{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3VU5OSXRJFKVPOQDBDPLL4WICY","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":"6ac4c0972e7b928d8d375a3bec3f1b7dcd2917672cfcdabb2851e0a56a1941d0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-22T03:09:21Z","title_canon_sha256":"0eab3aebd1c222ecb3ea5dbbd0b665b04183d143d620da92835a7f1a2c1e8cf8"},"schema_version":"1.0","source":{"id":"2606.22793","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.22793","created_at":"2026-06-23T02:13:59Z"},{"alias_kind":"arxiv_version","alias_value":"2606.22793v1","created_at":"2026-06-23T02:13:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.22793","created_at":"2026-06-23T02:13:59Z"},{"alias_kind":"pith_short_12","alias_value":"3VU5OSXRJFKV","created_at":"2026-06-23T02:13:59Z"},{"alias_kind":"pith_short_16","alias_value":"3VU5OSXRJFKVPOQD","created_at":"2026-06-23T02:13:59Z"},{"alias_kind":"pith_short_8","alias_value":"3VU5OSXR","created_at":"2026-06-23T02:13:59Z"}],"graph_snapshots":[{"event_id":"sha256:3a94d3640bb3998c1df377e97984bb29f4acaebbc804c709e4d567b02d0e41ab","target":"graph","created_at":"2026-06-23T02:13:59Z","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/2606.22793/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"On-policy distillation (OPD) trains an LLM on states induced by the current or recent student policy: the student generates complete or partial rollouts, a teacher or self-teacher scores the resulting tokens under their generated contexts, and dense log-probability, logit, or distributional signals are converted into post-training updates. This survey studies OPD as a feedback-to-update problem rather than a single loss family. We develop a formula-driven taxonomy from two routes -- direct distributional losses and policy-gradient-style log-ratio updates -- and use it to organize core methods,","authors_text":"Bowen Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-22T03:09:21Z","title":"A Formula-Driven Survey and Research Agenda for On-Policy Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.22793","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":"sha256:8a02d0ee9f263d42b42fc7963c6cba822351f702c9a6224ceec8fbcdb23b983a","target":"record","created_at":"2026-06-23T02:13:59Z","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":"6ac4c0972e7b928d8d375a3bec3f1b7dcd2917672cfcdabb2851e0a56a1941d0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-22T03:09:21Z","title_canon_sha256":"0eab3aebd1c222ecb3ea5dbbd0b665b04183d143d620da92835a7f1a2c1e8cf8"},"schema_version":"1.0","source":{"id":"2606.22793","kind":"arxiv","version":1}},"canonical_sha256":"dd69d74af1495557ba0308deb5f2c81625249231fd4a4419e426ab92e424aa5c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dd69d74af1495557ba0308deb5f2c81625249231fd4a4419e426ab92e424aa5c","first_computed_at":"2026-06-23T02:13:59.390007Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T02:13:59.390007Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1dDiWd2TtYjiNSQEy/nEGn8ViZ+pQFhEnl9TuQ5iUkKejLX10QGIyGoXgmx2PwFYFpRgjCi5xAdbG7i6fl6yBA==","signature_status":"signed_v1","signed_at":"2026-06-23T02:13:59.390512Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.22793","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8a02d0ee9f263d42b42fc7963c6cba822351f702c9a6224ceec8fbcdb23b983a","sha256:3a94d3640bb3998c1df377e97984bb29f4acaebbc804c709e4d567b02d0e41ab"],"state_sha256":"1458ed5ca62bebce48e3d1a82d3c60877c72fc9a80887d7e87a258335f56428b"}