{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3KIZBJ2HTWOYRUHPONEXZEKQVS","short_pith_number":"pith:3KIZBJ2H","schema_version":"1.0","canonical_sha256":"da9190a7479d9d88d0ef73497c9150ac980173d217d424d69fc3327482f83a60","source":{"kind":"arxiv","id":"2406.12723","version":6},"attestation_state":"computed","paper":{"title":"BIOSCAN-5M: A Multimodal Dataset for Insect Biodiversity","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","q-bio.PE"],"primary_cat":"cs.LG","authors_text":"Angel X. Chang, Austin T. Wang, Dirk Steinke, Graham W. Taylor, Iuliia Zarubiieva, Joakim Bruslund Haurum, Lila Kari, Nicholas Pellegrino, Pablo Millan Arias, Paul Fieguth, Scott C. Lowe, Zahra Gharaee, ZeMing Gong","submitted_at":"2024-06-18T15:45:21Z","abstract_excerpt":"As part of an ongoing worldwide effort to comprehend and monitor insect biodiversity, this paper presents the BIOSCAN-5M Insect dataset to the machine learning community and establish several benchmark tasks. BIOSCAN-5M is a comprehensive dataset containing multi-modal information for over 5 million insect specimens, and it significantly expands existing image-based biological datasets by including taxonomic labels, raw nucleotide barcode sequences, assigned barcode index numbers, geographical, and size information. We propose three benchmark experiments to demonstrate the impact of the multi-"},"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":"2406.12723","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-18T15:45:21Z","cross_cats_sorted":["cs.AI","cs.CV","q-bio.PE"],"title_canon_sha256":"ef504e44a73db9a7c820bbfed6480de7140f7ddb6b11f22f8e173e2756f44677","abstract_canon_sha256":"01f90bdccd8322e6ed8572b945b1da3691e910d713c8295b00c0612812d6939b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:25:07.389887Z","signature_b64":"e8s1pznW0Qz/V0W72t/MxVfthjPaIboXNZesgEhgkHfGnt33SFbRRYA55AKUZwIwUqH9cP25NQEOh5rsEfFXBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da9190a7479d9d88d0ef73497c9150ac980173d217d424d69fc3327482f83a60","last_reissued_at":"2026-07-05T10:25:07.389271Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:25:07.389271Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BIOSCAN-5M: A Multimodal Dataset for Insect Biodiversity","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","q-bio.PE"],"primary_cat":"cs.LG","authors_text":"Angel X. Chang, Austin T. Wang, Dirk Steinke, Graham W. Taylor, Iuliia Zarubiieva, Joakim Bruslund Haurum, Lila Kari, Nicholas Pellegrino, Pablo Millan Arias, Paul Fieguth, Scott C. Lowe, Zahra Gharaee, ZeMing Gong","submitted_at":"2024-06-18T15:45:21Z","abstract_excerpt":"As part of an ongoing worldwide effort to comprehend and monitor insect biodiversity, this paper presents the BIOSCAN-5M Insect dataset to the machine learning community and establish several benchmark tasks. BIOSCAN-5M is a comprehensive dataset containing multi-modal information for over 5 million insect specimens, and it significantly expands existing image-based biological datasets by including taxonomic labels, raw nucleotide barcode sequences, assigned barcode index numbers, geographical, and size information. We propose three benchmark experiments to demonstrate the impact of the multi-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.12723","kind":"arxiv","version":6},"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/2406.12723/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":"2406.12723","created_at":"2026-07-05T10:25:07.389342+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.12723v6","created_at":"2026-07-05T10:25:07.389342+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.12723","created_at":"2026-07-05T10:25:07.389342+00:00"},{"alias_kind":"pith_short_12","alias_value":"3KIZBJ2HTWOY","created_at":"2026-07-05T10:25:07.389342+00:00"},{"alias_kind":"pith_short_16","alias_value":"3KIZBJ2HTWOYRUHP","created_at":"2026-07-05T10:25:07.389342+00:00"},{"alias_kind":"pith_short_8","alias_value":"3KIZBJ2H","created_at":"2026-07-05T10:25:07.389342+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/3KIZBJ2HTWOYRUHPONEXZEKQVS","json":"https://pith.science/pith/3KIZBJ2HTWOYRUHPONEXZEKQVS.json","graph_json":"https://pith.science/api/pith-number/3KIZBJ2HTWOYRUHPONEXZEKQVS/graph.json","events_json":"https://pith.science/api/pith-number/3KIZBJ2HTWOYRUHPONEXZEKQVS/events.json","paper":"https://pith.science/paper/3KIZBJ2H"},"agent_actions":{"view_html":"https://pith.science/pith/3KIZBJ2HTWOYRUHPONEXZEKQVS","download_json":"https://pith.science/pith/3KIZBJ2HTWOYRUHPONEXZEKQVS.json","view_paper":"https://pith.science/paper/3KIZBJ2H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.12723&json=true","fetch_graph":"https://pith.science/api/pith-number/3KIZBJ2HTWOYRUHPONEXZEKQVS/graph.json","fetch_events":"https://pith.science/api/pith-number/3KIZBJ2HTWOYRUHPONEXZEKQVS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3KIZBJ2HTWOYRUHPONEXZEKQVS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3KIZBJ2HTWOYRUHPONEXZEKQVS/action/storage_attestation","attest_author":"https://pith.science/pith/3KIZBJ2HTWOYRUHPONEXZEKQVS/action/author_attestation","sign_citation":"https://pith.science/pith/3KIZBJ2HTWOYRUHPONEXZEKQVS/action/citation_signature","submit_replication":"https://pith.science/pith/3KIZBJ2HTWOYRUHPONEXZEKQVS/action/replication_record"}},"created_at":"2026-07-05T10:25:07.389342+00:00","updated_at":"2026-07-05T10:25:07.389342+00:00"}