{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4DFVM32HE7EDIK3QEOI4UFN5PO","short_pith_number":"pith:4DFVM32H","schema_version":"1.0","canonical_sha256":"e0cb566f4727c8342b702391ca15bd7b9a9b8f987ae694e694d3beb222184a9c","source":{"kind":"arxiv","id":"2411.00177","version":3},"attestation_state":"computed","paper":{"title":"LLM4Mat-Bench: Benchmarking Large Language Models for Materials Property Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cond-mat.mtrl-sci","authors_text":"Adji Bousso Dieng, Andre Niyongabo Rubungo, Jason Hattrick-Simpers, Kangming Li","submitted_at":"2024-10-31T19:48:12Z","abstract_excerpt":"Large language models (LLMs) are increasingly being used in materials science. However, little attention has been given to benchmarking and standardized evaluation for LLM-based materials property prediction, which hinders progress. We present LLM4Mat-Bench, the largest benchmark to date for evaluating the performance of LLMs in predicting the properties of crystalline materials. LLM4Mat-Bench contains about 1.9M crystal structures in total, collected from 10 publicly available materials data sources, and 45 distinct properties. LLM4Mat-Bench features different input modalities: crystal compos"},"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":"2411.00177","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2024-10-31T19:48:12Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"054625c376d44977cc0f772f975595448a67332a342743185a0e5b403920f7bc","abstract_canon_sha256":"14c872487204f0ef8dddae340a64d61f16d24570f0b7eb710e35d3f09f3b9a7d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:42:31.807262Z","signature_b64":"Tz3NGBzEXD0JZDkfU7gfLdquSszMGY0RIXJOkJuiMNyWd4goj3gZcI+0LM7d5AfNrXFG4xPFxsgs4GcCZ/zVBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e0cb566f4727c8342b702391ca15bd7b9a9b8f987ae694e694d3beb222184a9c","last_reissued_at":"2026-07-05T09:42:31.806707Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:42:31.806707Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM4Mat-Bench: Benchmarking Large Language Models for Materials Property Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cond-mat.mtrl-sci","authors_text":"Adji Bousso Dieng, Andre Niyongabo Rubungo, Jason Hattrick-Simpers, Kangming Li","submitted_at":"2024-10-31T19:48:12Z","abstract_excerpt":"Large language models (LLMs) are increasingly being used in materials science. However, little attention has been given to benchmarking and standardized evaluation for LLM-based materials property prediction, which hinders progress. We present LLM4Mat-Bench, the largest benchmark to date for evaluating the performance of LLMs in predicting the properties of crystalline materials. LLM4Mat-Bench contains about 1.9M crystal structures in total, collected from 10 publicly available materials data sources, and 45 distinct properties. LLM4Mat-Bench features different input modalities: crystal compos"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.00177","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/2411.00177/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":"2411.00177","created_at":"2026-07-05T09:42:31.806776+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.00177v3","created_at":"2026-07-05T09:42:31.806776+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.00177","created_at":"2026-07-05T09:42:31.806776+00:00"},{"alias_kind":"pith_short_12","alias_value":"4DFVM32HE7ED","created_at":"2026-07-05T09:42:31.806776+00:00"},{"alias_kind":"pith_short_16","alias_value":"4DFVM32HE7EDIK3Q","created_at":"2026-07-05T09:42:31.806776+00:00"},{"alias_kind":"pith_short_8","alias_value":"4DFVM32H","created_at":"2026-07-05T09:42:31.806776+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23571","citing_title":"INCARBench: A Benchmark for Scientific Configuration in VASP INCAR by Large Language Models","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21395","citing_title":"Atomistic Language Models Understand and Generate Materials","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4DFVM32HE7EDIK3QEOI4UFN5PO","json":"https://pith.science/pith/4DFVM32HE7EDIK3QEOI4UFN5PO.json","graph_json":"https://pith.science/api/pith-number/4DFVM32HE7EDIK3QEOI4UFN5PO/graph.json","events_json":"https://pith.science/api/pith-number/4DFVM32HE7EDIK3QEOI4UFN5PO/events.json","paper":"https://pith.science/paper/4DFVM32H"},"agent_actions":{"view_html":"https://pith.science/pith/4DFVM32HE7EDIK3QEOI4UFN5PO","download_json":"https://pith.science/pith/4DFVM32HE7EDIK3QEOI4UFN5PO.json","view_paper":"https://pith.science/paper/4DFVM32H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.00177&json=true","fetch_graph":"https://pith.science/api/pith-number/4DFVM32HE7EDIK3QEOI4UFN5PO/graph.json","fetch_events":"https://pith.science/api/pith-number/4DFVM32HE7EDIK3QEOI4UFN5PO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4DFVM32HE7EDIK3QEOI4UFN5PO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4DFVM32HE7EDIK3QEOI4UFN5PO/action/storage_attestation","attest_author":"https://pith.science/pith/4DFVM32HE7EDIK3QEOI4UFN5PO/action/author_attestation","sign_citation":"https://pith.science/pith/4DFVM32HE7EDIK3QEOI4UFN5PO/action/citation_signature","submit_replication":"https://pith.science/pith/4DFVM32HE7EDIK3QEOI4UFN5PO/action/replication_record"}},"created_at":"2026-07-05T09:42:31.806776+00:00","updated_at":"2026-07-05T09:42:31.806776+00:00"}