{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:MJVMJREVM3O4CDAP22UFVAIONX","short_pith_number":"pith:MJVMJREV","canonical_record":{"source":{"id":"2211.04974","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-09T15:39:32Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"40811b7ca27f01e82ab0cbedbe3fbbc8035f0147db2723deae9b8ebf12a97555","abstract_canon_sha256":"8ad6a23866195d469702f654c0c77972cabadc7e103a1c81b515a55100712bbf"},"schema_version":"1.0"},"canonical_sha256":"626ac4c49566ddc10c0fd6a85a810e6deacde15d0dd800792b7f3abd92d24316","source":{"kind":"arxiv","id":"2211.04974","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.04974","created_at":"2026-07-05T06:33:03Z"},{"alias_kind":"arxiv_version","alias_value":"2211.04974v2","created_at":"2026-07-05T06:33:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.04974","created_at":"2026-07-05T06:33:03Z"},{"alias_kind":"pith_short_12","alias_value":"MJVMJREVM3O4","created_at":"2026-07-05T06:33:03Z"},{"alias_kind":"pith_short_16","alias_value":"MJVMJREVM3O4CDAP","created_at":"2026-07-05T06:33:03Z"},{"alias_kind":"pith_short_8","alias_value":"MJVMJREV","created_at":"2026-07-05T06:33:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:MJVMJREVM3O4CDAP22UFVAIONX","target":"record","payload":{"canonical_record":{"source":{"id":"2211.04974","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-09T15:39:32Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"40811b7ca27f01e82ab0cbedbe3fbbc8035f0147db2723deae9b8ebf12a97555","abstract_canon_sha256":"8ad6a23866195d469702f654c0c77972cabadc7e103a1c81b515a55100712bbf"},"schema_version":"1.0"},"canonical_sha256":"626ac4c49566ddc10c0fd6a85a810e6deacde15d0dd800792b7f3abd92d24316","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:33:03.181370Z","signature_b64":"uEIGAXMUq6AplBwUiU+yntPCRQxNw9htzwqIn/Lu88ShtayI2dbETTHIOpTflmvjLVYbM9OxCQeeRbQ1BduHBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"626ac4c49566ddc10c0fd6a85a810e6deacde15d0dd800792b7f3abd92d24316","last_reissued_at":"2026-07-05T06:33:03.180881Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:33:03.180881Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2211.04974","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:33:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qxiE9/8mKPLP7Xw8dwPv1TbBg6S/KvfZ7PiP4j/BqmsgWTsc0i8o31zQRZeg0WOfoN+vqPTCC6VNfNseFN8lAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T07:42:57.705500Z"},"content_sha256":"14ce095375a57bee04315dc19328b2b3ec2c12856c4ae8fe356813cf91799e36","schema_version":"1.0","event_id":"sha256:14ce095375a57bee04315dc19328b2b3ec2c12856c4ae8fe356813cf91799e36"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:MJVMJREVM3O4CDAP22UFVAIONX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Leveraging Offline Data in Online Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aldo Pacchiano, Andrew Wagenmaker","submitted_at":"2022-11-09T15:39:32Z","abstract_excerpt":"Two central paradigms have emerged in the reinforcement learning (RL) community: online RL and offline RL. In the online RL setting, the agent has no prior knowledge of the environment, and must interact with it in order to find an $\\epsilon$-optimal policy. In the offline RL setting, the learner instead has access to a fixed dataset to learn from, but is unable to otherwise interact with the environment, and must obtain the best policy it can from this offline data. Practical scenarios often motivate an intermediate setting: if we have some set of offline data and, in addition, may also inter"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.04974","kind":"arxiv","version":2},"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/2211.04974/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":"2026-07-05T06:33:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DRIuxNudDjQYxyw777kPxFGYX+Dc2/naDVRqrdsbKhVZKhJVKmUxfpKYRoxZpL/mfJssmdFer+HfQn/yKlFFBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T07:42:57.706504Z"},"content_sha256":"119ca1ce789da0dec635cafa4d842234e059997e77a5e1617d3e28079cb82391","schema_version":"1.0","event_id":"sha256:119ca1ce789da0dec635cafa4d842234e059997e77a5e1617d3e28079cb82391"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MJVMJREVM3O4CDAP22UFVAIONX/bundle.json","state_url":"https://pith.science