Model type
Nearest-neighbour procedure; this record is the paper-specific evaluated configuration.
Configuration
NCD-gzip
NCD-gzip classifies genomic sequences using compression-derived distances and nearest neighbours.
Sources
Normalized compression distance for DNA classification · Introduction (paragraph 3); Methods/Metagenomic training data subsampling/Genome fragmentation (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
Normalized compression distance for DNA classification · Introduction (paragraph 3); Methods/Normalized compression distance (paragraph 3)At a glance
Biological inputs
Nucleotide sequences and a labelled reference set
Sources
Normalized compression distance for DNA classification · Related Works/HyenaDNA (paragraph 1); Introduction (paragraph 3)Outputs
Gene labels or taxonomic classes, depending on the experiment
Sources
Normalized compression distance for DNA classification · Results/Prokaryotic gene classification/Test (paragraph 2); Results/Prokaryotic gene classification/Gene/taxa out (paragraph 1)limited source coverage · Automated source review, 2026-09-16. All specifications and missing details
Evaluations and results
Release 2026-09-17-d277315f7d76 · 2 evaluations · 2 metric rows. Different protocols are not a single leaderboard.
| Metric and finding | Coverage and uncertainty | Evidence |
|---|---|---|
| NCD-gzip: CAMI II superkingdom read classification Configuration: NCD-gzipTask: CAMI II superkingdom read classificationDataset: CAMI II Sample_0 10,000-read subsample Superkingdom-level macro-averaged F1; NCD assigns every read. Author-reported evaluation · Evaluation metadata: needs review | ||
| 0.9804 Macro F1 Unit: unitless · Direction: unknown | Uncertainty: not reported in legacy extract Scored: Not reported · Eligible: Not reported | source checkedNormalized compression distance for DNA classification · Table 5, NCD Superkingdom row, F1 column Source checking is not independent reproduction. |
| NCD-gzip: CAMI II phylum read classification Configuration: NCD-gzipTask: CAMI II phylum read classificationDataset: CAMI II Sample_0 10,000-read subsample Phylum-level macro-averaged F1; distinct taxonomic rank from the other row. Author-reported evaluation · Evaluation metadata: needs review | ||
| 0.1263 Macro F1 Unit: unitless · Direction: unknown | Uncertainty: not reported in legacy extract Scored: Not reported · Eligible: Not reported | source checkedNormalized compression distance for DNA classification · Table 5, NCD Phylum row, F1 column Source checking is not independent reproduction. |
How it works
How the evaluated method works
gzip compression estimates normalised compression distance between sequences; a k-nearest-neighbour rule assigns labels from the reference examples.
Sources
Normalized compression distance for DNA classification · Introduction (paragraph 3); Methods/Normalized compression distance (paragraph 3)What was evaluated
The linked evaluation records identify NCD-gzip: CAMI II superkingdom read classification; NCD-gzip: CAMI II phylum read classification. Its dataset, split, adaptation and evidence origin remain attached to the reported results.
Sources
Normalized compression distance for DNA classification · The named evaluation’s methods and comparison table; exact preserved evaluation IDs: evaluation-lit-b3-023, evaluation-lit-b3-024Strengths and limitations
Strengths and considerations
- Provides a non-neural reference based on shared compressibility rather than a pretrained embedding.
Sources
Normalized compression distance for DNA classification · Methods/Metagenomic training data subsampling/Genome fragmentation (paragraph 2); Results/CAMI dataset (paragraph 3)
Limitations and conditions
- The paper reports O(MN) comparison scaling with reference and query counts, limiting large-database use.
