{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OTALFZJWSNXIX6P5J6UR2LNTXV","short_pith_number":"pith:OTALFZJW","schema_version":"1.0","canonical_sha256":"74c0b2e536936e8bf9fd4fa91d2db3bd72989be1f069240f2c3d0d08a1b82e7d","source":{"kind":"arxiv","id":"2502.20238","version":2},"attestation_state":"computed","paper":{"title":"FINEREASON: Evaluating and Improving LLMs' Deliberate Reasoning through Reflective Puzzle Solving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anh Tuan Luu, Chaoqun Liu, Deli Zhao, Guizhen Chen, Hao Zhang, Hou Pong Chan, Lidong Bing, Weiwen Xu, Yu Rong","submitted_at":"2025-02-27T16:23:25Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2502.20238","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-27T16:23:25Z","cross_cats_sorted":[],"title_canon_sha256":"1fe3f9fdc9e55266039dd6bbffb6421cac2b6a6df27318a1309db02f44fd7f1b","abstract_canon_sha256":"904a8de5f2ab7da35054d26e0b1d5e43dd8049121ba758995081505abf6099ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:21.587134Z","signature_b64":"TdtpTH/AKBV3Tx+CT//1RLJ3EzuhcVMDUw7FmM2mBCCMcEJbjZ1wGUCPdJGsichfaZvjvQ8dCsogUwQnwtPmCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"74c0b2e536936e8bf9fd4fa91d2db3bd72989be1f069240f2c3d0d08a1b82e7d","last_reissued_at":"2026-07-05T11:13:21.586651Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:21.586651Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FINEREASON: Evaluating and Improving LLMs' Deliberate Reasoning through Reflective Puzzle Solving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anh Tuan Luu, Chaoqun Liu, Deli Zhao, Guizhen Chen, Hao Zhang, Hou Pong Chan, Lidong Bing, Weiwen Xu, Yu Rong","submitted_at":"2025-02-27T16:23:25Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.20238","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2502.20238/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2502.20238","created_at":"2026-07-05T11:13:21.586711+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.20238v2","created_at":"2026-07-05T11:13:21.586711+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.20238","created_at":"2026-07-05T11:13:21.586711+00:00"},{"alias_kind":"pith_short_12","alias_value":"OTALFZJWSNXI","created_at":"2026-07-05T11:13:21.586711+00:00"},{"alias_kind":"pith_short_16","alias_value":"OTALFZJWSNXIX6P5","created_at":"2026-07-05T11:13:21.586711+00:00"},{"alias_kind":"pith_short_8","alias_value":"OTALFZJW","created_at":"2026-07-05T11:13:21.586711+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06840","citing_title":"Characterize Then Distill: Mechanistic Reasoning in Large Output Spaces","ref_index":111,"is_internal_anchor":false},{"citing_arxiv_id":"2503.09567","citing_title":"Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models","ref_index":75,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08905","citing_title":"Forge: Quality-Aware Reinforcement Learning for NP-Hard Optimization in LLMs","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OTALFZJWSNXIX6P5J6UR2LNTXV","json":"https://pith.science/pith/OTALFZJWSNXIX6P5J6UR2LNTXV.json","graph_json":"https://pith.science/api/pith-number/OTALFZJWSNXIX6P5J6UR2LNTXV/graph.json","events_json":"https://pith.science/api/pith-number/OTALFZJWSNXIX6P5J6UR2LNTXV/events.json","paper":"https://pith.science/paper/OTALFZJW"},"agent_actions":{"view_html":"https://pith.science/pith/OTALFZJWSNXIX6P5J6UR2LNTXV","download_json":"https://pith.science/pith/OTALFZJWSNXIX6P5J6UR2LNTXV.json","view_paper":"https://pith.science/paper/OTALFZJW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.20238&json=true","fetch_graph":"https://pith.science/api/pith-number/OTALFZJWSNXIX6P5J6UR2LNTXV/graph.json","fetch_events":"https://pith.science/api/pith-number/OTALFZJWSNXIX6P5J6UR2LNTXV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OTALFZJWSNXIX6P5J6UR2LNTXV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OTALFZJWSNXIX6P5J6UR2LNTXV/action/storage_attestation","attest_author":"https://pith.science/pith/OTALFZJWSNXIX6P5J6UR2LNTXV/action/author_attestation","sign_citation":"https://pith.science/pith/OTALFZJWSNXIX6P5J6UR2LNTXV/action/citation_signature","submit_replication":"https://pith.science/pith/OTALFZJWSNXIX6P5J6UR2LNTXV/action/replication_record"}},"created_at":"2026-07-05T11:13:21.586711+00:00","updated_at":"2026-07-05T11:13:21.586711+00:00"}