{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:NYNTOGTEI6ZW2WO43VGU4ZDGDG","short_pith_number":"pith:NYNTOGTE","canonical_record":{"source":{"id":"2206.02829","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-06T18:07:41Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"9ca5f7d171ca5ca6c3f19239c886a3255cf0043cf1e18efb92f4cb32489b71fb","abstract_canon_sha256":"56ca5306d36f4199dd3e2b16b0f7bc776129794a8e6e96c93c7be4e15c5a481e"},"schema_version":"1.0"},"canonical_sha256":"6e1b371a6447b36d59dcdd4d4e646619b38662122689c8844fdccf72b0b34094","source":{"kind":"arxiv","id":"2206.02829","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.02829","created_at":"2026-07-05T05:09:19Z"},{"alias_kind":"arxiv_version","alias_value":"2206.02829v3","created_at":"2026-07-05T05:09:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.02829","created_at":"2026-07-05T05:09:19Z"},{"alias_kind":"pith_short_12","alias_value":"NYNTOGTEI6ZW","created_at":"2026-07-05T05:09:19Z"},{"alias_kind":"pith_short_16","alias_value":"NYNTOGTEI6ZW2WO4","created_at":"2026-07-05T05:09:19Z"},{"alias_kind":"pith_short_8","alias_value":"NYNTOGTE","created_at":"2026-07-05T05:09:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:NYNTOGTEI6ZW2WO43VGU4ZDGDG","target":"record","payload":{"canonical_record":{"source":{"id":"2206.02829","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-06T18:07:41Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"9ca5f7d171ca5ca6c3f19239c886a3255cf0043cf1e18efb92f4cb32489b71fb","abstract_canon_sha256":"56ca5306d36f4199dd3e2b16b0f7bc776129794a8e6e96c93c7be4e15c5a481e"},"schema_version":"1.0"},"canonical_sha256":"6e1b371a6447b36d59dcdd4d4e646619b38662122689c8844fdccf72b0b34094","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:09:19.112636Z","signature_b64":"7oOoS6d7323ObFT/4Da/zoetMohIcceFg6NfV/dhUI88m5KMLHqxSSOY69HiBX09pzJNYlGaIMIDyj+kzyr8DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e1b371a6447b36d59dcdd4d4e646619b38662122689c8844fdccf72b0b34094","last_reissued_at":"2026-07-05T05:09:19.112204Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:09:19.112204Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2206.02829","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":"2026-07-05T05:09:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MyL3VBUQyS1V+xvwgPu2L7lMVEIOfQsbdp1L0QEb3/Adq5jGPnjPfwCLUZHGbVMVvU9p05qFpZD2OQ8paldyAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T21:26:04.162652Z"},"content_sha256":"58ae13f398fdaaf1bafb0d8b97d69f32fbfe21deb0460a9524a5a82f65c9a9ec","schema_version":"1.0","event_id":"sha256:58ae13f398fdaaf1bafb0d8b97d69f32fbfe21deb0460a9524a5a82f65c9a9ec"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:NYNTOGTEI6ZW2WO43VGU4ZDGDG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RORL: Robust Offline Reinforcement Learning via Conservative Smoothing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chenjia Bai, Chongjie Zhang, Lei Han, Rui Yang, Xiaoteng Ma, Zhaoran Wang","submitted_at":"2022-06-06T18:07:41Z","abstract_excerpt":"Offline reinforcement learning (RL) provides a promising direction to exploit massive amount of offline data for complex decision-making tasks. Due to the distribution shift issue, current offline RL algorithms are generally designed to be conservative in value estimation and action selection. However, such conservatism can impair the robustness of learned policies when encountering observation deviation under realistic conditions, such as sensor errors and adversarial attacks. To trade off robustness and conservatism, we propose Robust Offline Reinforcement Learning (RORL) with a novel conser"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.02829","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/2206.02829/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":"2026-07-05T05:09:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lCphu3j9jjKWII7CjmEMoF/ypXq0f3rJrWnO0R6k67E8CZ1XcfIqDN5HeJbu2d1aUSOlpj6scdw9JsKq11fRCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T21:26:04.163173Z"},"content_sha256":"b78b114ca5d16876de570054ad392c20d7d79635e36566463aab03449d513e0c","schema_version":"1.0","event_id":"sha256:b78b114ca5d16876de570054ad392c20d7d79635e36566463aab03449d513e0c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NYNTOGTEI6ZW2WO43VGU4ZDGDG/bundle.json","state_url