{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OTALFZJWSNXIX6P5J6UR2LNTXV","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":"904a8de5f2ab7da35054d26e0b1d5e43dd8049121ba758995081505abf6099ae","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-27T16:23:25Z","title_canon_sha256":"1fe3f9fdc9e55266039dd6bbffb6421cac2b6a6df27318a1309db02f44fd7f1b"},"schema_version":"1.0","source":{"id":"2502.20238","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.20238","created_at":"2026-07-05T11:13:21Z"},{"alias_kind":"arxiv_version","alias_value":"2502.20238v2","created_at":"2026-07-05T11:13:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.20238","created_at":"2026-07-05T11:13:21Z"},{"alias_kind":"pith_short_12","alias_value":"OTALFZJWSNXI","created_at":"2026-07-05T11:13:21Z"},{"alias_kind":"pith_short_16","alias_value":"OTALFZJWSNXIX6P5","created_at":"2026-07-05T11:13:21Z"},{"alias_kind":"pith_short_8","alias_value":"OTALFZJW","created_at":"2026-07-05T11:13:21Z"}],"graph_snapshots":[{"event_id":"sha256:74ab71f6ce25e785885e1a4436ef6cc66ae65d70741fad86bfb069f080f432f2","target":"graph","created_at":"2026-07-05T11:13:21Z","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/2502.20238/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many challenging reasoning tasks require not just rapid, intuitive responses, but a more deliberate, multi-step approach. Recent progress in large language models (LLMs) highlights an important shift from the \"System 1\" way of quick reactions to the \"System 2\" style of reflection-and-correction problem solving. However, current benchmarks heavily rely on the final-answer accuracy, leaving much of a model's intermediate reasoning steps unexamined. This fails to assess the model's ability to reflect and rectify mistakes within the reasoning process. To bridge this gap, we introduce FINEREASON, a","authors_text":"Anh Tuan Luu, Chaoqun Liu, Deli Zhao, Guizhen Chen, Hao Zhang, Hou Pong Chan, Lidong Bing, Weiwen Xu, Yu Rong","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-27T16:23:25Z","title":"FINEREASON: Evaluating and Improving LLMs' Deliberate Reasoning through Reflective Puzzle Solving"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.20238","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:b1911a30c54d94d8828e0cb203f100436bfa6d4c8a9bda9f94eef6d8bbcec103","target":"record","created_at":"2026-07-05T11:13:21Z","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":"904a8de5f2ab7da35054d26e0b1d5e43dd8049121ba758995081505abf6099ae","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-27T16:23:25Z","title_canon_sha256":"1fe3f9fdc9e55266039dd6bbffb6421cac2b6a6df27318a1309db02f44fd7f1b"},"schema_version":"1.0","source":{"id":"2502.20238","kind":"arxiv","version":2}},"canonical_sha256":"74c0b2e536936e8bf9fd4fa91d2db3bd72989be1f069240f2c3d0d08a1b82e7d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"74c0b2e536936e8bf9fd4fa91d2db3bd72989be1f069240f2c3d0d08a1b82e7d","first_computed_at":"2026-07-05T11:13:21.586651Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:21.586651Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TdtpTH/AKBV3Tx+CT//1RLJ3EzuhcVMDUw7FmM2mBCCMcEJbjZ1wGUCPdJGsichfaZvjvQ8dCsogUwQnwtPmCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:21.587134Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.20238","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b1911a30c54d94d8828e0cb203f100436bfa6d4c8a9bda9f94eef6d8bbcec103","sha256:74ab71f6ce25e785885e1a4436ef6cc66ae65d70741fad86bfb069f080f432f2"],"state_sha256":"f40e4bfb7de958b87ffb7adab2edc5c919a131ffa71136bb6e6dacb3a1c78225"}