{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:WUFI6RGNWCI2FFOSTQLX3Q3FUQ","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":"e5a866dc08a70c806235fb676e2604cda70626f7ea5fe5eaf73414e932431cb9","cross_cats_sorted":["cs.AI","cs.NE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-11-20T21:57:10Z","title_canon_sha256":"3e8fc7cb2e7563b77950716b0db8894f07d6dc5a76131f89f09d8893b9da0f6d"},"schema_version":"1.0","source":{"id":"2211.11096","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.11096","created_at":"2026-07-05T05:36:51Z"},{"alias_kind":"arxiv_version","alias_value":"2211.11096v2","created_at":"2026-07-05T05:36:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.11096","created_at":"2026-07-05T05:36:51Z"},{"alias_kind":"pith_short_12","alias_value":"WUFI6RGNWCI2","created_at":"2026-07-05T05:36:51Z"},{"alias_kind":"pith_short_16","alias_value":"WUFI6RGNWCI2FFOS","created_at":"2026-07-05T05:36:51Z"},{"alias_kind":"pith_short_8","alias_value":"WUFI6RGN","created_at":"2026-07-05T05:36:51Z"}],"graph_snapshots":[{"event_id":"sha256:650e7f8813209fb791dd3157369461417c0cf3a1eb46c4637c10c2faf98fb9e5","target":"graph","created_at":"2026-07-05T05:36:51Z","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/2211.11096/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning aims to train a policy on a pre-recorded and fixed dataset without any additional environment interactions. There are two major challenges in this setting: (1) extrapolation error caused by approximating the value of state-action pairs not well-covered by the training data and (2) distributional shift between behavior and inference policies. One way to tackle these problems is to induce conservatism - i.e., keeping the learned policies closer to the behavioral ones. To achieve this, we build upon recent works on learning policies in latent action spaces and use a","authors_text":"Alexander Nikulin, Denis Tarasov, Dmitriy Akimov, Sergey Kolesnikov, Vladislav Kurenkov","cross_cats":["cs.AI","cs.NE"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-11-20T21:57:10Z","title":"Let Offline RL Flow: Training Conservative Agents in the Latent Space of Normalizing Flows"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.11096","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:bb4ac4b03f61a06ac20c95491a50d57a7d694a3f905d5292c29efa418341adf6","target":"record","created_at":"2026-07-05T05:36:51Z","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":"e5a866dc08a70c806235fb676e2604cda70626f7ea5fe5eaf73414e932431cb9","cross_cats_sorted":["cs.AI","cs.NE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-11-20T21:57:10Z","title_canon_sha256":"3e8fc7cb2e7563b77950716b0db8894f07d6dc5a76131f89f09d8893b9da0f6d"},"schema_version":"1.0","source":{"id":"2211.11096","kind":"arxiv","version":2}},"canonical_sha256":"b50a8f44cdb091a295d29c177dc365a41a17de48e5db24abd9cf04da3e0adf52","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b50a8f44cdb091a295d29c177dc365a41a17de48e5db24abd9cf04da3e0adf52","first_computed_at":"2026-07-05T05:36:51.209497Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:36:51.209497Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zMJ9FppTrcTy7DN4SzXhevk1zDayWA22x7i9B1ROK3Wu8QRvu+x9U6QEUs20vX9mlBEyQmEN7SJd00DDFIMxAg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:36:51.209974Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.11096","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bb4ac4b03f61a06ac20c95491a50d57a7d694a3f905d5292c29efa418341adf6","sha256:650e7f8813209fb791dd3157369461417c0cf3a1eb46c4637c10c2faf98fb9e5"],"state_sha256":"34e1fbf8ea0005414be4eec8938fbbed0b1188cd418a95faf1b598022792fd63"}