{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3PL7WD5DEXB7CUU426G5UTMHFJ","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":"b98a3333f6a29dd81dabc0175938df48f642f959847abcaec9870f8b88a76912","cross_cats_sorted":["cs.LG","q-bio.QM","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.BM","submitted_at":"2024-11-19T22:08:26Z","title_canon_sha256":"32225165119a80980d41909012a45d7bf2c3c3a619818d3017e6444e09eba924"},"schema_version":"1.0","source":{"id":"2411.12886","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.12886","created_at":"2026-07-05T09:38:01Z"},{"alias_kind":"arxiv_version","alias_value":"2411.12886v1","created_at":"2026-07-05T09:38:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.12886","created_at":"2026-07-05T09:38:01Z"},{"alias_kind":"pith_short_12","alias_value":"3PL7WD5DEXB7","created_at":"2026-07-05T09:38:01Z"},{"alias_kind":"pith_short_16","alias_value":"3PL7WD5DEXB7CUU4","created_at":"2026-07-05T09:38:01Z"},{"alias_kind":"pith_short_8","alias_value":"3PL7WD5D","created_at":"2026-07-05T09:38:01Z"}],"graph_snapshots":[{"event_id":"sha256:0c4e755d7761dc2285a268bdea6cac4341192d2ac46a4954287fcc18aa5e1ff6","target":"graph","created_at":"2026-07-05T09:38:01Z","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/2411.12886/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Natural products are substances produced by organisms in nature and often possess biological activity and structural diversity. Drug development based on natural products has been common for many years. However, the intricate structures of these compounds present challenges in terms of structure determination and synthesis, particularly compared to the efficiency of high-throughput screening of synthetic compounds. In recent years, deep learning-based methods have been applied to the generation of molecules. In this study, we trained chemical language models on a natural product dataset and ge","authors_text":"Kairi Furui, Koh Sakano, Masahito Ohue","cross_cats":["cs.LG","q-bio.QM","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.BM","submitted_at":"2024-11-19T22:08:26Z","title":"NPGPT: Natural Product-Like Compound Generation with GPT-based Chemical Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.12886","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:c59e511add71ff2a46f16fa976d90112635421abb9cc708839fa89ea8f88687e","target":"record","created_at":"2026-07-05T09:38:01Z","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":"b98a3333f6a29dd81dabc0175938df48f642f959847abcaec9870f8b88a76912","cross_cats_sorted":["cs.LG","q-bio.QM","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.BM","submitted_at":"2024-11-19T22:08:26Z","title_canon_sha256":"32225165119a80980d41909012a45d7bf2c3c3a619818d3017e6444e09eba924"},"schema_version":"1.0","source":{"id":"2411.12886","kind":"arxiv","version":1}},"canonical_sha256":"dbd7fb0fa325c3f1529cd78dda4d872a579ae69bdda29097f23f82e468550408","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dbd7fb0fa325c3f1529cd78dda4d872a579ae69bdda29097f23f82e468550408","first_computed_at":"2026-07-05T09:38:01.756065Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:38:01.756065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qaawAuEMNZkPnrdL6K/klbMCDA4xLpgjJ3v3lxi1xABcIFcBmGN/UTOLtnGfez34gBCTnTfZKA5kmjWW3PzACQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:38:01.756610Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.12886","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c59e511add71ff2a46f16fa976d90112635421abb9cc708839fa89ea8f88687e","sha256:0c4e755d7761dc2285a268bdea6cac4341192d2ac46a4954287fcc18aa5e1ff6"],"state_sha256":"7411e88f85dbf910796428fb8d2a02dc4a5c18307a5c6d8e32805c0b64fcc39e"}