{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2IQCX44VFWFJEF43MLEGFCJCLW","short_pith_number":"pith:2IQCX44V","schema_version":"1.0","canonical_sha256":"d2202bf3952d8a92179b62c86289225d9aea0fef38960a2f5c73968681db80e5","source":{"kind":"arxiv","id":"2506.20743","version":1},"attestation_state":"computed","paper":{"title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CE"],"primary_cat":"cs.LG","authors_text":"Chen Zhao, Minh-Hao Van, Prateek Verma, Xintao Wu","submitted_at":"2025-06-25T18:10:30Z","abstract_excerpt":"Foundation models (FMs) are catalyzing a transformative shift in materials science (MatSci) by enabling scalable, general-purpose, and multimodal AI systems for scientific discovery. Unlike traditional machine learning models, which are typically narrow in scope and require task-specific engineering, FMs offer cross-domain generalization and exhibit emergent capabilities. Their versatility is especially well-suited to materials science, where research challenges span diverse data types and scales. This survey provides a comprehensive overview of foundation models, agentic systems, datasets, an"},"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":"2506.20743","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-25T18:10:30Z","cross_cats_sorted":["cs.CE"],"title_canon_sha256":"b6e330a8a602d3333f7ef66a87791e438587c03577d799ea0cbb2d32dbd83d50","abstract_canon_sha256":"977c66b04f788a5fa21928e7e7da653e30cc686f98e9071a0cef84421f9db502"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:27:33.267655Z","signature_b64":"wkcnOtX8VSVe3qMd8+Aiyccyeul4pMg8jcVDjgQPpbCgecD8wuNCV0hGq/x2rrl8x9h/z2B+OQOC/pxf0JjoBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2202bf3952d8a92179b62c86289225d9aea0fef38960a2f5c73968681db80e5","last_reissued_at":"2026-07-05T11:27:33.267139Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:27:33.267139Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CE"],"primary_cat":"cs.LG","authors_text":"Chen Zhao, Minh-Hao Van, Prateek Verma, Xintao Wu","submitted_at":"2025-06-25T18:10:30Z","abstract_excerpt":"Foundation models (FMs) are catalyzing a transformative shift in materials science (MatSci) by enabling scalable, general-purpose, and multimodal AI systems for scientific discovery. Unlike traditional machine learning models, which are typically narrow in scope and require task-specific engineering, FMs offer cross-domain generalization and exhibit emergent capabilities. Their versatility is especially well-suited to materials science, where research challenges span diverse data types and scales. This survey provides a comprehensive overview of foundation models, agentic systems, datasets, an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.20743","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/2506.20743/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":"2506.20743","created_at":"2026-07-05T11:27:33.267201+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.20743v1","created_at":"2026-07-05T11:27:33.267201+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.20743","created_at":"2026-07-05T11:27:33.267201+00:00"},{"alias_kind":"pith_short_12","alias_value":"2IQCX44VFWFJ","created_at":"2026-07-05T11:27:33.267201+00:00"},{"alias_kind":"pith_short_16","alias_value":"2IQCX44VFWFJEF43","created_at":"2026-07-05T11:27:33.267201+00:00"},{"alias_kind":"pith_short_8","alias_value":"2IQCX44V","created_at":"2026-07-05T11:27:33.267201+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01012","citing_title":"Property Prediction of Stacked Bilayer Materials: A Multimodal Learning Approach","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31495","citing_title":"General-purpose LLMs as Constrained Crystal Composition Generators","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11229","citing_title":"RECIPER: A Dual-View Retrieval Pipeline for Procedure-Oriented Materials Question Answering","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2IQCX44VFWFJEF43MLEGFCJCLW","json":"https://pith.science/pith/2IQCX44VFWFJEF43MLEGFCJCLW.json","graph_json":"https://pith.science/api/pith-number/2IQCX44VFWFJEF43MLEGFCJCLW/graph.json","events_json":"https://pith.science/api/pith-number/2IQCX44VFWFJEF43MLEGFCJCLW/events.json","paper":"https://pith.science/paper/2IQCX44V"},"agent_actions":{"view_html":"https://pith.science/pith/2IQCX44VFWFJEF43MLEGFCJCLW","download_json":"https://pith.science/pith/2IQCX44VFWFJEF43MLEGFCJCLW.json","view_paper":"https://pith.science/paper/2IQCX44V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.20743&json=true","fetch_graph":"https://pith.science/api/pith-number/2IQCX44VFWFJEF43MLEGFCJCLW/graph.json","fetch_events":"https://pith.science/api/pith-number/2IQCX44VFWFJEF43MLEGFCJCLW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2IQCX44VFWFJEF43MLEGFCJCLW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2IQCX44VFWFJEF43MLEGFCJCLW/action/storage_attestation","attest_author":"https://pith.science/pith/2IQCX44VFWFJEF43MLEGFCJCLW/action/author_attestation","sign_citation":"https://pith.science/pith/2IQCX44VFWFJEF43MLEGFCJCLW/action/citation_signature","submit_replication":"https://pith.science/pith/2IQCX44VFWFJEF43MLEGFCJCLW/action/replication_record"}},"created_at":"2026-07-05T11:27:33.267201+00:00","updated_at":"2026-07-05T11:27:33.267201+00:00"}