LSHVec: facets.method_types
Facets: method types of LSHVec
["supervised_machine_learning"]
Correct the method type from conventional_pipeline to supervised_machine_learning (use-case baseline review 2026-10-12, table 2). Read in the authors' 2019 preprint; the ACM BCB 2021 version (10.1145/3459930.3469521) returned HTTP 403 and was not read. Section 3 calls the read classifier "(unsupervised)", which Section 3.3 contradicts.
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 |
|---|---|---|
| Claimed field facets.method_types Context-only references | A Vector Representation of DNA Sequences Using Locality Sensitive Hashing Shi and Chen 2019 bioRxiv 10.1101/726729v1, Section 3.3 Taxonomy Classification (p.3): "taxonomy classification is supervised learning"; a one-layer softmax network trained on labelled reads over fastText skip-gram k-mer embeddings (Section 3.2) Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: bioRxiv version 1, posted 2019-08-06 (Europe PMC PPR88003); the only bioRxiv version | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: artifact_sha256 describes one retrieval (2026-10-12T13:29:19Z). The peer-reviewed version (ACM BCB 2021, doi:10.1145/3459930.3469521) returned HTTP 403 and was not read; it may differ from this preprint. bioRxiv rewrites the PDF modification date on each download (a re-retrieval on 2026-10-12 had ModDate of that time and a different hash), so the hash cannot be reproduced by re-downloading; the review's retrieval showed the same text at Sections 3.2 and 3.3. |
| Claimed field facets.method_types Context-only references | Critical Assessment of Metagenome Interpretation: the second round of challenges Shi and Chen 2019 bioRxiv 10.1101/726729v1, Section 3.3 Taxonomy Classification (p.3): "taxonomy classification is supervised learning"; a one-layer softmax network trained on labelled reads over fastText skip-gram k-mer embeddings (Section 3.2) Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Nature Methods 19(4):429, published 2022-04-08; PMC9007738 full-text XML | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Previous value ["conventional_pipeline"] Context-only references | A Vector Representation of DNA Sequences Using Locality Sensitive Hashing Shi and Chen 2019 bioRxiv 10.1101/726729v1, Section 3.3 Taxonomy Classification (p.3): "taxonomy classification is supervised learning"; a one-layer softmax network trained on labelled reads over fastText skip-gram k-mer embeddings (Section 3.2) Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: bioRxiv version 1, posted 2019-08-06 (Europe PMC PPR88003); the only bioRxiv version | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: artifact_sha256 describes one retrieval (2026-10-12T13:29:19Z). The peer-reviewed version (ACM BCB 2021, doi:10.1145/3459930.3469521) returned HTTP 403 and was not read; it may differ from this preprint. bioRxiv rewrites the PDF modification date on each download (a re-retrieval on 2026-10-12 had ModDate of that time and a different hash), so the hash cannot be reproduced by re-downloading; the review's retrieval showed the same text at Sections 3.2 and 3.3. |
| Previous value ["conventional_pipeline"] Context-only references | Critical Assessment of Metagenome Interpretation: the second round of challenges Shi and Chen 2019 bioRxiv 10.1101/726729v1, Section 3.3 Taxonomy Classification (p.3): "taxonomy classification is supervised learning"; a one-layer softmax network trained on labelled reads over fastText skip-gram k-mer embeddings (Section 3.2) Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Nature Methods 19(4):429, published 2022-04-08; PMC9007738 full-text XML | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Source location Shi and Chen 2019 bioRxiv 10.1101/726729v1, Section 3.3 Taxonomy Classification (p.3): "taxonomy classification is supervised learning"; a one-layer softmax network trained on labelled reads over fastText skip-gram k-mer embeddings (Section 3.2) Context-only references | A Vector Representation of DNA Sequences Using Locality Sensitive Hashing Shi and Chen 2019 bioRxiv 10.1101/726729v1, Section 3.3 Taxonomy Classification (p.3): "taxonomy classification is supervised learning"; a one-layer softmax network trained on labelled reads over fastText skip-gram k-mer embeddings (Section 3.2) Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: bioRxiv version 1, posted 2019-08-06 (Europe PMC PPR88003); the only bioRxiv version | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: artifact_sha256 describes one retrieval (2026-10-12T13:29:19Z). The peer-reviewed version (ACM BCB 2021, doi:10.1145/3459930.3469521) returned HTTP 403 and was not read; it may differ from this preprint. bioRxiv rewrites the PDF modification date on each download (a re-retrieval on 2026-10-12 had ModDate of that time and a different hash), so the hash cannot be reproduced by re-downloading; the review's retrieval showed the same text at Sections 3.2 and 3.3. |
| Source location Shi and Chen 2019 bioRxiv 10.1101/726729v1, Section 3.3 Taxonomy Classification (p.3): "taxonomy classification is supervised learning"; a one-layer softmax network trained on labelled reads over fastText skip-gram k-mer embeddings (Section 3.2) Context-only references | Critical Assessment of Metagenome Interpretation: the second round of challenges Shi and Chen 2019 bioRxiv 10.1101/726729v1, Section 3.3 Taxonomy Classification (p.3): "taxonomy classification is supervised learning"; a one-layer softmax network trained on labelled reads over fastText skip-gram k-mer embeddings (Section 3.2) Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Nature Methods 19(4):429, published 2022-04-08; PMC9007738 full-text XML | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Claimed value ["supervised_machine_learning"] Context-only references | A Vector Representation of DNA Sequences Using Locality Sensitive Hashing Shi and Chen 2019 bioRxiv 10.1101/726729v1, Section 3.3 Taxonomy Classification (p.3): "taxonomy classification is supervised learning"; a one-layer softmax network trained on labelled reads over fastText skip-gram k-mer embeddings (Section 3.2) Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: bioRxiv version 1, posted 2019-08-06 (Europe PMC PPR88003); the only bioRxiv version | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: artifact_sha256 describes one retrieval (2026-10-12T13:29:19Z). The peer-reviewed version (ACM BCB 2021, doi:10.1145/3459930.3469521) returned HTTP 403 and was not read; it may differ from this preprint. bioRxiv rewrites the PDF modification date on each download (a re-retrieval on 2026-10-12 had ModDate of that time and a different hash), so the hash cannot be reproduced by re-downloading; the review's retrieval showed the same text at Sections 3.2 and 3.3. |
