{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:JVAZJBHP6753E77JSHGHOKFAYF","short_pith_number":"pith:JVAZJBHP","canonical_record":{"source":{"id":"2205.13703","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-27T01:30:12Z","cross_cats_sorted":[],"title_canon_sha256":"0e43ae6b9829ef04b7f60f7f4ffddbf157953f8ad88bc10729377d604d3569ee","abstract_canon_sha256":"470bf9102c641821d3557b1a8e424607896439e912e3b00d03fae487760a2f8c"},"schema_version":"1.0"},"canonical_sha256":"4d419484eff7fbb27fe991cc7728a0c15879492f4f0e6ecbf08cacd3fb15070d","source":{"kind":"arxiv","id":"2205.13703","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.13703","created_at":"2026-07-05T04:26:51Z"},{"alias_kind":"arxiv_version","alias_value":"2205.13703v1","created_at":"2026-07-05T04:26:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.13703","created_at":"2026-07-05T04:26:51Z"},{"alias_kind":"pith_short_12","alias_value":"JVAZJBHP6753","created_at":"2026-07-05T04:26:51Z"},{"alias_kind":"pith_short_16","alias_value":"JVAZJBHP6753E77J","created_at":"2026-07-05T04:26:51Z"},{"alias_kind":"pith_short_8","alias_value":"JVAZJBHP","created_at":"2026-07-05T04:26:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:JVAZJBHP6753E77JSHGHOKFAYF","target":"record","payload":{"canonical_record":{"source":{"id":"2205.13703","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-27T01:30:12Z","cross_cats_sorted":[],"title_canon_sha256":"0e43ae6b9829ef04b7f60f7f4ffddbf157953f8ad88bc10729377d604d3569ee","abstract_canon_sha256":"470bf9102c641821d3557b1a8e424607896439e912e3b00d03fae487760a2f8c"},"schema_version":"1.0"},"canonical_sha256":"4d419484eff7fbb27fe991cc7728a0c15879492f4f0e6ecbf08cacd3fb15070d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:26:51.164784Z","signature_b64":"pMdMVCz6vs00nPmqAhLjWAtkwQxNm9tA3vahA6/I3O0ya3soD7F9PPLIurcjHfGH7+rsW0VpL5cmkpdBLnyyDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d419484eff7fbb27fe991cc7728a0c15879492f4f0e6ecbf08cacd3fb15070d","last_reissued_at":"2026-07-05T04:26:51.164355Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:26:51.164355Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.13703","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:26:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8KbYFyPgUunRx5baMjw9haVimEprjJkyesD+ociNfuovk7BxjJWga6Xntp4PQ63Hi7Zq1g7XeVA4qKvRpXOjDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T03:03:33.736089Z"},"content_sha256":"67fe6c1a6c04e1db438ff8f7a34d6ef7159f3e6064e292c828e74b2dce645667","schema_version":"1.0","event_id":"sha256:67fe6c1a6c04e1db438ff8f7a34d6ef7159f3e6064e292c828e74b2dce645667"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:JVAZJBHP6753E77JSHGHOKFAYF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Why So Pessimistic? Estimating Uncertainties for Offline RL through Ensembles, and Why Their Independence Matters","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ofir Nachum, Seyed Kamyar Seyed Ghasemipour, Shixiang Shane Gu","submitted_at":"2022-05-27T01:30:12Z","abstract_excerpt":"Motivated by the success of ensembles for uncertainty estimation in supervised learning, we take a renewed look at how ensembles of $Q$-functions can be leveraged as the primary source of pessimism for offline reinforcement learning (RL). We begin by identifying a critical flaw in a popular algorithmic choice used by many ensemble-based RL algorithms, namely the use of shared pessimistic target values when computing each ensemble member's Bellman error. Through theoretical analyses and construction of examples in toy MDPs, we demonstrate that shared pessimistic targets can paradoxically lead t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.13703","kind":"arxiv","version":1},"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/2205.13703/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":"2026-07-05T04:26:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"04oBmCMwWPOmtU+OhMTfYYs0ehFeQprbLW+8JRTmeGloNL94jiVGboWqI6zSOZIz2j/4CEp/itFvjd0AWxSwBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T03:03:33.736875Z"},"content_sha256":"2e3a7e86315bd4c025e0492434a31eaa40f7f0b3943c16369aaac9d4d7b040ff","schema_version":"1.0","event_id":"sha256:2e3a7e86315bd4c025e0492434a31eaa40f7f0b3943c16369aaac9d4d7b040ff"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JVAZJBHP6753E77JSHGHOKFAYF/bundle.json","state_url":"https://pith.science