{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YCUF56C44PKJUPLP2TPMDP7XKV","short_pith_number":"pith:YCUF56C4","schema_version":"1.0","canonical_sha256":"c0a85ef85ce3d49a3d6fd4dec1bff7554b9c6d0621b9a931af2f3e451c074c9f","source":{"kind":"arxiv","id":"2606.24084","version":1},"attestation_state":"computed","paper":{"title":"Blockwise Policy-Drift Gating for On-Policy Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Haiyun Jiang, Liwen Zheng","submitted_at":"2026-06-23T02:58:16Z","abstract_excerpt":"On-policy distillation (OPD) trains a student policy using teacher signals computed on trajectories sampled by the student itself. Recent work shows that sampled-token OPD can be fragile on long-horizon reasoning tasks and that local teacher-support matching is a simple and effective repair. This paper introduces blockwise policy-drift gating, a lightweight student-only old-current drift controller for OPD under rollout reuse. The method computes log-probability shifts between the behavior student and the current student on the sampled token path, aggregates these shifts over fixed blocks or s"},"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":"2606.24084","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-23T02:58:16Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"d42b8dd6f79674ef3fe6445e626e37d510d0a533fef269a8c2c1b1123e7149a4","abstract_canon_sha256":"c740801124f0ecbf6e213909a5e0be3f8e887d00e859a8fbbee92996d27d7296"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-24T01:14:39.874887Z","signature_b64":"57aS2RCXsjdfkwyDp7t82UJa3WdK4Mimv872YavBSNaiJsCITeWZ9+EQZq6E8zxlXQEnkXrAS56NTALxHUoVAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0a85ef85ce3d49a3d6fd4dec1bff7554b9c6d0621b9a931af2f3e451c074c9f","last_reissued_at":"2026-06-24T01:14:39.874533Z","signature_status":"signed_v1","first_computed_at":"2026-06-24T01:14:39.874533Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Blockwise Policy-Drift Gating for On-Policy Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Haiyun Jiang, Liwen Zheng","submitted_at":"2026-06-23T02:58:16Z","abstract_excerpt":"On-policy distillation (OPD) trains a student policy using teacher signals computed on trajectories sampled by the student itself. Recent work shows that sampled-token OPD can be fragile on long-horizon reasoning tasks and that local teacher-support matching is a simple and effective repair. This paper introduces blockwise policy-drift gating, a lightweight student-only old-current drift controller for OPD under rollout reuse. The method computes log-probability shifts between the behavior student and the current student on the sampled token path, aggregates these shifts over fixed blocks or s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.24084","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/2606.24084/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":"2606.24084","created_at":"2026-06-24T01:14:39.874594+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.24084v1","created_at":"2026-06-24T01:14:39.874594+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.24084","created_at":"2026-06-24T01:14:39.874594+00:00"},{"alias_kind":"pith_short_12","alias_value":"YCUF56C44PKJ","created_at":"2026-06-24T01:14:39.874594+00:00"},{"alias_kind":"pith_short_16","alias_value":"YCUF56C44PKJUPLP","created_at":"2026-06-24T01:14:39.874594+00:00"},{"alias_kind":"pith_short_8","alias_value":"YCUF56C4","created_at":"2026-06-24T01:14:39.874594+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/YCUF56C44PKJUPLP2TPMDP7XKV","json":"https://pith.science/pith/YCUF56C44PKJUPLP2TPMDP7XKV.json","graph_json":"https://pith.science/api/pith-number/YCUF56C44PKJUPLP2TPMDP7XKV/graph.json","events_json":"https://pith.science/api/pith-number/YCUF56C44PKJUPLP2TPMDP7XKV/events.json","paper":"https://pith.science/paper/YCUF56C4"},"agent_actions":{"view_html":"https://pith.science/pith/YCUF56C44PKJUPLP2TPMDP7XKV","download_json":"https://pith.science/pith/YCUF56C44PKJUPLP2TPMDP7XKV.json","view_paper":"https://pith.science/paper/YCUF56C4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.24084&json=true","fetch_graph":"https://pith.science/api/pith-number/YCUF56C44PKJUPLP2TPMDP7XKV/graph.json","fetch_events":"https://pith.science/api/pith-number/YCUF56C44PKJUPLP2TPMDP7XKV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YCUF56C44PKJUPLP2TPMDP7XKV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YCUF56C44PKJUPLP2TPMDP7XKV/action/storage_attestation","attest_author":"https://pith.science/pith/YCUF56C44PKJUPLP2TPMDP7XKV/action/author_attestation","sign_citation":"https://pith.science/pith/YCUF56C44PKJUPLP2TPMDP7XKV/action/citation_signature","submit_replication":"https://pith.science/pith/YCUF56C44PKJUPLP2TPMDP7XKV/action/replication_record"}},"created_at":"2026-06-24T01:14:39.874594+00:00","updated_at":"2026-06-24T01:14:39.874594+00:00"}