{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:JQZ6WO3NGQVCQXEFC3OLPN5FI5","short_pith_number":"pith:JQZ6WO3N","canonical_record":{"source":{"id":"2309.16235","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"physics.chem-ph","submitted_at":"2023-09-28T08:19:54Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","q-bio.BM"],"title_canon_sha256":"8cf04da55a59672aebbb34ee8d971c0cbe4b097c770e1db53aaca4596c1cd6fd","abstract_canon_sha256":"f9863688538f39186b5f12096751112a2d334e12b2ab4f3690e7b65adcfbc7f1"},"schema_version":"1.0"},"canonical_sha256":"4c33eb3b6d342a285c8516dcb7b7a5476958615fb2edd397c859132e82c72eac","source":{"kind":"arxiv","id":"2309.16235","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.16235","created_at":"2026-07-05T09:23:00Z"},{"alias_kind":"arxiv_version","alias_value":"2309.16235v1","created_at":"2026-07-05T09:23:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.16235","created_at":"2026-07-05T09:23:00Z"},{"alias_kind":"pith_short_12","alias_value":"JQZ6WO3NGQVC","created_at":"2026-07-05T09:23:00Z"},{"alias_kind":"pith_short_16","alias_value":"JQZ6WO3NGQVCQXEF","created_at":"2026-07-05T09:23:00Z"},{"alias_kind":"pith_short_8","alias_value":"JQZ6WO3N","created_at":"2026-07-05T09:23:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:JQZ6WO3NGQVCQXEFC3OLPN5FI5","target":"record","payload":{"canonical_record":{"source":{"id":"2309.16235","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"physics.chem-ph","submitted_at":"2023-09-28T08:19:54Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","q-bio.BM"],"title_canon_sha256":"8cf04da55a59672aebbb34ee8d971c0cbe4b097c770e1db53aaca4596c1cd6fd","abstract_canon_sha256":"f9863688538f39186b5f12096751112a2d334e12b2ab4f3690e7b65adcfbc7f1"},"schema_version":"1.0"},"canonical_sha256":"4c33eb3b6d342a285c8516dcb7b7a5476958615fb2edd397c859132e82c72eac","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:23:00.319155Z","signature_b64":"3vAtAGpw6ghZdoD1DVGnPJAIn735ANV+6ZA2o/YrWlVm2oj5GJnXpcuSXpbhOhO9ersaEVSGrdZAEsykKADXDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c33eb3b6d342a285c8516dcb7b7a5476958615fb2edd397c859132e82c72eac","last_reissued_at":"2026-07-05T09:23:00.318665Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:23:00.318665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.16235","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":"2026-07-05T09:23:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b2nya7DJNHvdCoDXZT0tRl9ooQog/aR0f7Ts7PYWe/ZtX/CsFHKVAlg/eQZb4dDsRSx9EVHPsOtqZjcVKSMcAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T00:17:40.378968Z"},"content_sha256":"07b818f68243bb24ad4da274cab0563c0c9f9947302d46061be7d860aa8cff93","schema_version":"1.0","event_id":"sha256:07b818f68243bb24ad4da274cab0563c0c9f9947302d46061be7d860aa8cff93"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:JQZ6WO3NGQVCQXEFC3OLPN5FI5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Language models in molecular discovery","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","q-bio.BM"],"primary_cat":"physics.chem-ph","authors_text":"Jannis Born, Nikita Janakarajan, Sarath Swaminathan, Teodoro Laino, Tim Erdmann","submitted_at":"2023-09-28T08:19:54Z","abstract_excerpt":"The success of language models, especially transformer-based architectures, has trickled into other domains giving rise to \"scientific language models\" that operate on small molecules, proteins or polymers. In chemistry, language models contribute to accelerating the molecule discovery cycle as evidenced by promising recent findings in early-stage drug discovery. Here, we review the role of language models in molecular discovery, underlining their strength in de novo drug design, property prediction and reaction chemistry. We highlight valuable open-source software assets thus lowering the ent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.16235","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/2309.16235/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":"2026-07-05T09:23:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r9ZUhWF0ngreWezSUOM1uH3m4rfrIoL86QU3ICo0SmUs5mLg72O7uj+g9vvCY01q4gRPkuP6mu/ioZYcNm4YDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T00:17:40.379491Z"},"content_sha256":"4dbda162a3ec6e7fb9c59b45be3a6fded5167f06d9770bd68957634ccfd329b5","schema_version":"1.0","event_id":"sha256:4dbda162a3ec6e7fb9c59b45be3a6fded5167f06d9770bd68957634ccfd329b5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JQZ6WO3NGQVCQXEFC3OLPN5FI5/bundle.json","state_url":"https://pith.science/pith/JQZ6WO3NGQVCQXEFC3OLPN5FI