{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OCVV67ZACMQEQ2YTEAGF6LTS7K","short_pith_number":"pith:OCVV67ZA","schema_version":"1.0","canonical_sha256":"70ab5f7f201320486b13200c5f2e72fa9546188f2de25dda1aa844f5f4d35d2b","source":{"kind":"arxiv","id":"2411.15500","version":1},"attestation_state":"computed","paper":{"title":"MolMetaLM: a Physicochemical Knowledge-Guided Molecular Meta Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.ET","authors_text":"Min Li, Min Zeng, Yang Li, Yang Zhang, Yifan Wu","submitted_at":"2024-11-23T09:27:38Z","abstract_excerpt":"Most current molecular language models transfer the masked language model or image-text generation model from natural language processing to molecular field. However, molecules are not solely characterized by atom/bond symbols; they encapsulate important physical/chemical properties. Moreover, normal language models bring grammar rules that are irrelevant for understanding molecules. In this study, we propose a novel physicochemical knowledge-guided molecular meta language framework MolMetaLM. We design a molecule-specialized meta language paradigm, formatted as multiple <S,P,O> (subject, pred"},"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":"2411.15500","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.ET","submitted_at":"2024-11-23T09:27:38Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"1ef4d21ed9d2899841d5ef138eb5a81a8d8375260b165b3bd6c96517d4be32e4","abstract_canon_sha256":"c23cf29d700f1b3a8ea08969f88e86b3512ae4a82442138bef6d6583eb8f2e20"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:39:35.943750Z","signature_b64":"rB3KFij37lIe6ntDd4qs3D6Vjd6bV+a/y9Nz0roGn7QhVRCGkQV4KXVw8VO7R9TSd+n/8CanbaJP1lkSGTxlAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70ab5f7f201320486b13200c5f2e72fa9546188f2de25dda1aa844f5f4d35d2b","last_reissued_at":"2026-07-05T09:39:35.943278Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:39:35.943278Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MolMetaLM: a Physicochemical Knowledge-Guided Molecular Meta Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.ET","authors_text":"Min Li, Min Zeng, Yang Li, Yang Zhang, Yifan Wu","submitted_at":"2024-11-23T09:27:38Z","abstract_excerpt":"Most current molecular language models transfer the masked language model or image-text generation model from natural language processing to molecular field. However, molecules are not solely characterized by atom/bond symbols; they encapsulate important physical/chemical properties. Moreover, normal language models bring grammar rules that are irrelevant for understanding molecules. In this study, we propose a novel physicochemical knowledge-guided molecular meta language framework MolMetaLM. We design a molecule-specialized meta language paradigm, formatted as multiple <S,P,O> (subject, pred"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.15500","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/2411.15500/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":"2411.15500","created_at":"2026-07-05T09:39:35.943350+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.15500v1","created_at":"2026-07-05T09:39:35.943350+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.15500","created_at":"2026-07-05T09:39:35.943350+00:00"},{"alias_kind":"pith_short_12","alias_value":"OCVV67ZACMQE","created_at":"2026-07-05T09:39:35.943350+00:00"},{"alias_kind":"pith_short_16","alias_value":"OCVV67ZACMQEQ2YT","created_at":"2026-07-05T09:39:35.943350+00:00"},{"alias_kind":"pith_short_8","alias_value":"OCVV67ZA","created_at":"2026-07-05T09:39:35.943350+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.02871","citing_title":"Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoning","ref_index":205,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OCVV67ZACMQEQ2YTEAGF6LTS7K","json":"https://pith.science/pith/OCVV67ZACMQEQ2YTEAGF6LTS7K.json","graph_json":"https://pith.science/api/pith-number/OCVV67ZACMQEQ2YTEAGF6LTS7K/graph.json","events_json":"https://pith.science/api/pith-number/OCVV67ZACMQEQ2YTEAGF6LTS7K/events.json","paper":"https://pith.science/paper/OCVV67ZA"},"agent_actions":{"view_html":"https://pith.science/pith/OCVV67ZACMQEQ2YTEAGF6LTS7K","download_json":"https://pith.science/pith/OCVV67ZACMQEQ2YTEAGF6LTS7K.json","view_paper":"https://pith.science/paper/OCVV67ZA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.15500&json=true","fetch_graph":"https://pith.science/api/pith-number/OCVV67ZACMQEQ2YTEAGF6LTS7K/graph.json","fetch_events":"https://pith.science/api/pith-number/OCVV67ZACMQEQ2YTEAGF6LTS7K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OCVV67ZACMQEQ2YTEAGF6LTS7K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OCVV67ZACMQEQ2YTEAGF6LTS7K/action/storage_attestation","attest_author":"https://pith.science/pith/OCVV67ZACMQEQ2YTEAGF6LTS7K/action/author_attestation","sign_citation":"https://pith.science/pith/OCVV67ZACMQEQ2YTEAGF6LTS7K/action/citation_signature","submit_replication":"https://pith.science/pith/OCVV67ZACMQEQ2YTEAGF6LTS7K/action/replication_record"}},"created_at":"2026-07-05T09:39:35.943350+00:00","updated_at":"2026-07-05T09:39:35.943350+00:00"}