{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NNVELSFSPWO6IJYZ7IRHFFRZ47","short_pith_number":"pith:NNVELSFS","schema_version":"1.0","canonical_sha256":"6b6a45c8b27d9de42719fa22729639e7d14175f665f57236773c844a527ae452","source":{"kind":"arxiv","id":"2406.00755","version":1},"attestation_state":"computed","paper":{"title":"Evaluating Mathematical Reasoning of Large Language Models: A Focus on Error Identification and Correction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Fuli Feng, Junrong Guo, Moxin Li, Wenjie Wang, Xiaoyuan Li, Yang Zhang","submitted_at":"2024-06-02T14:16:24Z","abstract_excerpt":"The rapid advancement of Large Language Models (LLMs) in the realm of mathematical reasoning necessitates comprehensive evaluations to gauge progress and inspire future directions. Existing assessments predominantly focus on problem-solving from the examinee perspective, overlooking a dual perspective of examiner regarding error identification and correction. From the examiner perspective, we define four evaluation tasks for error identification and correction along with a new dataset with annotated error types and steps. We also design diverse prompts to thoroughly evaluate eleven representat"},"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":"2406.00755","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-02T14:16:24Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"55f4ea8ab9696e3c3cf15f5967c3a651fba7ab0feb1c3f069db6ef25cb5fb49f","abstract_canon_sha256":"ca287ebedea60f0d0bc48b8c1f97345b66e91f0b7b46f530bf95a0e78cec745e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:27:10.245371Z","signature_b64":"VA9Dcl22EfUTEXq5N4LojbVzir2y8qDorlHYNxspZb53VzRsymq5L+3CY0Wb4J383QWV5nluEEsi6ZlzpDCMDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b6a45c8b27d9de42719fa22729639e7d14175f665f57236773c844a527ae452","last_reissued_at":"2026-07-05T08:27:10.244878Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:27:10.244878Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating Mathematical Reasoning of Large Language Models: A Focus on Error Identification and Correction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Fuli Feng, Junrong Guo, Moxin Li, Wenjie Wang, Xiaoyuan Li, Yang Zhang","submitted_at":"2024-06-02T14:16:24Z","abstract_excerpt":"The rapid advancement of Large Language Models (LLMs) in the realm of mathematical reasoning necessitates comprehensive evaluations to gauge progress and inspire future directions. Existing assessments predominantly focus on problem-solving from the examinee perspective, overlooking a dual perspective of examiner regarding error identification and correction. From the examiner perspective, we define four evaluation tasks for error identification and correction along with a new dataset with annotated error types and steps. We also design diverse prompts to thoroughly evaluate eleven representat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.00755","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/2406.00755/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":"2406.00755","created_at":"2026-07-05T08:27:10.244936+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.00755v1","created_at":"2026-07-05T08:27:10.244936+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.00755","created_at":"2026-07-05T08:27:10.244936+00:00"},{"alias_kind":"pith_short_12","alias_value":"NNVELSFSPWO6","created_at":"2026-07-05T08:27:10.244936+00:00"},{"alias_kind":"pith_short_16","alias_value":"NNVELSFSPWO6IJYZ","created_at":"2026-07-05T08:27:10.244936+00:00"},{"alias_kind":"pith_short_8","alias_value":"NNVELSFS","created_at":"2026-07-05T08:27:10.244936+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"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":34,"is_internal_anchor":false},{"citing_arxiv_id":"2502.02871","citing_title":"Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoning","ref_index":101,"is_internal_anchor":false},{"citing_arxiv_id":"2508.06226","citing_title":"GeoLaux: A Benchmark for Evaluating MLLMs' Geometry Performance on Long-Step Problems Requiring Auxiliary Lines","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22597","citing_title":"Rethinking Math Reasoning Evaluation: A Robust LLM-as-a-Judge Framework Beyond Symbolic Rigidity","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18835","citing_title":"Semantic Needles in Document Haystacks: Sensitivity Testing of LLM-as-a-Judge Similarity Scoring","ref_index":53,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NNVELSFSPWO6IJYZ7IRHFFRZ47","json":"https://pith.science/pith/NNVELSFSPWO6IJYZ7IRHFFRZ47.json","graph_json":"https://pith.science/api/pith-number/NNVELSFSPWO6IJYZ7IRHFFRZ47/graph.json","events_json":"https://pith.science/api/pith-number/NNVELSFSPWO6IJYZ7IRHFFRZ47/events.json","paper":"https://pith.science/paper/NNVELSFS"},"agent_actions":{"view_html":"https://pith.science/pith/NNVELSFSPWO6IJYZ7IRHFFRZ47","download_json":"https://pith.science/pith/NNVELSFSPWO6IJYZ7IRHFFRZ47.json","view_paper":"https://pith.science/paper/NNVELSFS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.00755&json=true","fetch_graph":"https://pith.science/api/pith-number/NNVELSFSPWO6IJYZ7IRHFFRZ47/graph.json","fetch_events":"https://pith.science/api/pith-number/NNVELSFSPWO6IJYZ7IRHFFRZ47/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NNVELSFSPWO6IJYZ7IRHFFRZ47/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NNVELSFSPWO6IJYZ7IRHFFRZ47/action/storage_attestation","attest_author":"https://pith.science/pith/NNVELSFSPWO6IJYZ7IRHFFRZ47/action/author_attestation","sign_citation":"https://pith.science/pith/NNVELSFSPWO6IJYZ7IRHFFRZ47/action/citation_signature","submit_replication":"https://pith.science/pith/NNVELSFSPWO6IJYZ7IRHFFRZ47/action/replication_record"}},"created_at":"2026-07-05T08:27:10.244936+00:00","updated_at":"2026-07-05T08:27:10.244936+00:00"}