{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NZ24QCSVA5E6FSBPVMBQM4EMFV","short_pith_number":"pith:NZ24QCSV","schema_version":"1.0","canonical_sha256":"6e75c80a550749e2c82fab0306708c2d738d5bd99d6152c6012306a6029ca7e2","source":{"kind":"arxiv","id":"2409.03161","version":2},"attestation_state":"computed","paper":{"title":"MaterialBENCH: Evaluating College-Level Materials Science Problem-Solving Abilities of Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cond-mat.mtrl-sci"],"primary_cat":"cs.CL","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)","submitted_at":"2024-09-05T01:36:00Z","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"},"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":"2409.03161","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-05T01:36:00Z","cross_cats_sorted":["cond-mat.mtrl-sci"],"title_canon_sha256":"1789a600d857d24425ecc6007a188733877ac4911940f6ea576197f787436047","abstract_canon_sha256":"0195a91ef7ff99ce647ac3d3e071659eab2411a58ffd266a1e1d7d9912f2adbc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:41:40.989040Z","signature_b64":"N49u5x1N/hyt1XpUkM0Do/lofPtkyzNq98GbN3vvVSiH9HOzFQCOJhm59Up4UFdgXdq5vQUfR4xTgaICUyuxBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e75c80a550749e2c82fab0306708c2d738d5bd99d6152c6012306a6029ca7e2","last_reissued_at":"2026-07-05T09:41:40.988484Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:41:40.988484Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MaterialBENCH: Evaluating College-Level Materials Science Problem-Solving Abilities of Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cond-mat.mtrl-sci"],"primary_cat":"cs.CL","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)","submitted_at":"2024-09-05T01:36:00Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.03161","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/2409.03161/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":"2409.03161","created_at":"2026-07-05T09:41:40.988566+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.03161v2","created_at":"2026-07-05T09:41:40.988566+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.03161","created_at":"2026-07-05T09:41:40.988566+00:00"},{"alias_kind":"pith_short_12","alias_value":"NZ24QCSVA5E6","created_at":"2026-07-05T09:41:40.988566+00:00"},{"alias_kind":"pith_short_16","alias_value":"NZ24QCSVA5E6FSBP","created_at":"2026-07-05T09:41:40.988566+00:00"},{"alias_kind":"pith_short_8","alias_value":"NZ24QCSV","created_at":"2026-07-05T09:41:40.988566+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NZ24QCSVA5E6FSBPVMBQM4EMFV","json":"https://pith.science/pith/NZ24QCSVA5E6FSBPVMBQM4EMFV.json","graph_json":"https://pith.science/api/pith-number/NZ24QCSVA5E6FSBPVMBQM4EMFV/graph.json","events_json":"https://pith.science/api/pith-number/NZ24QCSVA5E6FSBPVMBQM4EMFV/events.json","paper":"https://pith.science/paper/NZ24QCSV"},"agent_actions":{"view_html":"https://pith.science/pith/NZ24QCSVA5E6FSBPVMBQM4EMFV","download_json":"https://pith.science/pith/NZ24QCSVA5E6FSBPVMBQM4EMFV.json","view_paper":"https://pith.science/paper/NZ24QCSV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.03161&json=true","fetch_graph":"https://pith.science/api/pith-number/NZ24QCSVA5E6FSBPVMBQM4EMFV/graph.json","fetch_events":"https://pith.science/api/pith-number/NZ24QCSVA5E6FSBPVMBQM4EMFV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NZ24QCSVA5E6FSBPVMBQM4EMFV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NZ24QCSVA5E6FSBPVMBQM4EMFV/action/storage_attestation","attest_author":"https://pith.science/pith/NZ24QCSVA5E6FSBPVMBQM4EMFV/action/author_attestation","sign_citation":"https://pith.science/pith/NZ24QCSVA5E6FSBPVMBQM4EMFV/action/citation_signature","submit_replication":"https://pith.science/pith/NZ24QCSVA5E6FSBPVMBQM4EMFV/action/replication_record"}},"created_at":"2026-07-05T09:41:40.988566+00:00","updated_at":"2026-07-05T09:41:40.988566+00:00"}