{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:44SAH5HHEGQZBGZ6GCKTIXEMOY","short_pith_number":"pith:44SAH5HH","canonical_record":{"source":{"id":"2110.00188","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-01T03:13:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a427e23815826e67a610f359fb6615b668bbef9cb1f94c13f2a9645c2da3fa56","abstract_canon_sha256":"c5ba54c6d555b9e86a865500fb770345ca53bf4545d49a668b5347de5734b541"},"schema_version":"1.0"},"canonical_sha256":"e72403f4e721a1909b3e3095345c8c761edc00972376eac154a3d2daef211276","source":{"kind":"arxiv","id":"2110.00188","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.00188","created_at":"2026-07-05T03:31:30Z"},{"alias_kind":"arxiv_version","alias_value":"2110.00188v2","created_at":"2026-07-05T03:31:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.00188","created_at":"2026-07-05T03:31:30Z"},{"alias_kind":"pith_short_12","alias_value":"44SAH5HHEGQZ","created_at":"2026-07-05T03:31:30Z"},{"alias_kind":"pith_short_16","alias_value":"44SAH5HHEGQZBGZ6","created_at":"2026-07-05T03:31:30Z"},{"alias_kind":"pith_short_8","alias_value":"44SAH5HH","created_at":"2026-07-05T03:31:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:44SAH5HHEGQZBGZ6GCKTIXEMOY","target":"record","payload":{"canonical_record":{"source":{"id":"2110.00188","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-01T03:13:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a427e23815826e67a610f359fb6615b668bbef9cb1f94c13f2a9645c2da3fa56","abstract_canon_sha256":"c5ba54c6d555b9e86a865500fb770345ca53bf4545d49a668b5347de5734b541"},"schema_version":"1.0"},"canonical_sha256":"e72403f4e721a1909b3e3095345c8c761edc00972376eac154a3d2daef211276","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:31:30.924252Z","signature_b64":"Ho1HQhEzEf39ey+RU3d00Q56q/r0NW22UCLbI4gstdepZLPadA+S3y0uL1cnM4TI8/VUFC6791X30MAmPgZVBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e72403f4e721a1909b3e3095345c8c761edc00972376eac154a3d2daef211276","last_reissued_at":"2026-07-05T03:31:30.923774Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:31:30.923774Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.00188","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":"2026-07-05T03:31:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SoBpwqyI4NQ9a+zRtNvKgonU3+HOWK8d+HlFqxzh7ZvSCQ7fxFx//MzQCD3WAmYBjZi3F4QdoDOJJkr7OD4uBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:28:36.773529Z"},"content_sha256":"a5a39a5c2400782c60a9b561a9f8bcb1759a19bbf7af136649f315517a70aa63","schema_version":"1.0","event_id":"sha256:a5a39a5c2400782c60a9b561a9f8bcb1759a19bbf7af136649f315517a70aa63"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:44SAH5HHEGQZBGZ6GCKTIXEMOY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Offline Reinforcement Learning with Reverse Model-based Imagination","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chongjie Zhang, Guangxiang Zhu, Haozhe Jiang, Jianhao Wang, Siyuan Li, Wenzhe Li","submitted_at":"2021-10-01T03:13:22Z","abstract_excerpt":"In offline reinforcement learning (offline RL), one of the main challenges is to deal with the distributional shift between the learning policy and the given dataset. To address this problem, recent offline RL methods attempt to introduce conservatism bias to encourage learning in high-confidence areas. Model-free approaches directly encode such bias into policy or value function learning using conservative regularizations or special network structures, but their constrained policy search limits the generalization beyond the offline dataset. Model-based approaches learn forward dynamics models"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.00188","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/2110.00188/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":"2026-07-05T03:31:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h44Ofs4mmTGFhTqvnM2vrJOZdrajsVWgf1oYyU71j4ApVaXUeER6Wg1VDoMZenLySPxWg59LzSAgQ0JxpxZaCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:28:36.773903Z"},"content_sha256":"79dda8c3fbd8542c843f7203943221b0640898c450d615967dcfaa0ff4eb020c","schema_version":"1.0","event_id":"sha256:79dda8c3fbd8542c843f7203943221b0640898c450d615967dcfaa0ff4eb020c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/44SAH5HHEGQZBGZ6GCKTIXEMOY/bundle.json","state_url":"https://pith