 Methods/2.1 HyenaDNA (paragraph 5) |
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.
20 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 | ICCTax: a hierarchical taxonomic classifier for metagenomic sequences on a large language model 2 Methods/2.2 Complementary-view based hierarchical metric learning (paragraph 1); 3 Experiments/3.6 Taxonomic profiling on real metagenomic data (paragraph 1) Version: version of record | 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 ["Metagenomic reads or contigs and a taxonomic reference database","Kraken2","Taxonomic assignments"] Individual claims | ICCTax: a hierarchical taxonomic classifier for metagenomic sequences on a large language model 2 Methods/2.2 Complementary-view based hierarchical metric learning (paragraph 1); 3 Experiments/3.6 Taxonomic profiling on real metagenomic data (paragraph 1) Version: version of record | 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 | ICCTax: a hierarchical taxonomic classifier for metagenomic sequences on a large language model 2 Methods/2.2 Complementary-view based hierarchical metric learning (paragraph 1); 3 Experiments/3.6 Taxonomic profiling on real metagenomic data (paragraph 1) Version: version of record | 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 Reference-index taxonomic classifier; this record is the paper-specific evaluated configuration. Individual claims | DerrickWood/kraken2 README.md README.md model description Version: 8c190b1b668825935dbf6dee5f969227dc8269bb | 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 Sequence evidence is matched against a taxonomic reference index to assign reads or contigs. Database construction and the chosen confidence/settings remain part of the evaluated configuration. Individual claims | ICCTax: a hierarchical taxonomic classifier for metagenomic sequences on a large language model 2 Methods/2.2 Complementary-view based hierarchical metric learning (paragraph 1); 3 Experiments/3.6 Taxonomic profiling on real metagenomic data (paragraph 1) Version: version of record | 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 Not applicable: uses a reference index rather than a pretrained neural checkpoint. Individual claims | ICCTax: a hierarchical taxonomic classifier for metagenomic sequences on a large language model 2 Methods/2.1 HyenaDNA (paragraph 6); 2 Methods/2.1 HyenaDNA (paragraph 5) Version: version of record | inapplicable 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 Metagenomic reads or contigs and a taxonomic reference database Individual claims | ICCTax: a hierarchical taxonomic classifier for metagenomic sequences on a large language model 3 Experiments/3.6 Taxonomic profiling on real metagenomic data (paragraph 1); 3 Experiments/3.2 Experiments on ICCTax performance/3.2.2 Performance on the complete dataset (paragraph 1) Version: version of record | 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 Taxonomic assignments Individual claims | ICCTax: a hierarchical taxonomic classifier for metagenomic sequences on a large language model 2 Methods/2.3 Compactness loss (paragraph 7); 2 Methods/2.3 Compactness loss (paragraph 2) Version: version of record | 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 Not applicable as a neural model size. Individual claims | ICCTax: a hierarchical taxonomic classifier for metagenomic sequences on a large language model 2 Methods/2.1 HyenaDNA (paragraph 6); 2 Methods/2.1 HyenaDNA (paragraph 5) Version: version of record | inapplicable 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 |
| Known versions / configuration Kraken2 is the comparison-table label; that label does not specify an immutable weight revision. Individual claims | ICCTax: a hierarchical taxonomic classifier for metagenomic sequences on a large language model Model identification in the comparison table and corresponding Methods; immutable checkpoint revision is not supplied by the table label. Version: version of record | 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
- ICCTax: a hierarchical taxonomic classifier for metagenomic sequences on a large language model · Original source · version of record
- DerrickWood/kraken2 README.md · Original source · 8c190b1b668825935dbf6dee5f969227dc8269bb
- DerrickWood/kraken2 LICENSE · Original source · 8c190b1b668825935dbf6dee5f969227dc8269bb
Technical metadata and extraction receipts
Stable ID: reported-model-8861b9ad9b9c9b
- areas
- microbes-communities
- entity level
- method
- version
- Not reported
- reported name
- Kraken2
- 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: icctax-2025; evidence-reported-base-kraken2-readme-md; source locator: 2 Methods/2.2 Complementary-view based hierarchical metric learning (paragraph 1); 3 Experiments/3.6 Taxonomic profiling on real metagenomic data (paragraph 1) | README.md model description | 3 Experiments/3.2 Experiments on ICCTax performance/3.2.2 Performance on the complete dataset (paragraph 1); Abstract (paragraph 1); 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.