{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:V33FKYDQUWF5EFQ7OCPIDE6VHV","short_pith_number":"pith:V33FKYDQ","schema_version":"1.0","canonical_sha256":"aef6556070a58bd2161f709e8193d53d7af2ef1bb72550dbc58305d76a22c5c0","source":{"kind":"arxiv","id":"2508.16744","version":1},"attestation_state":"computed","paper":{"title":"Hyperbolic Multimodal Representation Learning for Biological Taxonomies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Angel X. Chang, Austin T. Wang, Chuanqi Tang, Graham W. Taylor, Joakim Bruslund Haurum, Nicholas Pellegrino, Scott C. Lowe, Xiaoliang Huo, ZeMing Gong","submitted_at":"2025-08-22T18:52:50Z","abstract_excerpt":"Taxonomic classification in biodiversity research involves organizing biological specimens into structured hierarchies based on evidence, which can come from multiple modalities such as images and genetic information. We investigate whether hyperbolic networks can provide a better embedding space for such hierarchical models. Our method embeds multimodal inputs into a shared hyperbolic space using contrastive and a novel stacked entailment-based objective. Experiments on the BIOSCAN-1M dataset show that hyperbolic embedding achieves competitive performance with Euclidean baselines, and outperf"},"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":"2508.16744","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-22T18:52:50Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"f9a92c242538828f92f8844e940da10c3855fdf85babca647183bcef4eab1a34","abstract_canon_sha256":"89906aa6fbf5ec33b505488a9dcf42574c0d90901de51354ce8460aeecf051c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:58:02.818043Z","signature_b64":"JFtjTHI89fDB9mWSgNSJGHhg05hU0QoKoSX6qA13PPRVi4ze5L2ROIoKb0zYuD0urblPqYXyHjagFyDO6GbWBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aef6556070a58bd2161f709e8193d53d7af2ef1bb72550dbc58305d76a22c5c0","last_reissued_at":"2026-07-05T11:58:02.817596Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:58:02.817596Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hyperbolic Multimodal Representation Learning for Biological Taxonomies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Angel X. Chang, Austin T. Wang, Chuanqi Tang, Graham W. Taylor, Joakim Bruslund Haurum, Nicholas Pellegrino, Scott C. Lowe, Xiaoliang Huo, ZeMing Gong","submitted_at":"2025-08-22T18:52:50Z","abstract_excerpt":"Taxonomic classification in biodiversity research involves organizing biological specimens into structured hierarchies based on evidence, which can come from multiple modalities such as images and genetic information. We investigate whether hyperbolic networks can provide a better embedding space for such hierarchical models. Our method embeds multimodal inputs into a shared hyperbolic space using contrastive and a novel stacked entailment-based objective. Experiments on the BIOSCAN-1M dataset show that hyperbolic embedding achieves competitive performance with Euclidean baselines, and outperf"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.16744","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/2508.16744/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":"2508.16744","created_at":"2026-07-05T11:58:02.817653+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.16744v1","created_at":"2026-07-05T11:58:02.817653+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.16744","created_at":"2026-07-05T11:58:02.817653+00:00"},{"alias_kind":"pith_short_12","alias_value":"V33FKYDQUWF5","created_at":"2026-07-05T11:58:02.817653+00:00"},{"alias_kind":"pith_short_16","alias_value":"V33FKYDQUWF5EFQ7","created_at":"2026-07-05T11:58:02.817653+00:00"},{"alias_kind":"pith_short_8","alias_value":"V33FKYDQ","created_at":"2026-07-05T11:58:02.817653+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/V33FKYDQUWF5EFQ7OCPIDE6VHV","json":"https://pith.science/pith/V33FKYDQUWF5EFQ7OCPIDE6VHV.json","graph_json":"https://pith.science/api/pith-number/V33FKYDQUWF5EFQ7OCPIDE6VHV/graph.json","events_json":"https://pith.science/api/pith-number/V33FKYDQUWF5EFQ7OCPIDE6VHV/events.json","paper":"https://pith.science/paper/V33FKYDQ"},"agent_actions":{"view_html":"https://pith.science/pith/V33FKYDQUWF5EFQ7OCPIDE6VHV","download_json":"https://pith.science/pith/V33FKYDQUWF5EFQ7OCPIDE6VHV.json","view_paper":"https://pith.science/paper/V33FKYDQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.16744&json=true","fetch_graph":"https://pith.science/api/pith-number/V33FKYDQUWF5EFQ7OCPIDE6VHV/graph.json","fetch_events":"https://pith.science/api/pith-number/V33FKYDQUWF5EFQ7OCPIDE6VHV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V33FKYDQUWF5EFQ7OCPIDE6VHV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V33FKYDQUWF5EFQ7OCPIDE6VHV/action/storage_attestation","attest_author":"https://pith.science/pith/V33FKYDQUWF5EFQ7OCPIDE6VHV/action/author_attestation","sign_citation":"https://pith.science/pith/V33FKYDQUWF5EFQ7OCPIDE6VHV/action/citation_signature","submit_replication":"https://pith.science/pith/V33FKYDQUWF5EFQ7OCPIDE6VHV/action/replication_record"}},"created_at":"2026-07-05T11:58:02.817653+00:00","updated_at":"2026-07-05T11:58:02.817653+00:00"}