{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OHAFB6UFO7PCY5Y4JCYITA65HX","short_pith_number":"pith:OHAFB6UF","schema_version":"1.0","canonical_sha256":"71c050fa8577de2c771c48b08983dd3de7e0dbb50dcb10eba22077f124d55b58","source":{"kind":"arxiv","id":"2503.07655","version":1},"attestation_state":"computed","paper":{"title":"GraphT5: Unified Molecular Graph-Language Modeling via Multi-Modal Cross-Token Attention","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Nayeon Kim, Sangyeup Kim, Sun Kim, Yinhua Piao","submitted_at":"2025-03-07T07:57:16Z","abstract_excerpt":"Molecular language modeling tasks such as molecule captioning have been recognized for their potential to further understand molecular properties that can aid drug discovery or material synthesis based on chemical reactions. Unlike the common use of molecule graphs in predicting molecular properties, most methods in molecular language modeling rely heavily on SMILES sequences. This preference is because the task involves generating a sequence of multiple tokens using transformer-based models. Therefore, a main challenge is determining how to integrate graph data, which contains structural and "},"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":"2503.07655","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-07T07:57:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9878f5f8033db1e83a721dc42194e862d048274cf9420a59f81d760e1266b93a","abstract_canon_sha256":"65443981e5d770a1baf3819974b6d174461fe843165dbc49df1584446f9a7b3e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:28:40.929057Z","signature_b64":"P7ZtswoqJjcbj5XBdya8h2qCr3EmXTuU1CHrFXCB29qQvOieACtdS+Dy7tbZIGb3NyN7DHT7dUpibwgzwDB0CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"71c050fa8577de2c771c48b08983dd3de7e0dbb50dcb10eba22077f124d55b58","last_reissued_at":"2026-07-05T10:28:40.928402Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:28:40.928402Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GraphT5: Unified Molecular Graph-Language Modeling via Multi-Modal Cross-Token Attention","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Nayeon Kim, Sangyeup Kim, Sun Kim, Yinhua Piao","submitted_at":"2025-03-07T07:57:16Z","abstract_excerpt":"Molecular language modeling tasks such as molecule captioning have been recognized for their potential to further understand molecular properties that can aid drug discovery or material synthesis based on chemical reactions. Unlike the common use of molecule graphs in predicting molecular properties, most methods in molecular language modeling rely heavily on SMILES sequences. This preference is because the task involves generating a sequence of multiple tokens using transformer-based models. Therefore, a main challenge is determining how to integrate graph data, which contains structural and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.07655","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/2503.07655/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":"2503.07655","created_at":"2026-07-05T10:28:40.928475+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.07655v1","created_at":"2026-07-05T10:28:40.928475+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.07655","created_at":"2026-07-05T10:28:40.928475+00:00"},{"alias_kind":"pith_short_12","alias_value":"OHAFB6UFO7PC","created_at":"2026-07-05T10:28:40.928475+00:00"},{"alias_kind":"pith_short_16","alias_value":"OHAFB6UFO7PCY5Y4","created_at":"2026-07-05T10:28:40.928475+00:00"},{"alias_kind":"pith_short_8","alias_value":"OHAFB6UF","created_at":"2026-07-05T10:28:40.928475+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.24089","citing_title":"BiMol-Diff: A Unified Diffusion Framework for Molecular Generation and Captioning","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OHAFB6UFO7PCY5Y4JCYITA65HX","json":"https://pith.science/pith/OHAFB6UFO7PCY5Y4JCYITA65HX.json","graph_json":"https://pith.science/api/pith-number/OHAFB6UFO7PCY5Y4JCYITA65HX/graph.json","events_json":"https://pith.science/api/pith-number/OHAFB6UFO7PCY5Y4JCYITA65HX/events.json","paper":"https://pith.science/paper/OHAFB6UF"},"agent_actions":{"view_html":"https://pith.science/pith/OHAFB6UFO7PCY5Y4JCYITA65HX","download_json":"https://pith.science/pith/OHAFB6UFO7PCY5Y4JCYITA65HX.json","view_paper":"https://pith.science/paper/OHAFB6UF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.07655&json=true","fetch_graph":"https://pith.science/api/pith-number/OHAFB6UFO7PCY5Y4JCYITA65HX/graph.json","fetch_events":"https://pith.science/api/pith-number/OHAFB6UFO7PCY5Y4JCYITA65HX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OHAFB6UFO7PCY5Y4JCYITA65HX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OHAFB6UFO7PCY5Y4JCYITA65HX/action/storage_attestation","attest_author":"https://pith.science/pith/OHAFB6UFO7PCY5Y4JCYITA65HX/action/author_attestation","sign_citation":"https://pith.science/pith/OHAFB6UFO7PCY5Y4JCYITA65HX/action/citation_signature","submit_replication":"https://pith.science/pith/OHAFB6UFO7PCY5Y4JCYITA65HX/action/replication_record"}},"created_at":"2026-07-05T10:28:40.928475+00:00","updated_at":"2026-07-05T10:28:40.928475+00:00"}