{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:PEULEP3JWVVVBO7BAZXXSXEQSG","short_pith_number":"pith:PEULEP3J","canonical_record":{"source":{"id":"2605.18675","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T17:15:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cffa3dccb15e5f6c74563023dcf3f6a3a144ee0c7e4bd105fa2c04e70c1876c4","abstract_canon_sha256":"f371d7f20a0e1653461093dca1de11abd318d73aded23db3a54747e76dc4f67e"},"schema_version":"1.0"},"canonical_sha256":"7928b23f69b56b50bbe1066f795c9091a6a1105b774a372548baa32f525dbb32","source":{"kind":"arxiv","id":"2605.18675","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.18675","created_at":"2026-05-20T00:06:14Z"},{"alias_kind":"arxiv_version","alias_value":"2605.18675v1","created_at":"2026-05-20T00:06:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18675","created_at":"2026-05-20T00:06:14Z"},{"alias_kind":"pith_short_12","alias_value":"PEULEP3JWVVV","created_at":"2026-05-20T00:06:14Z"},{"alias_kind":"pith_short_16","alias_value":"PEULEP3JWVVVBO7B","created_at":"2026-05-20T00:06:14Z"},{"alias_kind":"pith_short_8","alias_value":"PEULEP3J","created_at":"2026-05-20T00:06:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:PEULEP3JWVVVBO7BAZXXSXEQSG","target":"record","payload":{"canonical_record":{"source":{"id":"2605.18675","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T17:15:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cffa3dccb15e5f6c74563023dcf3f6a3a144ee0c7e4bd105fa2c04e70c1876c4","abstract_canon_sha256":"f371d7f20a0e1653461093dca1de11abd318d73aded23db3a54747e76dc4f67e"},"schema_version":"1.0"},"canonical_sha256":"7928b23f69b56b50bbe1066f795c9091a6a1105b774a372548baa32f525dbb32","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:06:14.212118Z","signature_b64":"I9klpPkYxmq9Ei3Nbseeq3KZQwsgWkq3bmF6t5l5c505SdTNwfqAHdtb3C63wmcfPjhLnmtF3++Ta4aqG4xuAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7928b23f69b56b50bbe1066f795c9091a6a1105b774a372548baa32f525dbb32","last_reissued_at":"2026-05-20T00:06:14.211302Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:06:14.211302Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.18675","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":"2026-05-20T00:06:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7cLPR1d72CoRx6oI3dazGOQgglaFiRAf7eJr7jyj2uQSE5ScnDqdLH0jIcKZ/czC8ZZ76sJQg2dN3KdJFacKDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T01:43:32.528693Z"},"content_sha256":"c1f08640857a8313343866a161731d5642b2c924cfbad0b7510d231b3e41b681","schema_version":"1.0","event_id":"sha256:c1f08640857a8313343866a161731d5642b2c924cfbad0b7510d231b3e41b681"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:PEULEP3JWVVVBO7BAZXXSXEQSG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"COOPO: Cyclic Offline-Online Policy Optimization Algorithm","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aditya Balu, Cody Fleming, Joshua Russell Waite, Qisai Liu, Soumik Sarkar, Zhanhong Jiang","submitted_at":"2026-05-18T17:15:27Z","abstract_excerpt":"Offline reinforcement learning struggles with distributional shift and constrained performance due to static dataset limitations, while online RL demands prohibitive environment interactions. The recent advent of hybrid offline-to-online methods bridges these domains but suffers from distribution drift during transitions and catastrophic forgetting of offline knowledge. We introduce COOPO (Cyclic Offline-Online Policy Optimization), a generalized framework that repeatedly cycles between constrained offline training and online fine-tuning. Each cycle first anchors the policy to the dataset via "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18675","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/2605.18675/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T00:01:59.127133Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"df7ef7b62b82a3afcbab10a0b4b34092afe7ac599bd62521b9af0b8f0720473c"},"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":"2026-05-20T00:06:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KQKEX3QUAVKNdbhN7uP1E5nW4a/oLN0urQXuB0KBCKYQpkjiC0Xkh/QN6K65bDDF3Y3WbYWyD347IRRfStNNDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T01:43:32.529106Z"},"content_sha256":"9530cd75461c23257febc665be013bcc5f2ee093b3917bd42fdeca4321538849","schema_version":"1.0","event_id":"sha256:9530cd75461c23257febc665be013bcc5f2ee093b3917bd42fdeca4321538849"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PEULEP3JWVVVBO7BAZXXSXEQSG/bundle.json","state_url":"https://pith