{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:IP34FEZ2T65SUWPI5RJLNLVDZN","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":"fb63402f0d7d235fd99cec3099f6461afb779c00cb0e9faf8ce6c1cf4836892e","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-15T02:52:37Z","title_canon_sha256":"622757621ef628dd745dbaafe68e86e4b3eaf97c157824ab74a3cb0e18d87fd5"},"schema_version":"1.0","source":{"id":"2607.13399","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.13399","created_at":"2026-07-16T00:22:15Z"},{"alias_kind":"arxiv_version","alias_value":"2607.13399v1","created_at":"2026-07-16T00:22:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.13399","created_at":"2026-07-16T00:22:15Z"},{"alias_kind":"pith_short_12","alias_value":"IP34FEZ2T65S","created_at":"2026-07-16T00:22:15Z"},{"alias_kind":"pith_short_16","alias_value":"IP34FEZ2T65SUWPI","created_at":"2026-07-16T00:22:15Z"},{"alias_kind":"pith_short_8","alias_value":"IP34FEZ2","created_at":"2026-07-16T00:22:15Z"}],"graph_snapshots":[{"event_id":"sha256:3e70da7f322768e3ae34e5c1766c8dd82ab1b923739f449974c00276fd349fd3","target":"graph","created_at":"2026-07-16T00:22:15Z","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/2607.13399/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"On-policy distillation (OPD) has become a key paradigm in LLM post-training, yet its training dynamics remain poorly understood. We present a systematic study examining the role, pathologies, and regulations of OPD. We first clarify the role of OPD as an exploration catalyst: it steers the student toward correct reasoning paths via dense token-level guidance, without expanding capability ceiling. We confirm this by showing that prompt diversity matters more than per-problem sampling numbers, and critically, that the effectiveness of OPD hinges entirely on the quality of its guiding signal. Thi","authors_text":"Boyang Xue, Hongru Wang, Kam-Fai Wong, Rui Wang, Tianqing Fang, Wenhao Yu, Yi Chen","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-15T02:52:37Z","title":"Demystifying On-Policy Distillation: Roles, Pathologies, and Regulations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.13399","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":"sha256:0b83c2401cec4c73e07e77f6726d6ebff40903c82a16e91c9fad58e1093b9916","target":"record","created_at":"2026-07-16T00:22:15Z","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":"fb63402f0d7d235fd99cec3099f6461afb779c00cb0e9faf8ce6c1cf4836892e","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-15T02:52:37Z","title_canon_sha256":"622757621ef628dd745dbaafe68e86e4b3eaf97c157824ab74a3cb0e18d87fd5"},"schema_version":"1.0","source":{"id":"2607.13399","kind":"arxiv","version":1}},"canonical_sha256":"43f7c2933a9fbb2a59e8ec52b6aea3cb4236d2b3eae76af2e74b0b21020156ac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"43f7c2933a9fbb2a59e8ec52b6aea3cb4236d2b3eae76af2e74b0b21020156ac","first_computed_at":"2026-07-16T00:22:15.927841Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-16T00:22:15.927841Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AUBZPCCx+DUBGxWik1uelT8KDy20qnwvN4RQiVXE6kKMb08lEzXw+JhqeSSgW7ofHlP/Z2jS2X5woaIAEI3DAg==","signature_status":"signed_v1","signed_at":"2026-07-16T00:22:15.928783Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.13399","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0b83c2401cec4c73e07e77f6726d6ebff40903c82a16e91c9fad58e1093b9916","sha256:3e70da7f322768e3ae34e5c1766c8dd82ab1b923739f449974c00276fd349fd3"],"state_sha256":"790346bd56a8a0443af475ff6b2f581f83f037188a06fa7734d21ce02eabb38d"}