{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2JNV4G544WLRFNR5EQXCFVBZQH","short_pith_number":"pith:2JNV4G54","schema_version":"1.0","canonical_sha256":"d25b5e1bbce59712b63d242e22d43981e9f2acec6c0a32105781fae84c24fda2","source":{"kind":"arxiv","id":"2608.05219","version":1},"attestation_state":"computed","paper":{"title":"When Privileged Guidance Misaligns: State-Matched Routing and Contextualized Self-Distillation for Multi-Turn Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jun Ling, Junzhuo Liu, Peng Wang, Weiwei Li","submitted_at":"2026-08-05T10:50:46Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2608.05219","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-05T10:50:46Z","cross_cats_sorted":[],"title_canon_sha256":"ed0940d98d38e4902df589d3979aa1e4d314cb8b8182dd64f5c87e37438c4ad7","abstract_canon_sha256":"854c86a704e8a3faf08e2042b0753a61893e3a42ce33f2fbaaacc4ebd656ed5b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-07T00:46:32.898933Z","signature_b64":"/FpiOSiNKdrKKnaJtNh9SI/RvF8cQjZAsldKdcNXYbLaKGcFFKmY76m/DYj9Op9oY/Um6si2kP27jk6eqPf2AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d25b5e1bbce59712b63d242e22d43981e9f2acec6c0a32105781fae84c24fda2","last_reissued_at":"2026-08-07T00:46:32.897586Z","signature_status":"signed_v1","first_computed_at":"2026-08-07T00:46:32.897586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"When Privileged Guidance Misaligns: State-Matched Routing and Contextualized Self-Distillation for Multi-Turn Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jun Ling, Junzhuo Liu, Peng Wang, Weiwei Li","submitted_at":"2026-08-05T10:50:46Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.05219","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/2608.05219/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2608.05219","created_at":"2026-08-07T00:46:32.898860+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.05219v1","created_at":"2026-08-07T00:46:32.898860+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.05219","created_at":"2026-08-07T00:46:32.898860+00:00"},{"alias_kind":"pith_short_12","alias_value":"2JNV4G544WLR","created_at":"2026-08-07T00:46:32.898860+00:00"},{"alias_kind":"pith_short_16","alias_value":"2JNV4G544WLRFNR5","created_at":"2026-08-07T00:46:32.898860+00:00"},{"alias_kind":"pith_short_8","alias_value":"2JNV4G54","created_at":"2026-08-07T00:46:32.898860+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2JNV4G544WLRFNR5EQXCFVBZQH","json":"https://pith.science/pith/2JNV4G544WLRFNR5EQXCFVBZQH.json","graph_json":"https://pith.science/api/pith-number/2JNV4G544WLRFNR5EQXCFVBZQH/graph.json","events_json":"https://pith.science/api/pith-number/2JNV4G544WLRFNR5EQXCFVBZQH/events.json","paper":"https://pith.science/paper/2JNV4G54"},"agent_actions":{"view_html":"https://pith.science/pith/2JNV4G544WLRFNR5EQXCFVBZQH","download_json":"https://pith.science/pith/2JNV4G544WLRFNR5EQXCFVBZQH.json","view_paper":"https://pith.science/paper/2JNV4G54","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.05219&json=true","fetch_graph":"https://pith.science/api/pith-number/2JNV4G544WLRFNR5EQXCFVBZQH/graph.json","fetch_events":"https://pith.science/api/pith-number/2JNV4G544WLRFNR5EQXCFVBZQH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2JNV4G544WLRFNR5EQXCFVBZQH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2JNV4G544WLRFNR5EQXCFVBZQH/action/storage_attestation","attest_author":"https://pith.science/pith/2JNV4G544WLRFNR5EQXCFVBZQH/action/author_attestation","sign_citation":"https://pith.science/pith/2JNV4G544WLRFNR5EQXCFVBZQH/action/citation_signature","submit_replication":"https://pith.science/pith/2JNV4G544WLRFNR5EQXCFVBZQH/action/replication_record"}},"created_at":"2026-08-07T00:46:32.898860+00:00","updated_at":"2026-08-07T00:46:32.898860+00:00"}