{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5NELFENSWQTHSIUUQ2OHGT5JTT","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":"a48fad65985b2082e3d3709e973b8f9fe311043ef53834db1278ba839c4079c1","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-13T00:18:34Z","title_canon_sha256":"543df4569bbaa22179cac1c376953b73c590b2c36795298d2bce778602e038ff"},"schema_version":"1.0","source":{"id":"2502.08859","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.08859","created_at":"2026-07-05T10:14:27Z"},{"alias_kind":"arxiv_version","alias_value":"2502.08859v2","created_at":"2026-07-05T10:14:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.08859","created_at":"2026-07-05T10:14:27Z"},{"alias_kind":"pith_short_12","alias_value":"5NELFENSWQTH","created_at":"2026-07-05T10:14:27Z"},{"alias_kind":"pith_short_16","alias_value":"5NELFENSWQTHSIUU","created_at":"2026-07-05T10:14:27Z"},{"alias_kind":"pith_short_8","alias_value":"5NELFENS","created_at":"2026-07-05T10:14:27Z"}],"graph_snapshots":[{"event_id":"sha256:fc5e1ee3c9c4964fd4b576906d55fc5e3dc0e00b80da447cb6937ccd1ca9114a","target":"graph","created_at":"2026-07-05T10:14:27Z","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/2502.08859/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As language models master existing reasoning benchmarks, we need new challenges to evaluate their cognitive frontiers. Puzzle-solving events are rich repositories of challenging multimodal problems that test a wide range of advanced reasoning and knowledge capabilities, making them a unique testbed for evaluating frontier language models. We introduce EnigmaEval, a dataset of problems and solutions derived from puzzle competitions and events that probes models' ability to perform implicit knowledge synthesis and multi-step deductive reasoning. Unlike existing reasoning and knowledge benchmarks","authors_text":"Adam Khoja, Clinton J. Wang, Cristina Menghini, Dan Hendrycks, Dean Lee, Jack Doughty, Jayson Lynch, Johannes Mols, Sean Hendryx, Summer Yue","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-13T00:18:34Z","title":"EnigmaEval: A Benchmark of Long Multimodal Reasoning Challenges"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.08859","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":"sha256:44310a671fc61db4f5f76bf252d87cff83709dd6b7e9ee6a473e8e11dabfadbe","target":"record","created_at":"2026-07-05T10:14:27Z","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":"a48fad65985b2082e3d3709e973b8f9fe311043ef53834db1278ba839c4079c1","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-13T00:18:34Z","title_canon_sha256":"543df4569bbaa22179cac1c376953b73c590b2c36795298d2bce778602e038ff"},"schema_version":"1.0","source":{"id":"2502.08859","kind":"arxiv","version":2}},"canonical_sha256":"eb48b291b2b426792294869c734fa99cf295ac9c2187e5c5da32aecc4b9f11ee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eb48b291b2b426792294869c734fa99cf295ac9c2187e5c5da32aecc4b9f11ee","first_computed_at":"2026-07-05T10:14:27.880961Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:14:27.880961Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"M/dQ7AOLuREDeCNObw3Qbx+gC/PaYGIGvYXRfWolV+o479FLmBM+pTpyPh/p9JDqOtGYinjuRynDyY7iYkL0BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:14:27.881484Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.08859","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:44310a671fc61db4f5f76bf252d87cff83709dd6b7e9ee6a473e8e11dabfadbe","sha256:fc5e1ee3c9c4964fd4b576906d55fc5e3dc0e00b80da447cb6937ccd1ca9114a"],"state_sha256":"bf1c13248b46fe1985659833bb46fca6468ada9589bbae364e4333052dbeac57"}