{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RODYI6IB5PM33XNXM453GL7A2U","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":"e81c6665c965eb802a8346a5f6f3909de146e12fe10c403a81f65ee61f6ff1ed","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-23T15:46:43Z","title_canon_sha256":"63efa8c70b58bba8f24514b11004d213681051ee1ffb30882080b886b4b596fc"},"schema_version":"1.0","source":{"id":"2501.13766","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.13766","created_at":"2026-07-05T10:19:37Z"},{"alias_kind":"arxiv_version","alias_value":"2501.13766v2","created_at":"2026-07-05T10:19:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.13766","created_at":"2026-07-05T10:19:37Z"},{"alias_kind":"pith_short_12","alias_value":"RODYI6IB5PM3","created_at":"2026-07-05T10:19:37Z"},{"alias_kind":"pith_short_16","alias_value":"RODYI6IB5PM33XNX","created_at":"2026-07-05T10:19:37Z"},{"alias_kind":"pith_short_8","alias_value":"RODYI6IB","created_at":"2026-07-05T10:19:37Z"}],"graph_snapshots":[{"event_id":"sha256:6601d2e482dd12415ec660ff1615d515805d42d3e184a3c0c593c2d29bcf2e5b","target":"graph","created_at":"2026-07-05T10:19:37Z","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/2501.13766/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have made significant strides in mathematical reasoning, underscoring the need for a comprehensive and fair evaluation of their capabilities. However, existing benchmarks often fall short, either lacking extensive coverage of undergraduate-level mathematical problems or probably suffering from test-set contamination. To address these issues, we introduce UGMathBench, a diverse and dynamic benchmark specifically designed for evaluating undergraduate-level mathematical reasoning with LLMs. UGMathBench comprises 5,062 problems across 16 subjects and 111 topics, featur","authors_text":"Can Yang, Jiaxin Zhang, Jishan Hu, Tianhao Chen, Xin Xu, Zitong Chao","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-23T15:46:43Z","title":"UGMathBench: A Diverse and Dynamic Benchmark for Undergraduate-Level Mathematical Reasoning with Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.13766","kind":"arxiv","version":2},"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":"sha256:872c639f1d1a11a3ddaef443833accf628f488a7b392e854b7b1d2c9bf452b22","target":"record","created_at":"2026-07-05T10:19:37Z","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":"e81c6665c965eb802a8346a5f6f3909de146e12fe10c403a81f65ee61f6ff1ed","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-23T15:46:43Z","title_canon_sha256":"63efa8c70b58bba8f24514b11004d213681051ee1ffb30882080b886b4b596fc"},"schema_version":"1.0","source":{"id":"2501.13766","kind":"arxiv","version":2}},"canonical_sha256":"8b87847901ebd9bdddb7673bb32fe0d518a8717cfb4125069c9009db98da56a4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8b87847901ebd9bdddb7673bb32fe0d518a8717cfb4125069c9009db98da56a4","first_computed_at":"2026-07-05T10:19:37.045404Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:19:37.045404Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S7TyzesqL5DVvnFtvQhZ7LAGYZdmqnUCmzh5pKuhY33Li0onGtLv4Erzhj2U+FwUnGqA9RMRrJHQU4f2IaslAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:19:37.045872Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.13766","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:872c639f1d1a11a3ddaef443833accf628f488a7b392e854b7b1d2c9bf452b22","sha256:6601d2e482dd12415ec660ff1615d515805d42d3e184a3c0c593c2d29bcf2e5b"],"state_sha256":"e59308aacf493a5454e0b2dabc7ec8b6416c5e571eafd659e8c12262e3d6aa5e"}