{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VQ2A3KPYQHAX55NZOIGZBV3CX2","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":"2c8599789631bde5ffb069a06463b7aa01f74e15a90c611a77527ad7af653909","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-22T16:06:49Z","title_canon_sha256":"b25d692a89e6433ed52c4c4ea82460209275b4a8b60fd100f679edae48cf4b64"},"schema_version":"1.0","source":{"id":"2402.14660","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.14660","created_at":"2026-07-05T07:48:35Z"},{"alias_kind":"arxiv_version","alias_value":"2402.14660v2","created_at":"2026-07-05T07:48:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.14660","created_at":"2026-07-05T07:48:35Z"},{"alias_kind":"pith_short_12","alias_value":"VQ2A3KPYQHAX","created_at":"2026-07-05T07:48:35Z"},{"alias_kind":"pith_short_16","alias_value":"VQ2A3KPYQHAX55NZ","created_at":"2026-07-05T07:48:35Z"},{"alias_kind":"pith_short_8","alias_value":"VQ2A3KPY","created_at":"2026-07-05T07:48:35Z"}],"graph_snapshots":[{"event_id":"sha256:e26438051d4ed78cde9d1e7d4e51d1f92481a9e76a017945efec65f33eff07fa","target":"graph","created_at":"2026-07-05T07:48:35Z","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/2402.14660/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-22T16:06:49Z","title":"ConceptMath: A Bilingual Concept-wise Benchmark for Measuring Mathematical Reasoning of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.14660","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":"sha256:20af455819326df3bfc0ffaaad821bff01797675977bbaf4d2b2ff22460a8410","target":"record","created_at":"2026-07-05T07:48:35Z","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":"2c8599789631bde5ffb069a06463b7aa01f74e15a90c611a77527ad7af653909","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-22T16:06:49Z","title_canon_sha256":"b25d692a89e6433ed52c4c4ea82460209275b4a8b60fd100f679edae48cf4b64"},"schema_version":"1.0","source":{"id":"2402.14660","kind":"arxiv","version":2}},"canonical_sha256":"ac340da9f881c17ef5b9720d90d762be8b55b053ba087ded9d903722bcd05d45","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ac340da9f881c17ef5b9720d90d762be8b55b053ba087ded9d903722bcd05d45","first_computed_at":"2026-07-05T07:48:35.421821Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:48:35.421821Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pmBeop3dUV+4NVmovwGSXTKjnrlMBwF5O9Y6P4Ch2reCZH+ifp2zkqG++vqxo7xqwbr5FpGFrx600ByEhPIXDA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:48:35.422338Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.14660","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:20af455819326df3bfc0ffaaad821bff01797675977bbaf4d2b2ff22460a8410","sha256:e26438051d4ed78cde9d1e7d4e51d1f92481a9e76a017945efec65f33eff07fa"],"state_sha256":"dd3b08f340bbfd4aa88ada3af0b36c402529225db7793ca3e81ae9ededd1dcbb"}