{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:YUKFFHHRB7BZHJ7G7YAROBBLVC","short_pith_number":"pith:YUKFFHHR","canonical_record":{"source":{"id":"2210.03802","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-07T20:13:50Z","cross_cats_sorted":[],"title_canon_sha256":"1917b4bdf9eaa847d2a98838535ecd0edc82844a009ce7412bcc27722b085d89","abstract_canon_sha256":"c71f700d174e8e5b4fca0761c1a90350432b10bf22240c0de982ae42ac30a7d6"},"schema_version":"1.0"},"canonical_sha256":"c514529cf10fc393a7e6fe0117042ba89e444fdb59b95abe72ce222dd896e28e","source":{"kind":"arxiv","id":"2210.03802","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.03802","created_at":"2026-07-05T05:47:46Z"},{"alias_kind":"arxiv_version","alias_value":"2210.03802v2","created_at":"2026-07-05T05:47:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.03802","created_at":"2026-07-05T05:47:46Z"},{"alias_kind":"pith_short_12","alias_value":"YUKFFHHRB7BZ","created_at":"2026-07-05T05:47:46Z"},{"alias_kind":"pith_short_16","alias_value":"YUKFFHHRB7BZHJ7G","created_at":"2026-07-05T05:47:46Z"},{"alias_kind":"pith_short_8","alias_value":"YUKFFHHR","created_at":"2026-07-05T05:47:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:YUKFFHHRB7BZHJ7G7YAROBBLVC","target":"record","payload":{"canonical_record":{"source":{"id":"2210.03802","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-07T20:13:50Z","cross_cats_sorted":[],"title_canon_sha256":"1917b4bdf9eaa847d2a98838535ecd0edc82844a009ce7412bcc27722b085d89","abstract_canon_sha256":"c71f700d174e8e5b4fca0761c1a90350432b10bf22240c0de982ae42ac30a7d6"},"schema_version":"1.0"},"canonical_sha256":"c514529cf10fc393a7e6fe0117042ba89e444fdb59b95abe72ce222dd896e28e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:47:46.187402Z","signature_b64":"41FPuG/E3aETid7zuKgKStsgLRrIPpLgdPNgeoBVpL0smtp1BtV08jb9wWp/GeH6pH6QKcW/94gNt4eDSx8RDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c514529cf10fc393a7e6fe0117042ba89e444fdb59b95abe72ce222dd896e28e","last_reissued_at":"2026-07-05T05:47:46.186876Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:47:46.186876Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.03802","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":"2026-07-05T05:47:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k5E32HEQbYAy4uDCA9g41dyk6VwHHGrbyp7C5tUDlOpvLIomQBmb+AvmzoF4GgWVZ1BduF0APNOedILwn30IBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T12:57:59.479310Z"},"content_sha256":"fc683198515dac73eb8eb19e76ecca6781a5fcd4402c3b85af1bb07b00da2a1b","schema_version":"1.0","event_id":"sha256:fc683198515dac73eb8eb19e76ecca6781a5fcd4402c3b85af1bb07b00da2a1b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:YUKFFHHRB7BZHJ7G7YAROBBLVC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Conservative Bayesian Model-Based Value Expansion for Offline Policy Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Baher Abdulhai, Hyunwoo Kim, Jihwan Jeong, Michael Gimelfarb, Scott Sanner, Xiaoyu Wang","submitted_at":"2022-10-07T20:13:50Z","abstract_excerpt":"Offline reinforcement learning (RL) addresses the problem of learning a performant policy from a fixed batch of data collected by following some behavior policy. Model-based approaches are particularly appealing in the offline setting since they can extract more learning signals from the logged dataset by learning a model of the environment. However, the performance of existing model-based approaches falls short of model-free counterparts, due to the compounding of estimation errors in the learned model. Driven by this observation, we argue that it is critical for a model-based method to under"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.03802","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/2210.03802/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":"2026-07-05T05:47:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lA5OE0pi09L1pzM/3cfb3mNFeGK/vuc3+sUVEG74klm4cUPDHuC9536aGW/wC3ciYz2DcIUmlLCgW08L/prmAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T12:57:59.479713Z"},"content_sha256":"295ba7deb36895d95eecc4ceaac75ca10ff33adbc61f6247846ba53375318232","schema_version":"1.0","event_id":"sha256:295ba7deb36895d95eecc4ceaac75ca10ff33adbc61f6247846ba53375318232"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YUKFFHHRB7BZHJ7G7YAROBBLVC/bundle.json","