{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YTU3JDZ5ZWBHE55EKJRTRXAYST","short_pith_number":"pith:YTU3JDZ5","schema_version":"1.0","canonical_sha256":"c4e9b48f3dcd827277a4526338dc1894dce10c7ba2f796b5ad390d6baaa00df1","source":{"kind":"arxiv","id":"2305.05708","version":1},"attestation_state":"computed","paper":{"title":"Language models can generate molecules, materials, and protein binding sites directly in three dimensions as XYZ, CIF, and PDB files","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["q-bio.QM"],"primary_cat":"cs.LG","authors_text":"Al\\'an Aspuru-Guzik, Daniel Flam-Shepherd","submitted_at":"2023-05-09T18:35:38Z","abstract_excerpt":"Language models are powerful tools for molecular design. Currently, the dominant paradigm is to parse molecular graphs into linear string representations that can easily be trained on. This approach has been very successful, however, it is limited to chemical structures that can be completely represented by a graph -- like organic molecules -- while materials and biomolecular structures like protein binding sites require a more complete representation that includes the relative positioning of their atoms in space. In this work, we show how language models, without any architecture modification"},"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":"2305.05708","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-09T18:35:38Z","cross_cats_sorted":["q-bio.QM"],"title_canon_sha256":"3202f1b98b23496fef6244a0c115f0820620ee2883b70cd9e8a6414aa4812161","abstract_canon_sha256":"3b058ae85209c5732ba3eafbb54f9462c651d1472ed0a0531e19d37e73f3c314"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:08:44.455623Z","signature_b64":"jsGB0tWdJV1Z4Sk7KRsz7jPyekc01KzBmHdIPh8uj0yK5DDlSbjQhcX8ACdq/r8JA18uIifrhy4VfSupqKAbCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c4e9b48f3dcd827277a4526338dc1894dce10c7ba2f796b5ad390d6baaa00df1","last_reissued_at":"2026-07-05T06:08:44.455208Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:08:44.455208Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Language models can generate molecules, materials, and protein binding sites directly in three dimensions as XYZ, CIF, and PDB files","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["q-bio.QM"],"primary_cat":"cs.LG","authors_text":"Al\\'an Aspuru-Guzik, Daniel Flam-Shepherd","submitted_at":"2023-05-09T18:35:38Z","abstract_excerpt":"Language models are powerful tools for molecular design. Currently, the dominant paradigm is to parse molecular graphs into linear string representations that can easily be trained on. This approach has been very successful, however, it is limited to chemical structures that can be completely represented by a graph -- like organic molecules -- while materials and biomolecular structures like protein binding sites require a more complete representation that includes the relative positioning of their atoms in space. In this work, we show how language models, without any architecture modification"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.05708","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/2305.05708/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":"2305.05708","created_at":"2026-07-05T06:08:44.455263+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.05708v1","created_at":"2026-07-05T06:08:44.455263+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.05708","created_at":"2026-07-05T06:08:44.455263+00:00"},{"alias_kind":"pith_short_12","alias_value":"YTU3JDZ5ZWBH","created_at":"2026-07-05T06:08:44.455263+00:00"},{"alias_kind":"pith_short_16","alias_value":"YTU3JDZ5ZWBHE55E","created_at":"2026-07-05T06:08:44.455263+00:00"},{"alias_kind":"pith_short_8","alias_value":"YTU3JDZ5","created_at":"2026-07-05T06:08:44.455263+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22926","citing_title":"Reaction-Network-Level Discovery of Ammonia Synthesis Catalysts via Ten-Million-Scale Generative Exploration","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17445","citing_title":"Toward Controllable Catalyst Inverse Design via Large-Scale Autoregressive Pretraining","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07712","citing_title":"MatMind: A Structure-Activity Knowledge-Driven Generative Foundation Model for Materials Science","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03764","citing_title":"RamanGPT: Bidirectional Mapping Between Crystal Structures and Raman Spectra with Graph Neural Networks and Generative Transformers","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31495","citing_title":"General-purpose LLMs as Constrained Crystal Composition Generators","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12784","citing_title":"ToolMol: Evolutionary Agentic Framework for Multi-objective Drug Discovery","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12784","citing_title":"ToolMol: Evolutionary Agentic Framework for Multi-objective Drug Discovery","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27709","citing_title":"Conditional Generative Models Enable Targeted Exploration of MAX Phase Design Space","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YTU3JDZ5ZWBHE55EKJRTRXAYST","json":"https://pith.science/pith/YTU3JDZ5ZWBHE55EKJRTRXAYST.json","graph_json":"https://pith.science/api/pith-number/YTU3JDZ5ZWBHE55EKJRTRXAYST/graph.json","events_json":"https://pith.science/api/pith-number/YTU3JDZ5ZWBHE55EKJRTRXAYST/events.json","paper":"https://pith.science/paper/YTU3JDZ5"},"agent_actions":{"view_html":"https://pith.science/pith/YTU3JDZ5ZWBHE55EKJRTRXAYST","download_json":"https://pith.science/pith/YTU3JDZ5ZWBHE55EKJRTRXAYST.json","view_paper":"https://pith.science/paper/YTU3JDZ5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.05708&json=true","fetch_graph":"https://pith.science/api/pith-number/YTU3JDZ5ZWBHE55EKJRTRXAYST/graph.json","fetch_events":"https://pith.science/api/pith-number/YTU3JDZ5ZWBHE55EKJRTRXAYST/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YTU3JDZ5ZWBHE55EKJRTRXAYST/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YTU3JDZ5ZWBHE55EKJRTRXAYST/action/storage_attestation","attest_author":"https://pith.science/pith/YTU3JDZ5ZWBHE55EKJRTRXAYST/action/author_attestation","sign_citation":"https://pith.science/pith/YTU3JDZ5ZWBHE55EKJRTRXAYST/action/citation_signature","submit_replication":"https://pith.science/pith/YTU3JDZ5ZWBHE55EKJRTRXAYST/action/replication_record"}},"created_at":"2026-07-05T06:08:44.455263+00:00","updated_at":"2026-07-05T06:08:44.455263+00:00"}