{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QDRCQ3OSEALCE7DLXINMPSIQ2P","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":"6e84775626cb69c734ae7fbee91a5684618aa168deb25e10a3e8eb378e244bff","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-27T06:09:29Z","title_canon_sha256":"30c404646821034cc125895a153e205e5fba914aa26973381365bf85447b1c05"},"schema_version":"1.0","source":{"id":"2605.28014","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.28014","created_at":"2026-05-28T01:04:56Z"},{"alias_kind":"arxiv_version","alias_value":"2605.28014v1","created_at":"2026-05-28T01:04:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28014","created_at":"2026-05-28T01:04:56Z"},{"alias_kind":"pith_short_12","alias_value":"QDRCQ3OSEALC","created_at":"2026-05-28T01:04:56Z"},{"alias_kind":"pith_short_16","alias_value":"QDRCQ3OSEALCE7DL","created_at":"2026-05-28T01:04:56Z"},{"alias_kind":"pith_short_8","alias_value":"QDRCQ3OS","created_at":"2026-05-28T01:04:56Z"}],"graph_snapshots":[{"event_id":"sha256:f9d767097be51af395b3d94dfb85098b2075f188e2cbe613072c6d74b02e9bf6","target":"graph","created_at":"2026-05-28T01:04:56Z","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/2605.28014/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"On-policy self-distillation (OPSD) improves the reasoning performance of large language models (LLMs) by providing dense token-level supervision for on-policy rollouts. However, existing OPSD methods often yield limited gains on in-domain reasoning and generalize poorly to out-of-domain problems. We identify two key causes: conditioning the self-teacher on a verified solution encourages imitation of training-domain reference trajectories rather than error-specific correction, and applying distillation to the full response can overwrite valid reasoning prefixes and reinforce overfitting.\n  We p","authors_text":"Daiting Shi, Jingzhou He, Liu Yang, Xiao-Ming Wu, Xin Xin, Xinyu Ma, Yujie Feng, Zhaochun Ren, Ziqi Zhao","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-27T06:09:29Z","title":"ROSD: Reflective On-Policy Self-Distillation for Language Model Reasoning across Domains"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28014","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":"sha256:71911a07ac77e392bc27d10b5ed7b2c172454cb9623088057b43016cc780777e","target":"record","created_at":"2026-05-28T01:04:56Z","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":"6e84775626cb69c734ae7fbee91a5684618aa168deb25e10a3e8eb378e244bff","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-27T06:09:29Z","title_canon_sha256":"30c404646821034cc125895a153e205e5fba914aa26973381365bf85447b1c05"},"schema_version":"1.0","source":{"id":"2605.28014","kind":"arxiv","version":1}},"canonical_sha256":"80e2286dd22016227c6bba1ac7c910d3d45772e9e4cf2c379247223e1a0684b6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"80e2286dd22016227c6bba1ac7c910d3d45772e9e4cf2c379247223e1a0684b6","first_computed_at":"2026-05-28T01:04:56.038579Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T01:04:56.038579Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0+I1/oV3yFiuB1rhbVWij/VzW98MnDMtOrajq01f26Zq/CAXSz/nXmXb36HMG+l7Pcka1ApDkNq41CkAC3jKCw==","signature_status":"signed_v1","signed_at":"2026-05-28T01:04:56.038961Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.28014","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:71911a07ac77e392bc27d10b5ed7b2c172454cb9623088057b43016cc780777e","sha256:f9d767097be51af395b3d94dfb85098b2075f188e2cbe613072c6d74b02e9bf6"],"state_sha256":"78561511b0bca20d5d9ebad05cb79ac47df328ecaa23917157087d1fa6afdbae"}