{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:NZU7AHWCFUB7T5FYPK5T3DFA4F","short_pith_number":"pith:NZU7AHWC","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"},"canonical_sha256":"6e69f01ec22d03f9f4b87abb3d8ca0e1668662704ffb127f5d54ffcd2e3ba5cb","source":{"kind":"arxiv","id":"2206.08569","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:NZU7AHWCFUB7T5FYPK5T3DFA4F","target":"record","payload":{"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"},"canonical_sha256":"6e69f01ec22d03f9f4b87abb3d8ca0e1668662704ffb127f5d54ffcd2e3ba5cb","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"},"source_kind":"arxiv","source_id":"2206.08569","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:07:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RZDGL0JS9nmRaetCK9VBvNp1QXxcicm3ICl2i3K9SvA+2Bd5Mmn98IveuhHhUwksotoNY3GZ+y/doYiaUa4NBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T19:10:11.138271Z"},"content_sha256":"94fb374f38069f5893378bade020aa25c0132674793ac52627b11bd29341a699","schema_version":"1.0","event_id":"sha256:94fb374f38069f5893378bade020aa25c0132674793ac52627b11bd29341a699"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:NZU7AHWCFUB7T5FYPK5T3DFA4F","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:07:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sBBVAqPVKCxYtBFO1e9aTe7uNh77i2Y8qSV7z3AOBRk/uaQOHDlIosprxazItVpYd2WwuPWW6f62Qbs6cCEECw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T19:10:11.138655Z"},"content_sha256":"ce28777a959d3c017b7cf6c4e6be493f306603f593b5dbc3e0c917d9b0a93e41","schema_version":"1.0","event_id":"sha256:ce28777a959d3c017b7cf6c4e6be493f306603f593b5dbc3e0c917d9b0a93e41"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NZU7AHWCFUB7T5FYPK5T3DFA4F/bundle.json","state_url":"https://pith.science/pith/NZU7AHWCFUB7T5FYPK5T3DFA4F/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NZU7AHWCFUB7T5FYPK5T3DFA4F/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-08T19:10:11Z","links":{"resolver":"https://pith.science/pith/NZU7AHWCFUB7T5FYPK5T3DFA4F","bundle":"https://pith.science/pith/NZU7AHWCFUB7T5FYPK5T3DFA4F/bundle.json","state":"https://pith.science/pith/NZU7AHWCFUB7T5FYPK5T3DFA4F/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NZU7AHWCFUB7T5FYPK5T3DFA4F/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NBog8b8v461Le/egcsa0lz22UDKN2CdpwIYtkI23i7QW0c/b/FfkeVglE7hP5tm5+C54ib4G81sE7Jm6e0RGAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T19:10:11.140747Z","bundle_sha256":"9520a7761a6c2ead33a3a26cbc4f36f4a1a29182c7706afa49cd8b6f7353a9db"}}