{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5SVAOR6X4KN7BQUHCPQQAADJ4U","short_pith_number":"pith:5SVAOR6X","schema_version":"1.0","canonical_sha256":"ecaa0747d7e29bf0c28713e1000069e51790ef791e85345056355990a04907de","source":{"kind":"arxiv","id":"2502.10350","version":1},"attestation_state":"computed","paper":{"title":"OptimOTU: Taxonomically aware OTU clustering with optimized thresholds and a bioinformatics workflow for metabarcoding data","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"q-bio.QM","authors_text":"Brendan Furneaux, Jenni Hultman, Nerea Abrego, Otso Ovaskainen, Panu Somervuo, Sten Anslan, Tomas Roslin","submitted_at":"2025-02-14T18:30:08Z","abstract_excerpt":"To turn environmentally derived metabarcoding data into community matrices for ecological analysis, sequences must first be clustered into operational taxonomic units (OTUs). This task is particularly complex for data including large numbers of taxa with incomplete reference libraries. OptimOTU offers a taxonomically aware approach to OTU clustering. It uses a set of taxonomically identified reference sequences to choose optimal genetic distance thresholds for grouping each ancestor taxon into clusters which most closely match its descendant taxa. Then, query sequences are clustered according "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2502.10350","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"q-bio.QM","submitted_at":"2025-02-14T18:30:08Z","cross_cats_sorted":[],"title_canon_sha256":"088d8a06db7b6e1311a1d614926a541ef0bfcf9bb88e3eed58e50a3db47668a0","abstract_canon_sha256":"b1e53e592392cd241bf1fcf6a2a87424c77df9563f2d14653d249cd422b9f960"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:14:32.957329Z","signature_b64":"gKbOooi9b6bTfwv7G2zyxTCpfuRlsKQBLmFy3IEETKM7OzDypmHgaO5wbGP+X7vXroWwkWTQZS5F7pm9QUSxBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ecaa0747d7e29bf0c28713e1000069e51790ef791e85345056355990a04907de","last_reissued_at":"2026-07-05T10:14:32.956833Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:14:32.956833Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OptimOTU: Taxonomically aware OTU clustering with optimized thresholds and a bioinformatics workflow for metabarcoding data","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"q-bio.QM","authors_text":"Brendan Furneaux, Jenni Hultman, Nerea Abrego, Otso Ovaskainen, Panu Somervuo, Sten Anslan, Tomas Roslin","submitted_at":"2025-02-14T18:30:08Z","abstract_excerpt":"To turn environmentally derived metabarcoding data into community matrices for ecological analysis, sequences must first be clustered into operational taxonomic units (OTUs). This task is particularly complex for data including large numbers of taxa with incomplete reference libraries. OptimOTU offers a taxonomically aware approach to OTU clustering. It uses a set of taxonomically identified reference sequences to choose optimal genetic distance thresholds for grouping each ancestor taxon into clusters which most closely match its descendant taxa. Then, query sequences are clustered according "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.10350","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2502.10350/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2502.10350","created_at":"2026-07-05T10:14:32.956889+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.10350v1","created_at":"2026-07-05T10:14:32.956889+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.10350","created_at":"2026-07-05T10:14:32.956889+00:00"},{"alias_kind":"pith_short_12","alias_value":"5SVAOR6X4KN7","created_at":"2026-07-05T10:14:32.956889+00:00"},{"alias_kind":"pith_short_16","alias_value":"5SVAOR6X4KN7BQUH","created_at":"2026-07-05T10:14:32.956889+00:00"},{"alias_kind":"pith_short_8","alias_value":"5SVAOR6X","created_at":"2026-07-05T10:14:32.956889+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5SVAOR6X4KN7BQUHCPQQAADJ4U","json":"https://pith.science/pith/5SVAOR6X4KN7BQUHCPQQAADJ4U.json","graph_json":"https://pith.science/api/pith-number/5SVAOR6X4KN7BQUHCPQQAADJ4U/graph.json","events_json":"https://pith.science/api/pith-number/5SVAOR6X4KN7BQUHCPQQAADJ4U/events.json","paper":"https://pith.science/paper/5SVAOR6X"},"agent_actions":{"view_html":"https://pith.science/pith/5SVAOR6X4KN7BQUHCPQQAADJ4U","download_json":"https://pith.science/pith/5SVAOR6X4KN7BQUHCPQQAADJ4U.json","view_paper":"https://pith.science/paper/5SVAOR6X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.10350&json=true","fetch_graph":"https://pith.science/api/pith-number/5SVAOR6X4KN7BQUHCPQQAADJ4U/graph.json","fetch_events":"https://pith.science/api/pith-number/5SVAOR6X4KN7BQUHCPQQAADJ4U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5SVAOR6X4KN7BQUHCPQQAADJ4U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5SVAOR6X4KN7BQUHCPQQAADJ4U/action/storage_attestation","attest_author":"https://pith.science/pith/5SVAOR6X4KN7BQUHCPQQAADJ4U/action/author_attestation","sign_citation":"https://pith.science/pith/5SVAOR6X4KN7BQUHCPQQAADJ4U/action/citation_signature","submit_replication":"https://pith.science/pith/5SVAOR6X4KN7BQUHCPQQAADJ4U/action/replication_record"}},"created_at":"2026-07-05T10:14:32.956889+00:00","updated_at":"2026-07-05T10:14:32.956889+00:00"}