{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:Y77XZRWZ4OFCCL33JBY6VYIVJB","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"9d3eebc7ac4dc62978241d6e00605f6b05a5e38ca3625651c2a19d3a0669dae5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-10-14T05:59:40Z","title_canon_sha256":"537871390a0251b3e1f898f250c6d70d503cab07815dde5a92c04ac56b90e04d"},"schema_version":"1.0","source":{"id":"2510.12171","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.12171","created_at":"2026-06-09T02:07:11Z"},{"alias_kind":"arxiv_version","alias_value":"2510.12171v2","created_at":"2026-06-09T02:07:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.12171","created_at":"2026-06-09T02:07:11Z"},{"alias_kind":"pith_short_12","alias_value":"Y77XZRWZ4OFC","created_at":"2026-06-09T02:07:11Z"},{"alias_kind":"pith_short_16","alias_value":"Y77XZRWZ4OFCCL33","created_at":"2026-06-09T02:07:11Z"},{"alias_kind":"pith_short_8","alias_value":"Y77XZRWZ","created_at":"2026-06-09T02:07:11Z"}],"graph_snapshots":[{"event_id":"sha256:3b2aeab23880cf4278a7c71143d573b166da0de13f075a729539496e6156100f","target":"graph","created_at":"2026-06-09T02:07:11Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2510.12171/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-10-14T05:59:40Z","title":"MatSciBench: Benchmarking the Reasoning Ability of Large Language Models in Materials Science"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.12171","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4f60fa18c31597613f0e68016a1cb0786e4014a030c5ae9acdfa10ddd46f3f5d","target":"record","created_at":"2026-06-09T02:07:11Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"9d3eebc7ac4dc62978241d6e00605f6b05a5e38ca3625651c2a19d3a0669dae5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-10-14T05:59:40Z","title_canon_sha256":"537871390a0251b3e1f898f250c6d70d503cab07815dde5a92c04ac56b90e04d"},"schema_version":"1.0","source":{"id":"2510.12171","kind":"arxiv","version":2}},"canonical_sha256":"c7ff7cc6d9e38a212f7b4871eae115486b2c90f5a4c54d52e041c2f460b38f55","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c7ff7cc6d9e38a212f7b4871eae115486b2c90f5a4c54d52e041c2f460b38f55","first_computed_at":"2026-06-09T02:07:11.098410Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T02:07:11.098410Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Wjr3epoLSUsDERYKnebkMe0cry96ZRPQRKK7XYnGEDbYPkL9zgLOR8SW7pv5Y0ppnTv8vFEEhW0ls5CYAXf4Ag==","signature_status":"signed_v1","signed_at":"2026-06-09T02:07:11.099455Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.12171","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4f60fa18c31597613f0e68016a1cb0786e4014a030c5ae9acdfa10ddd46f3f5d","sha256:3b2aeab23880cf4278a7c71143d573b166da0de13f075a729539496e6156100f"],"state_sha256":"cc1f7b16d29536c8b8ea4000547cb12d40d24f7319a2db1aebe54b9ae39a19ff"}