{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:HWJORDD67BIQPHTJVFISXJOJCP","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":"f70112e539f2d2c9aa6f5d11eb7679351f8353168dab77fe831eeafde92a60ec","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-17T23:58:14Z","title_canon_sha256":"6917545833bb91fa11cb95a9c0ea18efee55dcd2f74685eef004b2012f0503da"},"schema_version":"1.0","source":{"id":"2606.19659","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.19659","created_at":"2026-06-19T16:12:31Z"},{"alias_kind":"arxiv_version","alias_value":"2606.19659v1","created_at":"2026-06-19T16:12:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19659","created_at":"2026-06-19T16:12:31Z"},{"alias_kind":"pith_short_12","alias_value":"HWJORDD67BIQ","created_at":"2026-06-19T16:12:31Z"},{"alias_kind":"pith_short_16","alias_value":"HWJORDD67BIQPHTJ","created_at":"2026-06-19T16:12:31Z"},{"alias_kind":"pith_short_8","alias_value":"HWJORDD6","created_at":"2026-06-19T16:12:31Z"}],"graph_snapshots":[{"event_id":"sha256:30cd40e4ef94b79bf357bece9a64d95014f6afcc8c2140d256bb91d92bbbc8bd","target":"graph","created_at":"2026-06-19T16:12:31Z","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/2606.19659/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"On-policy distillation (OPD) improves student models by training them on trajectories induced by their own policy, making it a promising approach for mitigating exposure bias in agent training. However, most OPD studies focus on single-turn settings, while realistic LLM agents interact with environments over multiple turns. In this regime, early errors can alter future observations and compound across the trajectory, and standard dense token-level OPD becomes brittle, as it may over-penalize semantically valid alternatives, reinforce local degeneracies such as repeated actions, and propagate u","authors_text":"Bo Peng, Jiayi Liu, Lizhu Zhang, Mingyi Wang, Xiangjun Fan, Yifan Wu, Yuhang Zhou, Zhuokai Zhao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-17T23:58:14Z","title":"SAGE-OPD: Selective Agent-Guided Intervention for Multi-Turn On-Policy Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.19659","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":"sha256:2cc4786bb4de2e8bc2b5552116534e7e653ffec27d9c3d95553dc36d20c5c79d","target":"record","created_at":"2026-06-19T16:12:31Z","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":"f70112e539f2d2c9aa6f5d11eb7679351f8353168dab77fe831eeafde92a60ec","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-17T23:58:14Z","title_canon_sha256":"6917545833bb91fa11cb95a9c0ea18efee55dcd2f74685eef004b2012f0503da"},"schema_version":"1.0","source":{"id":"2606.19659","kind":"arxiv","version":1}},"canonical_sha256":"3d92e88c7ef851079e69a9512ba5c913e0689db1dcb03af30eb2d8d33a50abc0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3d92e88c7ef851079e69a9512ba5c913e0689db1dcb03af30eb2d8d33a50abc0","first_computed_at":"2026-06-19T16:12:31.518720Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:12:31.518720Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OORFM2G/sqXVtOelqLWMckYjXtXsCFsfGhgDYMBvh1ahltqILtSZO7r3vw/o3/KiD24rnOBCzcUokF19L5HgDQ==","signature_status":"signed_v1","signed_at":"2026-06-19T16:12:31.519071Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.19659","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2cc4786bb4de2e8bc2b5552116534e7e653ffec27d9c3d95553dc36d20c5c79d","sha256:30cd40e4ef94b79bf357bece9a64d95014f6afcc8c2140d256bb91d92bbbc8bd"],"state_sha256":"de109fb7cd2f48dc0a05839a8a986bfe9c3bebdc5b90b6d45a01a33f28ce2c4c"}