{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:YTU3JDZ5ZWBHE55EKJRTRXAYST","short_pith_number":"pith:YTU3JDZ5","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"},"canonical_sha256":"c4e9b48f3dcd827277a4526338dc1894dce10c7ba2f796b5ad390d6baaa00df1","source":{"kind":"arxiv","id":"2305.05708","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.05708","created_at":"2026-07-05T06:08:44Z"},{"alias_kind":"arxiv_version","alias_value":"2305.05708v1","created_at":"2026-07-05T06:08:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.05708","created_at":"2026-07-05T06:08:44Z"},{"alias_kind":"pith_short_12","alias_value":"YTU3JDZ5ZWBH","created_at":"2026-07-05T06:08:44Z"},{"alias_kind":"pith_short_16","alias_value":"YTU3JDZ5ZWBHE55E","created_at":"2026-07-05T06:08:44Z"},{"alias_kind":"pith_short_8","alias_value":"YTU3JDZ5","created_at":"2026-07-05T06:08:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:YTU3JDZ5ZWBHE55EKJRTRXAYST","target":"record","payload":{"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"},"canonical_sha256":"c4e9b48f3dcd827277a4526338dc1894dce10c7ba2f796b5ad390d6baaa00df1","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"},"source_kind":"arxiv","source_id":"2305.05708","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:08:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q1HLHfc/iiGh1WH1vcdScnpR+Caeua1hbNeHf0ICjv/DNkP4pSutmlN68Ev6dXJ3ZTqemuI4dQyFfg3GF89/BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T01:56:34.926613Z"},"content_sha256":"81d4a3453bb3c04f99f8e0f37966aefd70eaf21cfa5a73a5a1e76be0c72fef04","schema_version":"1.0","event_id":"sha256:81d4a3453bb3c04f99f8e0f37966aefd70eaf21cfa5a73a5a1e76be0c72fef04"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:YTU3JDZ5ZWBHE55EKJRTRXAYST","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:08:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JegBgOsNDz3B9Llpylnndi1VI+yaqYXijHCtoBQMZH6F0k/1zBKUGKoNgKwLq3c+i/S5NPGvCqKUF9IbDt8WBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T01:56:34.927143Z"},"content_sha256":"beed9fe2b5ed8d7f03f7bafcb69369395600a3e2267a25a36cf6c59c5d65e886","schema_version":"1.0","event_id":"sha256:beed9fe2b5ed8d7f03f7bafcb69369395600a3e2267a25a36cf6c59c5d65e886"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YTU3JDZ5ZWBHE55EKJRTRXAYST/bundle.json","state_url":"https://pith.science/pith/YTU3JDZ5ZWBHE55EKJRTRXAYST/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YTU3JDZ5ZWBHE55EKJRTRXAYST/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T01:56:34Z","links":{"resolver":"https://pith.science/pith/YTU3JDZ5ZWBHE55EKJRTRXAYST","bundle":"https://pith.science/pith/YTU3JDZ5ZWBHE55EKJRTRXAYST/bundle.json","state":"https://pith.science/pith/YTU3JDZ5ZWBHE55EKJRTRXAYST/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YTU3JDZ5ZWBHE55EKJRTRXAYST/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:YTU3JDZ5ZWBHE55EKJRTRXAYST","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"3b058ae85209c5732ba3eafbb54f9462c651d1472ed0a0531e19d37e73f3c314","cross_cats_sorted":["q-bio.QM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-09T18:35:38Z","title_canon_sha256":"3202f1b98b23496fef6244a0c115f0820620ee2883b70cd9e8a6414aa4812161"},"schema_version":"1.0","source":{"id":"2305.05708","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.05708","created_at":"2026-07-05T06:08:44Z"},{"alias_kind":"arxiv_version","alias_value":"2305.05708v1","created_at":"2026-07-05T06:08:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.05708","created_at":"2026-07-05T06:08:44Z"},{"alias_kind":"pith_short_12","alias_value":"YTU3JDZ5ZWBH","created_at":"2026-07-05T06:08:44Z"},{"alias_kind":"pith_short_16","alias_value":"YTU3JDZ5ZWBHE55E","created_at":"2026-07-05T06:08:44Z"},{"alias_kind":"pith_short_8","alias_value":"YTU3JDZ5","created_at":"2026-07-05T06:08:44Z"}],"graph_snapshots":[{"event_id":"sha256:beed9fe2b5ed8d7f03f7bafcb69369395600a3e2267a25a36cf6c59c5d65e886","target":"graph","created_at":"2026-07-05T06:08:44Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2305.05708/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Al\\'an Aspuru-Guzik, Daniel Flam-Shepherd","cross_cats":["q-bio.QM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-09T18:35:38Z","title":"Language models can generate molecules, materials, and protein binding sites directly in three dimensions as XYZ, CIF, and PDB files"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.05708","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:81d4a3453bb3c04f99f8e0f37966aefd70eaf21cfa5a73a5a1e76be0c72fef04","target":"record","created_at":"2026-07-05T06:08:44Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"3b058ae85209c5732ba3eafbb54f9462c651d1472ed0a0531e19d37e73f3c314","cross_cats_sorted":["q-bio.QM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-09T18:35:38Z","title_canon_sha256":"3202f1b98b23496fef6244a0c115f0820620ee2883b70cd9e8a6414aa4812161"},"schema_version":"1.0","source":{"id":"2305.05708","kind":"arxiv","version":1}},"canonical_sha256":"c4e9b48f3dcd827277a4526338dc1894dce10c7ba2f796b5ad390d6baaa00df1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c4e9b48f3dcd827277a4526338dc1894dce10c7ba2f796b5ad390d6baaa00df1","first_computed_at":"2026-07-05T06:08:44.455208Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:08:44.455208Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jsGB0tWdJV1Z4Sk7KRsz7jPyekc01KzBmHdIPh8uj0yK5DDlSbjQhcX8ACdq/r8JA18uIifrhy4VfSupqKAbCA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:08:44.455623Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.05708","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:81d4a3453bb3c04f99f8e0f37966aefd70eaf21cfa5a73a5a1e76be0c72fef04","sha256:beed9fe2b5ed8d7f03f7bafcb69369395600a3e2267a25a36cf6c59c5d65e886"],"state_sha256":"ecbfe9128b163536f852ddbee2b64842d9bb66a9f1d941a7dcde8682fb9a757c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jda3iCRSYlJQzwSn5Yxl1Q6DqFchBzxEoD49FY0d7SY6kah2TamBp1wl+5HUanxueEpsr9vrqhw2jPS5Dxg8Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T01:56:34.932829Z","bundle_sha256":"a806f7675eaa7679b76b921b24ff14c07d09d75123e94510d41d50a8ed0268a2"}}