{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:CBEEOBLGPICEHEA2Z4XLNAIJXK","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":"a9184d7c6d59ef3af229b21f02699e96db38448ff469e64bc9b57a58fa5de679","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T17:51:26Z","title_canon_sha256":"60abd1093f1e5ad88b032b32f4d827f812f2b30903d70e62abea598a1d78bda8"},"schema_version":"1.0","source":{"id":"2605.15155","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15155","created_at":"2026-05-17T23:38:53Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15155v1","created_at":"2026-05-17T23:38:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15155","created_at":"2026-05-17T23:38:53Z"},{"alias_kind":"pith_short_12","alias_value":"CBEEOBLGPICE","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"CBEEOBLGPICEHEA2","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"CBEEOBLG","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:ad9c942f571a787d873c5b25b249e7c957e1398f68de73401646d459b6196baf","target":"graph","created_at":"2026-05-17T23:38:53Z","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"},"paper":{"abstract_excerpt":"Reinforcement learning (RL) has emerged as a central paradigm for post-training LLM agents, yet its trajectory-level reward signal provides only coarse supervision for long-horizon interaction. On-Policy Self-Distillation (OPSD) complements RL by introducing dense token-level guidance from a teacher branch augmented with privileged context. However, transferring OPSD to multi-turn agents proves problematic: compounding multi-turn instability destabilizes supervision, while skill-conditioned privileged guidance requires asymmetric treatment for negative teacher rejections may arise from imperfe","authors_text":"Jinyang Wu, Jun Xiao, Qi Gu, Weiming Lu, Xunliang Cai, Yongliang Shen, Yueting Zhuang, Zhengxi Lu, Zhiyuan Yao, Zhuowen Han, Zi-Han Wang","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T17:51:26Z","title":"Self-Distilled Agentic Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.15155","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":"sha256:6bb842537dae5c6b087da56120a4c590060662995fa547a284db6d6c8346e3c6","target":"record","created_at":"2026-05-17T23:38:53Z","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":"a9184d7c6d59ef3af229b21f02699e96db38448ff469e64bc9b57a58fa5de679","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T17:51:26Z","title_canon_sha256":"60abd1093f1e5ad88b032b32f4d827f812f2b30903d70e62abea598a1d78bda8"},"schema_version":"1.0","source":{"id":"2605.15155","kind":"arxiv","version":1}},"canonical_sha256":"10484705667a0443901acf2eb68109ba9d838e9da2fdc74055d9ff3350a18930","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"10484705667a0443901acf2eb68109ba9d838e9da2fdc74055d9ff3350a18930","first_computed_at":"2026-05-17T23:38:53.978198Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:53.978198Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"H7zF0MJ4WpHwJWCwO/66bYG7144JPDEg4pTYpr9QzeATohBggB435wvpmRjdTBUb79vKWjH1gqizdd3SJkonDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:53.978756Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.15155","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6bb842537dae5c6b087da56120a4c590060662995fa547a284db6d6c8346e3c6","sha256:ad9c942f571a787d873c5b25b249e7c957e1398f68de73401646d459b6196baf"],"state_sha256":"80c500c7851c3fd2ffe1772fc0734e7a09ab50b6eae1071abc1ac504b67bb628"}