{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ENMMDGR5YEGORHTX2XPVCTSHKN","short_pith_number":"pith:ENMMDGR5","schema_version":"1.0","canonical_sha256":"2358c19a3dc10ce89e77d5df514e475367f7337e24b3d454b73ea144f52fe84e","source":{"kind":"arxiv","id":"2412.09560","version":2},"attestation_state":"computed","paper":{"title":"Foundational Large Language Models for Materials Research","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL","cs.IR"],"primary_cat":"cond-mat.mtrl-sci","authors_text":"Biswajit Mishra, Dhruv Ahlawat, Hargun Singh Grover, Mausam, Mohd Zaki, N. M. Anoop Krishnan, Santiago Miret, Somaditya Singh, Vaibhav Bihani, Vaibhav Mishra","submitted_at":"2024-12-12T18:46:38Z","abstract_excerpt":"Materials discovery and development are critical for addressing global challenges. Yet, the exponential growth in materials science literature comprising vast amounts of textual data has created significant bottlenecks in knowledge extraction, synthesis, and scientific reasoning. Large Language Models (LLMs) offer unprecedented opportunities to accelerate materials research through automated analysis and prediction. Still, their effective deployment requires domain-specific adaptation for understanding and solving domain-relevant tasks. Here, we present LLaMat, a family of foundational models "},"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":"2412.09560","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2024-12-12T18:46:38Z","cross_cats_sorted":["cs.CL","cs.IR"],"title_canon_sha256":"6f49ba0343e6449211c108397ba85d76ca0a7252b558afe950ed4f0dc4c9848a","abstract_canon_sha256":"db041630340c494a1083286e90a4e451e977a4c09aaf6a1747126f528395ce94"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:06:09.774418Z","signature_b64":"X6v5iaHDHxha4TeBGBT5rrbh/8DrzDBuIcdSGmgpx+a4pFsFp3aDhvvjQ2IwSuPd45ZYKwMjYYb3dgMuM5Z2Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2358c19a3dc10ce89e77d5df514e475367f7337e24b3d454b73ea144f52fe84e","last_reissued_at":"2026-07-05T10:06:09.773917Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:06:09.773917Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Foundational Large Language Models for Materials Research","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL","cs.IR"],"primary_cat":"cond-mat.mtrl-sci","authors_text":"Biswajit Mishra, Dhruv Ahlawat, Hargun Singh Grover, Mausam, Mohd Zaki, N. M. Anoop Krishnan, Santiago Miret, Somaditya Singh, Vaibhav Bihani, Vaibhav Mishra","submitted_at":"2024-12-12T18:46:38Z","abstract_excerpt":"Materials discovery and development are critical for addressing global challenges. Yet, the exponential growth in materials science literature comprising vast amounts of textual data has created significant bottlenecks in knowledge extraction, synthesis, and scientific reasoning. Large Language Models (LLMs) offer unprecedented opportunities to accelerate materials research through automated analysis and prediction. Still, their effective deployment requires domain-specific adaptation for understanding and solving domain-relevant tasks. Here, we present LLaMat, a family of foundational models "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09560","kind":"arxiv","version":2},"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/2412.09560/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":"2412.09560","created_at":"2026-07-05T10:06:09.773974+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.09560v2","created_at":"2026-07-05T10:06:09.773974+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09560","created_at":"2026-07-05T10:06:09.773974+00:00"},{"alias_kind":"pith_short_12","alias_value":"ENMMDGR5YEGO","created_at":"2026-07-05T10:06:09.773974+00:00"},{"alias_kind":"pith_short_16","alias_value":"ENMMDGR5YEGORHTX","created_at":"2026-07-05T10:06:09.773974+00:00"},{"alias_kind":"pith_short_8","alias_value":"ENMMDGR5","created_at":"2026-07-05T10:06:09.773974+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07712","citing_title":"MatMind: A Structure-Activity Knowledge-Driven Generative Foundation Model for Materials Science","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29555","citing_title":"From Blind Guess to Informed Judgment: Teaching LLMs to Evaluate Materials by Building Knowledge-Augmented Preference Signals","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2507.16307","citing_title":"Perovskite-R1: a domain-specialized large language model for intelligent discovery of precursor additives and experimental design","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03515","citing_title":"Scale-Dependent Input Representation and Confidence Estimation for LLMs in Materials Property Prediction","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ENMMDGR5YEGORHTX2XPVCTSHKN","json":"https://pith.science/pith/ENMMDGR5YEGORHTX2XPVCTSHKN.json","graph_json":"https://pith.science/api/pith-number/ENMMDGR5YEGORHTX2XPVCTSHKN/graph.json","events_json":"https://pith.science/api/pith-number/ENMMDGR5YEGORHTX2XPVCTSHKN/events.json","paper":"https://pith.science/paper/ENMMDGR5"},"agent_actions":{"view_html":"https://pith.science/pith/ENMMDGR5YEGORHTX2XPVCTSHKN","download_json":"https://pith.science/pith/ENMMDGR5YEGORHTX2XPVCTSHKN.json","view_paper":"https://pith.science/paper/ENMMDGR5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.09560&json=true","fetch_graph":"https://pith.science/api/pith-number/ENMMDGR5YEGORHTX2XPVCTSHKN/graph.json","fetch_events":"https://pith.science/api/pith-number/ENMMDGR5YEGORHTX2XPVCTSHKN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ENMMDGR5YEGORHTX2XPVCTSHKN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ENMMDGR5YEGORHTX2XPVCTSHKN/action/storage_attestation","attest_author":"https://pith.science/pith/ENMMDGR5YEGORHTX2XPVCTSHKN/action/author_attestation","sign_citation":"https://pith.science/pith/ENMMDGR5YEGORHTX2XPVCTSHKN/action/citation_signature","submit_replication":"https://pith.science/pith/ENMMDGR5YEGORHTX2XPVCTSHKN/action/replication_record"}},"created_at":"2026-07-05T10:06:09.773974+00:00","updated_at":"2026-07-05T10:06:09.773974+00:00"}