{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:F36R2QR76ID5EF4YBBZ72N5QPC","short_pith_number":"pith:F36R2QR7","schema_version":"1.0","canonical_sha256":"2efd1d423ff207d217980873fd37b07890835d3dc97f57e56af78c90e32176c2","source":{"kind":"arxiv","id":"2412.11970","version":3},"attestation_state":"computed","paper":{"title":"DARWIN 1.5: Large Language Models as Materials Science Adapted Learners","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bram Hoex, Chunyu Kit, Clara Grazian, Dongzhan Zhou, Shaozhou Wang, Tong Xie, Wanli Ouyang, Wenjie Zhang, Yixuan Liu, Yuchen Zeng, Yuwei Wan","submitted_at":"2024-12-16T16:51:27Z","abstract_excerpt":"Materials discovery and design aim to find compositions and structures with desirable properties over highly complex and diverse physical spaces. Traditional solutions, such as high-throughput simulations or machine learning, often rely on complex descriptors, which hinder generalizability and transferability across different material systems. Moreover, These descriptors may inadequately represent macro-scale material properties, which are influenced by structural imperfections and compositional variations in real-world samples, thus limiting their practical applicability. To address these cha"},"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":"2412.11970","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-16T16:51:27Z","cross_cats_sorted":[],"title_canon_sha256":"210e63785c4b6d6bcbe38d9f523aec362b1536a4444a473f2852a460e8585c29","abstract_canon_sha256":"1f425044f487dd1b80b493e59b4840352f446ae4f6847c9e741f1c3542981ac0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:26.021636Z","signature_b64":"42TFgaZKN1gPFeiTP/w+F2olGbS13wr5+8klDlXkT75H2zQ4zKkRO9niwwr3fBSfwk3NzlhLT/OL0Zwd5iv+Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2efd1d423ff207d217980873fd37b07890835d3dc97f57e56af78c90e32176c2","last_reissued_at":"2026-07-05T11:06:26.021066Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:26.021066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DARWIN 1.5: Large Language Models as Materials Science Adapted Learners","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bram Hoex, Chunyu Kit, Clara Grazian, Dongzhan Zhou, Shaozhou Wang, Tong Xie, Wanli Ouyang, Wenjie Zhang, Yixuan Liu, Yuchen Zeng, Yuwei Wan","submitted_at":"2024-12-16T16:51:27Z","abstract_excerpt":"Materials discovery and design aim to find compositions and structures with desirable properties over highly complex and diverse physical spaces. Traditional solutions, such as high-throughput simulations or machine learning, often rely on complex descriptors, which hinder generalizability and transferability across different material systems. Moreover, These descriptors may inadequately represent macro-scale material properties, which are influenced by structural imperfections and compositional variations in real-world samples, thus limiting their practical applicability. To address these cha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.11970","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/2412.11970/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":"2412.11970","created_at":"2026-07-05T11:06:26.021130+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.11970v3","created_at":"2026-07-05T11:06:26.021130+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11970","created_at":"2026-07-05T11:06:26.021130+00:00"},{"alias_kind":"pith_short_12","alias_value":"F36R2QR76ID5","created_at":"2026-07-05T11:06:26.021130+00:00"},{"alias_kind":"pith_short_16","alias_value":"F36R2QR76ID5EF4Y","created_at":"2026-07-05T11:06:26.021130+00:00"},{"alias_kind":"pith_short_8","alias_value":"F36R2QR7","created_at":"2026-07-05T11:06:26.021130+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.03205","citing_title":"From Knowledge to Action: Outcomes of the 2025 Large Language Model (LLM) Hackathon for Applications in Materials Science and Chemistry","ref_index":274,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02267","citing_title":"Composition-Weighted Symbolic Regression for General-Purpose Property Prediction","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F36R2QR76ID5EF4YBBZ72N5QPC","json":"https://pith.science/pith/F36R2QR76ID5EF4YBBZ72N5QPC.json","graph_json":"https://pith.science/api/pith-number/F36R2QR76ID5EF4YBBZ72N5QPC/graph.json","events_json":"https://pith.science/api/pith-number/F36R2QR76ID5EF4YBBZ72N5QPC/events.json","paper":"https://pith.science/paper/F36R2QR7"},"agent_actions":{"view_html":"https://pith.science/pith/F36R2QR76ID5EF4YBBZ72N5QPC","download_json":"https://pith.science/pith/F36R2QR76ID5EF4YBBZ72N5QPC.json","view_paper":"https://pith.science/paper/F36R2QR7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.11970&json=true","fetch_graph":"https://pith.science/api/pith-number/F36R2QR76ID5EF4YBBZ72N5QPC/graph.json","fetch_events":"https://pith.science/api/pith-number/F36R2QR76ID5EF4YBBZ72N5QPC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F36R2QR76ID5EF4YBBZ72N5QPC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F36R2QR76ID5EF4YBBZ72N5QPC/action/storage_attestation","attest_author":"https://pith.science/pith/F36R2QR76ID5EF4YBBZ72N5QPC/action/author_attestation","sign_citation":"https://pith.science/pith/F36R2QR76ID5EF4YBBZ72N5QPC/action/citation_signature","submit_replication":"https://pith.science/pith/F36R2QR76ID5EF4YBBZ72N5QPC/action/replication_record"}},"created_at":"2026-07-05T11:06:26.021130+00:00","updated_at":"2026-07-05T11:06:26.021130+00:00"}