.science/pith/44SAH5HHEGQZBGZ6GCKTIXEMOY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/44SAH5HHEGQZBGZ6GCKTIXEMOY/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":"2026-07-06T23:28:36Z","links":{"resolver":"https://pith.science/pith/44SAH5HHEGQZBGZ6GCKTIXEMOY","bundle":"https://pith.science/pith/44SAH5HHEGQZBGZ6GCKTIXEMOY/bundle.json","state":"https://pith.science/pith/44SAH5HHEGQZBGZ6GCKTIXEMOY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/44SAH5HHEGQZBGZ6GCKTIXEMOY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:44SAH5HHEGQZBGZ6GCKTIXEMOY","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":"c5ba54c6d555b9e86a865500fb770345ca53bf4545d49a668b5347de5734b541","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-01T03:13:22Z","title_canon_sha256":"a427e23815826e67a610f359fb6615b668bbef9cb1f94c13f2a9645c2da3fa56"},"schema_version":"1.0","source":{"id":"2110.00188","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.00188","created_at":"2026-07-05T03:31:30Z"},{"alias_kind":"arxiv_version","alias_value":"2110.00188v2","created_at":"2026-07-05T03:31:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.00188","created_at":"2026-07-05T03:31:30Z"},{"alias_kind":"pith_short_12","alias_value":"44SAH5HHEGQZ","created_at":"2026-07-05T03:31:30Z"},{"alias_kind":"pith_short_16","alias_value":"44SAH5HHEGQZBGZ6","created_at":"2026-07-05T03:31:30Z"},{"alias_kind":"pith_short_8","alias_value":"44SAH5HH","created_at":"2026-07-05T03:31:30Z"}],"graph_snapshots":[{"event_id":"sha256:79dda8c3fbd8542c843f7203943221b0640898c450d615967dcfaa0ff4eb020c","target":"graph","created_at":"2026-07-05T03:31:30Z","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/2110.00188/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In offline reinforcement learning (offline RL), one of the main challenges is to deal with the distributional shift between the learning policy and the given dataset. To address this problem, recent offline RL methods attempt to introduce conservatism bias to encourage learning in high-confidence areas. Model-free approaches directly encode such bias into policy or value function learning using conservative regularizations or special network structures, but their constrained policy search limits the generalization beyond the offline dataset. Model-based approaches learn forward dynamics models","authors_text":"Chongjie Zhang, Guangxiang Zhu, Haozhe Jiang, Jianhao Wang, Siyuan Li, Wenzhe Li","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-01T03:13:22Z","title":"Offline Reinforcement Learning with Reverse Model-based Imagination"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.00188","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:a5a39a5c2400782c60a9b561a9f8bcb1759a19bbf7af136649f315517a70aa63","target":"record","created_at":"2026-07-05T03:31:30Z","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":"c5ba54c6d555b9e86a865500fb770345ca53bf4545d49a668b5347de5734b541","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-01T03:13:22Z","title_canon_sha256":"a427e23815826e67a610f359fb6615b668bbef9cb1f94c13f2a9645c2da3fa56"},"schema_version":"1.0","source":{"id":"2110.00188","kind":"arxiv","version":2}},"canonical_sha256":"e72403f4e721a1909b3e3095345c8c761edc00972376eac154a3d2daef211276","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e72403f4e721a1909b3e3095345c8c761edc00972376eac154a3d2daef211276","first_computed_at":"2026-07-05T03:31:30.923774Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:31:30.923774Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ho1HQhEzEf39ey+RU3d00Q56q/r0NW22UCLbI4gstdepZLPadA+S3y0uL1cnM4TI8/VUFC6791X30MAmPgZVBg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:31:30.924252Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.00188","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a5a39a5c2400782c60a9b561a9f8bcb1759a19bbf7af136649f315517a70aa63","sha256:79dda8c3fbd8542c843f7203943221b0640898c450d615967dcfaa0ff4eb020c"],"state_sha256":"7d117401ee12a47640c7e5c774713f0977ad5941b71dee141f0416620bf29df2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4zur0hsjpZMZ5VMuHhxRireOHBgvBtHOezMEytMscGOXM24rGo48u+nh/yPrWFDRekYJLXQbZYFPwMXdccPADw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T23:28:36.776288Z","bundle_sha256":"e1c7d6a8ddbb043409fcbe7aa52512db8c13484bc767babd78eb771a66ede460"}}