{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SRKQMILEGWQEYCWBGFJYQDIBRO","short_pith_number":"pith:SRKQMILE","schema_version":"1.0","canonical_sha256":"945506216435a04c0ac13153880d018b93c7a7dd31762ae96c71dbbdf796402d","source":{"kind":"arxiv","id":"2311.12410","version":3},"attestation_state":"computed","paper":{"title":"nach0: Multimodal Natural and Chemical Languages Foundation Model","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","q-bio.QM"],"primary_cat":"cs.CL","authors_text":"Aastha Jhunjhunwala, Al\\'an Aspuru-Guzik, Alex Aliper, Alex Zhavoronkov, Annika Brundyn, Anthony Costa, Daniil Polykovskiy, Elena Tutubalina, Maksim Kuznetsov, Micha Livne, Zulfat Miftahutdinov","submitted_at":"2023-11-21T07:56:30Z","abstract_excerpt":"Large Language Models (LLMs) have substantially driven scientific progress in various domains, and many papers have demonstrated their ability to tackle complex problems with creative solutions. Our paper introduces a new foundation model, nach0, capable of solving various chemical and biological tasks: biomedical question answering, named entity recognition, molecular generation, molecular synthesis, attributes prediction, and others. nach0 is a multi-domain and multi-task encoder-decoder LLM pre-trained on unlabeled text from scientific literature, patents, and molecule strings to incorporat"},"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":"2311.12410","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-21T07:56:30Z","cross_cats_sorted":["cs.AI","cs.LG","q-bio.QM"],"title_canon_sha256":"1301cfd7265587c26f7d791c24eca3ff779bc8eaf4cd6b88de1cf27319e020d8","abstract_canon_sha256":"9930982fd5d4a22cab8e10636c04e744a9f246e6ec3e9380192575312e2f2c15"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:37:35.909017Z","signature_b64":"d9ChJ3JxQLh4Jx9d5C+XZohZOfmaELbU2tA1pjUhBB3WFmChgLfOYXfVZjf0cw+OuFm5EAXMUBWVWrUWY57pCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"945506216435a04c0ac13153880d018b93c7a7dd31762ae96c71dbbdf796402d","last_reissued_at":"2026-07-05T08:37:35.908485Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:37:35.908485Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"nach0: Multimodal Natural and Chemical Languages Foundation Model","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","q-bio.QM"],"primary_cat":"cs.CL","authors_text":"Aastha Jhunjhunwala, Al\\'an Aspuru-Guzik, Alex Aliper, Alex Zhavoronkov, Annika Brundyn, Anthony Costa, Daniil Polykovskiy, Elena Tutubalina, Maksim Kuznetsov, Micha Livne, Zulfat Miftahutdinov","submitted_at":"2023-11-21T07:56:30Z","abstract_excerpt":"Large Language Models (LLMs) have substantially driven scientific progress in various domains, and many papers have demonstrated their ability to tackle complex problems with creative solutions. Our paper introduces a new foundation model, nach0, capable of solving various chemical and biological tasks: biomedical question answering, named entity recognition, molecular generation, molecular synthesis, attributes prediction, and others. nach0 is a multi-domain and multi-task encoder-decoder LLM pre-trained on unlabeled text from scientific literature, patents, and molecule strings to incorporat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.12410","kind":"arxiv","version":3},"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/2311.12410/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":"2311.12410","created_at":"2026-07-05T08:37:35.908545+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.12410v3","created_at":"2026-07-05T08:37:35.908545+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.12410","created_at":"2026-07-05T08:37:35.908545+00:00"},{"alias_kind":"pith_short_12","alias_value":"SRKQMILEGWQE","created_at":"2026-07-05T08:37:35.908545+00:00"},{"alias_kind":"pith_short_16","alias_value":"SRKQMILEGWQEYCWB","created_at":"2026-07-05T08:37:35.908545+00:00"},{"alias_kind":"pith_short_8","alias_value":"SRKQMILE","created_at":"2026-07-05T08:37:35.908545+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SRKQMILEGWQEYCWBGFJYQDIBRO","json":"https://pith.science/pith/SRKQMILEGWQEYCWBGFJYQDIBRO.json","graph_json":"https://pith.science/api/pith-number/SRKQMILEGWQEYCWBGFJYQDIBRO/graph.json","events_json":"https://pith.science/api/pith-number/SRKQMILEGWQEYCWBGFJYQDIBRO/events.json","paper":"https://pith.science/paper/SRKQMILE"},"agent_actions":{"view_html":"https://pith.science/pith/SRKQMILEGWQEYCWBGFJYQDIBRO","download_json":"https://pith.science/pith/SRKQMILEGWQEYCWBGFJYQDIBRO.json","view_paper":"https://pith.science/paper/SRKQMILE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.12410&json=true","fetch_graph":"https://pith.science/api/pith-number/SRKQMILEGWQEYCWBGFJYQDIBRO/graph.json","fetch_events":"https://pith.science/api/pith-number/SRKQMILEGWQEYCWBGFJYQDIBRO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SRKQMILEGWQEYCWBGFJYQDIBRO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SRKQMILEGWQEYCWBGFJYQDIBRO/action/storage_attestation","attest_author":"https://pith.science/pith/SRKQMILEGWQEYCWBGFJYQDIBRO/action/author_attestation","sign_citation":"https://pith.science/pith/SRKQMILEGWQEYCWBGFJYQDIBRO/action/citation_signature","submit_replication":"https://pith.science/pith/SRKQMILEGWQEYCWBGFJYQDIBRO/action/replication_record"}},"created_at":"2026-07-05T08:37:35.908545+00:00","updated_at":"2026-07-05T08:37:35.908545+00:00"}