/pith/JVAZJBHP6753E77JSHGHOKFAYF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JVAZJBHP6753E77JSHGHOKFAYF/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":"2026-08-06T03:03:33Z","links":{"resolver":"https://pith.science/pith/JVAZJBHP6753E77JSHGHOKFAYF","bundle":"https://pith.science/pith/JVAZJBHP6753E77JSHGHOKFAYF/bundle.json","state":"https://pith.science/pith/JVAZJBHP6753E77JSHGHOKFAYF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JVAZJBHP6753E77JSHGHOKFAYF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:JVAZJBHP6753E77JSHGHOKFAYF","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":"470bf9102c641821d3557b1a8e424607896439e912e3b00d03fae487760a2f8c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-27T01:30:12Z","title_canon_sha256":"0e43ae6b9829ef04b7f60f7f4ffddbf157953f8ad88bc10729377d604d3569ee"},"schema_version":"1.0","source":{"id":"2205.13703","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.13703","created_at":"2026-07-05T04:26:51Z"},{"alias_kind":"arxiv_version","alias_value":"2205.13703v1","created_at":"2026-07-05T04:26:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.13703","created_at":"2026-07-05T04:26:51Z"},{"alias_kind":"pith_short_12","alias_value":"JVAZJBHP6753","created_at":"2026-07-05T04:26:51Z"},{"alias_kind":"pith_short_16","alias_value":"JVAZJBHP6753E77J","created_at":"2026-07-05T04:26:51Z"},{"alias_kind":"pith_short_8","alias_value":"JVAZJBHP","created_at":"2026-07-05T04:26:51Z"}],"graph_snapshots":[{"event_id":"sha256:2e3a7e86315bd4c025e0492434a31eaa40f7f0b3943c16369aaac9d4d7b040ff","target":"graph","created_at":"2026-07-05T04:26:51Z","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/2205.13703/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Motivated by the success of ensembles for uncertainty estimation in supervised learning, we take a renewed look at how ensembles of $Q$-functions can be leveraged as the primary source of pessimism for offline reinforcement learning (RL). We begin by identifying a critical flaw in a popular algorithmic choice used by many ensemble-based RL algorithms, namely the use of shared pessimistic target values when computing each ensemble member's Bellman error. Through theoretical analyses and construction of examples in toy MDPs, we demonstrate that shared pessimistic targets can paradoxically lead t","authors_text":"Ofir Nachum, Seyed Kamyar Seyed Ghasemipour, Shixiang Shane Gu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-27T01:30:12Z","title":"Why So Pessimistic? Estimating Uncertainties for Offline RL through Ensembles, and Why Their Independence Matters"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.13703","kind":"arxiv","version":1},"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":"sha256:67fe6c1a6c04e1db438ff8f7a34d6ef7159f3e6064e292c828e74b2dce645667","target":"record","created_at":"2026-07-05T04:26:51Z","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":"470bf9102c641821d3557b1a8e424607896439e912e3b00d03fae487760a2f8c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-27T01:30:12Z","title_canon_sha256":"0e43ae6b9829ef04b7f60f7f4ffddbf157953f8ad88bc10729377d604d3569ee"},"schema_version":"1.0","source":{"id":"2205.13703","kind":"arxiv","version":1}},"canonical_sha256":"4d419484eff7fbb27fe991cc7728a0c15879492f4f0e6ecbf08cacd3fb15070d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4d419484eff7fbb27fe991cc7728a0c15879492f4f0e6ecbf08cacd3fb15070d","first_computed_at":"2026-07-05T04:26:51.164355Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:26:51.164355Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pMdMVCz6vs00nPmqAhLjWAtkwQxNm9tA3vahA6/I3O0ya3soD7F9PPLIurcjHfGH7+rsW0VpL5cmkpdBLnyyDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:26:51.164784Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.13703","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:67fe6c1a6c04e1db438ff8f7a34d6ef7159f3e6064e292c828e74b2dce645667","sha256:2e3a7e86315bd4c025e0492434a31eaa40f7f0b3943c16369aaac9d4d7b040ff"],"state_sha256":"87d951c3c1e19d7b3369eacadaf576101b924e8333ae68e0b61faf06506336b3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TAFfWWPo6pm/xPcZ6MiPiVJgysK1LM2hq4eaf7G9A17+CLQUCkXZ0jNWlKnUhQKB3FxfEFN1DOzKMjLU3eL6Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T03:03:33.742488Z","bundle_sha256":"f43904130a308c47a4b938675fe1acd14c2f8ce31dec36c798eb6621e90391cd"}}