{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:NZU7AHWCFUB7T5FYPK5T3DFA4F","short_pith_number":"pith:NZU7AHWC","schema_version":"1.0","canonical_sha256":"6e69f01ec22d03f9f4b87abb3d8ca0e1668662704ffb127f5d54ffcd2e3ba5cb","source":{"kind":"arxiv","id":"2206.08569","version":2},"attestation_state":"computed","paper":{"title":"Bootstrapped Transformer for Offline Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Dongsheng Li, Hanye Zhao, Kan Ren, Kerong Wang, Weinan Zhang, Xufang Luo","submitted_at":"2022-06-17T05:57:47Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2206.08569","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-17T05:57:47Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"0bd1c4d9fc5656930cc3ddc5a3ddef3d458d3b6e3963c4eb7f63d82b8df07dc7","abstract_canon_sha256":"24743518503c1317ff3582b704ee39b56ad6f357590253b157b8e2a2c4cd1e20"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:07:46.149506Z","signature_b64":"BaZueF3U5OlY1Odz2gDgDsPvoLKyrKPrLtzc8/tFRwPoSG38Gviw7+D0EAGGf+KLMiGHp+8jQZsL/p0Te/QtCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e69f01ec22d03f9f4b87abb3d8ca0e1668662704ffb127f5d54ffcd2e3ba5cb","last_reissued_at":"2026-07-05T05:07:46.149026Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:07:46.149026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bootstrapped Transformer for Offline Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Dongsheng Li, Hanye Zhao, Kan Ren, Kerong Wang, Weinan Zhang, Xufang Luo","submitted_at":"2022-06-17T05:57:47Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.08569","kind":"arxiv","version":2},"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/2206.08569/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2206.08569","created_at":"2026-07-05T05:07:46.149080+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.08569v2","created_at":"2026-07-05T05:07:46.149080+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.08569","created_at":"2026-07-05T05:07:46.149080+00:00"},{"alias_kind":"pith_short_12","alias_value":"NZU7AHWCFUB7","created_at":"2026-07-05T05:07:46.149080+00:00"},{"alias_kind":"pith_short_16","alias_value":"NZU7AHWCFUB7T5FY","created_at":"2026-07-05T05:07:46.149080+00:00"},{"alias_kind":"pith_short_8","alias_value":"NZU7AHWC","created_at":"2026-07-05T05:07:46.149080+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.20350","citing_title":"Decision Flow Policy Optimization","ref_index":82,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NZU7AHWCFUB7T5FYPK5T3DFA4F","json":"https://pith.science/pith/NZU7AHWCFUB7T5FYPK5T3DFA4F.json","graph_json":"https://pith.science/api/pith-number/NZU7AHWCFUB7T5FYPK5T3DFA4F/graph.json","events_json":"https://pith.science/api/pith-number/NZU7AHWCFUB7T5FYPK5T3DFA4F/events.json","paper":"https://pith.science/paper/NZU7AHWC"},"agent_actions":{"view_html":"https://pith.science/pith/NZU7AHWCFUB7T5FYPK5T3DFA4F","download_json":"https://pith.science/pith/NZU7AHWCFUB7T5FYPK5T3DFA4F.json","view_paper":"https://pith.science/paper/NZU7AHWC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.08569&json=true","fetch_graph":"https://pith.science/api/pith-number/NZU7AHWCFUB7T5FYPK5T3DFA4F/graph.json","fetch_events":"https://pith.science/api/pith-number/NZU7AHWCFUB7T5FYPK5T3DFA4F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NZU7AHWCFUB7T5FYPK5T3DFA4F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NZU7AHWCFUB7T5FYPK5T3DFA4F/action/storage_attestation","attest_author":"https://pith.science/pith/NZU7AHWCFUB7T5FYPK5T3DFA4F/action/author_attestation","sign_citation":"https://pith.science/pith/NZU7AHWCFUB7T5FYPK5T3DFA4F/action/citation_signature","submit_replication":"https://pith.science/pith/NZU7AHWCFUB7T5FYPK5T3DFA4F/action/replication_record"}},"created_at":"2026-07-05T05:07:46.149080+00:00","updated_at":"2026-07-05T05:07:46.149080+00:00"}