{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GLPKSP57IBUP3AR5EQPWUYE7DU","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":"e3300942e3c9e42bd31bb04e1f70e9257b4fd741fcc80de7cf838f9eea8d5483","cross_cats_sorted":["cs.AI","cs.LG","cs.LO","cs.NE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-05T17:57:50Z","title_canon_sha256":"404cc51ad2409fd2649ad750ca11794e48baa76167ef26dde4ef5aa6872cc69b"},"schema_version":"1.0","source":{"id":"2508.08292","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.08292","created_at":"2026-07-05T12:00:07Z"},{"alias_kind":"arxiv_version","alias_value":"2508.08292v2","created_at":"2026-07-05T12:00:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.08292","created_at":"2026-07-05T12:00:07Z"},{"alias_kind":"pith_short_12","alias_value":"GLPKSP57IBUP","created_at":"2026-07-05T12:00:07Z"},{"alias_kind":"pith_short_16","alias_value":"GLPKSP57IBUP3AR5","created_at":"2026-07-05T12:00:07Z"},{"alias_kind":"pith_short_8","alias_value":"GLPKSP57","created_at":"2026-07-05T12:00:07Z"}],"graph_snapshots":[{"event_id":"sha256:748c0f156069eb26b5071be34e820846d01ac3b4fa0e6023acfba0ee9e837369","target":"graph","created_at":"2026-07-05T12:00:07Z","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/2508.08292/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current mathematical reasoning benchmarks for large language models (LLMs) are approaching saturation, with some achieving > 90% accuracy, and are increasingly compromised by training-set contamination. We introduce Putnam-AXIOM, a benchmark of 522 university-level competition problems drawn from the prestigious William Lowell Putnam Mathematical Competition, and Putnam-AXIOM Variation, an unseen companion set of 100 functional variants generated by programmatically perturbing variables and constants. The variation protocol produces an unlimited stream of equally difficult, unseen instances --","authors_text":"Aryan Gulati, Brando Miranda, Bruno Dumont, Elyas Obbad, Emily Xia, Eric Chen, Kai Fronsdal, Sanmi Koyejo","cross_cats":["cs.AI","cs.LG","cs.LO","cs.NE"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-05T17:57:50Z","title":"Putnam-AXIOM: A Functional and Static Benchmark for Measuring Higher Level Mathematical Reasoning in LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.08292","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":"sha256:13878b16e66efb89ba2729445efe43ec94d4d1a1c23a58ff72b909d2405ef0f2","target":"record","created_at":"2026-07-05T12:00:07Z","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":"e3300942e3c9e42bd31bb04e1f70e9257b4fd741fcc80de7cf838f9eea8d5483","cross_cats_sorted":["cs.AI","cs.LG","cs.LO","cs.NE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-05T17:57:50Z","title_canon_sha256":"404cc51ad2409fd2649ad750ca11794e48baa76167ef26dde4ef5aa6872cc69b"},"schema_version":"1.0","source":{"id":"2508.08292","kind":"arxiv","version":2}},"canonical_sha256":"32dea93fbf4068fd823d241f6a609f1d26212c86139c2e53a9c3fd03ef5460e6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"32dea93fbf4068fd823d241f6a609f1d26212c86139c2e53a9c3fd03ef5460e6","first_computed_at":"2026-07-05T12:00:07.978095Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:00:07.978095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pRgrKeX9JfUPgs0O2ycrOZmmHS2dm4olb+G/7mfkUTkl2qXIrYD8v74MHzRPDWTlhU1cJ9dc7VOQvVB2EJiTCw==","signature_status":"signed_v1","signed_at":"2026-07-05T12:00:07.978580Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.08292","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:13878b16e66efb89ba2729445efe43ec94d4d1a1c23a58ff72b909d2405ef0f2","sha256:748c0f156069eb26b5071be34e820846d01ac3b4fa0e6023acfba0ee9e837369"],"state_sha256":"94dc65c9d50beeea575bfac790f61f8fc72c162cc205044cf89dc7d2b75679ba"}