{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2JNV4G544WLRFNR5EQXCFVBZQH","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":"854c86a704e8a3faf08e2042b0753a61893e3a42ce33f2fbaaacc4ebd656ed5b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-05T10:50:46Z","title_canon_sha256":"ed0940d98d38e4902df589d3979aa1e4d314cb8b8182dd64f5c87e37438c4ad7"},"schema_version":"1.0","source":{"id":"2608.05219","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.05219","created_at":"2026-08-07T00:46:32Z"},{"alias_kind":"arxiv_version","alias_value":"2608.05219v1","created_at":"2026-08-07T00:46:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.05219","created_at":"2026-08-07T00:46:32Z"},{"alias_kind":"pith_short_12","alias_value":"2JNV4G544WLR","created_at":"2026-08-07T00:46:32Z"},{"alias_kind":"pith_short_16","alias_value":"2JNV4G544WLRFNR5","created_at":"2026-08-07T00:46:32Z"},{"alias_kind":"pith_short_8","alias_value":"2JNV4G54","created_at":"2026-08-07T00:46:32Z"}],"graph_snapshots":[{"event_id":"sha256:81e8909f586ab8b3e7f08f41d00191ebb04acda40376d9ff6deb5f9f7d2acfc5","target":"graph","created_at":"2026-08-07T00:46:32Z","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/2608.05219/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Privileged on-policy distillation provides dense supervision for multi-turn agents by allowing a synchronized teacher to re-score the student's response at every turn with access to training-only references, such as successful trajectories. In interactive environments, however, the student's preceding actions continually change the execution state. As the student takes different actions or completes subgoals in a different order, its rollout may reach states not covered by the reference, making the reference an unreliable source of guidance for the state actually reached. Applying privileged d","authors_text":"Jun Ling, Junzhuo Liu, Peng Wang, Weiwei Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-05T10:50:46Z","title":"When Privileged Guidance Misaligns: State-Matched Routing and Contextualized Self-Distillation for Multi-Turn Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.05219","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:a78144842b1f5d060b052a9aa80320906182d935c1eb15c987d89d2a359e9639","target":"record","created_at":"2026-08-07T00:46:32Z","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":"854c86a704e8a3faf08e2042b0753a61893e3a42ce33f2fbaaacc4ebd656ed5b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-05T10:50:46Z","title_canon_sha256":"ed0940d98d38e4902df589d3979aa1e4d314cb8b8182dd64f5c87e37438c4ad7"},"schema_version":"1.0","source":{"id":"2608.05219","kind":"arxiv","version":1}},"canonical_sha256":"d25b5e1bbce59712b63d242e22d43981e9f2acec6c0a32105781fae84c24fda2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d25b5e1bbce59712b63d242e22d43981e9f2acec6c0a32105781fae84c24fda2","first_computed_at":"2026-08-07T00:46:32.897586Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-07T00:46:32.897586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/FpiOSiNKdrKKnaJtNh9SI/RvF8cQjZAsldKdcNXYbLaKGcFFKmY76m/DYj9Op9oY/Um6si2kP27jk6eqPf2AQ==","signature_status":"signed_v1","signed_at":"2026-08-07T00:46:32.898933Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.05219","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a78144842b1f5d060b052a9aa80320906182d935c1eb15c987d89d2a359e9639","sha256:81e8909f586ab8b3e7f08f41d00191ebb04acda40376d9ff6deb5f9f7d2acfc5"],"state_sha256":"5c341199397eab5c0ab12b62712f6576e4364bb4c5a13243f399e99b7df9665b"}