{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NNVELSFSPWO6IJYZ7IRHFFRZ47","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":"ca287ebedea60f0d0bc48b8c1f97345b66e91f0b7b46f530bf95a0e78cec745e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-02T14:16:24Z","title_canon_sha256":"55f4ea8ab9696e3c3cf15f5967c3a651fba7ab0feb1c3f069db6ef25cb5fb49f"},"schema_version":"1.0","source":{"id":"2406.00755","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.00755","created_at":"2026-07-05T08:27:10Z"},{"alias_kind":"arxiv_version","alias_value":"2406.00755v1","created_at":"2026-07-05T08:27:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.00755","created_at":"2026-07-05T08:27:10Z"},{"alias_kind":"pith_short_12","alias_value":"NNVELSFSPWO6","created_at":"2026-07-05T08:27:10Z"},{"alias_kind":"pith_short_16","alias_value":"NNVELSFSPWO6IJYZ","created_at":"2026-07-05T08:27:10Z"},{"alias_kind":"pith_short_8","alias_value":"NNVELSFS","created_at":"2026-07-05T08:27:10Z"}],"graph_snapshots":[{"event_id":"sha256:e0976132e0e2bb682a30f03baf8d3bf442ac9d452699300056955cfbe07f99f4","target":"graph","created_at":"2026-07-05T08:27:10Z","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/2406.00755/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Fuli Feng, Junrong Guo, Moxin Li, Wenjie Wang, Xiaoyuan Li, Yang Zhang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-02T14:16:24Z","title":"Evaluating Mathematical Reasoning of Large Language Models: A Focus on Error Identification and Correction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.00755","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":"sha256:22ede8b6bcd6c4caea3b408e21b3d51a2db52e24544228468c5c41e80551c9e9","target":"record","created_at":"2026-07-05T08:27:10Z","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":"ca287ebedea60f0d0bc48b8c1f97345b66e91f0b7b46f530bf95a0e78cec745e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-02T14:16:24Z","title_canon_sha256":"55f4ea8ab9696e3c3cf15f5967c3a651fba7ab0feb1c3f069db6ef25cb5fb49f"},"schema_version":"1.0","source":{"id":"2406.00755","kind":"arxiv","version":1}},"canonical_sha256":"6b6a45c8b27d9de42719fa22729639e7d14175f665f57236773c844a527ae452","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6b6a45c8b27d9de42719fa22729639e7d14175f665f57236773c844a527ae452","first_computed_at":"2026-07-05T08:27:10.244878Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:27:10.244878Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VA9Dcl22EfUTEXq5N4LojbVzir2y8qDorlHYNxspZb53VzRsymq5L+3CY0Wb4J383QWV5nluEEsi6ZlzpDCMDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:27:10.245371Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.00755","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:22ede8b6bcd6c4caea3b408e21b3d51a2db52e24544228468c5c41e80551c9e9","sha256:e0976132e0e2bb682a30f03baf8d3bf442ac9d452699300056955cfbe07f99f4"],"state_sha256":"c2197832eed5a29ff012f1b28ed1ea01cdc9e5dbd4ace2b590cee02e723eae29"}