{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:V45PAR7M3NYVDLUQHOU3AELQSA","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":"2b841f347b4cdecf99b9c01b869b8dfc614499d17db45ea9ed4c05da406dfb8d","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-21T04:12:48Z","title_canon_sha256":"9b78b8cb7cf06fab5c5fdb6700673aa886bcdaf0e02ef459899642025709b937"},"schema_version":"1.0","source":{"id":"2207.10295","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.10295","created_at":"2026-07-05T04:42:23Z"},{"alias_kind":"arxiv_version","alias_value":"2207.10295v1","created_at":"2026-07-05T04:42:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.10295","created_at":"2026-07-05T04:42:23Z"},{"alias_kind":"pith_short_12","alias_value":"V45PAR7M3NYV","created_at":"2026-07-05T04:42:23Z"},{"alias_kind":"pith_short_16","alias_value":"V45PAR7M3NYVDLUQ","created_at":"2026-07-05T04:42:23Z"},{"alias_kind":"pith_short_8","alias_value":"V45PAR7M","created_at":"2026-07-05T04:42:23Z"}],"graph_snapshots":[{"event_id":"sha256:c1481f57599510a5521220abc1a3e8c0160dc42a7e349d74684221ecbeb38a38","target":"graph","created_at":"2026-07-05T04:42:23Z","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/2207.10295/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Impressive results in natural language processing (NLP) based on the Transformer neural network architecture have inspired researchers to explore viewing offline reinforcement learning (RL) as a generic sequence modeling problem. Recent works based on this paradigm have achieved state-of-the-art results in several of the mostly deterministic offline Atari and D4RL benchmarks. However, because these methods jointly model the states and actions as a single sequencing problem, they struggle to disentangle the effects of the policy and world dynamics on the return. Thus, in adversarial or stochast","authors_text":"Adam Villaflor, Jeff Schneider, John Dolan, Swapnil Pande, Zhe Huang","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-21T04:12:48Z","title":"Addressing Optimism Bias in Sequence Modeling for Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.10295","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:b2633e7b2a5c9adf9b8e75d9352023268859fc36723a300fbb08e9b9a186889e","target":"record","created_at":"2026-07-05T04:42:23Z","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":"2b841f347b4cdecf99b9c01b869b8dfc614499d17db45ea9ed4c05da406dfb8d","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-21T04:12:48Z","title_canon_sha256":"9b78b8cb7cf06fab5c5fdb6700673aa886bcdaf0e02ef459899642025709b937"},"schema_version":"1.0","source":{"id":"2207.10295","kind":"arxiv","version":1}},"canonical_sha256":"af3af047ecdb7151ae903ba9b0117090349f7aa8acc4ea987187bf8cc0b1e335","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"af3af047ecdb7151ae903ba9b0117090349f7aa8acc4ea987187bf8cc0b1e335","first_computed_at":"2026-07-05T04:42:23.564418Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:42:23.564418Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"73naOheXlidRbT5+/RAStUVZT6FsIzQU8T4niOsRSt3RZXIPZouTgi82z+GoQdDE7z41cTIlStJ4ORY7GHgrAw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:42:23.564792Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.10295","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b2633e7b2a5c9adf9b8e75d9352023268859fc36723a300fbb08e9b9a186889e","sha256:c1481f57599510a5521220abc1a3e8c0160dc42a7e349d74684221ecbeb38a38"],"state_sha256":"78793c0077c57f53a56a7716fb7e0dbba7fd59b9d0bda8977f837c1e64527554"}