{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:W3AI5JRUIPZ7ZGCQCPMUXPRSRX","short_pith_number":"pith:W3AI5JRU","canonical_record":{"source":{"id":"2606.09825","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-08T17:59:39Z","cross_cats_sorted":["cs.AI","cs.SY","eess.SY","math.OC"],"title_canon_sha256":"038550cd49c34447cde31261f0ff2169d8f6151c8748849d9d995d7429734b84","abstract_canon_sha256":"526168a29acd39313b0d5c9965471933ef02c4f812e75862e10bdf45f4308f58"},"schema_version":"1.0"},"canonical_sha256":"b6c08ea63443f3fc985013d94bbe328de6001c611b82b59f47c3ed5d5912f3f1","source":{"kind":"arxiv","id":"2606.09825","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.09825","created_at":"2026-06-09T02:09:12Z"},{"alias_kind":"arxiv_version","alias_value":"2606.09825v1","created_at":"2026-06-09T02:09:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09825","created_at":"2026-06-09T02:09:12Z"},{"alias_kind":"pith_short_12","alias_value":"W3AI5JRUIPZ7","created_at":"2026-06-09T02:09:12Z"},{"alias_kind":"pith_short_16","alias_value":"W3AI5JRUIPZ7ZGCQ","created_at":"2026-06-09T02:09:12Z"},{"alias_kind":"pith_short_8","alias_value":"W3AI5JRU","created_at":"2026-06-09T02:09:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:W3AI5JRUIPZ7ZGCQCPMUXPRSRX","target":"record","payload":{"canonical_record":{"source":{"id":"2606.09825","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-08T17:59:39Z","cross_cats_sorted":["cs.AI","cs.SY","eess.SY","math.OC"],"title_canon_sha256":"038550cd49c34447cde31261f0ff2169d8f6151c8748849d9d995d7429734b84","abstract_canon_sha256":"526168a29acd39313b0d5c9965471933ef02c4f812e75862e10bdf45f4308f58"},"schema_version":"1.0"},"canonical_sha256":"b6c08ea63443f3fc985013d94bbe328de6001c611b82b59f47c3ed5d5912f3f1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:09:12.648624Z","signature_b64":"+bDR+aVeFFwNigFzGt6A8G0KdLmeaAMmxw5LP2uYErAJ4R7F7GfE2WjiYsycQ45jaBF3Jilm/giUs6vX1GssCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b6c08ea63443f3fc985013d94bbe328de6001c611b82b59f47c3ed5d5912f3f1","last_reissued_at":"2026-06-09T02:09:12.647788Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:09:12.647788Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.09825","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":"2026-06-09T02:09:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Gx9jHD6+hDg2O4kfY/hkSujH5sKZRRIUb4r2i1HtNFU99YnA4r5RszDlifTvpQMFvrAuJTM0p77uB6x5eI0rDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T17:47:28.245745Z"},"content_sha256":"5d77438460cdbe61467e8ef1a906fddc5571200300cdb8e796df9a5fee0245e2","schema_version":"1.0","event_id":"sha256:5d77438460cdbe61467e8ef1a906fddc5571200300cdb8e796df9a5fee0245e2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:W3AI5JRUIPZ7ZGCQCPMUXPRSRX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Agency-Transferring Model-Free Policy Enhancement Technique","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SY","eess.SY","math.OC"],"primary_cat":"cs.LG","authors_text":"Anton Bolychev, Georgiy Malaniya, Pavel Osinenko, Sinan Ibrahim","submitted_at":"2026-06-08T17:59:39Z","abstract_excerpt":"Training reinforcement learning (RL) policies from scratch is\n  costly: it requires careful reward and environment design,\n  extensive tuning, and substantial computation.\n  Yet many control problems already have a functional but\n  suboptimal policy available as a baseline.\n  This paper proposes a method for embedding such a baseline into\n  the RL training process, simultaneously improving training\n  efficiency relative to from-scratch methods and producing a\n  learning policy that outperforms the baseline.\n  At each step, the method arbitrates between the baseline policy\n  and a trainable lea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09825","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/2606.09825/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":"2026-06-09T02:09:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1V9JzMxuW/2eAXWgPPPJYSi4ijhSCwJuRoZJevIsXcjGzkpnGJAfsQr3PfG+AKpHJyZTCVJZbjC+Pn5WABQ3AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T17:47:28.246143Z"},"content_sha256":"708038ba817a4fea8d5efbdfd6b4d44d554947af74fd4586eae3637360197add","schema_version":"1.0","event_id":"sha256:708038ba817a4fea8d5efbdfd6b4d44d554947af74fd4586eae3637360197add"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/W3AI5JRUIPZ7ZGCQCPMUXPRSRX/bundle.json","state_url":"https://pith.science/pith