{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZG7HCOSIWWJI65GA6LYLHCGPGU","short_pith_number":"pith:ZG7HCOSI","schema_version":"1.0","canonical_sha256":"c9be713a48b5928f74c0f2f0b388cf3523b33c5d85f01747b75edc9555feeb0f","source":{"kind":"arxiv","id":"2405.12209","version":1},"attestation_state":"computed","paper":{"title":"MathBench: Evaluating the Theory and Application Proficiency of LLMs with a Hierarchical Mathematics Benchmark","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dahua Lin, Fengzhe Zhou, Haodong Duan, Hongwei Liu, Kai Chen, Songyang Zhang, Wenwei Zhang, Yuxuan Qiao, Zhiwei Fei, Zilong Zheng","submitted_at":"2024-05-20T17:52:29Z","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"},"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":"2405.12209","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-20T17:52:29Z","cross_cats_sorted":[],"title_canon_sha256":"c6835d37feddc382ef75929dba501149b0904614bb9c5635496fa63d95aedd46","abstract_canon_sha256":"3006b638af2337a5d6c615a6be7f734ec5032127580cda36d5cf90b39fe52a28"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:21:01.656660Z","signature_b64":"1q9FTB3CEtFhXsU32LGtySZsh35zaNXjB1ngj4z7QKTy/fj1zUwBZLa20roJONkTi5RcHFB4tvWxiG9/F1/9DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c9be713a48b5928f74c0f2f0b388cf3523b33c5d85f01747b75edc9555feeb0f","last_reissued_at":"2026-07-05T08:21:01.656172Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:21:01.656172Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MathBench: Evaluating the Theory and Application Proficiency of LLMs with a Hierarchical Mathematics Benchmark","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dahua Lin, Fengzhe Zhou, Haodong Duan, Hongwei Liu, Kai Chen, Songyang Zhang, Wenwei Zhang, Yuxuan Qiao, Zhiwei Fei, Zilong Zheng","submitted_at":"2024-05-20T17:52:29Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.12209","kind":"arxiv","version":1},"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/2405.12209/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":"2405.12209","created_at":"2026-07-05T08:21:01.656228+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.12209v1","created_at":"2026-07-05T08:21:01.656228+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.12209","created_at":"2026-07-05T08:21:01.656228+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZG7HCOSIWWJI","created_at":"2026-07-05T08:21:01.656228+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZG7HCOSIWWJI65GA","created_at":"2026-07-05T08:21:01.656228+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZG7HCOSI","created_at":"2026-07-05T08:21:01.656228+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2410.04509","citing_title":"ErrorRadar: Benchmarking Complex Mathematical Reasoning of Multimodal Large Language Models Via Error Detection","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2503.16549","citing_title":"MathFlow: Enhancing the Perceptual Flow of MLLMs for Visual Mathematical Problems","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2504.19451","citing_title":"Computational Experiments in Number Theory","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15851","citing_title":"DPrivBench: Benchmarking LLMs' Reasoning for Differential Privacy","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16593","citing_title":"Revisiting a Pain in the Neck: A Semantic Reasoning Benchmark for Language Models","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15851","citing_title":"DPrivBench: Benchmarking LLMs' Reasoning for Differential Privacy","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16593","citing_title":"Revisiting a Pain in the Neck: A Semantic Reasoning Benchmark for Language Models","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZG7HCOSIWWJI65GA6LYLHCGPGU","json":"https://pith.science/pith/ZG7HCOSIWWJI65GA6LYLHCGPGU.json","graph_json":"https://pith.science/api/pith-number/ZG7HCOSIWWJI65GA6LYLHCGPGU/graph.json","events_json":"https://pith.science/api/pith-number/ZG7HCOSIWWJI65GA6LYLHCGPGU/events.json","paper":"https://pith.science/paper/ZG7HCOSI"},"agent_actions":{"view_html":"https://pith.science/pith/ZG7HCOSIWWJI65GA6LYLHCGPGU","download_json":"https://pith.science/pith/ZG7HCOSIWWJI65GA6LYLHCGPGU.json","view_paper":"https://pith.science/paper/ZG7HCOSI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.12209&json=true","fetch_graph":"https://pith.science/api/pith-number/ZG7HCOSIWWJI65GA6LYLHCGPGU/graph.json","fetch_events":"https://pith.science/api/pith-number/ZG7HCOSIWWJI65GA6LYLHCGPGU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZG7HCOSIWWJI65GA6LYLHCGPGU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZG7HCOSIWWJI65GA6LYLHCGPGU/action/storage_attestation","attest_author":"https://pith.science/pith/ZG7HCOSIWWJI65GA6LYLHCGPGU/action/author_attestation","sign_citation":"https://pith.science/pith/ZG7HCOSIWWJI65GA6LYLHCGPGU/action/citation_signature","submit_replication":"https://pith.science/pith/ZG7HCOSIWWJI65GA6LYLHCGPGU/action/replication_record"}},"created_at":"2026-07-05T08:21:01.656228+00:00","updated_at":"2026-07-05T08:21:01.656228+00:00"}