{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:MDSXF4AXCDWTTS7DIBMF3SMT7S","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":"5f8f4a148b3c74c73e69f1732970213b70444e583582b698f5a93a6e99766701","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-27T12:52:58Z","title_canon_sha256":"3bd426bd554ccde146934ecf0b785ccbe2ab5b6de6b56a8062aee7daf002ea49"},"schema_version":"1.0","source":{"id":"2605.28421","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.28421","created_at":"2026-05-28T01:05:17Z"},{"alias_kind":"arxiv_version","alias_value":"2605.28421v1","created_at":"2026-05-28T01:05:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28421","created_at":"2026-05-28T01:05:17Z"},{"alias_kind":"pith_short_12","alias_value":"MDSXF4AXCDWT","created_at":"2026-05-28T01:05:17Z"},{"alias_kind":"pith_short_16","alias_value":"MDSXF4AXCDWTTS7D","created_at":"2026-05-28T01:05:17Z"},{"alias_kind":"pith_short_8","alias_value":"MDSXF4AX","created_at":"2026-05-28T01:05:17Z"}],"graph_snapshots":[{"event_id":"sha256:1adfcc2dadc4f4f800cb0bf3c21f10cd8e63cdb476c39f37b09b47883dc2b62c","target":"graph","created_at":"2026-05-28T01:05:17Z","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/2605.28421/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning has become a central paradigm for advancing reasoning in large language models, yet most existing methods still depend on stronger teacher models or heavily curated difficult datasets, limiting scalable capability improvement. In this paper, we introduce DenoiseRL, a reinforcement learning framework that substitutes external supervision with recovery-oriented optimization over failures from weak models. Instead of relying on stronger supervision or carefully engineered data, DenoiseRL learns directly from incorrect reasoning traces by converting them into opportunities f","authors_text":"Caijun Xu, Changyi Xiao, Yixin Cao, Zhongyuan Peng","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-27T12:52:58Z","title":"DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28421","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:ca873e6c50196dc7820bf7c53758867c2e0b2bfee83ebc4d5e99d3eb8e0573cf","target":"record","created_at":"2026-05-28T01:05:17Z","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":"5f8f4a148b3c74c73e69f1732970213b70444e583582b698f5a93a6e99766701","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-27T12:52:58Z","title_canon_sha256":"3bd426bd554ccde146934ecf0b785ccbe2ab5b6de6b56a8062aee7daf002ea49"},"schema_version":"1.0","source":{"id":"2605.28421","kind":"arxiv","version":1}},"canonical_sha256":"60e572f01710ed39cbe340585dc993fcae7fbaa1da8b547cf1dad94c68cc5725","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"60e572f01710ed39cbe340585dc993fcae7fbaa1da8b547cf1dad94c68cc5725","first_computed_at":"2026-05-28T01:05:17.695814Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T01:05:17.695814Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uvYgUyUScwiyCzTmYaSgE63BtycKBc+il8HQ60C5piz01+GoYPxJnm7wEvz7sHfNDG59XjxkUWCLIsOALhDECw==","signature_status":"signed_v1","signed_at":"2026-05-28T01:05:17.696244Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.28421","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ca873e6c50196dc7820bf7c53758867c2e0b2bfee83ebc4d5e99d3eb8e0573cf","sha256:1adfcc2dadc4f4f800cb0bf3c21f10cd8e63cdb476c39f37b09b47883dc2b62c"],"state_sha256":"e7b14115c1b8f57059bc90a52f1a28696323c68c89ce2750eb900e92c0273e92"}