{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:F7CSN45KYVDE3XCTVMPEHVV3EV","short_pith_number":"pith:F7CSN45K","schema_version":"1.0","canonical_sha256":"2fc526f3aac5464ddc53ab1e43d6bb2575c66c3c498ba00b1637a6abab8f8f68","source":{"kind":"arxiv","id":"2305.10688","version":2},"attestation_state":"computed","paper":{"title":"MolXPT: Wrapping Molecules with Text for Generative Pre-training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Lijun Wu, Ming Zhang, Shufang Xie, Tao Qin, Tie-Yan Liu, Wei Zhang, Yingce Xia, Zequn Liu","submitted_at":"2023-05-18T03:58:19Z","abstract_excerpt":"Generative pre-trained Transformer (GPT) has demonstrates its great success in natural language processing and related techniques have been adapted into molecular modeling. Considering that text is the most important record for scientific discovery, in this paper, we propose MolXPT, a unified language model of text and molecules pre-trained on SMILES (a sequence representation of molecules) wrapped by text. Briefly, we detect the molecule names in each sequence and replace them to the corresponding SMILES. In this way, the SMILES could leverage the information from surrounding text, and vice v"},"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":"2305.10688","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-18T03:58:19Z","cross_cats_sorted":[],"title_canon_sha256":"c023a3e9920a1cc7bb3b9d3c36f91a5032fff393b69d8fd32b4df33044f4765b","abstract_canon_sha256":"9aa0edcebacb1b85b00848e45afcbeaebf7bcd1e55d9004df50b532f57f9a9ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:14:10.500200Z","signature_b64":"MH4dx+hMe1wbvggCFoIHCmE5w0FpctdiId0yqZAVO/kriWDEBRQs00j9iW+f967vLZaOqXPo0VHqxJdxfwiaBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2fc526f3aac5464ddc53ab1e43d6bb2575c66c3c498ba00b1637a6abab8f8f68","last_reissued_at":"2026-07-05T06:14:10.499824Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:14:10.499824Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MolXPT: Wrapping Molecules with Text for Generative Pre-training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Lijun Wu, Ming Zhang, Shufang Xie, Tao Qin, Tie-Yan Liu, Wei Zhang, Yingce Xia, Zequn Liu","submitted_at":"2023-05-18T03:58:19Z","abstract_excerpt":"Generative pre-trained Transformer (GPT) has demonstrates its great success in natural language processing and related techniques have been adapted into molecular modeling. Considering that text is the most important record for scientific discovery, in this paper, we propose MolXPT, a unified language model of text and molecules pre-trained on SMILES (a sequence representation of molecules) wrapped by text. Briefly, we detect the molecule names in each sequence and replace them to the corresponding SMILES. In this way, the SMILES could leverage the information from surrounding text, and vice v"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.10688","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/2305.10688/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":"2305.10688","created_at":"2026-07-05T06:14:10.499879+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.10688v2","created_at":"2026-07-05T06:14:10.499879+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.10688","created_at":"2026-07-05T06:14:10.499879+00:00"},{"alias_kind":"pith_short_12","alias_value":"F7CSN45KYVDE","created_at":"2026-07-05T06:14:10.499879+00:00"},{"alias_kind":"pith_short_16","alias_value":"F7CSN45KYVDE3XCT","created_at":"2026-07-05T06:14:10.499879+00:00"},{"alias_kind":"pith_short_8","alias_value":"F7CSN45K","created_at":"2026-07-05T06:14:10.499879+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/F7CSN45KYVDE3XCTVMPEHVV3EV","json":"https://pith.science/pith/F7CSN45KYVDE3XCTVMPEHVV3EV.json","graph_json":"https://pith.science/api/pith-number/F7CSN45KYVDE3XCTVMPEHVV3EV/graph.json","events_json":"https://pith.science/api/pith-number/F7CSN45KYVDE3XCTVMPEHVV3EV/events.json","paper":"https://pith.science/paper/F7CSN45K"},"agent_actions":{"view_html":"https://pith.science/pith/F7CSN45KYVDE3XCTVMPEHVV3EV","download_json":"https://pith.science/pith/F7CSN45KYVDE3XCTVMPEHVV3EV.json","view_paper":"https://pith.science/paper/F7CSN45K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.10688&json=true","fetch_graph":"https://pith.science/api/pith-number/F7CSN45KYVDE3XCTVMPEHVV3EV/graph.json","fetch_events":"https://pith.science/api/pith-number/F7CSN45KYVDE3XCTVMPEHVV3EV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F7CSN45KYVDE3XCTVMPEHVV3EV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F7CSN45KYVDE3XCTVMPEHVV3EV/action/storage_attestation","attest_author":"https://pith.science/pith/F7CSN45KYVDE3XCTVMPEHVV3EV/action/author_attestation","sign_citation":"https://pith.science/pith/F7CSN45KYVDE3XCTVMPEHVV3EV/action/citation_signature","submit_replication":"https://pith.science/pith/F7CSN45KYVDE3XCTVMPEHVV3EV/action/replication_record"}},"created_at":"2026-07-05T06:14:10.499879+00:00","updated_at":"2026-07-05T06:14:10.499879+00:00"}