/W3AI5JRUIPZ7ZGCQCPMUXPRSRX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/W3AI5JRUIPZ7ZGCQCPMUXPRSRX/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":"2026-06-28T17:47:28Z","links":{"resolver":"https://pith.science/pith/W3AI5JRUIPZ7ZGCQCPMUXPRSRX","bundle":"https://pith.science/pith/W3AI5JRUIPZ7ZGCQCPMUXPRSRX/bundle.json","state":"https://pith.science/pith/W3AI5JRUIPZ7ZGCQCPMUXPRSRX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/W3AI5JRUIPZ7ZGCQCPMUXPRSRX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:W3AI5JRUIPZ7ZGCQCPMUXPRSRX","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":"526168a29acd39313b0d5c9965471933ef02c4f812e75862e10bdf45f4308f58","cross_cats_sorted":["cs.AI","cs.SY","eess.SY","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-08T17:59:39Z","title_canon_sha256":"038550cd49c34447cde31261f0ff2169d8f6151c8748849d9d995d7429734b84"},"schema_version":"1.0","source":{"id":"2606.09825","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.09825","created_at":"2026-06-09T02:09:12Z"},{"alias_kind":"arxiv_version","alias_value":"2606.09825v1","created_at":"2026-06-09T02:09:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09825","created_at":"2026-06-09T02:09:12Z"},{"alias_kind":"pith_short_12","alias_value":"W3AI5JRUIPZ7","created_at":"2026-06-09T02:09:12Z"},{"alias_kind":"pith_short_16","alias_value":"W3AI5JRUIPZ7ZGCQ","created_at":"2026-06-09T02:09:12Z"},{"alias_kind":"pith_short_8","alias_value":"W3AI5JRU","created_at":"2026-06-09T02:09:12Z"}],"graph_snapshots":[{"event_id":"sha256:708038ba817a4fea8d5efbdfd6b4d44d554947af74fd4586eae3637360197add","target":"graph","created_at":"2026-06-09T02:09:12Z","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/2606.09825/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training reinforcement learning (RL) policies from scratch is\n  costly: it requires careful reward and environment design,\n  extensive tuning, and substantial computation.\n  Yet many control problems already have a functional but\n  suboptimal policy available as a baseline.\n  This paper proposes a method for embedding such a baseline into\n  the RL training process, simultaneously improving training\n  efficiency relative to from-scratch methods and producing a\n  learning policy that outperforms the baseline.\n  At each step, the method arbitrates between the baseline policy\n  and a trainable lea","authors_text":"Anton Bolychev, Georgiy Malaniya, Pavel Osinenko, Sinan Ibrahim","cross_cats":["cs.AI","cs.SY","eess.SY","math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-08T17:59:39Z","title":"An Agency-Transferring Model-Free Policy Enhancement Technique"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09825","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":"sha256:5d77438460cdbe61467e8ef1a906fddc5571200300cdb8e796df9a5fee0245e2","target":"record","created_at":"2026-06-09T02:09:12Z","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":"526168a29acd39313b0d5c9965471933ef02c4f812e75862e10bdf45f4308f58","cross_cats_sorted":["cs.AI","cs.SY","eess.SY","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-08T17:59:39Z","title_canon_sha256":"038550cd49c34447cde31261f0ff2169d8f6151c8748849d9d995d7429734b84"},"schema_version":"1.0","source":{"id":"2606.09825","kind":"arxiv","version":1}},"canonical_sha256":"b6c08ea63443f3fc985013d94bbe328de6001c611b82b59f47c3ed5d5912f3f1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b6c08ea63443f3fc985013d94bbe328de6001c611b82b59f47c3ed5d5912f3f1","first_computed_at":"2026-06-09T02:09:12.647788Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T02:09:12.647788Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+bDR+aVeFFwNigFzGt6A8G0KdLmeaAMmxw5LP2uYErAJ4R7F7GfE2WjiYsycQ45jaBF3Jilm/giUs6vX1GssCQ==","signature_status":"signed_v1","signed_at":"2026-06-09T02:09:12.648624Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.09825","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5d77438460cdbe61467e8ef1a906fddc5571200300cdb8e796df9a5fee0245e2","sha256:708038ba817a4fea8d5efbdfd6b4d44d554947af74fd4586eae3637360197add"],"state_sha256":"8cb59a3026e49b16237361c5c2abc3bb1b6a69d126bfe46687e332fe942849d7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mmk37paFmsMGRDs9y8M/pR5lPPv7tY2/bIW32UCF8p4w/svbK2pSwI3L8hUo3Eu9X3bJwOCCQpY0Ny/GjNBABw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T17:47:28.248092Z","bundle_sha256":"e516af91f771dc6a5373c10357fdb9aef0db116077954842648e83e75ed05e29"}}