{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:CXJ7ZWLVBBRXQ6VM7LQNNIIJSB","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":"f51b37a2794821431e100779f482443962d2cea1116602f0e29c5a1e77f3ee38","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T11:06:06Z","title_canon_sha256":"1e328abdbed002a73956ef302236dfa3cfcec84fa5dd66adb991ac3e00d103c7"},"schema_version":"1.0","source":{"id":"2605.31159","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.31159","created_at":"2026-06-01T01:04:01Z"},{"alias_kind":"arxiv_version","alias_value":"2605.31159v1","created_at":"2026-06-01T01:04:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.31159","created_at":"2026-06-01T01:04:01Z"},{"alias_kind":"pith_short_12","alias_value":"CXJ7ZWLVBBRX","created_at":"2026-06-01T01:04:01Z"},{"alias_kind":"pith_short_16","alias_value":"CXJ7ZWLVBBRXQ6VM","created_at":"2026-06-01T01:04:01Z"},{"alias_kind":"pith_short_8","alias_value":"CXJ7ZWLV","created_at":"2026-06-01T01:04:01Z"}],"graph_snapshots":[{"event_id":"sha256:a5c479fd6776d47df52842eacff0f482a8a51b6ed41fc3350baf8fd21e64120a","target":"graph","created_at":"2026-06-01T01:04:01Z","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/2605.31159/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 on prefixes sampled from its own policy while matching a stronger teacher. This addresses the prefix mismatch of offline distillation, but early student rollouts can still be poor, placing teacher supervision on weak or low-quality prefixes. We propose Trust-Region behavior Blending (TRB), a warmup method that replaces the early rollout policy with the closest-to-teacher behavior policy inside a student-centered KL trust region, while keeping the per-prefix reverse-KL OPD loss unchanged. The KL budget is annealed to zero, so training returns to pur","authors_text":"Alexey Gorbatovski, Alexey Malakhov, Boris Shaposhnikov, Daniil Gavrilov, Daniil Plyusov, Daria Korotyshova, Nikita Balagansky","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T11:06:06Z","title":"Trust-Region Behavior Blending for On-Policy Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.31159","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":"sha256:42682b2ed74f68b005a9764477f9b0cc74f08d41a52f70c4cf6e478892951cbe","target":"record","created_at":"2026-06-01T01:04:01Z","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":"f51b37a2794821431e100779f482443962d2cea1116602f0e29c5a1e77f3ee38","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T11:06:06Z","title_canon_sha256":"1e328abdbed002a73956ef302236dfa3cfcec84fa5dd66adb991ac3e00d103c7"},"schema_version":"1.0","source":{"id":"2605.31159","kind":"arxiv","version":1}},"canonical_sha256":"15d3fcd9750863787aacfae0d6a10990559733463ac066df758b45be6f3f2cf6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"15d3fcd9750863787aacfae0d6a10990559733463ac066df758b45be6f3f2cf6","first_computed_at":"2026-06-01T01:04:01.774178Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-01T01:04:01.774178Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aR2YHahNx17Q/N/91622/UtqWmjMR5foQFUKRzUstSe62SgjIhASscRkUzjRYPU03KOtnd8z8OiJwziDxEDYCA==","signature_status":"signed_v1","signed_at":"2026-06-01T01:04:01.774822Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.31159","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:42682b2ed74f68b005a9764477f9b0cc74f08d41a52f70c4cf6e478892951cbe","sha256:a5c479fd6776d47df52842eacff0f482a8a51b6ed41fc3350baf8fd21e64120a"],"state_sha256":"22a2e8db83685f7bcbef8ec261418f9f447ac15173538b690cf8dfaaa4e80eea"}