{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XMAWJUOUA35E2P3IIVZT2VYDPE","short_pith_number":"pith:XMAWJUOU","schema_version":"1.0","canonical_sha256":"bb0164d1d406fa4d3f6845733d5703791736fac65795740b7cd9a04f8754f742","source":{"kind":"arxiv","id":"2402.17810","version":2},"attestation_state":"computed","paper":{"title":"BioT5+: Towards Generalized Biological Understanding with IUPAC Integration and Multi-task Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CE","cs.LG","q-bio.BM"],"primary_cat":"q-bio.QM","authors_text":"Jinhua Zhu, Kaiyuan Gao, Lijun Wu, Qizhi Pei, Rui Yan, Shufang Xie, Tao Qin, Xiaozhuan Liang, Yin Fang","submitted_at":"2024-02-27T12:43:09Z","abstract_excerpt":"Recent research trends in computational biology have increasingly focused on integrating text and bio-entity modeling, especially in the context of molecules and proteins. However, previous efforts like BioT5 faced challenges in generalizing across diverse tasks and lacked a nuanced understanding of molecular structures, particularly in their textual representations (e.g., IUPAC). This paper introduces BioT5+, an extension of the BioT5 framework, tailored to enhance biological research and drug discovery. BioT5+ incorporates several novel features: integration of IUPAC names for molecular unde"},"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":"2402.17810","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.QM","submitted_at":"2024-02-27T12:43:09Z","cross_cats_sorted":["cs.AI","cs.CE","cs.LG","q-bio.BM"],"title_canon_sha256":"4bb54f334ae4b14d7a3cacbdcb32013b973ceab9826166190868a3849b9cf087","abstract_canon_sha256":"35fa1498a8e21e76ada9c98073bc8cf6164c6b48a2b8d94fe7bdcdd9ff792852"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:32.554235Z","signature_b64":"xG09QCVT7dnKCBTobZy76jnHxsz0DGUQVCcFY83L4OIKyc4MZdE7ytv4MxlY6SlT9alPiMvnexSnyDbK08GPCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb0164d1d406fa4d3f6845733d5703791736fac65795740b7cd9a04f8754f742","last_reissued_at":"2026-07-05T08:25:32.553778Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:32.553778Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BioT5+: Towards Generalized Biological Understanding with IUPAC Integration and Multi-task Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CE","cs.LG","q-bio.BM"],"primary_cat":"q-bio.QM","authors_text":"Jinhua Zhu, Kaiyuan Gao, Lijun Wu, Qizhi Pei, Rui Yan, Shufang Xie, Tao Qin, Xiaozhuan Liang, Yin Fang","submitted_at":"2024-02-27T12:43:09Z","abstract_excerpt":"Recent research trends in computational biology have increasingly focused on integrating text and bio-entity modeling, especially in the context of molecules and proteins. However, previous efforts like BioT5 faced challenges in generalizing across diverse tasks and lacked a nuanced understanding of molecular structures, particularly in their textual representations (e.g., IUPAC). This paper introduces BioT5+, an extension of the BioT5 framework, tailored to enhance biological research and drug discovery. BioT5+ incorporates several novel features: integration of IUPAC names for molecular unde"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.17810","kind":"arxiv","version":2},"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/2402.17810/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":"2402.17810","created_at":"2026-07-05T08:25:32.553836+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.17810v2","created_at":"2026-07-05T08:25:32.553836+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.17810","created_at":"2026-07-05T08:25:32.553836+00:00"},{"alias_kind":"pith_short_12","alias_value":"XMAWJUOUA35E","created_at":"2026-07-05T08:25:32.553836+00:00"},{"alias_kind":"pith_short_16","alias_value":"XMAWJUOUA35E2P3I","created_at":"2026-07-05T08:25:32.553836+00:00"},{"alias_kind":"pith_short_8","alias_value":"XMAWJUOU","created_at":"2026-07-05T08:25:32.553836+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/XMAWJUOUA35E2P3IIVZT2VYDPE","json":"https://pith.science/pith/XMAWJUOUA35E2P3IIVZT2VYDPE.json","graph_json":"https://pith.science/api/pith-number/XMAWJUOUA35E2P3IIVZT2VYDPE/graph.json","events_json":"https://pith.science/api/pith-number/XMAWJUOUA35E2P3IIVZT2VYDPE/events.json","paper":"https://pith.science/paper/XMAWJUOU"},"agent_actions":{"view_html":"https://pith.science/pith/XMAWJUOUA35E2P3IIVZT2VYDPE","download_json":"https://pith.science/pith/XMAWJUOUA35E2P3IIVZT2VYDPE.json","view_paper":"https://pith.science/paper/XMAWJUOU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.17810&json=true","fetch_graph":"https://pith.science/api/pith-number/XMAWJUOUA35E2P3IIVZT2VYDPE/graph.json","fetch_events":"https://pith.science/api/pith-number/XMAWJUOUA35E2P3IIVZT2VYDPE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XMAWJUOUA35E2P3IIVZT2VYDPE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XMAWJUOUA35E2P3IIVZT2VYDPE/action/storage_attestation","attest_author":"https://pith.science/pith/XMAWJUOUA35E2P3IIVZT2VYDPE/action/author_attestation","sign_citation":"https://pith.science/pith/XMAWJUOUA35E2P3IIVZT2VYDPE/action/citation_signature","submit_replication":"https://pith.science/pith/XMAWJUOUA35E2P3IIVZT2VYDPE/action/replication_record"}},"created_at":"2026-07-05T08:25:32.553836+00:00","updated_at":"2026-07-05T08:25:32.553836+00:00"}