":"https://pith.science/pith/NYNTOGTEI6ZW2WO43VGU4ZDGDG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NYNTOGTEI6ZW2WO43VGU4ZDGDG/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":"2026-08-12T21:26:04Z","links":{"resolver":"https://pith.science/pith/NYNTOGTEI6ZW2WO43VGU4ZDGDG","bundle":"https://pith.science/pith/NYNTOGTEI6ZW2WO43VGU4ZDGDG/bundle.json","state":"https://pith.science/pith/NYNTOGTEI6ZW2WO43VGU4ZDGDG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NYNTOGTEI6ZW2WO43VGU4ZDGDG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:NYNTOGTEI6ZW2WO43VGU4ZDGDG","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":"56ca5306d36f4199dd3e2b16b0f7bc776129794a8e6e96c93c7be4e15c5a481e","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-06T18:07:41Z","title_canon_sha256":"9ca5f7d171ca5ca6c3f19239c886a3255cf0043cf1e18efb92f4cb32489b71fb"},"schema_version":"1.0","source":{"id":"2206.02829","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.02829","created_at":"2026-07-05T05:09:19Z"},{"alias_kind":"arxiv_version","alias_value":"2206.02829v3","created_at":"2026-07-05T05:09:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.02829","created_at":"2026-07-05T05:09:19Z"},{"alias_kind":"pith_short_12","alias_value":"NYNTOGTEI6ZW","created_at":"2026-07-05T05:09:19Z"},{"alias_kind":"pith_short_16","alias_value":"NYNTOGTEI6ZW2WO4","created_at":"2026-07-05T05:09:19Z"},{"alias_kind":"pith_short_8","alias_value":"NYNTOGTE","created_at":"2026-07-05T05:09:19Z"}],"graph_snapshots":[{"event_id":"sha256:b78b114ca5d16876de570054ad392c20d7d79635e36566463aab03449d513e0c","target":"graph","created_at":"2026-07-05T05:09:19Z","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/2206.02829/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning (RL) provides a promising direction to exploit massive amount of offline data for complex decision-making tasks. Due to the distribution shift issue, current offline RL algorithms are generally designed to be conservative in value estimation and action selection. However, such conservatism can impair the robustness of learned policies when encountering observation deviation under realistic conditions, such as sensor errors and adversarial attacks. To trade off robustness and conservatism, we propose Robust Offline Reinforcement Learning (RORL) with a novel conser","authors_text":"Chenjia Bai, Chongjie Zhang, Lei Han, Rui Yang, Xiaoteng Ma, Zhaoran Wang","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-06T18:07:41Z","title":"RORL: Robust Offline Reinforcement Learning via Conservative Smoothing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.02829","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":"sha256:58ae13f398fdaaf1bafb0d8b97d69f32fbfe21deb0460a9524a5a82f65c9a9ec","target":"record","created_at":"2026-07-05T05:09:19Z","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":"56ca5306d36f4199dd3e2b16b0f7bc776129794a8e6e96c93c7be4e15c5a481e","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-06T18:07:41Z","title_canon_sha256":"9ca5f7d171ca5ca6c3f19239c886a3255cf0043cf1e18efb92f4cb32489b71fb"},"schema_version":"1.0","source":{"id":"2206.02829","kind":"arxiv","version":3}},"canonical_sha256":"6e1b371a6447b36d59dcdd4d4e646619b38662122689c8844fdccf72b0b34094","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6e1b371a6447b36d59dcdd4d4e646619b38662122689c8844fdccf72b0b34094","first_computed_at":"2026-07-05T05:09:19.112204Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:09:19.112204Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7oOoS6d7323ObFT/4Da/zoetMohIcceFg6NfV/dhUI88m5KMLHqxSSOY69HiBX09pzJNYlGaIMIDyj+kzyr8DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:09:19.112636Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.02829","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:58ae13f398fdaaf1bafb0d8b97d69f32fbfe21deb0460a9524a5a82f65c9a9ec","sha256:b78b114ca5d16876de570054ad392c20d7d79635e36566463aab03449d513e0c"],"state_sha256":"f850e063c8b214ab87a3a08e4f95a2257247a8469a60bbb293cea4df5397c436"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"23r2l073mCT/bBRoIeYcv+zmcqvgQnjCk/LIVc+PTxuy7HC6C/Rt7kcGHBRbRp9TJl4O/YBPpsg+py57gP6+Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T21:26:04.167356Z","bundle_sha256":"75b8716ec2238ea54a0f656fa3a68737b94ad5859d1022493a8a42c5e8a9727e"}}