{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NZ24QCSVA5E6FSBPVMBQM4EMFV","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":"0195a91ef7ff99ce647ac3d3e071659eab2411a58ffd266a1e1d7d9912f2adbc","cross_cats_sorted":["cond-mat.mtrl-sci"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-05T01:36:00Z","title_canon_sha256":"1789a600d857d24425ecc6007a188733877ac4911940f6ea576197f787436047"},"schema_version":"1.0","source":{"id":"2409.03161","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.03161","created_at":"2026-07-05T09:41:40Z"},{"alias_kind":"arxiv_version","alias_value":"2409.03161v2","created_at":"2026-07-05T09:41:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.03161","created_at":"2026-07-05T09:41:40Z"},{"alias_kind":"pith_short_12","alias_value":"NZ24QCSVA5E6","created_at":"2026-07-05T09:41:40Z"},{"alias_kind":"pith_short_16","alias_value":"NZ24QCSVA5E6FSBP","created_at":"2026-07-05T09:41:40Z"},{"alias_kind":"pith_short_8","alias_value":"NZ24QCSV","created_at":"2026-07-05T09:41:40Z"}],"graph_snapshots":[{"event_id":"sha256:d90f2ee1056e815f64a2a60cb2305708d43b8cada831e234a35ed36219c529d9","target":"graph","created_at":"2026-07-05T09:41:40Z","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/2409.03161/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A college-level benchmark dataset for large language models (LLMs) in the materials science field, MaterialBENCH, is constructed. This dataset consists of problem-answer pairs, based on university textbooks. There are two types of problems: one is the free-response answer type, and the other is the multiple-choice type. Multiple-choice problems are constructed by adding three incorrect answers as choices to a correct answer, so that LLMs can choose one of the four as a response. Most of the problems for free-response answer and multiple-choice types overlap except for the format of the answers","authors_text":"(2) Osaka Univ., (3) Univ. Tokyo), Keisuke Nagato (3) ((1) OMRON SINIC X, Michiko Yoshitake (1), Ryo Igarashi (1), Yoshitaka Ushiku (1), Yuta Suzuki (2)","cross_cats":["cond-mat.mtrl-sci"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-05T01:36:00Z","title":"MaterialBENCH: Evaluating College-Level Materials Science Problem-Solving Abilities of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.03161","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:e2fc68fe96641de00c677dc43710f780a646cfd2884ac604dccc464ee66a7162","target":"record","created_at":"2026-07-05T09:41:40Z","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":"0195a91ef7ff99ce647ac3d3e071659eab2411a58ffd266a1e1d7d9912f2adbc","cross_cats_sorted":["cond-mat.mtrl-sci"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-05T01:36:00Z","title_canon_sha256":"1789a600d857d24425ecc6007a188733877ac4911940f6ea576197f787436047"},"schema_version":"1.0","source":{"id":"2409.03161","kind":"arxiv","version":2}},"canonical_sha256":"6e75c80a550749e2c82fab0306708c2d738d5bd99d6152c6012306a6029ca7e2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6e75c80a550749e2c82fab0306708c2d738d5bd99d6152c6012306a6029ca7e2","first_computed_at":"2026-07-05T09:41:40.988484Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:41:40.988484Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"N49u5x1N/hyt1XpUkM0Do/lofPtkyzNq98GbN3vvVSiH9HOzFQCOJhm59Up4UFdgXdq5vQUfR4xTgaICUyuxBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:41:40.989040Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.03161","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e2fc68fe96641de00c677dc43710f780a646cfd2884ac604dccc464ee66a7162","sha256:d90f2ee1056e815f64a2a60cb2305708d43b8cada831e234a35ed36219c529d9"],"state_sha256":"8807755cd769c607122769f95adaef52fd923ab4b7e91ae476c2f63694fabd42"}