{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:H2XEQASHTBSGQD74J3KM6DF676","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":"0cb7b7640cf9e62de5b08484971b66322177424d10e8cc6016b301d3dd1d8602","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-12T02:31:02Z","title_canon_sha256":"163efdf989d894252f20fa4c1d45f16bb52315b76e24e338694fe02a2162314f"},"schema_version":"1.0","source":{"id":"2608.11573","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.11573","created_at":"2026-08-13T00:22:12Z"},{"alias_kind":"arxiv_version","alias_value":"2608.11573v1","created_at":"2026-08-13T00:22:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.11573","created_at":"2026-08-13T00:22:12Z"},{"alias_kind":"pith_short_12","alias_value":"H2XEQASHTBSG","created_at":"2026-08-13T00:22:12Z"},{"alias_kind":"pith_short_16","alias_value":"H2XEQASHTBSGQD74","created_at":"2026-08-13T00:22:12Z"},{"alias_kind":"pith_short_8","alias_value":"H2XEQASH","created_at":"2026-08-13T00:22:12Z"}],"graph_snapshots":[{"event_id":"sha256:ab6c9fb2fbbb5cd3cd5c777bc387326c61fc7c897a493be07577a759cd5c9746","target":"graph","created_at":"2026-08-13T00:22:12Z","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/2608.11573/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Achieving effective self-correction, where models verify and correct their own mistakes, remains a fundamental challenge for large language models (LLMs). In this work, we propose Self-Fix Step-DPO (SFS-DPO), a reinforcement learning based, two-stage framework for step-level self-verification and self-correction. The first stage strengthens step-level reasoning via step-level preference optimization, while the second stage explicitly trains models to self-verify and self-correct. We further introduce a teacher-assisted variant, SFS-DPO-R, which incorporates explanatory rationales for error ver","authors_text":"Cong-Duy Nguyen, Do Xuan Long, Luu Anh Tuan, Nhat M. Hoang, Ponhvoan Srey, Vu Duc Anh","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-12T02:31:02Z","title":"Reinforcing Step-level Reasoning for Effective Self-Correction in LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.11573","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":"sha256:3e0628fcb7c10eec57630c6451c1474b739646753f1780e0413d4f90ca64bef1","target":"record","created_at":"2026-08-13T00:22:12Z","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":"0cb7b7640cf9e62de5b08484971b66322177424d10e8cc6016b301d3dd1d8602","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-12T02:31:02Z","title_canon_sha256":"163efdf989d894252f20fa4c1d45f16bb52315b76e24e338694fe02a2162314f"},"schema_version":"1.0","source":{"id":"2608.11573","kind":"arxiv","version":1}},"canonical_sha256":"3eae4802479864680ffc4ed4cf0cbeffb9ebd49a82995e4db651c3bdbc885b4d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3eae4802479864680ffc4ed4cf0cbeffb9ebd49a82995e4db651c3bdbc885b4d","first_computed_at":"2026-08-13T00:22:12.795070Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-13T00:22:12.795070Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kmOaNg8/VbATiDl4NkZkxF5Uq8FxLWfonFRqkLXhvPztvPwUvCzNXrQdS09kcZaTlfBDfBn5ZzyAz+30dObZBg==","signature_status":"signed_v1","signed_at":"2026-08-13T00:22:12.796762Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.11573","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3e0628fcb7c10eec57630c6451c1474b739646753f1780e0413d4f90ca64bef1","sha256:ab6c9fb2fbbb5cd3cd5c777bc387326c61fc7c897a493be07577a759cd5c9746"],"state_sha256":"0110c229fcc9d20b28c7c5db34cad217b2ba0a4e6c37e3b745d4750ba8e55649"}