{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VQ2A3KPYQHAX55NZOIGZBV3CX2","short_pith_number":"pith:VQ2A3KPY","schema_version":"1.0","canonical_sha256":"ac340da9f881c17ef5b9720d90d762be8b55b053ba087ded9d903722bcd05d45","source":{"kind":"arxiv","id":"2402.14660","version":2},"attestation_state":"computed","paper":{"title":"ConceptMath: A Bilingual Concept-wise Benchmark for Measuring Mathematical Reasoning of Large Language Models","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bo Zheng, Chenchen Zhang, Haibin Chen, Jiaheng Liu, Jie Liu, Tiezheng Ge, Wanli Ouyang, Wenbo Su, Xingyuan Bu, Yanan Wu, Yuanxing Zhang, Zhanhui Zhou, Zhiqi Bai","submitted_at":"2024-02-22T16:06:49Z","abstract_excerpt":"This paper introduces ConceptMath, a bilingual (English and Chinese), fine-grained benchmark that evaluates concept-wise mathematical reasoning of Large Language Models (LLMs). Unlike traditional benchmarks that evaluate general mathematical reasoning with an average accuracy, ConceptMath systematically organizes math problems under a hierarchy of math concepts, so that mathematical reasoning can be evaluated at different granularity with concept-wise accuracies. Based on our ConcepthMath, we evaluate a broad range of LLMs, and we observe existing LLMs, though achieving high average accuracies"},"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":"2402.14660","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-22T16:06:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b25d692a89e6433ed52c4c4ea82460209275b4a8b60fd100f679edae48cf4b64","abstract_canon_sha256":"2c8599789631bde5ffb069a06463b7aa01f74e15a90c611a77527ad7af653909"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:48:35.422338Z","signature_b64":"pmBeop3dUV+4NVmovwGSXTKjnrlMBwF5O9Y6P4Ch2reCZH+ifp2zkqG++vqxo7xqwbr5FpGFrx600ByEhPIXDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac340da9f881c17ef5b9720d90d762be8b55b053ba087ded9d903722bcd05d45","last_reissued_at":"2026-07-05T07:48:35.421821Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:48:35.421821Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ConceptMath: A Bilingual Concept-wise Benchmark for Measuring Mathematical Reasoning of Large Language Models","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bo Zheng, Chenchen Zhang, Haibin Chen, Jiaheng Liu, Jie Liu, Tiezheng Ge, Wanli Ouyang, Wenbo Su, Xingyuan Bu, Yanan Wu, Yuanxing Zhang, Zhanhui Zhou, Zhiqi Bai","submitted_at":"2024-02-22T16:06:49Z","abstract_excerpt":"This paper introduces ConceptMath, a bilingual (English and Chinese), fine-grained benchmark that evaluates concept-wise mathematical reasoning of Large Language Models (LLMs). Unlike traditional benchmarks that evaluate general mathematical reasoning with an average accuracy, ConceptMath systematically organizes math problems under a hierarchy of math concepts, so that mathematical reasoning can be evaluated at different granularity with concept-wise accuracies. Based on our ConcepthMath, we evaluate a broad range of LLMs, and we observe existing LLMs, though achieving high average accuracies"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.14660","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/2402.14660/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":"2402.14660","created_at":"2026-07-05T07:48:35.421885+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.14660v2","created_at":"2026-07-05T07:48:35.421885+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.14660","created_at":"2026-07-05T07:48:35.421885+00:00"},{"alias_kind":"pith_short_12","alias_value":"VQ2A3KPYQHAX","created_at":"2026-07-05T07:48:35.421885+00:00"},{"alias_kind":"pith_short_16","alias_value":"VQ2A3KPYQHAX55NZ","created_at":"2026-07-05T07:48:35.421885+00:00"},{"alias_kind":"pith_short_8","alias_value":"VQ2A3KPY","created_at":"2026-07-05T07:48:35.421885+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.10454","citing_title":"One Example Shown, Many Concepts Known! Counterexample-Driven Conceptual Reasoning in Mathematical LLMs","ref_index":48,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VQ2A3KPYQHAX55NZOIGZBV3CX2","json":"https://pith.science/pith/VQ2A3KPYQHAX55NZOIGZBV3CX2.json","graph_json":"https://pith.science/api/pith-number/VQ2A3KPYQHAX55NZOIGZBV3CX2/graph.json","events_json":"https://pith.science/api/pith-number/VQ2A3KPYQHAX55NZOIGZBV3CX2/events.json","paper":"https://pith.science/paper/VQ2A3KPY"},"agent_actions":{"view_html":"https://pith.science/pith/VQ2A3KPYQHAX55NZOIGZBV3CX2","download_json":"https://pith.science/pith/VQ2A3KPYQHAX55NZOIGZBV3CX2.json","view_paper":"https://pith.science/paper/VQ2A3KPY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.14660&json=true","fetch_graph":"https://pith.science/api/pith-number/VQ2A3KPYQHAX55NZOIGZBV3CX2/graph.json","fetch_events":"https://pith.science/api/pith-number/VQ2A3KPYQHAX55NZOIGZBV3CX2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VQ2A3KPYQHAX55NZOIGZBV3CX2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VQ2A3KPYQHAX55NZOIGZBV3CX2/action/storage_attestation","attest_author":"https://pith.science/pith/VQ2A3KPYQHAX55NZOIGZBV3CX2/action/author_attestation","sign_citation":"https://pith.science/pith/VQ2A3KPYQHAX55NZOIGZBV3CX2/action/citation_signature","submit_replication":"https://pith.science/pith/VQ2A3KPYQHAX55NZOIGZBV3CX2/action/replication_record"}},"created_at":"2026-07-05T07:48:35.421885+00:00","updated_at":"2026-07-05T07:48:35.421885+00:00"}