{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EX7UBVBXLXSZBFUR535J4QJQVR","short_pith_number":"pith:EX7UBVBX","schema_version":"1.0","canonical_sha256":"25ff40d4375de5909691eefa9e4130ac4fb6d71e4391cb4e8037bc04826cf674","source":{"kind":"arxiv","id":"2308.13565","version":1},"attestation_state":"computed","paper":{"title":"DARWIN Series: Domain Specific Large Language Models for Natural Science","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cond-mat.mtrl-sci","physics.app-ph"],"primary_cat":"cs.CL","authors_text":"Bram Hoex, Chunyu Kit, Clara Grazian, Imran Razzak, Qingyuan Linghu, Shaozhou Wang, Tong Xie, Wei Huang, Wenjie Zhang, Yixuan Liu, Yuwei Wan, ZhenYu Yin","submitted_at":"2023-08-25T01:40:48Z","abstract_excerpt":"Emerging tools bring forth fresh approaches to work, and the field of natural science is no different. In natural science, traditional manual, serial, and labour-intensive work is being augmented by automated, parallel, and iterative processes driven by artificial intelligence-based experimental automation and more. To add new capabilities in natural science, enabling the acceleration and enrichment of automation of the discovery process, we present DARWIN, a series of tailored LLMs for natural science, mainly in physics, chemistry, and material science. This series relies on open-source LLM, "},"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":"2308.13565","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-25T01:40:48Z","cross_cats_sorted":["cond-mat.mtrl-sci","physics.app-ph"],"title_canon_sha256":"a59c886dfce623d630f4bde093160b1e7c6d35d2a4ad795cf55cb5b278b191ba","abstract_canon_sha256":"8bad21293869caf45aa557be5097100083fb46e2bcd884c98ba130c4bf992505"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:44:52.234934Z","signature_b64":"cdNA7cw2MFy046y2O1ofZoWj7lG9IQKKVThzz9FQkLiEfwjUSt3DPPFqoBRZ8gP8tnBM9dbJjEzRtDzilThVCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"25ff40d4375de5909691eefa9e4130ac4fb6d71e4391cb4e8037bc04826cf674","last_reissued_at":"2026-07-05T06:44:52.234459Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:44:52.234459Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DARWIN Series: Domain Specific Large Language Models for Natural Science","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cond-mat.mtrl-sci","physics.app-ph"],"primary_cat":"cs.CL","authors_text":"Bram Hoex, Chunyu Kit, Clara Grazian, Imran Razzak, Qingyuan Linghu, Shaozhou Wang, Tong Xie, Wei Huang, Wenjie Zhang, Yixuan Liu, Yuwei Wan, ZhenYu Yin","submitted_at":"2023-08-25T01:40:48Z","abstract_excerpt":"Emerging tools bring forth fresh approaches to work, and the field of natural science is no different. In natural science, traditional manual, serial, and labour-intensive work is being augmented by automated, parallel, and iterative processes driven by artificial intelligence-based experimental automation and more. To add new capabilities in natural science, enabling the acceleration and enrichment of automation of the discovery process, we present DARWIN, a series of tailored LLMs for natural science, mainly in physics, chemistry, and material science. This series relies on open-source LLM, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.13565","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/2308.13565/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":"2308.13565","created_at":"2026-07-05T06:44:52.234525+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.13565v1","created_at":"2026-07-05T06:44:52.234525+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.13565","created_at":"2026-07-05T06:44:52.234525+00:00"},{"alias_kind":"pith_short_12","alias_value":"EX7UBVBXLXSZ","created_at":"2026-07-05T06:44:52.234525+00:00"},{"alias_kind":"pith_short_16","alias_value":"EX7UBVBXLXSZBFUR","created_at":"2026-07-05T06:44:52.234525+00:00"},{"alias_kind":"pith_short_8","alias_value":"EX7UBVBX","created_at":"2026-07-05T06:44:52.234525+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31464","citing_title":"Team MKC at CLPsych 2026: Capturing and Characterizing Mental Health Changes through Social Media Timeline Dynamics","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22162","citing_title":"Spectra as Language: Large Language Models for Scalable Stellar Parameter and Abundance Inference","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22162","citing_title":"Spectra as Language: Large Language Models for Scalable Stellar Parameter and Abundance Inference","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2502.02871","citing_title":"Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoning","ref_index":211,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22162","citing_title":"Spectra as Language: Large Language Models for Scalable Stellar Parameter and Abundance Inference","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2507.21990","citing_title":"ChemDFM-R: A Chemical Reasoning LLM Enhanced with Atomized Chemical Knowledge","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02267","citing_title":"Composition-Weighted Symbolic Regression for General-Purpose Property Prediction","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EX7UBVBXLXSZBFUR535J4QJQVR","json":"https://pith.science/pith/EX7UBVBXLXSZBFUR535J4QJQVR.json","graph_json":"https://pith.science/api/pith-number/EX7UBVBXLXSZBFUR535J4QJQVR/graph.json","events_json":"https://pith.science/api/pith-number/EX7UBVBXLXSZBFUR535J4QJQVR/events.json","paper":"https://pith.science/paper/EX7UBVBX"},"agent_actions":{"view_html":"https://pith.science/pith/EX7UBVBXLXSZBFUR535J4QJQVR","download_json":"https://pith.science/pith/EX7UBVBXLXSZBFUR535J4QJQVR.json","view_paper":"https://pith.science/paper/EX7UBVBX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.13565&json=true","fetch_graph":"https://pith.science/api/pith-number/EX7UBVBXLXSZBFUR535J4QJQVR/graph.json","fetch_events":"https://pith.science/api/pith-number/EX7UBVBXLXSZBFUR535J4QJQVR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EX7UBVBXLXSZBFUR535J4QJQVR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EX7UBVBXLXSZBFUR535J4QJQVR/action/storage_attestation","attest_author":"https://pith.science/pith/EX7UBVBXLXSZBFUR535J4QJQVR/action/author_attestation","sign_citation":"https://pith.science/pith/EX7UBVBXLXSZBFUR535J4QJQVR/action/citation_signature","submit_replication":"https://pith.science/pith/EX7UBVBXLXSZBFUR535J4QJQVR/action/replication_record"}},"created_at":"2026-07-05T06:44:52.234525+00:00","updated_at":"2026-07-05T06:44:52.234525+00:00"}