{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:2WNJ33BKIQHZX4QSZH7LRPK3GX","short_pith_number":"pith:2WNJ33BK","canonical_record":{"source":{"id":"2302.02948","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-06T17:30:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"be7fa1af956b1e2aa90aea42acf62866861a1d59f34578a1c26fde23c27c8e9a","abstract_canon_sha256":"455565e0e8852fd2770db23f66ab4522c9b4742982c6a38db453d1d22a947783"},"schema_version":"1.0"},"canonical_sha256":"d59a9dec2a440f9bf212c9feb8bd5b35f3aa8939feb7cb4e083af1d0d04f9709","source":{"kind":"arxiv","id":"2302.02948","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.02948","created_at":"2026-07-05T06:15:45Z"},{"alias_kind":"arxiv_version","alias_value":"2302.02948v4","created_at":"2026-07-05T06:15:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.02948","created_at":"2026-07-05T06:15:45Z"},{"alias_kind":"pith_short_12","alias_value":"2WNJ33BKIQHZ","created_at":"2026-07-05T06:15:45Z"},{"alias_kind":"pith_short_16","alias_value":"2WNJ33BKIQHZX4QS","created_at":"2026-07-05T06:15:45Z"},{"alias_kind":"pith_short_8","alias_value":"2WNJ33BK","created_at":"2026-07-05T06:15:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:2WNJ33BKIQHZX4QSZH7LRPK3GX","target":"record","payload":{"canonical_record":{"source":{"id":"2302.02948","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-06T17:30:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"be7fa1af956b1e2aa90aea42acf62866861a1d59f34578a1c26fde23c27c8e9a","abstract_canon_sha256":"455565e0e8852fd2770db23f66ab4522c9b4742982c6a38db453d1d22a947783"},"schema_version":"1.0"},"canonical_sha256":"d59a9dec2a440f9bf212c9feb8bd5b35f3aa8939feb7cb4e083af1d0d04f9709","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:15:45.472210Z","signature_b64":"oaNi5fsTmIYxY4mWQ0PDQyQ+1K/tpoJWlI4J3czTrQRmFkw7KFj5bE+zWXJrCefH5K+9xzDeyMK5HzOuQLk8Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d59a9dec2a440f9bf212c9feb8bd5b35f3aa8939feb7cb4e083af1d0d04f9709","last_reissued_at":"2026-07-05T06:15:45.471723Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:15:45.471723Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.02948","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:15:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OBcxr/aEBLY8L5BaiSMf8x+DXXTw5hr83GZxrFrttBFhrxzmShvBHbsym8l1dc9xjtJMLMtjIpn/h4qKWvXQCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:51:21.937430Z"},"content_sha256":"f8b0d70868fc746e5c68bdd9ff5ced84fb8eea4c635ca7fa5f7aa69d1c96cf97","schema_version":"1.0","event_id":"sha256:f8b0d70868fc746e5c68bdd9ff5ced84fb8eea4c635ca7fa5f7aa69d1c96cf97"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:2WNJ33BKIQHZX4QSZH7LRPK3GX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient Online Reinforcement Learning with Offline Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ilya Kostrikov, Laura Smith, Philip J. Ball, Sergey Levine","submitted_at":"2023-02-06T17:30:22Z","abstract_excerpt":"Sample efficiency and exploration remain major challenges in online reinforcement learning (RL). A powerful approach that can be applied to address these issues is the inclusion of offline data, such as prior trajectories from a human expert or a sub-optimal exploration policy. Previous methods have relied on extensive modifications and additional complexity to ensure the effective use of this data. Instead, we ask: can we simply apply existing off-policy methods to leverage offline data when learning online? In this work, we demonstrate that the answer is yes; however, a set of minimal but im"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.02948","kind":"arxiv","version":4},"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/2302.02948/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":"2026-07-05T06:15:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u+yMjWewaGrs61HQfrP+lbclhzCrxRHVqQQcyzvsKSE2bOCjdcvpFX2e2HWFhEXrJCAFMwoVzOSd/K5CTArrBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:51:21.938238Z"},"content_sha256":"2276de8a0bad563c1850acf27020fda316ce5805b06bfd829c49a09e98fa50f2","schema_version":"1.0","event_id":"sha256:2276de8a0bad563c1850acf27020fda316ce5805b06bfd829c49a09e98fa50f2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2WNJ33BKIQHZX4QSZH7LRPK3GX/bundle.json","state_url":"https://pith.science