{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:ZLP7INGQ3BQIOS43WD6FNJW6YE","short_pith_number":"pith:ZLP7INGQ","canonical_record":{"source":{"id":"2206.05581","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2022-06-11T18:03:26Z","cross_cats_sorted":["cs.LG","stat.ME"],"title_canon_sha256":"94fa80dce743ed75a6964333e1ef91f7742d7e03c3a934bc8a840c2f65992dee","abstract_canon_sha256":"55dca9e18dfcbc080d82daf4ce3ec88d393c233aa270292837eb52d672099c36"},"schema_version":"1.0"},"canonical_sha256":"cadff434d0d860874b9bb0fc56a6dec13918c15963bc76f28badfa2d1767d705","source":{"kind":"arxiv","id":"2206.05581","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.05581","created_at":"2026-07-05T07:38:06Z"},{"alias_kind":"arxiv_version","alias_value":"2206.05581v3","created_at":"2026-07-05T07:38:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.05581","created_at":"2026-07-05T07:38:06Z"},{"alias_kind":"pith_short_12","alias_value":"ZLP7INGQ3BQI","created_at":"2026-07-05T07:38:06Z"},{"alias_kind":"pith_short_16","alias_value":"ZLP7INGQ3BQIOS43","created_at":"2026-07-05T07:38:06Z"},{"alias_kind":"pith_short_8","alias_value":"ZLP7INGQ","created_at":"2026-07-05T07:38:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:ZLP7INGQ3BQIOS43WD6FNJW6YE","target":"record","payload":{"canonical_record":{"source":{"id":"2206.05581","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2022-06-11T18:03:26Z","cross_cats_sorted":["cs.LG","stat.ME"],"title_canon_sha256":"94fa80dce743ed75a6964333e1ef91f7742d7e03c3a934bc8a840c2f65992dee","abstract_canon_sha256":"55dca9e18dfcbc080d82daf4ce3ec88d393c233aa270292837eb52d672099c36"},"schema_version":"1.0"},"canonical_sha256":"cadff434d0d860874b9bb0fc56a6dec13918c15963bc76f28badfa2d1767d705","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:38:06.807015Z","signature_b64":"OHQ2hsJTPosRd46LewgPLwpnULW1Q47Edt1+lCoCClfKjy6B5+yoOdJbSUgiG9MxoHWUpGbxY4mXqAdkwkWwBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cadff434d0d860874b9bb0fc56a6dec13918c15963bc76f28badfa2d1767d705","last_reissued_at":"2026-07-05T07:38:06.806563Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:38:06.806563Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2206.05581","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:38:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4edmUaTDRKNm0tH2QEIwHJt4f5aRO7gvq9LZ8gexNtVExivl6kgDLyKg5EKdJOaUPE95l1ZPgv/QC/bx13sECQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T10:33:43.195245Z"},"content_sha256":"8fc0950b1e5d0a957c7fd7e160089ac7431edf06fc5fb124d0bee6343ea13be9","schema_version":"1.0","event_id":"sha256:8fc0950b1e5d0a957c7fd7e160089ac7431edf06fc5fb124d0bee6343ea13be9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:ZLP7INGQ3BQIOS43WD6FNJW6YE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Federated Offline Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ME"],"primary_cat":"stat.ML","authors_text":"Aaron Sonabend-W, Doudou Zhou, Junwei Lu, Tianxi Cai, Yufeng Zhang, Zhaoran Wang","submitted_at":"2022-06-11T18:03:26Z","abstract_excerpt":"Evidence-based or data-driven dynamic treatment regimes are essential for personalized medicine, which can benefit from offline reinforcement learning (RL). Although massive healthcare data are available across medical institutions, they are prohibited from sharing due to privacy constraints. Besides, heterogeneity exists in different sites. As a result, federated offline RL algorithms are necessary and promising to deal with the problems. In this paper, we propose a multi-site Markov decision process model that allows for both homogeneous and heterogeneous effects across sites. The proposed m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.05581","kind":"arxiv","version":3},"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/2206.05581/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":"2026-07-05T07:38:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2KYttFkp80JAAibywYYMRbMvAyLOXGNOUIJIaQdAYOmzzXsGh9EvjV1xoKM6tyZkyuaUN3h4TinNbniDV1HCCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T10:33:43.195648Z"},"content_sha256":"772b5c7b67e8c282d017087699d6cb908de49b0eb1a925b1585df90148749209","schema_version":"1.0","event_id":"sha256:772b5c7b67e8c282d017087699d6cb908de49b0eb1a925b1585df90148749209"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZLP7INGQ3BQIOS43WD6FNJW6YE/bundle.json","state_url":"https://pith.science/pith/ZLP7INGQ3BQIOS43WD6FNJW6YE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZLP7INGQ3BQIOS43WD6FNJW6YE/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":"2026-08-07T10:33:43Z","links":{"resolver":"https://pith.science/pith/ZLP7INGQ3BQIOS43WD6FNJW6YE","bundle":"https://pith.science/pith/ZLP7INGQ3BQIOS43WD6FNJW6YE/bundle.json","state":"https://pith.science/pith/ZLP7INGQ3BQIOS43WD6FNJW6YE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZLP7INGQ3BQIOS43WD6FNJW6YE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:ZLP7INGQ3BQIOS43WD6FNJW6YE","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":"55dca9e18dfcbc080d82daf4ce3ec88d393c233aa270292837eb52d672099c36","cross_cats_sorted":["cs.LG","stat.ME"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2022-06-11T18:03:26Z","title_canon_sha256":"94fa80dce743ed75a6964333e1ef91f7742d7e03c3a934bc8a840c2f65992dee"},"schema_version":"1.0","source":{"id":"2206.05581","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.05581","created_at":"2026-07-05T07:38:06Z"},{"alias_kind":"arxiv_version","alias_value":"2206.05581v3","created_at":"2026-07-05T07:38:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.05581","created_at":"2026-07-05T07:38:06Z"},{"alias_kind":"pith_short_12","alias_value":"ZLP7INGQ3BQI","created_at":"2026-07-05T07:38:06Z"},{"alias_kind":"pith_short_16","alias_value":"ZLP7INGQ3BQIOS43","created_at":"2026-07-05T07:38:06Z"},{"alias_kind":"pith_short_8","alias_value":"ZLP7INGQ","created_at":"2026-07-05T07:38:06Z"}],"graph_snapshots":[{"event_id":"sha256:772b5c7b67e8c282d017087699d6cb908de49b0eb1a925b1585df90148749209","target":"graph","created_at":"2026-07-05T07:38:06Z","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/2206.05581/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Evidence-based or data-driven dynamic treatment regimes are essential for personalized medicine, which can benefit from offline reinforcement learning (RL). Although massive healthcare data are available across medical institutions, they are prohibited from sharing due to privacy constraints. Besides, heterogeneity exists in different sites. As a result, federated offline RL algorithms are necessary and promising to deal with the problems. In this paper, we propose a multi-site Markov decision process model that allows for both homogeneous and heterogeneous effects across sites. The proposed m","authors_text":"Aaron Sonabend-W, Doudou Zhou, Junwei Lu, Tianxi Cai, Yufeng Zhang, Zhaoran Wang","cross_cats":["cs.LG","stat.ME"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2022-06-11T18:03:26Z","title":"Federated Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.05581","kind":"arxiv","version":3},"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":"sha256:8fc0950b1e5d0a957c7fd7e160089ac7431edf06fc5fb124d0bee6343ea13be9","target":"record","created_at":"2026-07-05T07:38:06Z","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":"55dca9e18dfcbc080d82daf4ce3ec88d393c233aa270292837eb52d672099c36","cross_cats_sorted":["cs.LG","stat.ME"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2022-06-11T18:03:26Z","title_canon_sha256":"94fa80dce743ed75a6964333e1ef91f7742d7e03c3a934bc8a840c2f65992dee"},"schema_version":"1.0","source":{"id":"2206.05581","kind":"arxiv","version":3}},"canonical_sha256":"cadff434d0d860874b9bb0fc56a6dec13918c15963bc76f28badfa2d1767d705","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cadff434d0d860874b9bb0fc56a6dec13918c15963bc76f28badfa2d1767d705","first_computed_at":"2026-07-05T07:38:06.806563Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:38:06.806563Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OHQ2hsJTPosRd46LewgPLwpnULW1Q47Edt1+lCoCClfKjy6B5+yoOdJbSUgiG9MxoHWUpGbxY4mXqAdkwkWwBA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:38:06.807015Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.05581","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8fc0950b1e5d0a957c7fd7e160089ac7431edf06fc5fb124d0bee6343ea13be9","sha256:772b5c7b67e8c282d017087699d6cb908de49b0eb1a925b1585df90148749209"],"state_sha256":"ef22308321bba5bec47797a4cfa870ce45f674cce0244843aa95d307a1eae96e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OG2Gnnnf68HDL2NDL7VJJqa9BAe51lO83bzPFQDuqUgAi/d90TEdgaHL6ew5EYx6nEXLlfetl2d6mRGxVcl+Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T10:33:43.198562Z","bundle_sha256":"2a42db530a65793036ac1bfbb4f0c6f63750c12d8e6fc578230909496dbcedcd"}}