{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SR6XTHBWVR3NRS3OEMOOSJHNKM","short_pith_number":"pith:SR6XTHBW","schema_version":"1.0","canonical_sha256":"947d799c36ac76d8cb6e231ce924ed53345e31ef5b072088a53d4540744b7686","source":{"kind":"arxiv","id":"2403.13244","version":4},"attestation_state":"computed","paper":{"title":"Instruction Multi-Constraint Molecular Generation Using a Teacher-Student Large Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chunyan Li, Houtim Lai, Jianmin Wang, Jianxin Lin, Leyi Wei, Longyue Wang, Peng Zhou, Siqi Sun, Wei Liu, Xiangxiang Zeng, Xibao Cai, Yiping Liu, Yuansheng Liu, Zixu Wang","submitted_at":"2024-03-20T02:15:55Z","abstract_excerpt":"While various models and computational tools have been proposed for structure and property analysis of molecules, generating molecules that conform to all desired structures and properties remains a challenge. Here, we introduce a multi-constraint molecular generation large language model, TSMMG, which, akin to a student, incorporates knowledge from various small models and tools, namely, the 'teachers'. To train TSMMG, we construct a large set of text-molecule pairs by extracting molecular knowledge from these 'teachers', enabling it to generate novel molecules that conform to the description"},"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":"2403.13244","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-20T02:15:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cd0ea278f777610bafa4d247c54fcd7927085e10d3e6a09f6165ab16919ee32e","abstract_canon_sha256":"a865d6e6552c13f4b4999666545d6e15b204639ceca344d4e78ea38c8d570bec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:18:24.082000Z","signature_b64":"VaQel0AZjn8V2wwe5YudYLJeLAXF1dhK/uHipmL+fhHjdZ+kw57suGrCbSkUwu0zIuQJVvG1IzuTmqMWIFiuAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"947d799c36ac76d8cb6e231ce924ed53345e31ef5b072088a53d4540744b7686","last_reissued_at":"2026-07-05T09:18:24.081527Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:18:24.081527Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Instruction Multi-Constraint Molecular Generation Using a Teacher-Student Large Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chunyan Li, Houtim Lai, Jianmin Wang, Jianxin Lin, Leyi Wei, Longyue Wang, Peng Zhou, Siqi Sun, Wei Liu, Xiangxiang Zeng, Xibao Cai, Yiping Liu, Yuansheng Liu, Zixu Wang","submitted_at":"2024-03-20T02:15:55Z","abstract_excerpt":"While various models and computational tools have been proposed for structure and property analysis of molecules, generating molecules that conform to all desired structures and properties remains a challenge. Here, we introduce a multi-constraint molecular generation large language model, TSMMG, which, akin to a student, incorporates knowledge from various small models and tools, namely, the 'teachers'. To train TSMMG, we construct a large set of text-molecule pairs by extracting molecular knowledge from these 'teachers', enabling it to generate novel molecules that conform to the description"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.13244","kind":"arxiv","version":4},"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/2403.13244/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":"2403.13244","created_at":"2026-07-05T09:18:24.081580+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.13244v4","created_at":"2026-07-05T09:18:24.081580+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.13244","created_at":"2026-07-05T09:18:24.081580+00:00"},{"alias_kind":"pith_short_12","alias_value":"SR6XTHBWVR3N","created_at":"2026-07-05T09:18:24.081580+00:00"},{"alias_kind":"pith_short_16","alias_value":"SR6XTHBWVR3NRS3O","created_at":"2026-07-05T09:18:24.081580+00:00"},{"alias_kind":"pith_short_8","alias_value":"SR6XTHBW","created_at":"2026-07-05T09:18:24.081580+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/SR6XTHBWVR3NRS3OEMOOSJHNKM","json":"https://pith.science/pith/SR6XTHBWVR3NRS3OEMOOSJHNKM.json","graph_json":"https://pith.science/api/pith-number/SR6XTHBWVR3NRS3OEMOOSJHNKM/graph.json","events_json":"https://pith.science/api/pith-number/SR6XTHBWVR3NRS3OEMOOSJHNKM/events.json","paper":"https://pith.science/paper/SR6XTHBW"},"agent_actions":{"view_html":"https://pith.science/pith/SR6XTHBWVR3NRS3OEMOOSJHNKM","download_json":"https://pith.science/pith/SR6XTHBWVR3NRS3OEMOOSJHNKM.json","view_paper":"https://pith.science/paper/SR6XTHBW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.13244&json=true","fetch_graph":"https://pith.science/api/pith-number/SR6XTHBWVR3NRS3OEMOOSJHNKM/graph.json","fetch_events":"https://pith.science/api/pith-number/SR6XTHBWVR3NRS3OEMOOSJHNKM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SR6XTHBWVR3NRS3OEMOOSJHNKM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SR6XTHBWVR3NRS3OEMOOSJHNKM/action/storage_attestation","attest_author":"https://pith.science/pith/SR6XTHBWVR3NRS3OEMOOSJHNKM/action/author_attestation","sign_citation":"https://pith.science/pith/SR6XTHBWVR3NRS3OEMOOSJHNKM/action/citation_signature","submit_replication":"https://pith.science/pith/SR6XTHBWVR3NRS3OEMOOSJHNKM/action/replication_record"}},"created_at":"2026-07-05T09:18:24.081580+00:00","updated_at":"2026-07-05T09:18:24.081580+00:00"}