{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CXJ7ZWLVBBRXQ6VM7LQNNIIJSB","short_pith_number":"pith:CXJ7ZWLV","schema_version":"1.0","canonical_sha256":"15d3fcd9750863787aacfae0d6a10990559733463ac066df758b45be6f3f2cf6","source":{"kind":"arxiv","id":"2605.31159","version":1},"attestation_state":"computed","paper":{"title":"Trust-Region Behavior Blending for On-Policy Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alexey Gorbatovski, Alexey Malakhov, Boris Shaposhnikov, Daniil Gavrilov, Daniil Plyusov, Daria Korotyshova, Nikita Balagansky","submitted_at":"2026-05-29T11:06:06Z","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"},"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":"2605.31159","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-29T11:06:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1e328abdbed002a73956ef302236dfa3cfcec84fa5dd66adb991ac3e00d103c7","abstract_canon_sha256":"f51b37a2794821431e100779f482443962d2cea1116602f0e29c5a1e77f3ee38"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:04:01.774822Z","signature_b64":"aR2YHahNx17Q/N/91622/UtqWmjMR5foQFUKRzUstSe62SgjIhASscRkUzjRYPU03KOtnd8z8OiJwziDxEDYCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15d3fcd9750863787aacfae0d6a10990559733463ac066df758b45be6f3f2cf6","last_reissued_at":"2026-06-01T01:04:01.774178Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:04:01.774178Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Trust-Region Behavior Blending for On-Policy Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alexey Gorbatovski, Alexey Malakhov, Boris Shaposhnikov, Daniil Gavrilov, Daniil Plyusov, Daria Korotyshova, Nikita Balagansky","submitted_at":"2026-05-29T11:06:06Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.31159","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/2605.31159/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":"2605.31159","created_at":"2026-06-01T01:04:01.774287+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.31159v1","created_at":"2026-06-01T01:04:01.774287+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.31159","created_at":"2026-06-01T01:04:01.774287+00:00"},{"alias_kind":"pith_short_12","alias_value":"CXJ7ZWLVBBRX","created_at":"2026-06-01T01:04:01.774287+00:00"},{"alias_kind":"pith_short_16","alias_value":"CXJ7ZWLVBBRXQ6VM","created_at":"2026-06-01T01:04:01.774287+00:00"},{"alias_kind":"pith_short_8","alias_value":"CXJ7ZWLV","created_at":"2026-06-01T01:04:01.774287+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/CXJ7ZWLVBBRXQ6VM7LQNNIIJSB","json":"https://pith.science/pith/CXJ7ZWLVBBRXQ6VM7LQNNIIJSB.json","graph_json":"https://pith.science/api/pith-number/CXJ7ZWLVBBRXQ6VM7LQNNIIJSB/graph.json","events_json":"https://pith.science/api/pith-number/CXJ7ZWLVBBRXQ6VM7LQNNIIJSB/events.json","paper":"https://pith.science/paper/CXJ7ZWLV"},"agent_actions":{"view_html":"https://pith.science/pith/CXJ7ZWLVBBRXQ6VM7LQNNIIJSB","download_json":"https://pith.science/pith/CXJ7ZWLVBBRXQ6VM7LQNNIIJSB.json","view_paper":"https://pith.science/paper/CXJ7ZWLV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.31159&json=true","fetch_graph":"https://pith.science/api/pith-number/CXJ7ZWLVBBRXQ6VM7LQNNIIJSB/graph.json","fetch_events":"https://pith.science/api/pith-number/CXJ7ZWLVBBRXQ6VM7LQNNIIJSB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CXJ7ZWLVBBRXQ6VM7LQNNIIJSB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CXJ7ZWLVBBRXQ6VM7LQNNIIJSB/action/storage_attestation","attest_author":"https://pith.science/pith/CXJ7ZWLVBBRXQ6VM7LQNNIIJSB/action/author_attestation","sign_citation":"https://pith.science/pith/CXJ7ZWLVBBRXQ6VM7LQNNIIJSB/action/citation_signature","submit_replication":"https://pith.science/pith/CXJ7ZWLVBBRXQ6VM7LQNNIIJSB/action/replication_record"}},"created_at":"2026-06-01T01:04:01.774287+00:00","updated_at":"2026-06-01T01:04:01.774287+00:00"}