{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:XMAWJUOUA35E2P3IIVZT2VYDPE","short_pith_number":"pith:XMAWJUOU","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"},"canonical_sha256":"bb0164d1d406fa4d3f6845733d5703791736fac65795740b7cd9a04f8754f742","source":{"kind":"arxiv","id":"2402.17810","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.17810","created_at":"2026-07-05T08:25:32Z"},{"alias_kind":"arxiv_version","alias_value":"2402.17810v2","created_at":"2026-07-05T08:25:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.17810","created_at":"2026-07-05T08:25:32Z"},{"alias_kind":"pith_short_12","alias_value":"XMAWJUOUA35E","created_at":"2026-07-05T08:25:32Z"},{"alias_kind":"pith_short_16","alias_value":"XMAWJUOUA35E2P3I","created_at":"2026-07-05T08:25:32Z"},{"alias_kind":"pith_short_8","alias_value":"XMAWJUOU","created_at":"2026-07-05T08:25:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:XMAWJUOUA35E2P3IIVZT2VYDPE","target":"record","payload":{"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"},"canonical_sha256":"bb0164d1d406fa4d3f6845733d5703791736fac65795740b7cd9a04f8754f742","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"},"source_kind":"arxiv","source_id":"2402.17810","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:25:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GUNCMxnt0d+m2RS9PXqbAL4pq1jk0sEGk5JKGKNFQyGIAlmub9fC2B6w4xfRozxPyIV2eTiBhpyD9VqRoDOLDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:33:11.847274Z"},"content_sha256":"69cff6da3cf6ee4a03d537bf320fa7aa23703998d79f685456739051e3d81d73","schema_version":"1.0","event_id":"sha256:69cff6da3cf6ee4a03d537bf320fa7aa23703998d79f685456739051e3d81d73"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:XMAWJUOUA35E2P3IIVZT2VYDPE","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:25:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R7iF2foaQi0z7FR9xQEDNJr1jmsaQWWoJ4d09+0Ys7jxpubM1XW64HhHKIzCYgaCgmWxWr/1gRjpu9vjSBk6AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:33:11.847984Z"},"content_sha256":"5b461d70239eb8248aab68cc6cfacc8e2906488b54d82d6aed30b5b1b1da9f12","schema_version":"1.0","event_id":"sha256:5b461d70239eb8248aab68cc6cfacc8e2906488b54d82d6aed30b5b1b1da9f12"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XMAWJUOUA35E2P3IIVZT2VYDPE/bundle.json","state_url":"https://pith.science/pith/XMAWJUOUA35E2P3IIVZT2VYDPE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XMAWJUOUA35E2P3IIVZT2VYDPE/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-07T05:33:11Z","links":{"resolver":"https://pith.science/pith/XMAWJUOUA35E2P3IIVZT2VYDPE","bundle":"https://pith.science/pith/XMAWJUOUA35E2P3IIVZT2VYDPE/bundle.json","state":"https://pith.science/pith/XMAWJUOUA35E2P3IIVZT2VYDPE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XMAWJUOUA35E2P3IIVZT2VYDPE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XMAWJUOUA35E2P3IIVZT2VYDPE","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"35fa1498a8e21e76ada9c98073bc8cf6164c6b48a2b8d94fe7bdcdd9ff792852","cross_cats_sorted":["cs.AI","cs.CE","cs.LG","q-bio.BM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.QM","submitted_at":"2024-02-27T12:43:09Z","title_canon_sha256":"4bb54f334ae4b14d7a3cacbdcb32013b973ceab9826166190868a3849b9cf087"},"schema_version":"1.0","source":{"id":"2402.17810","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.17810","created_at":"2026-07-05T08:25:32Z"},{"alias_kind":"arxiv_version","alias_value":"2402.17810v2","created_at":"2026-07-05T08:25:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.17810","created_at":"2026-07-05T08:25:32Z"},{"alias_kind":"pith_short_12","alias_value":"XMAWJUOUA35E","created_at":"2026-07-05T08:25:32Z"},{"alias_kind":"pith_short_16","alias_value":"XMAWJUOUA35E2P3I","created_at":"2026-07-05T08:25:32Z"},{"alias_kind":"pith_short_8","alias_value":"XMAWJUOU","created_at":"2026-07-05T08:25:32Z"}],"graph_snapshots":[{"event_id":"sha256:5b461d70239eb8248aab68cc6cfacc8e2906488b54d82d6aed30b5b1b1da9f12","target":"graph","created_at":"2026-07-05T08:25:32Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2402.17810/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jinhua Zhu, Kaiyuan Gao, Lijun Wu, Qizhi Pei, Rui Yan, Shufang Xie, Tao Qin, Xiaozhuan Liang, Yin Fang","cross_cats":["cs.AI","cs.CE","cs.LG","q-bio.BM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.QM","submitted_at":"2024-02-27T12:43:09Z","title":"BioT5+: Towards Generalized Biological Understanding with IUPAC Integration and Multi-task Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.17810","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:69cff6da3cf6ee4a03d537bf320fa7aa23703998d79f685456739051e3d81d73","target":"record","created_at":"2026-07-05T08:25:32Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"35fa1498a8e21e76ada9c98073bc8cf6164c6b48a2b8d94fe7bdcdd9ff792852","cross_cats_sorted":["cs.AI","cs.CE","cs.LG","q-bio.BM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.QM","submitted_at":"2024-02-27T12:43:09Z","title_canon_sha256":"4bb54f334ae4b14d7a3cacbdcb32013b973ceab9826166190868a3849b9cf087"},"schema_version":"1.0","source":{"id":"2402.17810","kind":"arxiv","version":2}},"canonical_sha256":"bb0164d1d406fa4d3f6845733d5703791736fac65795740b7cd9a04f8754f742","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bb0164d1d406fa4d3f6845733d5703791736fac65795740b7cd9a04f8754f742","first_computed_at":"2026-07-05T08:25:32.553778Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:25:32.553778Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xG09QCVT7dnKCBTobZy76jnHxsz0DGUQVCcFY83L4OIKyc4MZdE7ytv4MxlY6SlT9alPiMvnexSnyDbK08GPCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:25:32.554235Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.17810","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:69cff6da3cf6ee4a03d537bf320fa7aa23703998d79f685456739051e3d81d73","sha256:5b461d70239eb8248aab68cc6cfacc8e2906488b54d82d6aed30b5b1b1da9f12"],"state_sha256":"0cde6d42f60798711a5e88e6188879930a2232dc517d2468cdc1818db091c11e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SCbgMzUF091MoSTTiN/8P+OZiNrxGyxYuQER28vLmR1LdnUX42art1bkvXoJwHSYnSr0MPjrGflgdfJwBIB4Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T05:33:11.850431Z","bundle_sha256":"316973da351e0553356ce52b6d94dabcf04fbbb0e982ca7bfc50fa631fa91282"}}