{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:A5ZISYDNQWYR3RGYO4DW3EIFBD","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":"8458af8e36f93edf80bc8cc40834f0da891d52703b6d60bd25a0df45df6da039","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-30T23:37:37Z","title_canon_sha256":"6a2c4557ba2be2652faa5cc6b2666d5a8e8263bb9f6e17882c46fcf1c5da2048"},"schema_version":"1.0","source":{"id":"2506.00309","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00309","created_at":"2026-07-05T11:28:36Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00309v3","created_at":"2026-07-05T11:28:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00309","created_at":"2026-07-05T11:28:36Z"},{"alias_kind":"pith_short_12","alias_value":"A5ZISYDNQWYR","created_at":"2026-07-05T11:28:36Z"},{"alias_kind":"pith_short_16","alias_value":"A5ZISYDNQWYR3RGY","created_at":"2026-07-05T11:28:36Z"},{"alias_kind":"pith_short_8","alias_value":"A5ZISYDN","created_at":"2026-07-05T11:28:36Z"}],"graph_snapshots":[{"event_id":"sha256:c844b3ec18a99b52162e9fb3fef3ea0ddaae07081b56146aca844b487e27c0d4","target":"graph","created_at":"2026-07-05T11:28:36Z","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/2506.00309/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have shown impressive performance on a range of educational tasks, but are still understudied for their potential to solve mathematical problems. In this study, we compare three prominent LLMs, including GPT-4o, DeepSeek-V3, and Gemini-2.0, on three mathematics datasets of varying complexities (GSM8K, MATH500, and MIT Open Courseware datasets). We take a five-dimensional approach based on the Structured Chain-of-Thought (SCoT) framework to assess final answer correctness, step completeness, step validity, intermediate calculation accuracy, and problem comprehension","authors_text":"Chengfeng Wu, Qinglin Zhou, Rohitash Chandra, Runxi Wang, Ruonan Wang, Yunwen Shen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-30T23:37:37Z","title":"Evaluation of LLMs for mathematical problem solving"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00309","kind":"arxiv","version":3},"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:ada61f7355217b93c36a8c5a27e2cdc9038a67320dead59edb851753af4df98a","target":"record","created_at":"2026-07-05T11:28:36Z","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":"8458af8e36f93edf80bc8cc40834f0da891d52703b6d60bd25a0df45df6da039","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-30T23:37:37Z","title_canon_sha256":"6a2c4557ba2be2652faa5cc6b2666d5a8e8263bb9f6e17882c46fcf1c5da2048"},"schema_version":"1.0","source":{"id":"2506.00309","kind":"arxiv","version":3}},"canonical_sha256":"077289606d85b11dc4d877076d910508e1e7fc871c28847620655e3eb4d374a0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"077289606d85b11dc4d877076d910508e1e7fc871c28847620655e3eb4d374a0","first_computed_at":"2026-07-05T11:28:36.873290Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:28:36.873290Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SWvg6ZvVjveYPYtH0KObI2/k2PZzoZURJYi+AQvQk4ItMb0seeOC6Dib3gXaxOkc0mTZP8uhucRJd27D1JVXBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:28:36.873797Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.00309","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ada61f7355217b93c36a8c5a27e2cdc9038a67320dead59edb851753af4df98a","sha256:c844b3ec18a99b52162e9fb3fef3ea0ddaae07081b56146aca844b487e27c0d4"],"state_sha256":"f76fb0d761eec134b045dcce79a5976841a3cff7ae950b137911d18882ef257a"}