Sources
Normalized compression distance for DNA classification · Methods/Normalized compression distance/NCD timing (paragraph 1); Introduction (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-7b052acf17b5baSpecifications
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 | Nearest-neighbour procedure; this record is the paper-specific evaluated configuration.SourcesNormalized compression distance for DNA classification · Introduction (paragraph 3); Methods/Normalized compression distance (paragraph 3) |
| Architecture / procedure | gzip compression estimates normalised compression distance between sequences; a k-nearest-neighbour rule assigns labels from the reference examples.SourcesNormalized compression distance for DNA classification · Introduction (paragraph 3); Methods/Normalized compression distance (paragraph 3) |
| Biological inputs | Nucleotide sequences and a labelled reference setSourcesNormalized compression distance for DNA classification · Related Works/HyenaDNA (paragraph 1); Introduction (paragraph 3) |
| Outputs | Gene labels or taxonomic classes, depending on the experimentSourcesNormalized compression distance for DNA classification · Results/Prokaryotic gene classification/Test (paragraph 2); Results/Prokaryotic gene classification/Gene/taxa out (paragraph 1) |
| Parameters | Not applicable to the compression/nearest-neighbour method. · Not applicableSourcesNormalized compression distance for DNA classification · Introduction (paragraph 3); Methods/Normalized compression distance (paragraph 2) |
| Known versions / configuration | NCD-gzip is the comparison-table label; that label does not specify an immutable weight revision. · Not reported in inspected sourcesSourcesNormalized compression distance for DNA classification · Model identification in the comparison table and corresponding Methods; immutable checkpoint revision is not supplied by the table label. |
| Training data / fitting | No learned foundation-model weights; the labelled comparison set acts as the reference.SourcesNormalized compression distance for DNA classification · Methods/Datasets/Metagenomic reads (paragraph 1); Results/CAMI dataset (paragraph 3) |
| 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 applicableSourcesNormalized compression distance for DNA classification · Methods/Metagenomic training data subsampling/Genome fragmentation (paragraph 1); Methods/Metagenomic training data subsampling (paragraph 1) |
| Access | Official study implementation and usage documentation: https://github.com/ghproducts/genomics-ncd-gzip/blob/d5bb37be194a2716bc65543c65a26a65eebc1849/README.md. This pinned documentation revision is not automatically the evaluated weight revision.Sourcesghproducts/genomics-ncd-gzip README.md · README.md; installation, model download and usage instructions |
| Code licence | CC0 1.0 (study repository code at the cited revision; this does not establish every dependency or historical checkpoint licence).Sourcesghproducts/genomics-ncd-gzip LICENSE · LICENSE; complete licence text |
| Weights licence | Not applicable: no pretrained weight file is required. · Not applicableSourcesNormalized compression distance for DNA classification · Results/Timing results (paragraph 2); Methods/Normalized compression distance (paragraph 3) |
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.
19 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 | Normalized compression distance for DNA classification Introduction (paragraph 3); Methods/Normalized compression distance (paragraph 3) 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 ["Nucleotide sequences and a labelled reference set","NCD-gzip","Gene labels or taxonomic classes, depending on the experiment"] Individual claims | Normalized compression distance for DNA classification Introduction (paragraph 3); Methods/Normalized compression distance (paragraph 3) 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 | Normalized compression distance for DNA classification Introduction (paragraph 3); Methods/Normalized compression distance (paragraph 3) 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 Nearest-neighbour procedure; this record is the paper-specific evaluated configuration. Individual claims | Normalized compression distance for DNA classification Introduction (paragraph 3); Methods/Normalized compression distance (paragraph 3) 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 |
| Architecture / procedure gzip compression estimates normalised compression distance between sequences; a k-nearest-neighbour rule assigns labels from the reference examples. Individual claims | Normalized compression distance for DNA classification Introduction (paragraph 3); Methods/Normalized compression distance (paragraph 3) 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: no pretrained weight file is required. Individual claims | Normalized compression distance for DNA classification Results/Timing results (paragraph 2); Methods/Normalized compression distance (paragraph 3) 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 Nucleotide sequences and a labelled reference set Individual claims | Normalized compression distance for DNA classification Related Works/HyenaDNA (paragraph 1); Introduction (paragraph 3) 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 Gene labels or taxonomic classes, depending on the experiment Individual claims | Normalized compression distance for DNA classification Results/Prokaryotic gene classification/Test (paragraph 2); Results/Prokaryotic gene classification/Gene/taxa out (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 |
| Parameters Not applicable to the compression/nearest-neighbour method. Individual claims | Normalized compression distance for DNA classification Introduction (paragraph 3); Methods/Normalized compression distance (paragraph 2) 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 NCD-gzip is the comparison-table label; that label does not specify an immutable weight revision. Individual claims | Normalized compression distance for DNA classification 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
- Normalized compression distance for DNA classification · Original source · version of record
- ghproducts/genomics-ncd-gzip README.md · Original source · d5bb37be194a2716bc65543c65a26a65eebc1849
- ghproducts/genomics-ncd-gzip LICENSE · Original source · d5bb37be194a2716bc65543c65a26a65eebc1849
Technical metadata and extraction receipts
Stable ID: reported-model-7b052acf17b5ba
- areas
- microbes-communities
- entity level
- method
- version
- Not reported
- reported name
- NCD-gzip
- 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: ncd-metagenomics-2026; source locator: Introduction (paragraph 3); Methods/Normalized compression distance (paragraph 3) | Introduction (paragraph 3); Methods/Metagenomic training data subsampling/Genome fragmentation (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.