{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RG6DV36NBNPWMYDKWPJAUP4W24","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":"8ae513bfc7574d4cd59f058bfa264ca8d5773258137eddbf9eb977d75e6b67b6","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-22T02:24:35Z","title_canon_sha256":"54c7bc405e367d2006b826934d8a1a95006f60d302d886eef9a96f467af17524"},"schema_version":"1.0","source":{"id":"2505.16135","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.16135","created_at":"2026-07-05T11:07:30Z"},{"alias_kind":"arxiv_version","alias_value":"2505.16135v1","created_at":"2026-07-05T11:07:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16135","created_at":"2026-07-05T11:07:30Z"},{"alias_kind":"pith_short_12","alias_value":"RG6DV36NBNPW","created_at":"2026-07-05T11:07:30Z"},{"alias_kind":"pith_short_16","alias_value":"RG6DV36NBNPWMYDK","created_at":"2026-07-05T11:07:30Z"},{"alias_kind":"pith_short_8","alias_value":"RG6DV36N","created_at":"2026-07-05T11:07:30Z"}],"graph_snapshots":[{"event_id":"sha256:9603940b2fa599aa28b58d7590abe2aeb682738bf90bf6433871f7eb7fbe1280","target":"graph","created_at":"2026-07-05T11:07:30Z","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/2505.16135/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing reasoning benchmarks for large language models (LLMs) frequently fail to capture authentic creativity, often rewarding memorization of previously observed patterns. We address this shortcoming with Sudoku-Bench, a curated benchmark of challenging and unconventional Sudoku variants specifically selected to evaluate creative, multi-step logical reasoning. Sudoku variants form an unusually effective domain for reasoning research: each puzzle introduces unique or subtly interacting constraints, making memorization infeasible and requiring solvers to identify novel logical breakthroughs (`","authors_text":"Edoardo Cetin, Jeffrey Seely, Llion Jones, Tianyu Zhao, Yuki Imajuku","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-22T02:24:35Z","title":"Sudoku-Bench: Evaluating creative reasoning with Sudoku variants"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16135","kind":"arxiv","version":1},"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":"sha256:59f6acfa3eee71c0c5c77d9f60b30e37bb82f1b82f0ddde6dd316f28cd938436","target":"record","created_at":"2026-07-05T11:07:30Z","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":"8ae513bfc7574d4cd59f058bfa264ca8d5773258137eddbf9eb977d75e6b67b6","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-22T02:24:35Z","title_canon_sha256":"54c7bc405e367d2006b826934d8a1a95006f60d302d886eef9a96f467af17524"},"schema_version":"1.0","source":{"id":"2505.16135","kind":"arxiv","version":1}},"canonical_sha256":"89bc3aefcd0b5f66606ab3d20a3f96d713c6fd8b5581f21a32b15a8c057aa300","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"89bc3aefcd0b5f66606ab3d20a3f96d713c6fd8b5581f21a32b15a8c057aa300","first_computed_at":"2026-07-05T11:07:30.467121Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:07:30.467121Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hb53MeckinGwEF2T6dYT4gVzdpciRhcUlfR5g+LTt84qD0axSCdJ3H+nC/9FbWxr61jPrXF34By7VCwje5aWDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:07:30.467655Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.16135","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:59f6acfa3eee71c0c5c77d9f60b30e37bb82f1b82f0ddde6dd316f28cd938436","sha256:9603940b2fa599aa28b58d7590abe2aeb682738bf90bf6433871f7eb7fbe1280"],"state_sha256":"1ea82efd4edb5e3ae4a809fc81faf52fa34d975f1e4105ffcb99c732212dc4a4"}