{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OGADK5M666EGG5EY65ZLURY4X2","short_pith_number":"pith:OGADK5M6","schema_version":"1.0","canonical_sha256":"718035759ef788637498f772ba471cbe91a3d96237b3c9db16403c78e152edb0","source":{"kind":"arxiv","id":"2605.28396","version":1},"attestation_state":"computed","paper":{"title":"ADWIN: Adaptive Windows for Horizon-Aware On-Policy Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chenming Tang, Clive Bai, Kun Liang, Saiyong Yang, Weijie Liu, Yunfang Wu","submitted_at":"2026-05-27T12:33:44Z","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"},"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":"2605.28396","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-27T12:33:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"aa257c1749779601417684d260872daa111bc9ce6e9696137b7255936f3d8b2d","abstract_canon_sha256":"263ee0ef3f9ef18e6e9c10a1a2c0c0bab36c9dff0f2d6fedb8eabc7d6a22dc70"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:05:17.009142Z","signature_b64":"Q5mo/onJGwsXBTpbLEhR0OlAJ3Fa75jHUkpHrx1Fl+CrDDDTzq8XG8BlwyogZoLa1duKmt2KQ2A39MsuNI4hBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"718035759ef788637498f772ba471cbe91a3d96237b3c9db16403c78e152edb0","last_reissued_at":"2026-05-28T01:05:17.008720Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:05:17.008720Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ADWIN: Adaptive Windows for Horizon-Aware On-Policy Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chenming Tang, Clive Bai, Kun Liang, Saiyong Yang, Weijie Liu, Yunfang Wu","submitted_at":"2026-05-27T12:33:44Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28396","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/2605.28396/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":"2605.28396","created_at":"2026-05-28T01:05:17.008780+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.28396v1","created_at":"2026-05-28T01:05:17.008780+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28396","created_at":"2026-05-28T01:05:17.008780+00:00"},{"alias_kind":"pith_short_12","alias_value":"OGADK5M666EG","created_at":"2026-05-28T01:05:17.008780+00:00"},{"alias_kind":"pith_short_16","alias_value":"OGADK5M666EGG5EY","created_at":"2026-05-28T01:05:17.008780+00:00"},{"alias_kind":"pith_short_8","alias_value":"OGADK5M6","created_at":"2026-05-28T01:05:17.008780+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/OGADK5M666EGG5EY65ZLURY4X2","json":"https://pith.science/pith/OGADK5M666EGG5EY65ZLURY4X2.json","graph_json":"https://pith.science/api/pith-number/OGADK5M666EGG5EY65ZLURY4X2/graph.json","events_json":"https://pith.science/api/pith-number/OGADK5M666EGG5EY65ZLURY4X2/events.json","paper":"https://pith.science/paper/OGADK5M6"},"agent_actions":{"view_html":"https://pith.science/pith/OGADK5M666EGG5EY65ZLURY4X2","download_json":"https://pith.science/pith/OGADK5M666EGG5EY65ZLURY4X2.json","view_paper":"https://pith.science/paper/OGADK5M6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.28396&json=true","fetch_graph":"https://pith.science/api/pith-number/OGADK5M666EGG5EY65ZLURY4X2/graph.json","fetch_events":"https://pith.science/api/pith-number/OGADK5M666EGG5EY65ZLURY4X2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OGADK5M666EGG5EY65ZLURY4X2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OGADK5M666EGG5EY65ZLURY4X2/action/storage_attestation","attest_author":"https://pith.science/pith/OGADK5M666EGG5EY65ZLURY4X2/action/author_attestation","sign_citation":"https://pith.science/pith/OGADK5M666EGG5EY65ZLURY4X2/action/citation_signature","submit_replication":"https://pith.science/pith/OGADK5M666EGG5EY65ZLURY4X2/action/replication_record"}},"created_at":"2026-05-28T01:05:17.008780+00:00","updated_at":"2026-05-28T01:05:17.008780+00:00"}