/pith/2WNJ33BKIQHZX4QSZH7LRPK3GX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2WNJ33BKIQHZX4QSZH7LRPK3GX/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":"2026-08-08T11:51:21Z","links":{"resolver":"https://pith.science/pith/2WNJ33BKIQHZX4QSZH7LRPK3GX","bundle":"https://pith.science/pith/2WNJ33BKIQHZX4QSZH7LRPK3GX/bundle.json","state":"https://pith.science/pith/2WNJ33BKIQHZX4QSZH7LRPK3GX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2WNJ33BKIQHZX4QSZH7LRPK3GX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:2WNJ33BKIQHZX4QSZH7LRPK3GX","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":"455565e0e8852fd2770db23f66ab4522c9b4742982c6a38db453d1d22a947783","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-06T17:30:22Z","title_canon_sha256":"be7fa1af956b1e2aa90aea42acf62866861a1d59f34578a1c26fde23c27c8e9a"},"schema_version":"1.0","source":{"id":"2302.02948","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.02948","created_at":"2026-07-05T06:15:45Z"},{"alias_kind":"arxiv_version","alias_value":"2302.02948v4","created_at":"2026-07-05T06:15:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.02948","created_at":"2026-07-05T06:15:45Z"},{"alias_kind":"pith_short_12","alias_value":"2WNJ33BKIQHZ","created_at":"2026-07-05T06:15:45Z"},{"alias_kind":"pith_short_16","alias_value":"2WNJ33BKIQHZX4QS","created_at":"2026-07-05T06:15:45Z"},{"alias_kind":"pith_short_8","alias_value":"2WNJ33BK","created_at":"2026-07-05T06:15:45Z"}],"graph_snapshots":[{"event_id":"sha256:2276de8a0bad563c1850acf27020fda316ce5805b06bfd829c49a09e98fa50f2","target":"graph","created_at":"2026-07-05T06:15:45Z","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/2302.02948/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sample efficiency and exploration remain major challenges in online reinforcement learning (RL). A powerful approach that can be applied to address these issues is the inclusion of offline data, such as prior trajectories from a human expert or a sub-optimal exploration policy. Previous methods have relied on extensive modifications and additional complexity to ensure the effective use of this data. Instead, we ask: can we simply apply existing off-policy methods to leverage offline data when learning online? In this work, we demonstrate that the answer is yes; however, a set of minimal but im","authors_text":"Ilya Kostrikov, Laura Smith, Philip J. Ball, Sergey Levine","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-06T17:30:22Z","title":"Efficient Online Reinforcement Learning with Offline Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.02948","kind":"arxiv","version":4},"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:f8b0d70868fc746e5c68bdd9ff5ced84fb8eea4c635ca7fa5f7aa69d1c96cf97","target":"record","created_at":"2026-07-05T06:15:45Z","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":"455565e0e8852fd2770db23f66ab4522c9b4742982c6a38db453d1d22a947783","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-06T17:30:22Z","title_canon_sha256":"be7fa1af956b1e2aa90aea42acf62866861a1d59f34578a1c26fde23c27c8e9a"},"schema_version":"1.0","source":{"id":"2302.02948","kind":"arxiv","version":4}},"canonical_sha256":"d59a9dec2a440f9bf212c9feb8bd5b35f3aa8939feb7cb4e083af1d0d04f9709","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d59a9dec2a440f9bf212c9feb8bd5b35f3aa8939feb7cb4e083af1d0d04f9709","first_computed_at":"2026-07-05T06:15:45.471723Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:15:45.471723Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oaNi5fsTmIYxY4mWQ0PDQyQ+1K/tpoJWlI4J3czTrQRmFkw7KFj5bE+zWXJrCefH5K+9xzDeyMK5HzOuQLk8Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:15:45.472210Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.02948","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f8b0d70868fc746e5c68bdd9ff5ced84fb8eea4c635ca7fa5f7aa69d1c96cf97","sha256:2276de8a0bad563c1850acf27020fda316ce5805b06bfd829c49a09e98fa50f2"],"state_sha256":"2a8300b49b7842c287ec7413417d0fe6f7e37ff6b3e710c4e3006eb45f6327fc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"05s4TzlhCpNx8AVQtgZHR0J2pHghkt6eJioDFw4Qnn/VWvbUAMh7DVhVQcJmQSBl+lsviCrQXEgzv86zzGgSAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T11:51:21.943861Z","bundle_sha256":"c007615756aec160aefdbd4adfea5a6a2dd00bb7673304e50052095658557deb"}}