.science/pith/PEULEP3JWVVVBO7BAZXXSXEQSG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PEULEP3JWVVVBO7BAZXXSXEQSG/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":"2026-05-28T01:43:32Z","links":{"resolver":"https://pith.science/pith/PEULEP3JWVVVBO7BAZXXSXEQSG","bundle":"https://pith.science/pith/PEULEP3JWVVVBO7BAZXXSXEQSG/bundle.json","state":"https://pith.science/pith/PEULEP3JWVVVBO7BAZXXSXEQSG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PEULEP3JWVVVBO7BAZXXSXEQSG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:PEULEP3JWVVVBO7BAZXXSXEQSG","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":"f371d7f20a0e1653461093dca1de11abd318d73aded23db3a54747e76dc4f67e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T17:15:27Z","title_canon_sha256":"cffa3dccb15e5f6c74563023dcf3f6a3a144ee0c7e4bd105fa2c04e70c1876c4"},"schema_version":"1.0","source":{"id":"2605.18675","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.18675","created_at":"2026-05-20T00:06:14Z"},{"alias_kind":"arxiv_version","alias_value":"2605.18675v1","created_at":"2026-05-20T00:06:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18675","created_at":"2026-05-20T00:06:14Z"},{"alias_kind":"pith_short_12","alias_value":"PEULEP3JWVVV","created_at":"2026-05-20T00:06:14Z"},{"alias_kind":"pith_short_16","alias_value":"PEULEP3JWVVVBO7B","created_at":"2026-05-20T00:06:14Z"},{"alias_kind":"pith_short_8","alias_value":"PEULEP3J","created_at":"2026-05-20T00:06:14Z"}],"graph_snapshots":[{"event_id":"sha256:9530cd75461c23257febc665be013bcc5f2ee093b3917bd42fdeca4321538849","target":"graph","created_at":"2026-05-20T00:06:14Z","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":[{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-20T00:01:59.127133Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.18675/integrity.json","findings":[],"snapshot_sha256":"df7ef7b62b82a3afcbab10a0b4b34092afe7ac599bd62521b9af0b8f0720473c","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning struggles with distributional shift and constrained performance due to static dataset limitations, while online RL demands prohibitive environment interactions. The recent advent of hybrid offline-to-online methods bridges these domains but suffers from distribution drift during transitions and catastrophic forgetting of offline knowledge. We introduce COOPO (Cyclic Offline-Online Policy Optimization), a generalized framework that repeatedly cycles between constrained offline training and online fine-tuning. Each cycle first anchors the policy to the dataset via ","authors_text":"Aditya Balu, Cody Fleming, Joshua Russell Waite, Qisai Liu, Soumik Sarkar, Zhanhong Jiang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T17:15:27Z","title":"COOPO: Cyclic Offline-Online Policy Optimization Algorithm"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18675","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:c1f08640857a8313343866a161731d5642b2c924cfbad0b7510d231b3e41b681","target":"record","created_at":"2026-05-20T00:06:14Z","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":"f371d7f20a0e1653461093dca1de11abd318d73aded23db3a54747e76dc4f67e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T17:15:27Z","title_canon_sha256":"cffa3dccb15e5f6c74563023dcf3f6a3a144ee0c7e4bd105fa2c04e70c1876c4"},"schema_version":"1.0","source":{"id":"2605.18675","kind":"arxiv","version":1}},"canonical_sha256":"7928b23f69b56b50bbe1066f795c9091a6a1105b774a372548baa32f525dbb32","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7928b23f69b56b50bbe1066f795c9091a6a1105b774a372548baa32f525dbb32","first_computed_at":"2026-05-20T00:06:14.211302Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:06:14.211302Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"I9klpPkYxmq9Ei3Nbseeq3KZQwsgWkq3bmF6t5l5c505SdTNwfqAHdtb3C63wmcfPjhLnmtF3++Ta4aqG4xuAw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:06:14.212118Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.18675","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c1f08640857a8313343866a161731d5642b2c924cfbad0b7510d231b3e41b681","sha256:9530cd75461c23257febc665be013bcc5f2ee093b3917bd42fdeca4321538849"],"state_sha256":"92c88b6808ac29030bae87a6acb78f4ccd4f4ec8bbce62c203334b65dd21cb02"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8AaHYsD1ziJS/qS5o/r69x6we+lymey7xGV/E8vvBFBf3/X3230uNU6GtrW0KfMKr3QUf1KR1QZVIgu86np6Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T01:43:32.531889Z","bundle_sha256":"0ab1a2ed8407275d2cb72229b8d172bfac6435e550c45faabb69170d28e35413"}}