{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:433GHL2WAGHMSY6HGR25X4JGWY","short_pith_number":"pith:433GHL2W","schema_version":"1.0","canonical_sha256":"e6f663af56018ec963c73475dbf126b61f000d87f1dfbac2d262313b761dc525","source":{"kind":"arxiv","id":"2505.23982","version":1},"attestation_state":"computed","paper":{"title":"MSQA: Benchmarking LLMs on Graduate-Level Materials Science Reasoning and Knowledge","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chao Zhang, Jerry Junyang Cheung, Rampi Ramprasad, Shiyao Shen, Yinghao Li, Yuchen Zhuang","submitted_at":"2025-05-29T20:22:57Z","abstract_excerpt":"Despite recent advances in large language models (LLMs) for materials science, there is a lack of benchmarks for evaluating their domain-specific knowledge and complex reasoning abilities. To bridge this gap, we introduce MSQA, a comprehensive evaluation benchmark of 1,757 graduate-level materials science questions in two formats: detailed explanatory responses and binary True/False assessments. MSQA distinctively challenges LLMs by requiring both precise factual knowledge and multi-step reasoning across seven materials science sub-fields, such as structure-property relationships, synthesis pr"},"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":"2505.23982","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-29T20:22:57Z","cross_cats_sorted":[],"title_canon_sha256":"4069f2dcad8aaddbea1db579aaeb8e7d6a915998c9673c55b2c94ad7a7b6634d","abstract_canon_sha256":"6b4d2bea4e96a29fd436bc83c9f11b88d026976a911415069ae1da02b674e582"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:39.514684Z","signature_b64":"X1oBiJ1H5g7TuraHPNByl/hTNGk3W/cfqlblngAvrRehr0QBxBqpFl2QZZdiKqj+Uxk77QBJEjtdmGcY5m2ODQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e6f663af56018ec963c73475dbf126b61f000d87f1dfbac2d262313b761dc525","last_reissued_at":"2026-07-05T11:12:39.514157Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:39.514157Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MSQA: Benchmarking LLMs on Graduate-Level Materials Science Reasoning and Knowledge","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chao Zhang, Jerry Junyang Cheung, Rampi Ramprasad, Shiyao Shen, Yinghao Li, Yuchen Zhuang","submitted_at":"2025-05-29T20:22:57Z","abstract_excerpt":"Despite recent advances in large language models (LLMs) for materials science, there is a lack of benchmarks for evaluating their domain-specific knowledge and complex reasoning abilities. To bridge this gap, we introduce MSQA, a comprehensive evaluation benchmark of 1,757 graduate-level materials science questions in two formats: detailed explanatory responses and binary True/False assessments. MSQA distinctively challenges LLMs by requiring both precise factual knowledge and multi-step reasoning across seven materials science sub-fields, such as structure-property relationships, synthesis pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23982","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/2505.23982/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":"2505.23982","created_at":"2026-07-05T11:12:39.514221+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.23982v1","created_at":"2026-07-05T11:12:39.514221+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23982","created_at":"2026-07-05T11:12:39.514221+00:00"},{"alias_kind":"pith_short_12","alias_value":"433GHL2WAGHM","created_at":"2026-07-05T11:12:39.514221+00:00"},{"alias_kind":"pith_short_16","alias_value":"433GHL2WAGHMSY6H","created_at":"2026-07-05T11:12:39.514221+00:00"},{"alias_kind":"pith_short_8","alias_value":"433GHL2W","created_at":"2026-07-05T11:12:39.514221+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"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":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29833","citing_title":"OmniMatBench: A Human-Calibrated Multimodal Reasoning Benchmark Across 19 Materials Science Subfields","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02934","citing_title":"PolyReal: A Benchmark for Real-World Polymer Science Workflows","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/433GHL2WAGHMSY6HGR25X4JGWY","json":"https://pith.science/pith/433GHL2WAGHMSY6HGR25X4JGWY.json","graph_json":"https://pith.science/api/pith-number/433GHL2WAGHMSY6HGR25X4JGWY/graph.json","events_json":"https://pith.science/api/pith-number/433GHL2WAGHMSY6HGR25X4JGWY/events.json","paper":"https://pith.science/paper/433GHL2W"},"agent_actions":{"view_html":"https://pith.science/pith/433GHL2WAGHMSY6HGR25X4JGWY","download_json":"https://pith.science/pith/433GHL2WAGHMSY6HGR25X4JGWY.json","view_paper":"https://pith.science/paper/433GHL2W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.23982&json=true","fetch_graph":"https://pith.science/api/pith-number/433GHL2WAGHMSY6HGR25X4JGWY/graph.json","fetch_events":"https://pith.science/api/pith-number/433GHL2WAGHMSY6HGR25X4JGWY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/433GHL2WAGHMSY6HGR25X4JGWY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/433GHL2WAGHMSY6HGR25X4JGWY/action/storage_attestation","attest_author":"https://pith.science/pith/433GHL2WAGHMSY6HGR25X4JGWY/action/author_attestation","sign_citation":"https://pith.science/pith/433GHL2WAGHMSY6HGR25X4JGWY/action/citation_signature","submit_replication":"https://pith.science/pith/433GHL2WAGHMSY6HGR25X4JGWY/action/replication_record"}},"created_at":"2026-07-05T11:12:39.514221+00:00","updated_at":"2026-07-05T11:12:39.514221+00:00"}