{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DFVYWZHKCJEWOUNW3PRJFZK2CE","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":"6501993ff04be18b17060b4eaf78eb088c5c92833afd47e0bce4d26abe9e5b3f","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-03T06:44:49Z","title_canon_sha256":"8218633ce41279d54796d5ecb6e0e45be7dd0da8436105160443a13ebc8a83f7"},"schema_version":"1.0","source":{"id":"2502.01100","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.01100","created_at":"2026-07-05T11:37:15Z"},{"alias_kind":"arxiv_version","alias_value":"2502.01100v2","created_at":"2026-07-05T11:37:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.01100","created_at":"2026-07-05T11:37:15Z"},{"alias_kind":"pith_short_12","alias_value":"DFVYWZHKCJEW","created_at":"2026-07-05T11:37:15Z"},{"alias_kind":"pith_short_16","alias_value":"DFVYWZHKCJEWOUNW","created_at":"2026-07-05T11:37:15Z"},{"alias_kind":"pith_short_8","alias_value":"DFVYWZHK","created_at":"2026-07-05T11:37:15Z"}],"graph_snapshots":[{"event_id":"sha256:4478f270c9058398165f39d8b13af5afd44c77f3fa8da18fafa8faf6e635326c","target":"graph","created_at":"2026-07-05T11:37:15Z","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/2502.01100/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We investigate the logical reasoning capabilities of large language models (LLMs) and their scalability in complex non-monotonic reasoning. To this end, we introduce ZebraLogic, a comprehensive evaluation framework for assessing LLM reasoning performance on logic grid puzzles derived from constraint satisfaction problems (CSPs). ZebraLogic enables the generation of puzzles with controllable and quantifiable complexity, facilitating a systematic study of the scaling limits of models such as Llama, o1 models, and DeepSeek-R1. By encompassing a broad range of search space complexities and diverse","authors_text":"Ashish Sabharwal, Bill Yuchen Lin, Kyle Richardson, Peter Clark, Radha Poovendran, Ronan Le Bras, Yejin Choi","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-03T06:44:49Z","title":"ZebraLogic: On the Scaling Limits of LLMs for Logical Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.01100","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:f5f0019b990f46a824de3360f27879a57891037a3d7f867b097ac8ab85677802","target":"record","created_at":"2026-07-05T11:37:15Z","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":"6501993ff04be18b17060b4eaf78eb088c5c92833afd47e0bce4d26abe9e5b3f","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-03T06:44:49Z","title_canon_sha256":"8218633ce41279d54796d5ecb6e0e45be7dd0da8436105160443a13ebc8a83f7"},"schema_version":"1.0","source":{"id":"2502.01100","kind":"arxiv","version":2}},"canonical_sha256":"196b8b64ea12496751b6dbe292e55a11350f3bb2a52a27c1d2031ff26a32402f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"196b8b64ea12496751b6dbe292e55a11350f3bb2a52a27c1d2031ff26a32402f","first_computed_at":"2026-07-05T11:37:15.554311Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:37:15.554311Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NQtcymeAZT4COMAxajTZPh1MkAym0oqUR/D6GsC2Ca9j49/s+UU/0JrMJq36BQnVXB4GH9LD4N4W1b3AoUsMBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:37:15.554967Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.01100","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f5f0019b990f46a824de3360f27879a57891037a3d7f867b097ac8ab85677802","sha256:4478f270c9058398165f39d8b13af5afd44c77f3fa8da18fafa8faf6e635326c"],"state_sha256":"174eacea4f2be8704ed1e7a9409d6187abee393fcccc10464e7566bd10d3d902"}