{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:YCUF56C44PKJUPLP2TPMDP7XKV","short_pith_number":"pith:YCUF56C4","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"},"canonical_sha256":"c0a85ef85ce3d49a3d6fd4dec1bff7554b9c6d0621b9a931af2f3e451c074c9f","source":{"kind":"arxiv","id":"2606.24084","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.24084","created_at":"2026-06-24T01:14:39Z"},{"alias_kind":"arxiv_version","alias_value":"2606.24084v1","created_at":"2026-06-24T01:14:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.24084","created_at":"2026-06-24T01:14:39Z"},{"alias_kind":"pith_short_12","alias_value":"YCUF56C44PKJ","created_at":"2026-06-24T01:14:39Z"},{"alias_kind":"pith_short_16","alias_value":"YCUF56C44PKJUPLP","created_at":"2026-06-24T01:14:39Z"},{"alias_kind":"pith_short_8","alias_value":"YCUF56C4","created_at":"2026-06-24T01:14:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:YCUF56C44PKJUPLP2TPMDP7XKV","target":"record","payload":{"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"},"canonical_sha256":"c0a85ef85ce3d49a3d6fd4dec1bff7554b9c6d0621b9a931af2f3e451c074c9f","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"},"source_kind":"arxiv","source_id":"2606.24084","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-24T01:14:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hUgfWTQhyKcuu4sX4ZFQbp/Cy0PqfnnmsxEp+uBvQLfNbhKnwyBUbvhuaHm9Y3fc19EwDF0IBhfW7XQJxAsjCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T22:47:11.639022Z"},"content_sha256":"a787b86dbbf5a6c12ac7c46f6d3de069449942b3f77a6690933dcea40da73fb6","schema_version":"1.0","event_id":"sha256:a787b86dbbf5a6c12ac7c46f6d3de069449942b3f77a6690933dcea40da73fb6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:YCUF56C44PKJUPLP2TPMDP7XKV","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-24T01:14:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xs7nA59/T7e4Ezf+PvGkn3XU/TXHJRKipUydTOztJPJEYgmlhaAhkTA6VAt+cRBvvJcpRugAufoMmKPRUqfMBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T22:47:11.639448Z"},"content_sha256":"bf2e514f826de852aef62b5f8657d41c1f03c2ce3a2c5501728296f439f1a79e","schema_version":"1.0","event_id":"sha256:bf2e514f826de852aef62b5f8657d41c1f03c2ce3a2c5501728296f439f1a79e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YCUF56C44PKJUPLP2TPMDP7XKV/bundle.json","state_url":"https://pith.science/pith/YCUF56C44PKJUPLP2TPMDP7XKV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YCUF56C44PKJUPLP2TPMDP7XKV/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-27T22:47:11Z","links":{"resolver":"https://pith.science/pith/YCUF56C44PKJUPLP2TPMDP7XKV","bundle":"https://pith.science/pith/YCUF56C44PKJUPLP2TPMDP7XKV/bundle.json","state":"https://pith.science/pith/YCUF56C44PKJUPLP2TPMDP7XKV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YCUF56C44PKJUPLP2TPMDP7XKV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YCUF56C44PKJUPLP2TPMDP7XKV","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":"c740801124f0ecbf6e213909a5e0be3f8e887d00e859a8fbbee92996d27d7296","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-23T02:58:16Z","title_canon_sha256":"d42b8dd6f79674ef3fe6445e626e37d510d0a533fef269a8c2c1b1123e7149a4"},"schema_version":"1.0","source":{"id":"2606.24084","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.24084","created_at":"2026-06-24T01:14:39Z"},{"alias_kind":"arxiv_version","alias_value":"2606.24084v1","created_at":"2026-06-24T01:14:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.24084","created_at":"2026-06-24T01:14:39Z"},{"alias_kind":"pith_short_12","alias_value":"YCUF56C44PKJ","created_at":"2026-06-24T01:14:39Z"},{"alias_kind":"pith_short_16","alias_value":"YCUF56C44PKJUPLP","created_at":"2026-06-24T01:14:39Z"},{"alias_kind":"pith_short_8","alias_value":"YCUF56C4","created_at":"2026-06-24T01:14:39Z"}],"graph_snapshots":[{"event_id":"sha256:bf2e514f826de852aef62b5f8657d41c1f03c2ce3a2c5501728296f439f1a79e","target":"graph","created_at":"2026-06-24T01:14:39Z","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/2606.24084/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Haiyun Jiang, Liwen Zheng","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-23T02:58:16Z","title":"Blockwise Policy-Drift Gating for On-Policy Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.24084","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:a787b86dbbf5a6c12ac7c46f6d3de069449942b3f77a6690933dcea40da73fb6","target":"record","created_at":"2026-06-24T01:14:39Z","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":"c740801124f0ecbf6e213909a5e0be3f8e887d00e859a8fbbee92996d27d7296","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-23T02:58:16Z","title_canon_sha256":"d42b8dd6f79674ef3fe6445e626e37d510d0a533fef269a8c2c1b1123e7149a4"},"schema_version":"1.0","source":{"id":"2606.24084","kind":"arxiv","version":1}},"canonical_sha256":"c0a85ef85ce3d49a3d6fd4dec1bff7554b9c6d0621b9a931af2f3e451c074c9f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c0a85ef85ce3d49a3d6fd4dec1bff7554b9c6d0621b9a931af2f3e451c074c9f","first_computed_at":"2026-06-24T01:14:39.874533Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-24T01:14:39.874533Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"57aS2RCXsjdfkwyDp7t82UJa3WdK4Mimv872YavBSNaiJsCITeWZ9+EQZq6E8zxlXQEnkXrAS56NTALxHUoVAQ==","signature_status":"signed_v1","signed_at":"2026-06-24T01:14:39.874887Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.24084","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a787b86dbbf5a6c12ac7c46f6d3de069449942b3f77a6690933dcea40da73fb6","sha256:bf2e514f826de852aef62b5f8657d41c1f03c2ce3a2c5501728296f439f1a79e"],"state_sha256":"25f66ef35201732ffd039c99110d45a73704b6102aad704245913607123b4de9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RrP+kEfZ7bdmRL9F/ktCYkbrgSZRKm0rqszI5Mtfn7gHBvD622dUAGLdtha6ruwZ0EJSYyLLLKnuEgnpqLxNDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-27T22:47:11.641438Z","bundle_sha256":"c9fb876316824dd44c9cdd99482410504e68d0062f7f3e4fc564aa61ebcf5b0c"}}