| Claimed value ["supervised_machine_learning"] Context-only references | Critical Assessment of Metagenome Interpretation: the second round of challenges Shi and Chen 2019 bioRxiv 10.1101/726729v1, Section 3.3 Taxonomy Classification (p.3): "taxonomy classification is supervised learning"; a one-layer softmax network trained on labelled reads over fastText skip-gram k-mer embeddings (Section 3.2) Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Nature Methods 19(4):429, published 2022-04-08; PMC9007738 full-text XML | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Description Correct the method type from conventional_pipeline to supervised_machine_learning (use-case baseline review 2026-10-12, table 2). Read in the authors' 2019 preprint; the ACM BCB 2021 version (10.1145/3459930.3469521) returned HTTP 403 and was not read. Section 3 calls the read classifier "(unsupervised)", which Section 3.3 contradicts. Context-only references | A Vector Representation of DNA Sequences Using Locality Sensitive Hashing Shi and Chen 2019 bioRxiv 10.1101/726729v1, Section 3.3 Taxonomy Classification (p.3): "taxonomy classification is supervised learning"; a one-layer softmax network trained on labelled reads over fastText skip-gram k-mer embeddings (Section 3.2) Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: bioRxiv version 1, posted 2019-08-06 (Europe PMC PPR88003); the only bioRxiv version | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: artifact_sha256 describes one retrieval (2026-10-12T13:29:19Z). The peer-reviewed version (ACM BCB 2021, doi:10.1145/3459930.3469521) returned HTTP 403 and was not read; it may differ from this preprint. bioRxiv rewrites the PDF modification date on each download (a re-retrieval on 2026-10-12 had ModDate of that time and a different hash), so the hash cannot be reproduced by re-downloading; the review's retrieval showed the same text at Sections 3.2 and 3.3. |
| Description Correct the method type from conventional_pipeline to supervised_machine_learning (use-case baseline review 2026-10-12, table 2). Read in the authors' 2019 preprint; the ACM BCB 2021 version (10.1145/3459930.3469521) returned HTTP 403 and was not read. Section 3 calls the read classifier "(unsupervised)", which Section 3.3 contradicts. Context-only references | Critical Assessment of Metagenome Interpretation: the second round of challenges Shi and Chen 2019 bioRxiv 10.1101/726729v1, Section 3.3 Taxonomy Classification (p.3): "taxonomy classification is supervised learning"; a one-layer softmax network trained on labelled reads over fastText skip-gram k-mer embeddings (Section 3.2) Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Nature Methods 19(4):429, published 2022-04-08; PMC9007738 full-text XML | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
Sources and history
Release 2026-11-21-c8bea25e5abb · Record review: source checked
2 source records and release history
- Critical Assessment of Metagenome Interpretation: the second round of challenges · Original source · Nature Methods 19(4):429, published 2022-04-08; PMC9007738 full-text XML
- A Vector Representation of DNA Sequences Using Locality Sensitive Hashing · Original source · bioRxiv version 1, posted 2019-08-06 (Europe PMC PPR88003); the only bioRxiv version
Technical metadata and extraction receipts
Stable ID: metadata-correction-tags-20261012-71eff19615ea6730f78a
- field
- facets.method_types
- previous value
- ["conventional_pipeline"]
- value
- ["supervised_machine_learning"]
- source locator
- Shi and Chen 2019 bioRxiv 10.1101/726729v1, Section 3.3 Taxonomy Classification (p.3): "taxonomy classification is supervised learning"; a one-layer softmax network trained on labelled reads over fastText skip-gram k-mer embeddings (Section 3.2)
- review
- method: source-hash-verification; automated-source-review; reviewer: claude; reviewer note: Separate Claude review agent, independent of the agent that prepared the corrections; no human review claimed; date: 2026-10-12; method note: Compared previous_value with origin/main and the store; re-retrieved the source (bioRxiv stamps each download, so the hash differs from the source record; the cited text is the same) and read the passage in source_locator; checked the new value against the method-type definitions in data/vocab/method-type.ttl.; artifact sha256: adb61dd196d8468efa8ca043981c1fc99e5bac59b80a7649485ceda0e0413c33; retrieval url: https://www.biorxiv.org/content/10.1101/726729v1.full.pdf; note: Correct the method type from conventional_pipeline to supervised_machine_learning (use-case baseline review 2026-10-12, table 2). Read in the authors' 2019 preprint; the ACM BCB 2021 version (10.1145/3459930.3469521) returned HTTP 403 and was not read. Section 3 calls the read classifier "(unsupervised)", which Section 3.3 contradicts. Evidence from docs/reviews/use-cases/baselines-2026-10-12.md. Independent review 2026-10-12: approved. Section 3.3: "taxonomy classification is supervised learning", a one-layer softmax network over k-mer embeddings learned without labels (Section 3.2). See docs/reviews/2026-10-12-method-type-corrections.md.
Related records
- subject: LSHVec