state_url":"https://pith.science/pith/YUKFFHHRB7BZHJ7G7YAROBBLVC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YUKFFHHRB7BZHJ7G7YAROBBLVC/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":"2026-07-05T12:57:59Z","links":{"resolver":"https://pith.science/pith/YUKFFHHRB7BZHJ7G7YAROBBLVC","bundle":"https://pith.science/pith/YUKFFHHRB7BZHJ7G7YAROBBLVC/bundle.json","state":"https://pith.science/pith/YUKFFHHRB7BZHJ7G7YAROBBLVC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YUKFFHHRB7BZHJ7G7YAROBBLVC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:YUKFFHHRB7BZHJ7G7YAROBBLVC","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":"c71f700d174e8e5b4fca0761c1a90350432b10bf22240c0de982ae42ac30a7d6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-07T20:13:50Z","title_canon_sha256":"1917b4bdf9eaa847d2a98838535ecd0edc82844a009ce7412bcc27722b085d89"},"schema_version":"1.0","source":{"id":"2210.03802","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.03802","created_at":"2026-07-05T05:47:46Z"},{"alias_kind":"arxiv_version","alias_value":"2210.03802v2","created_at":"2026-07-05T05:47:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.03802","created_at":"2026-07-05T05:47:46Z"},{"alias_kind":"pith_short_12","alias_value":"YUKFFHHRB7BZ","created_at":"2026-07-05T05:47:46Z"},{"alias_kind":"pith_short_16","alias_value":"YUKFFHHRB7BZHJ7G","created_at":"2026-07-05T05:47:46Z"},{"alias_kind":"pith_short_8","alias_value":"YUKFFHHR","created_at":"2026-07-05T05:47:46Z"}],"graph_snapshots":[{"event_id":"sha256:295ba7deb36895d95eecc4ceaac75ca10ff33adbc61f6247846ba53375318232","target":"graph","created_at":"2026-07-05T05:47:46Z","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/2210.03802/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning (RL) addresses the problem of learning a performant policy from a fixed batch of data collected by following some behavior policy. Model-based approaches are particularly appealing in the offline setting since they can extract more learning signals from the logged dataset by learning a model of the environment. However, the performance of existing model-based approaches falls short of model-free counterparts, due to the compounding of estimation errors in the learned model. Driven by this observation, we argue that it is critical for a model-based method to under","authors_text":"Baher Abdulhai, Hyunwoo Kim, Jihwan Jeong, Michael Gimelfarb, Scott Sanner, Xiaoyu Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-07T20:13:50Z","title":"Conservative Bayesian Model-Based Value Expansion for Offline Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.03802","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:fc683198515dac73eb8eb19e76ecca6781a5fcd4402c3b85af1bb07b00da2a1b","target":"record","created_at":"2026-07-05T05:47:46Z","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":"c71f700d174e8e5b4fca0761c1a90350432b10bf22240c0de982ae42ac30a7d6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-07T20:13:50Z","title_canon_sha256":"1917b4bdf9eaa847d2a98838535ecd0edc82844a009ce7412bcc27722b085d89"},"schema_version":"1.0","source":{"id":"2210.03802","kind":"arxiv","version":2}},"canonical_sha256":"c514529cf10fc393a7e6fe0117042ba89e444fdb59b95abe72ce222dd896e28e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c514529cf10fc393a7e6fe0117042ba89e444fdb59b95abe72ce222dd896e28e","first_computed_at":"2026-07-05T05:47:46.186876Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:47:46.186876Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"41FPuG/E3aETid7zuKgKStsgLRrIPpLgdPNgeoBVpL0smtp1BtV08jb9wWp/GeH6pH6QKcW/94gNt4eDSx8RDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:47:46.187402Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.03802","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fc683198515dac73eb8eb19e76ecca6781a5fcd4402c3b85af1bb07b00da2a1b","sha256:295ba7deb36895d95eecc4ceaac75ca10ff33adbc61f6247846ba53375318232"],"state_sha256":"06c40f0588df194b1fd6c7a07b6a7e96509f3a61f83e7cb54b427bd74c9d658d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FFbyRhKtW9Ok4moivYOVg7Tn9xILGnz5q0ChDniEb8/TAlAjN9xQ5Jc89noKHVGxRaNQUs+Upe8vidyGo9k4Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T12:57:59.481809Z","bundle_sha256":"c80ee2876b7a525779c793512c0637f6162dece9a64bea0d2981ec993d0d79b5"}}