{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WK7MJNIPW5OLCMQ5UQJEJKG3SB","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":"aa3fa19ababd8784465f7f7ca2ada7a0c1aa52d44bff08d07df648d7a0512277","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-27T19:21:05Z","title_canon_sha256":"604fc6d644092207ef784b2a059fdd834f71710b9fe57a0c64d9700f6f609a61"},"schema_version":"1.0","source":{"id":"2503.21934","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.21934","created_at":"2026-07-05T12:05:15Z"},{"alias_kind":"arxiv_version","alias_value":"2503.21934v5","created_at":"2026-07-05T12:05:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.21934","created_at":"2026-07-05T12:05:15Z"},{"alias_kind":"pith_short_12","alias_value":"WK7MJNIPW5OL","created_at":"2026-07-05T12:05:15Z"},{"alias_kind":"pith_short_16","alias_value":"WK7MJNIPW5OLCMQ5","created_at":"2026-07-05T12:05:15Z"},{"alias_kind":"pith_short_8","alias_value":"WK7MJNIP","created_at":"2026-07-05T12:05:15Z"}],"graph_snapshots":[{"event_id":"sha256:f1cf6840de759ff82fcc17b2bee7021af421cd6c114dc6b7bf569d902355cfd1","target":"graph","created_at":"2026-07-05T12:05:15Z","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/2503.21934/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent math benchmarks for large language models (LLMs) such as MathArena indicate that state-of-the-art reasoning models achieve impressive performance on mathematical competitions like AIME, with the leading model, Gemini-2.5-Pro, achieving scores comparable to top human competitors. However, these benchmarks evaluate models solely based on final numerical answers, neglecting rigorous reasoning and proof generation which are essential for real-world mathematical tasks. To address this, we introduce a comprehensive evaluation of full-solution reasoning for challenging mathematical problems. U","authors_text":"Ivo Petrov, Jasper Dekoninck, Kristian Minchev, Lyuben Baltadzhiev, Maria Drencheva, Martin Vechev, Mislav Balunovi\\'c, Nikola Jovanovi\\'c","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-27T19:21:05Z","title":"Proof or Bluff? Evaluating LLMs on 2025 USA Math Olympiad"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.21934","kind":"arxiv","version":5},"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:bb724019b2c51f74f88075b68a6fcf412051963641c87471544e9e516e73f923","target":"record","created_at":"2026-07-05T12:05:15Z","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":"aa3fa19ababd8784465f7f7ca2ada7a0c1aa52d44bff08d07df648d7a0512277","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-27T19:21:05Z","title_canon_sha256":"604fc6d644092207ef784b2a059fdd834f71710b9fe57a0c64d9700f6f609a61"},"schema_version":"1.0","source":{"id":"2503.21934","kind":"arxiv","version":5}},"canonical_sha256":"b2bec4b50fb75cb1321da41244a8db904d0ce5e42588aed9b19845e181eeafe3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b2bec4b50fb75cb1321da41244a8db904d0ce5e42588aed9b19845e181eeafe3","first_computed_at":"2026-07-05T12:05:15.335885Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:05:15.335885Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QzDtFF+EkZLT5ru6dW+KJR+0ftXFrnnCgSacq58E19vQis2WU/o/SOcaBTs7e48lUmSFMpMkZbkacGip9f6WDw==","signature_status":"signed_v1","signed_at":"2026-07-05T12:05:15.336475Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.21934","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bb724019b2c51f74f88075b68a6fcf412051963641c87471544e9e516e73f923","sha256:f1cf6840de759ff82fcc17b2bee7021af421cd6c114dc6b7bf569d902355cfd1"],"state_sha256":"92f76d10599198bf0ce1901c447bd88df1562150e7ed6e61d5950c2687bd18ad"}