/pith/MJVMJREVM3O4CDAP22UFVAIONX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MJVMJREVM3O4CDAP22UFVAIONX/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":"2026-08-08T07:42:57Z","links":{"resolver":"https://pith.science/pith/MJVMJREVM3O4CDAP22UFVAIONX","bundle":"https://pith.science/pith/MJVMJREVM3O4CDAP22UFVAIONX/bundle.json","state":"https://pith.science/pith/MJVMJREVM3O4CDAP22UFVAIONX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MJVMJREVM3O4CDAP22UFVAIONX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:MJVMJREVM3O4CDAP22UFVAIONX","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":"8ad6a23866195d469702f654c0c77972cabadc7e103a1c81b515a55100712bbf","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-09T15:39:32Z","title_canon_sha256":"40811b7ca27f01e82ab0cbedbe3fbbc8035f0147db2723deae9b8ebf12a97555"},"schema_version":"1.0","source":{"id":"2211.04974","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.04974","created_at":"2026-07-05T06:33:03Z"},{"alias_kind":"arxiv_version","alias_value":"2211.04974v2","created_at":"2026-07-05T06:33:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.04974","created_at":"2026-07-05T06:33:03Z"},{"alias_kind":"pith_short_12","alias_value":"MJVMJREVM3O4","created_at":"2026-07-05T06:33:03Z"},{"alias_kind":"pith_short_16","alias_value":"MJVMJREVM3O4CDAP","created_at":"2026-07-05T06:33:03Z"},{"alias_kind":"pith_short_8","alias_value":"MJVMJREV","created_at":"2026-07-05T06:33:03Z"}],"graph_snapshots":[{"event_id":"sha256:119ca1ce789da0dec635cafa4d842234e059997e77a5e1617d3e28079cb82391","target":"graph","created_at":"2026-07-05T06:33:03Z","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/2211.04974/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Two central paradigms have emerged in the reinforcement learning (RL) community: online RL and offline RL. In the online RL setting, the agent has no prior knowledge of the environment, and must interact with it in order to find an $\\epsilon$-optimal policy. In the offline RL setting, the learner instead has access to a fixed dataset to learn from, but is unable to otherwise interact with the environment, and must obtain the best policy it can from this offline data. Practical scenarios often motivate an intermediate setting: if we have some set of offline data and, in addition, may also inter","authors_text":"Aldo Pacchiano, Andrew Wagenmaker","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-09T15:39:32Z","title":"Leveraging Offline Data in Online Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.04974","kind":"arxiv","version":2},"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":"sha256:14ce095375a57bee04315dc19328b2b3ec2c12856c4ae8fe356813cf91799e36","target":"record","created_at":"2026-07-05T06:33:03Z","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":"8ad6a23866195d469702f654c0c77972cabadc7e103a1c81b515a55100712bbf","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-09T15:39:32Z","title_canon_sha256":"40811b7ca27f01e82ab0cbedbe3fbbc8035f0147db2723deae9b8ebf12a97555"},"schema_version":"1.0","source":{"id":"2211.04974","kind":"arxiv","version":2}},"canonical_sha256":"626ac4c49566ddc10c0fd6a85a810e6deacde15d0dd800792b7f3abd92d24316","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"626ac4c49566ddc10c0fd6a85a810e6deacde15d0dd800792b7f3abd92d24316","first_computed_at":"2026-07-05T06:33:03.180881Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:33:03.180881Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uEIGAXMUq6AplBwUiU+yntPCRQxNw9htzwqIn/Lu88ShtayI2dbETTHIOpTflmvjLVYbM9OxCQeeRbQ1BduHBg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:33:03.181370Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.04974","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:14ce095375a57bee04315dc19328b2b3ec2c12856c4ae8fe356813cf91799e36","sha256:119ca1ce789da0dec635cafa4d842234e059997e77a5e1617d3e28079cb82391"],"state_sha256":"7dcccf711d4e376dcd25e2deb4cf93720a1e2e5475a07b5c319e5a5c9108dd43"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UrfOChDku6oypZvG47z2nz/eHutcS65jQC0+xwA9jMqJb89AP5Xq285IZLYivp2c4LwAshEgWx14DBjx3TuPDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T07:42:57.713135Z","bundle_sha256":"008bce33ef755663da09542837ed02adaa9c9419ae2825ddb964fd0900b608fd"}}