{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:AUASRUT6YXELGBTN7RGLFTQC6K","short_pith_number":"pith:AUASRUT6","schema_version":"1.0","canonical_sha256":"050128d27ec5c8b3066dfc4cb2ce02f2a54124e889d202165759e6bcff82233e","source":{"kind":"arxiv","id":"2308.16259","version":2},"attestation_state":"computed","paper":{"title":"Materials Informatics Transformer: A Language Model for Interpretable Materials Properties Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.mtrl-sci","physics.chem-ph"],"primary_cat":"cs.LG","authors_text":"Amir Barati Farimani, Changwen Xu, Hongshuo Huang, Rishikesh Magar","submitted_at":"2023-08-30T18:34:55Z","abstract_excerpt":"Recently, the remarkable capabilities of large language models (LLMs) have been illustrated across a variety of research domains such as natural language processing, computer vision, and molecular modeling. We extend this paradigm by utilizing LLMs for material property prediction by introducing our model Materials Informatics Transformer (MatInFormer). Specifically, we introduce a novel approach that involves learning the grammar of crystallography through the tokenization of pertinent space group information. We further illustrate the adaptability of MatInFormer by incorporating task-specifi"},"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":"2308.16259","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-08-30T18:34:55Z","cross_cats_sorted":["cond-mat.mtrl-sci","physics.chem-ph"],"title_canon_sha256":"56061d2bc7f7d103d6f2b29a0cc0f3c531d8cb50e641471787cf5d5d5eab9b5d","abstract_canon_sha256":"15f23dabc148eee5c5fe1ec280cd283059d3600b8648c00f434218067128eb47"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:46:50.350489Z","signature_b64":"w995XpkbGE2aXd8HnKevsxNeGOQGecrM8XxWAah08Lq+O+9Q4v6jlk6hYSL/ep4ENqL1mnATmF6bk/l1udXGDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"050128d27ec5c8b3066dfc4cb2ce02f2a54124e889d202165759e6bcff82233e","last_reissued_at":"2026-07-05T06:46:50.350114Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:46:50.350114Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Materials Informatics Transformer: A Language Model for Interpretable Materials Properties Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.mtrl-sci","physics.chem-ph"],"primary_cat":"cs.LG","authors_text":"Amir Barati Farimani, Changwen Xu, Hongshuo Huang, Rishikesh Magar","submitted_at":"2023-08-30T18:34:55Z","abstract_excerpt":"Recently, the remarkable capabilities of large language models (LLMs) have been illustrated across a variety of research domains such as natural language processing, computer vision, and molecular modeling. We extend this paradigm by utilizing LLMs for material property prediction by introducing our model Materials Informatics Transformer (MatInFormer). Specifically, we introduce a novel approach that involves learning the grammar of crystallography through the tokenization of pertinent space group information. We further illustrate the adaptability of MatInFormer by incorporating task-specifi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.16259","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/2308.16259/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":"2308.16259","created_at":"2026-07-05T06:46:50.350179+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.16259v2","created_at":"2026-07-05T06:46:50.350179+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.16259","created_at":"2026-07-05T06:46:50.350179+00:00"},{"alias_kind":"pith_short_12","alias_value":"AUASRUT6YXEL","created_at":"2026-07-05T06:46:50.350179+00:00"},{"alias_kind":"pith_short_16","alias_value":"AUASRUT6YXELGBTN","created_at":"2026-07-05T06:46:50.350179+00:00"},{"alias_kind":"pith_short_8","alias_value":"AUASRUT6","created_at":"2026-07-05T06:46:50.350179+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.04053","citing_title":"TopoMAS: Large Language Model Driven Topological Materials Multiagent System","ref_index":34,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AUASRUT6YXELGBTN7RGLFTQC6K","json":"https://pith.science/pith/AUASRUT6YXELGBTN7RGLFTQC6K.json","graph_json":"https://pith.science/api/pith-number/AUASRUT6YXELGBTN7RGLFTQC6K/graph.json","events_json":"https://pith.science/api/pith-number/AUASRUT6YXELGBTN7RGLFTQC6K/events.json","paper":"https://pith.science/paper/AUASRUT6"},"agent_actions":{"view_html":"https://pith.science/pith/AUASRUT6YXELGBTN7RGLFTQC6K","download_json":"https://pith.science/pith/AUASRUT6YXELGBTN7RGLFTQC6K.json","view_paper":"https://pith.science/paper/AUASRUT6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.16259&json=true","fetch_graph":"https://pith.science/api/pith-number/AUASRUT6YXELGBTN7RGLFTQC6K/graph.json","fetch_events":"https://pith.science/api/pith-number/AUASRUT6YXELGBTN7RGLFTQC6K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AUASRUT6YXELGBTN7RGLFTQC6K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AUASRUT6YXELGBTN7RGLFTQC6K/action/storage_attestation","attest_author":"https://pith.science/pith/AUASRUT6YXELGBTN7RGLFTQC6K/action/author_attestation","sign_citation":"https://pith.science/pith/AUASRUT6YXELGBTN7RGLFTQC6K/action/citation_signature","submit_replication":"https://pith.science/pith/AUASRUT6YXELGBTN7RGLFTQC6K/action/replication_record"}},"created_at":"2026-07-05T06:46:50.350179+00:00","updated_at":"2026-07-05T06:46:50.350179+00:00"}