{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZG7HCOSIWWJI65GA6LYLHCGPGU","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":"3006b638af2337a5d6c615a6be7f734ec5032127580cda36d5cf90b39fe52a28","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-20T17:52:29Z","title_canon_sha256":"c6835d37feddc382ef75929dba501149b0904614bb9c5635496fa63d95aedd46"},"schema_version":"1.0","source":{"id":"2405.12209","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.12209","created_at":"2026-07-05T08:21:01Z"},{"alias_kind":"arxiv_version","alias_value":"2405.12209v1","created_at":"2026-07-05T08:21:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.12209","created_at":"2026-07-05T08:21:01Z"},{"alias_kind":"pith_short_12","alias_value":"ZG7HCOSIWWJI","created_at":"2026-07-05T08:21:01Z"},{"alias_kind":"pith_short_16","alias_value":"ZG7HCOSIWWJI65GA","created_at":"2026-07-05T08:21:01Z"},{"alias_kind":"pith_short_8","alias_value":"ZG7HCOSI","created_at":"2026-07-05T08:21:01Z"}],"graph_snapshots":[{"event_id":"sha256:7641dd19d17705d1a55b02ccb70d02b55bd005dea84905e18786e1339fbd1838","target":"graph","created_at":"2026-07-05T08:21:01Z","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/2405.12209/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in large language models (LLMs) have showcased significant improvements in mathematics. However, traditional math benchmarks like GSM8k offer a unidimensional perspective, falling short in providing a holistic assessment of the LLMs' math capabilities. To address this gap, we introduce MathBench, a new benchmark that rigorously assesses the mathematical capabilities of large language models. MathBench spans a wide range of mathematical disciplines, offering a detailed evaluation of both theoretical understanding and practical problem-solving skills. The benchmark progresses","authors_text":"Dahua Lin, Fengzhe Zhou, Haodong Duan, Hongwei Liu, Kai Chen, Songyang Zhang, Wenwei Zhang, Yuxuan Qiao, Zhiwei Fei, Zilong Zheng","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-20T17:52:29Z","title":"MathBench: Evaluating the Theory and Application Proficiency of LLMs with a Hierarchical Mathematics Benchmark"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.12209","kind":"arxiv","version":1},"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":"sha256:04d934f94093461ec6adbf89bed2e1e5d2e80e63b24b62b36ed742765d168cd5","target":"record","created_at":"2026-07-05T08:21:01Z","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":"3006b638af2337a5d6c615a6be7f734ec5032127580cda36d5cf90b39fe52a28","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-20T17:52:29Z","title_canon_sha256":"c6835d37feddc382ef75929dba501149b0904614bb9c5635496fa63d95aedd46"},"schema_version":"1.0","source":{"id":"2405.12209","kind":"arxiv","version":1}},"canonical_sha256":"c9be713a48b5928f74c0f2f0b388cf3523b33c5d85f01747b75edc9555feeb0f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c9be713a48b5928f74c0f2f0b388cf3523b33c5d85f01747b75edc9555feeb0f","first_computed_at":"2026-07-05T08:21:01.656172Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:21:01.656172Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1q9FTB3CEtFhXsU32LGtySZsh35zaNXjB1ngj4z7QKTy/fj1zUwBZLa20roJONkTi5RcHFB4tvWxiG9/F1/9DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:21:01.656660Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.12209","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:04d934f94093461ec6adbf89bed2e1e5d2e80e63b24b62b36ed742765d168cd5","sha256:7641dd19d17705d1a55b02ccb70d02b55bd005dea84905e18786e1339fbd1838"],"state_sha256":"1d4a39fe1ca6cd199ae1a5e44908e6f0c2b4fc1b94f79c0ed440f3e361fc7311"}