{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:NZU7AHWCFUB7T5FYPK5T3DFA4F","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":"24743518503c1317ff3582b704ee39b56ad6f357590253b157b8e2a2c4cd1e20","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-17T05:57:47Z","title_canon_sha256":"0bd1c4d9fc5656930cc3ddc5a3ddef3d458d3b6e3963c4eb7f63d82b8df07dc7"},"schema_version":"1.0","source":{"id":"2206.08569","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.08569","created_at":"2026-07-05T05:07:46Z"},{"alias_kind":"arxiv_version","alias_value":"2206.08569v2","created_at":"2026-07-05T05:07:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.08569","created_at":"2026-07-05T05:07:46Z"},{"alias_kind":"pith_short_12","alias_value":"NZU7AHWCFUB7","created_at":"2026-07-05T05:07:46Z"},{"alias_kind":"pith_short_16","alias_value":"NZU7AHWCFUB7T5FY","created_at":"2026-07-05T05:07:46Z"},{"alias_kind":"pith_short_8","alias_value":"NZU7AHWC","created_at":"2026-07-05T05:07:46Z"}],"graph_snapshots":[{"event_id":"sha256:ce28777a959d3c017b7cf6c4e6be493f306603f593b5dbc3e0c917d9b0a93e41","target":"graph","created_at":"2026-07-05T05:07:46Z","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/2206.08569/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning (RL) aims at learning policies from previously collected static trajectory data without interacting with the real environment. Recent works provide a novel perspective by viewing offline RL as a generic sequence generation problem, adopting sequence models such as Transformer architecture to model distributions over trajectories, and repurposing beam search as a planning algorithm. However, the training datasets utilized in general offline RL tasks are quite limited and often suffer from insufficient distribution coverage, which could be harmful to training seque","authors_text":"Dongsheng Li, Hanye Zhao, Kan Ren, Kerong Wang, Weinan Zhang, Xufang Luo","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-17T05:57:47Z","title":"Bootstrapped Transformer for Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.08569","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":"sha256:94fb374f38069f5893378bade020aa25c0132674793ac52627b11bd29341a699","target":"record","created_at":"2026-07-05T05:07:46Z","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":"24743518503c1317ff3582b704ee39b56ad6f357590253b157b8e2a2c4cd1e20","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-17T05:57:47Z","title_canon_sha256":"0bd1c4d9fc5656930cc3ddc5a3ddef3d458d3b6e3963c4eb7f63d82b8df07dc7"},"schema_version":"1.0","source":{"id":"2206.08569","kind":"arxiv","version":2}},"canonical_sha256":"6e69f01ec22d03f9f4b87abb3d8ca0e1668662704ffb127f5d54ffcd2e3ba5cb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6e69f01ec22d03f9f4b87abb3d8ca0e1668662704ffb127f5d54ffcd2e3ba5cb","first_computed_at":"2026-07-05T05:07:46.149026Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:07:46.149026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BaZueF3U5OlY1Odz2gDgDsPvoLKyrKPrLtzc8/tFRwPoSG38Gviw7+D0EAGGf+KLMiGHp+8jQZsL/p0Te/QtCA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:07:46.149506Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.08569","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:94fb374f38069f5893378bade020aa25c0132674793ac52627b11bd29341a699","sha256:ce28777a959d3c017b7cf6c4e6be493f306603f593b5dbc3e0c917d9b0a93e41"],"state_sha256":"78781e7573a669397ee190d7e596a3341c8a17d3eb0e7135f0000bb61843b2ef"}