{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Y77XZRWZ4OFCCL33JBY6VYIVJB","short_pith_number":"pith:Y77XZRWZ","schema_version":"1.0","canonical_sha256":"c7ff7cc6d9e38a212f7b4871eae115486b2c90f5a4c54d52e041c2f460b38f55","source":{"kind":"arxiv","id":"2510.12171","version":2},"attestation_state":"computed","paper":{"title":"MatSciBench: Benchmarking the Reasoning Ability of Large Language Models in Materials Science","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Changquan Gu, Dawei Zhou, Jianpeng Chen, Jingru Gan, Junkai Zhang, Ling Li, Mingyu Derek Ma, Wei Wang, Xiaoxuan Wang, Yanqiao Zhu, Zian Jia","submitted_at":"2025-10-14T05:59:40Z","abstract_excerpt":"Large Language Models have shown strong scientific reasoning ability, but their performance on materials science problems remains less studied. To fill this gap, we introduce MatSciBench, a comprehensive college-level benchmark comprising 1340 problems that span the essential subdisciplines of materials science. MatSciBench features a structured and fine-grained taxonomy that categorizes materials science questions into 6 primary fields and 31 subfields, together with a three-tier difficulty classification based on the reasoning length needed to solve each problem. MatSciBench includes detaile"},"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":"2510.12171","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-10-14T05:59:40Z","cross_cats_sorted":[],"title_canon_sha256":"537871390a0251b3e1f898f250c6d70d503cab07815dde5a92c04ac56b90e04d","abstract_canon_sha256":"9d3eebc7ac4dc62978241d6e00605f6b05a5e38ca3625651c2a19d3a0669dae5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:07:11.099455Z","signature_b64":"Wjr3epoLSUsDERYKnebkMe0cry96ZRPQRKK7XYnGEDbYPkL9zgLOR8SW7pv5Y0ppnTv8vFEEhW0ls5CYAXf4Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7ff7cc6d9e38a212f7b4871eae115486b2c90f5a4c54d52e041c2f460b38f55","last_reissued_at":"2026-06-09T02:07:11.098410Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:07:11.098410Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MatSciBench: Benchmarking the Reasoning Ability of Large Language Models in Materials Science","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Changquan Gu, Dawei Zhou, Jianpeng Chen, Jingru Gan, Junkai Zhang, Ling Li, Mingyu Derek Ma, Wei Wang, Xiaoxuan Wang, Yanqiao Zhu, Zian Jia","submitted_at":"2025-10-14T05:59:40Z","abstract_excerpt":"Large Language Models have shown strong scientific reasoning ability, but their performance on materials science problems remains less studied. To fill this gap, we introduce MatSciBench, a comprehensive college-level benchmark comprising 1340 problems that span the essential subdisciplines of materials science. MatSciBench features a structured and fine-grained taxonomy that categorizes materials science questions into 6 primary fields and 31 subfields, together with a three-tier difficulty classification based on the reasoning length needed to solve each problem. MatSciBench includes detaile"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.12171","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/2510.12171/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":"2510.12171","created_at":"2026-06-09T02:07:11.098527+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.12171v2","created_at":"2026-06-09T02:07:11.098527+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.12171","created_at":"2026-06-09T02:07:11.098527+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y77XZRWZ4OFC","created_at":"2026-06-09T02:07:11.098527+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y77XZRWZ4OFCCL33","created_at":"2026-06-09T02:07:11.098527+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y77XZRWZ","created_at":"2026-06-09T02:07:11.098527+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2605.18630","citing_title":"SCICONVBENCH: Benchmarking LLMs on Multi-Turn Clarification for Task Formulation in Computational Science","ref_index":79,"is_internal_anchor":true},{"citing_arxiv_id":"2604.19758","citing_title":"ThermoQA: A Three-Tier Benchmark for Evaluating Thermodynamic Reasoning in Large Language Models","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2604.02934","citing_title":"PolyReal: A Benchmark for Real-World Polymer Science Workflows","ref_index":55,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y77XZRWZ4OFCCL33JBY6VYIVJB","json":"https://pith.science/pith/Y77XZRWZ4OFCCL33JBY6VYIVJB.json","graph_json":"https://pith.science/api/pith-number/Y77XZRWZ4OFCCL33JBY6VYIVJB/graph.json","events_json":"https://pith.science/api/pith-number/Y77XZRWZ4OFCCL33JBY6VYIVJB/events.json","paper":"https://pith.science/paper/Y77XZRWZ"},"agent_actions":{"view_html":"https://pith.science/pith/Y77XZRWZ4OFCCL33JBY6VYIVJB","download_json":"https://pith.science/pith/Y77XZRWZ4OFCCL33JBY6VYIVJB.json","view_paper":"https://pith.science/paper/Y77XZRWZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.12171&json=true","fetch_graph":"https://pith.science/api/pith-number/Y77XZRWZ4OFCCL33JBY6VYIVJB/graph.json","fetch_events":"https://pith.science/api/pith-number/Y77XZRWZ4OFCCL33JBY6VYIVJB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y77XZRWZ4OFCCL33JBY6VYIVJB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y77XZRWZ4OFCCL33JBY6VYIVJB/action/storage_attestation","attest_author":"https://pith.science/pith/Y77XZRWZ4OFCCL33JBY6VYIVJB/action/author_attestation","sign_citation":"https://pith.science/pith/Y77XZRWZ4OFCCL33JBY6VYIVJB/action/citation_signature","submit_replication":"https://pith.science/pith/Y77XZRWZ4OFCCL33JBY6VYIVJB/action/replication_record"}},"created_at":"2026-06-09T02:07:11.098527+00:00","updated_at":"2026-06-09T02:07:11.098527+00:00"}