{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:X3EKF6HQGCFIBAZXRQRQREAESV","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":"016d00358164e5b3e636b540eaf6ea3c1b806af8712ca48895db8e874ccace61","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-26T23:01:16Z","title_canon_sha256":"8a76fc2bef4d7824f7a2bd7ff36d0d461a61c8641d02874a0cd05648f50dbc81"},"schema_version":"1.0","source":{"id":"2502.19613","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.19613","created_at":"2026-07-05T10:20:49Z"},{"alias_kind":"arxiv_version","alias_value":"2502.19613v1","created_at":"2026-07-05T10:20:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.19613","created_at":"2026-07-05T10:20:49Z"},{"alias_kind":"pith_short_12","alias_value":"X3EKF6HQGCFI","created_at":"2026-07-05T10:20:49Z"},{"alias_kind":"pith_short_16","alias_value":"X3EKF6HQGCFIBAZX","created_at":"2026-07-05T10:20:49Z"},{"alias_kind":"pith_short_8","alias_value":"X3EKF6HQ","created_at":"2026-07-05T10:20:49Z"}],"graph_snapshots":[{"event_id":"sha256:bff505eba106e57e32980fce5789b04f870629d648a84f1a5647d43f34ba0c80","target":"graph","created_at":"2026-07-05T10:20:49Z","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/2502.19613/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study self-rewarding reasoning large language models (LLMs), which can simultaneously generate step-by-step reasoning and evaluate the correctness of their outputs during the inference time-without external feedback. This integrated approach allows a single model to independently guide its reasoning process, offering computational advantages for model deployment. We particularly focus on the representative task of self-correction, where models autonomously detect errors in their responses, revise outputs, and decide when to terminate iterative refinement loops. To enable this, we propose a ","authors_text":"Chenlu Ye, Hanning Zhang, Lichang Chen, Nan Jiang, Tong Zhang, Wei Xiong","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-26T23:01:16Z","title":"Self-rewarding correction for mathematical reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.19613","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":"sha256:9ecd4c90deef1c51e40fdbb0f295d134ef995f9cf8ded790e6cffdefdb15e7cf","target":"record","created_at":"2026-07-05T10:20:49Z","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":"016d00358164e5b3e636b540eaf6ea3c1b806af8712ca48895db8e874ccace61","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-26T23:01:16Z","title_canon_sha256":"8a76fc2bef4d7824f7a2bd7ff36d0d461a61c8641d02874a0cd05648f50dbc81"},"schema_version":"1.0","source":{"id":"2502.19613","kind":"arxiv","version":1}},"canonical_sha256":"bec8a2f8f0308a8083378c230890049546fc9d37deb39e0517001501555e55de","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bec8a2f8f0308a8083378c230890049546fc9d37deb39e0517001501555e55de","first_computed_at":"2026-07-05T10:20:49.869978Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:20:49.869978Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5igP9KC2oxWVmmhdPbemkYSsX6IVzHlmfDuwGzl15A0/+XfTU1dFu8Hi8u2KryEp205rYnteYV1mUDg6Rar0Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:20:49.870489Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.19613","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9ecd4c90deef1c51e40fdbb0f295d134ef995f9cf8ded790e6cffdefdb15e7cf","sha256:bff505eba106e57e32980fce5789b04f870629d648a84f1a5647d43f34ba0c80"],"state_sha256":"4fe1c9aae348858a0d2cdb1ccc8409cd4f17bf9cabdd9e5fce93fe88113c134e"}