{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:63LAKJEWVBW6DLENT5FTTD4LOL","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":"c0e79116d0cbde1ce7119e9cd9cce6daecd1c25053f9adf5632e009f0e0fad6e","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-09-15T00:18:34Z","title_canon_sha256":"52bc7fde7973c70e30caa01e39be9a4a43018c516f093000e59b884f13423536"},"schema_version":"1.0","source":{"id":"2009.06799","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.06799","created_at":"2026-07-05T01:55:13Z"},{"alias_kind":"arxiv_version","alias_value":"2009.06799v3","created_at":"2026-07-05T01:55:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.06799","created_at":"2026-07-05T01:55:13Z"},{"alias_kind":"pith_short_12","alias_value":"63LAKJEWVBW6","created_at":"2026-07-05T01:55:13Z"},{"alias_kind":"pith_short_16","alias_value":"63LAKJEWVBW6DLEN","created_at":"2026-07-05T01:55:13Z"},{"alias_kind":"pith_short_8","alias_value":"63LAKJEW","created_at":"2026-07-05T01:55:13Z"}],"graph_snapshots":[{"event_id":"sha256:a3ebdccb6ba29e7e44cbfa17835f006be27ff454e25152ff8017d1dcb51d9f84","target":"graph","created_at":"2026-07-05T01:55:13Z","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/2009.06799/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study worst-case guarantees on the expected return of fixed-dataset policy optimization algorithms. Our core contribution is a unified conceptual and mathematical framework for the study of algorithms in this regime. This analysis reveals that for naive approaches, the possibility of erroneous value overestimation leads to a difficult-to-satisfy requirement: in order to guarantee that we select a policy which is near-optimal, we may need the dataset to be informative of the value of every policy. To avoid this, algorithms can follow the pessimism principle, which states that we should choos","authors_text":"Carles Gelada, Jacob Buckman, Marc G. Bellemare","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-09-15T00:18:34Z","title":"The Importance of Pessimism in Fixed-Dataset Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.06799","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:e08b78f22f13c3dfa44f5f9c593ef82ceb0ae363a762881969b584cb1fa6bd69","target":"record","created_at":"2026-07-05T01:55:13Z","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":"c0e79116d0cbde1ce7119e9cd9cce6daecd1c25053f9adf5632e009f0e0fad6e","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-09-15T00:18:34Z","title_canon_sha256":"52bc7fde7973c70e30caa01e39be9a4a43018c516f093000e59b884f13423536"},"schema_version":"1.0","source":{"id":"2009.06799","kind":"arxiv","version":3}},"canonical_sha256":"f6d6052496a86de1ac8d9f4b398f8b72fd4001f1c47f5657d8d04ad6c6e99829","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f6d6052496a86de1ac8d9f4b398f8b72fd4001f1c47f5657d8d04ad6c6e99829","first_computed_at":"2026-07-05T01:55:13.080742Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:55:13.080742Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MkXCSY4S9P5zWz0VT2YnBGu3E4+Ef5HEUW0E/fTDENwnBD7Qs8wzQ9wllWFFRozzhU+Zl49Zlpg0plKsCuDlDA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:55:13.081086Z","signed_message":"canonical_sha256_bytes"},"source_id":"2009.06799","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e08b78f22f13c3dfa44f5f9c593ef82ceb0ae363a762881969b584cb1fa6bd69","sha256:a3ebdccb6ba29e7e44cbfa17835f006be27ff454e25152ff8017d1dcb51d9f84"],"state_sha256":"6828eb5bbf48c590973c4efc9ad78b3829d5181bfd9e2aeff5cc7865b14427e1"}