{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:XCREXTINU7NRX6EWYAFPYHDPW4","short_pith_number":"pith:XCREXTIN","canonical_record":{"source":{"id":"2606.11559","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-10T01:35:34Z","cross_cats_sorted":[],"title_canon_sha256":"1b1da3aa1a74318fe479116ac1b2592d148268fbc3c71c19b478f9341bafe211","abstract_canon_sha256":"faa25554030dbeca96e27e479b73f5806c2645abf5f3b5a01dba8e50912ef04f"},"schema_version":"1.0"},"canonical_sha256":"b8a24bcd0da7db1bf896c00afc1c6fb7279d0344edc8fd9c4a59397671f8f221","source":{"kind":"arxiv","id":"2606.11559","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:XCREXTINU7NRX6EWYAFPYHDPW4","target":"record","payload":{"canonical_record":{"source":{"id":"2606.11559","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-10T01:35:34Z","cross_cats_sorted":[],"title_canon_sha256":"1b1da3aa1a74318fe479116ac1b2592d148268fbc3c71c19b478f9341bafe211","abstract_canon_sha256":"faa25554030dbeca96e27e479b73f5806c2645abf5f3b5a01dba8e50912ef04f"},"schema_version":"1.0"},"canonical_sha256":"b8a24bcd0da7db1bf896c00afc1c6fb7279d0344edc8fd9c4a59397671f8f221","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T01:09:56.072439Z","signature_b64":"sBXS6Drl90hRhLZKi7AXkyYXJrYJrDfp7y03tcPExQ2XEN+bFlhIjr2yQFyDjxdGuagSv3k/MPBs3tOuffsdAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b8a24bcd0da7db1bf896c00afc1c6fb7279d0344edc8fd9c4a59397671f8f221","last_reissued_at":"2026-06-11T01:09:56.071616Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T01:09:56.071616Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.11559","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-11T01:09:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tffTGH1IYn1tFolIMLbwxUStjNIvPyCr9qzV0+V2D2q0UB/zZdaF9d3CqyhQy9D+ehMIuonI5szSE3s0F6fyBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T09:57:49.269689Z"},"content_sha256":"b01995e3e959d5815533653b92f06f108f8ccf144ea5ec64c6585db4ecf7b9ce","schema_version":"1.0","event_id":"sha256:b01995e3e959d5815533653b92f06f108f8ccf144ea5ec64c6585db4ecf7b9ce"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:XCREXTINU7NRX6EWYAFPYHDPW4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"HERO: Hindsight-Enhanced Reflection from Environment Observations for Agentic Self-Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bohan Lyu, Haoran Liu, Jingbo Shang, Xiyao Li, Yuwei Zhang","submitted_at":"2026-06-10T01:35:34Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11559","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.11559/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-11T01:09:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mvnfovrHzFrC6yiQkY8MHVBwfTLFBOySK4tydrANUR40e80OXc5AJQAK4fO1monmymAJMUZqQ5BX+VTkStlHBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T09:57:49.270047Z"},"content_sha256":"357956e2a270372e0157f6880484edd296f98195e38d813e33dd752af3c829eb","schema_version":"1.0","event_id":"sha256:357956e2a270372e0157f6880484edd296f98195e38d813e33dd752af3c829eb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XCREXTINU7NRX6EWYAFPYHDPW4/bundle.json","state_url":"https://pith.science/pith/XCREXTINU7NRX6EWYAFPYHDPW4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XCREXTINU7NRX6EWYAFPYHDPW4/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-02T09:57:49Z","links":{"resolver":"https://pith.science/pith/XCREXTINU7NRX6EWYAFPYHDPW4","bundle":"https://pith.science/pith/XCREXTINU7NRX6EWYAFPYHDPW4/bundle.json","state":"https://pith.science/pith/XCREXTINU7NRX6EWYAFPYHDPW4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XCREXTINU7NRX6EWYAFPYHDPW4/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vFG1vtwBTWkJwkl2kr5kg6crBlQ2NMK0t4JDfoG8YvC72MMZbaSXZq70wy0Bac2Owel7M/5Ow5dvADY5gF7nAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-02T09:57:49.272221Z","bundle_sha256":"448853b1bfc6e2b9de92af41c54c0592593d1b0c7c539200eb8b50317c113504"}}