{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OGADK5M666EGG5EY65ZLURY4X2","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":"263ee0ef3f9ef18e6e9c10a1a2c0c0bab36c9dff0f2d6fedb8eabc7d6a22dc70","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-27T12:33:44Z","title_canon_sha256":"aa257c1749779601417684d260872daa111bc9ce6e9696137b7255936f3d8b2d"},"schema_version":"1.0","source":{"id":"2605.28396","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.28396","created_at":"2026-05-28T01:05:17Z"},{"alias_kind":"arxiv_version","alias_value":"2605.28396v1","created_at":"2026-05-28T01:05:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28396","created_at":"2026-05-28T01:05:17Z"},{"alias_kind":"pith_short_12","alias_value":"OGADK5M666EG","created_at":"2026-05-28T01:05:17Z"},{"alias_kind":"pith_short_16","alias_value":"OGADK5M666EGG5EY","created_at":"2026-05-28T01:05:17Z"},{"alias_kind":"pith_short_8","alias_value":"OGADK5M6","created_at":"2026-05-28T01:05:17Z"}],"graph_snapshots":[{"event_id":"sha256:d82e18de4ef89aef9139adcd773f88d66fd8bcf43df08065bde92cba18a04ebb","target":"graph","created_at":"2026-05-28T01:05:17Z","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/2605.28396/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"On-policy distillation (OPD) transfers reasoning behavior by training a student on teacher feedback along student-generated trajectories, but standard full-rollout training ties every update to a costly completion and can over-allocate supervision to late positions with low marginal value for the current student. We revisit this assumption through the useful supervision horizon: student-induced rollouts can drift from teacher-preferred continuations, while aligned prefixes may already preserve the long-horizon OPD update direction. We propose ADWIN, an adaptive-window framework for OPD that tr","authors_text":"Chenming Tang, Clive Bai, Kun Liang, Saiyong Yang, Weijie Liu, Yunfang Wu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-27T12:33:44Z","title":"ADWIN: Adaptive Windows for Horizon-Aware On-Policy Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28396","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:f83551cdd8760731814768b9892f3cf35c2d0b5200a7d8f6049cac2570f65a80","target":"record","created_at":"2026-05-28T01:05:17Z","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":"263ee0ef3f9ef18e6e9c10a1a2c0c0bab36c9dff0f2d6fedb8eabc7d6a22dc70","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-27T12:33:44Z","title_canon_sha256":"aa257c1749779601417684d260872daa111bc9ce6e9696137b7255936f3d8b2d"},"schema_version":"1.0","source":{"id":"2605.28396","kind":"arxiv","version":1}},"canonical_sha256":"718035759ef788637498f772ba471cbe91a3d96237b3c9db16403c78e152edb0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"718035759ef788637498f772ba471cbe91a3d96237b3c9db16403c78e152edb0","first_computed_at":"2026-05-28T01:05:17.008720Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T01:05:17.008720Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Q5mo/onJGwsXBTpbLEhR0OlAJ3Fa75jHUkpHrx1Fl+CrDDDTzq8XG8BlwyogZoLa1duKmt2KQ2A39MsuNI4hBQ==","signature_status":"signed_v1","signed_at":"2026-05-28T01:05:17.009142Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.28396","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f83551cdd8760731814768b9892f3cf35c2d0b5200a7d8f6049cac2570f65a80","sha256:d82e18de4ef89aef9139adcd773f88d66fd8bcf43df08065bde92cba18a04ebb"],"state_sha256":"e324d462567a4846cee3785de6caf5faa2e1a63d8943781382b688c99de99819"}