{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TC22BRVYBBIC3V6E4V3HUGAAKE","short_pith_number":"pith:TC22BRVY","schema_version":"1.0","canonical_sha256":"98b5a0c6b808502dd7c4e5767a18005137f6f09ecdcfc7c1a98ac9894cace9fa","source":{"kind":"arxiv","id":"2311.06708","version":1},"attestation_state":"computed","paper":{"title":"ReactionT5: a large-scale pre-trained model towards application of limited reaction data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"physics.chem-ph","authors_text":"Ryosuke Kojima, Tatsuya Sagawa","submitted_at":"2023-11-12T02:25:00Z","abstract_excerpt":"Transformer-based deep neural networks have revolutionized the field of molecular-related prediction tasks by treating molecules as symbolic sequences. These models have been successfully applied in various organic chemical applications by pretraining them with extensive compound libraries and subsequently fine-tuning them with smaller in-house datasets for specific tasks. However, many conventional methods primarily focus on single molecules, with limited exploration of pretraining for reactions involving multiple molecules. In this paper, we propose ReactionT5, a novel model that leverages p"},"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":"2311.06708","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"physics.chem-ph","submitted_at":"2023-11-12T02:25:00Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"486146fc1fef09e643b4e204bcaa963a4b3a5cedbe0da79e0b687af80fb044c2","abstract_canon_sha256":"f07135f4b053c9573f7ca64bdb3aa719728f3ee223ea70ab3e4bcbb0642665a6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:12:02.415900Z","signature_b64":"iByA3b5gGtimbCFARTFhtGeqd0H5hDCZS1JQAaLsZHKoPAMVO8kRGl8xFjCAR5ilyml1zFIZK7KNyt7h+hHpBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"98b5a0c6b808502dd7c4e5767a18005137f6f09ecdcfc7c1a98ac9894cace9fa","last_reissued_at":"2026-07-05T07:12:02.415454Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:12:02.415454Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ReactionT5: a large-scale pre-trained model towards application of limited reaction data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"physics.chem-ph","authors_text":"Ryosuke Kojima, Tatsuya Sagawa","submitted_at":"2023-11-12T02:25:00Z","abstract_excerpt":"Transformer-based deep neural networks have revolutionized the field of molecular-related prediction tasks by treating molecules as symbolic sequences. These models have been successfully applied in various organic chemical applications by pretraining them with extensive compound libraries and subsequently fine-tuning them with smaller in-house datasets for specific tasks. However, many conventional methods primarily focus on single molecules, with limited exploration of pretraining for reactions involving multiple molecules. In this paper, we propose ReactionT5, a novel model that leverages p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.06708","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/2311.06708/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":"2311.06708","created_at":"2026-07-05T07:12:02.415511+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.06708v1","created_at":"2026-07-05T07:12:02.415511+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.06708","created_at":"2026-07-05T07:12:02.415511+00:00"},{"alias_kind":"pith_short_12","alias_value":"TC22BRVYBBIC","created_at":"2026-07-05T07:12:02.415511+00:00"},{"alias_kind":"pith_short_16","alias_value":"TC22BRVYBBIC3V6E","created_at":"2026-07-05T07:12:02.415511+00:00"},{"alias_kind":"pith_short_8","alias_value":"TC22BRVY","created_at":"2026-07-05T07:12:02.415511+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05691","citing_title":"Where to cut, how deep: BPE and Unigram-LM on chemistry SMILES","ref_index":40,"is_internal_anchor":true},{"citing_arxiv_id":"2606.12113","citing_title":"Augmenting Molecular Language Models with Local $n$-gram Memory","ref_index":63,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TC22BRVYBBIC3V6E4V3HUGAAKE","json":"https://pith.science/pith/TC22BRVYBBIC3V6E4V3HUGAAKE.json","graph_json":"https://pith.science/api/pith-number/TC22BRVYBBIC3V6E4V3HUGAAKE/graph.json","events_json":"https://pith.science/api/pith-number/TC22BRVYBBIC3V6E4V3HUGAAKE/events.json","paper":"https://pith.science/paper/TC22BRVY"},"agent_actions":{"view_html":"https://pith.science/pith/TC22BRVYBBIC3V6E4V3HUGAAKE","download_json":"https://pith.science/pith/TC22BRVYBBIC3V6E4V3HUGAAKE.json","view_paper":"https://pith.science/paper/TC22BRVY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.06708&json=true","fetch_graph":"https://pith.science/api/pith-number/TC22BRVYBBIC3V6E4V3HUGAAKE/graph.json","fetch_events":"https://pith.science/api/pith-number/TC22BRVYBBIC3V6E4V3HUGAAKE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TC22BRVYBBIC3V6E4V3HUGAAKE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TC22BRVYBBIC3V6E4V3HUGAAKE/action/storage_attestation","attest_author":"https://pith.science/pith/TC22BRVYBBIC3V6E4V3HUGAAKE/action/author_attestation","sign_citation":"https://pith.science/pith/TC22BRVYBBIC3V6E4V3HUGAAKE/action/citation_signature","submit_replication":"https://pith.science/pith/TC22BRVYBBIC3V6E4V3HUGAAKE/action/replication_record"}},"created_at":"2026-07-05T07:12:02.415511+00:00","updated_at":"2026-07-05T07:12:02.415511+00:00"}