{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XCREXTINU7NRX6EWYAFPYHDPW4","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":"faa25554030dbeca96e27e479b73f5806c2645abf5f3b5a01dba8e50912ef04f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-10T01:35:34Z","title_canon_sha256":"1b1da3aa1a74318fe479116ac1b2592d148268fbc3c71c19b478f9341bafe211"},"schema_version":"1.0","source":{"id":"2606.11559","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.11559","created_at":"2026-06-11T01:09:56Z"},{"alias_kind":"arxiv_version","alias_value":"2606.11559v1","created_at":"2026-06-11T01:09:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11559","created_at":"2026-06-11T01:09:56Z"},{"alias_kind":"pith_short_12","alias_value":"XCREXTINU7NR","created_at":"2026-06-11T01:09:56Z"},{"alias_kind":"pith_short_16","alias_value":"XCREXTINU7NRX6EW","created_at":"2026-06-11T01:09:56Z"},{"alias_kind":"pith_short_8","alias_value":"XCREXTIN","created_at":"2026-06-11T01:09:56Z"}],"graph_snapshots":[{"event_id":"sha256:357956e2a270372e0157f6880484edd296f98195e38d813e33dd752af3c829eb","target":"graph","created_at":"2026-06-11T01:09:56Z","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/2606.11559/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning typically improves multi-turn agent capabilities through the terminal outcome of the trajectories, which makes it difficult to determine credit assignments for each intermediate turns. Recent on-policy self-distillation methods offer a promising alternative by converting privileged feedback into dense token-level supervision through a self-teacher. Our study is motivated by the unexpected performance degradation observed when naively extending this paradigm to multi-turn settings, which we attribute to a lack of alignment between privileged feedback, such as successful t","authors_text":"Bohan Lyu, Haoran Liu, Jingbo Shang, Xiyao Li, Yuwei Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-10T01:35:34Z","title":"HERO: Hindsight-Enhanced Reflection from Environment Observations for Agentic Self-Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11559","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:b01995e3e959d5815533653b92f06f108f8ccf144ea5ec64c6585db4ecf7b9ce","target":"record","created_at":"2026-06-11T01:09:56Z","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":"faa25554030dbeca96e27e479b73f5806c2645abf5f3b5a01dba8e50912ef04f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-10T01:35:34Z","title_canon_sha256":"1b1da3aa1a74318fe479116ac1b2592d148268fbc3c71c19b478f9341bafe211"},"schema_version":"1.0","source":{"id":"2606.11559","kind":"arxiv","version":1}},"canonical_sha256":"b8a24bcd0da7db1bf896c00afc1c6fb7279d0344edc8fd9c4a59397671f8f221","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b8a24bcd0da7db1bf896c00afc1c6fb7279d0344edc8fd9c4a59397671f8f221","first_computed_at":"2026-06-11T01:09:56.071616Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-11T01:09:56.071616Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sBXS6Drl90hRhLZKi7AXkyYXJrYJrDfp7y03tcPExQ2XEN+bFlhIjr2yQFyDjxdGuagSv3k/MPBs3tOuffsdAA==","signature_status":"signed_v1","signed_at":"2026-06-11T01:09:56.072439Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.11559","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b01995e3e959d5815533653b92f06f108f8ccf144ea5ec64c6585db4ecf7b9ce","sha256:357956e2a270372e0157f6880484edd296f98195e38d813e33dd752af3c829eb"],"state_sha256":"462191eb25d3a4397ad8cfa2afb3285fa4429e276cd3d4fc01c25d0203ad62ca"}