5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JQZ6WO3NGQVCQXEFC3OLPN5FI5/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":"2026-08-21T00:17:40Z","links":{"resolver":"https://pith.science/pith/JQZ6WO3NGQVCQXEFC3OLPN5FI5","bundle":"https://pith.science/pith/JQZ6WO3NGQVCQXEFC3OLPN5FI5/bundle.json","state":"https://pith.science/pith/JQZ6WO3NGQVCQXEFC3OLPN5FI5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JQZ6WO3NGQVCQXEFC3OLPN5FI5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:JQZ6WO3NGQVCQXEFC3OLPN5FI5","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":"f9863688538f39186b5f12096751112a2d334e12b2ab4f3690e7b65adcfbc7f1","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","q-bio.BM"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"physics.chem-ph","submitted_at":"2023-09-28T08:19:54Z","title_canon_sha256":"8cf04da55a59672aebbb34ee8d971c0cbe4b097c770e1db53aaca4596c1cd6fd"},"schema_version":"1.0","source":{"id":"2309.16235","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.16235","created_at":"2026-07-05T09:23:00Z"},{"alias_kind":"arxiv_version","alias_value":"2309.16235v1","created_at":"2026-07-05T09:23:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.16235","created_at":"2026-07-05T09:23:00Z"},{"alias_kind":"pith_short_12","alias_value":"JQZ6WO3NGQVC","created_at":"2026-07-05T09:23:00Z"},{"alias_kind":"pith_short_16","alias_value":"JQZ6WO3NGQVCQXEF","created_at":"2026-07-05T09:23:00Z"},{"alias_kind":"pith_short_8","alias_value":"JQZ6WO3N","created_at":"2026-07-05T09:23:00Z"}],"graph_snapshots":[{"event_id":"sha256:4dbda162a3ec6e7fb9c59b45be3a6fded5167f06d9770bd68957634ccfd329b5","target":"graph","created_at":"2026-07-05T09:23:00Z","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/2309.16235/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The success of language models, especially transformer-based architectures, has trickled into other domains giving rise to \"scientific language models\" that operate on small molecules, proteins or polymers. In chemistry, language models contribute to accelerating the molecule discovery cycle as evidenced by promising recent findings in early-stage drug discovery. Here, we review the role of language models in molecular discovery, underlining their strength in de novo drug design, property prediction and reaction chemistry. We highlight valuable open-source software assets thus lowering the ent","authors_text":"Jannis Born, Nikita Janakarajan, Sarath Swaminathan, Teodoro Laino, Tim Erdmann","cross_cats":["cs.AI","cs.CL","cs.LG","q-bio.BM"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"physics.chem-ph","submitted_at":"2023-09-28T08:19:54Z","title":"Language models in molecular discovery"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.16235","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":"sha256:07b818f68243bb24ad4da274cab0563c0c9f9947302d46061be7d860aa8cff93","target":"record","created_at":"2026-07-05T09:23:00Z","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":"f9863688538f39186b5f12096751112a2d334e12b2ab4f3690e7b65adcfbc7f1","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","q-bio.BM"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"physics.chem-ph","submitted_at":"2023-09-28T08:19:54Z","title_canon_sha256":"8cf04da55a59672aebbb34ee8d971c0cbe4b097c770e1db53aaca4596c1cd6fd"},"schema_version":"1.0","source":{"id":"2309.16235","kind":"arxiv","version":1}},"canonical_sha256":"4c33eb3b6d342a285c8516dcb7b7a5476958615fb2edd397c859132e82c72eac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4c33eb3b6d342a285c8516dcb7b7a5476958615fb2edd397c859132e82c72eac","first_computed_at":"2026-07-05T09:23:00.318665Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:23:00.318665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3vAtAGpw6ghZdoD1DVGnPJAIn735ANV+6ZA2o/YrWlVm2oj5GJnXpcuSXpbhOhO9ersaEVSGrdZAEsykKADXDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:23:00.319155Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.16235","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:07b818f68243bb24ad4da274cab0563c0c9f9947302d46061be7d860aa8cff93","sha256:4dbda162a3ec6e7fb9c59b45be3a6fded5167f06d9770bd68957634ccfd329b5"],"state_sha256":"ba59d0c7185a5184c2ae9a925699c69e670a7ac7350fb2093b9756b113b29cbc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jUCbbIjneRiqWSHc/QM3zCoTMO2QeKukAlVSpOcYouzOtCFEZII0jupIVfFqioB5rA+dNZrjPw5jD4FpTHoKAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T00:17:40.385265Z","bundle_sha256":"3a9978824e7cd4829e332f8ceb6101cc31349e6bfb62662ea8e4dd87f5f504fe"}}