{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:B5EG6AHSLU6PFA6N3ON3GJSLAZ","short_pith_number":"pith:B5EG6AHS","canonical_record":{"source":{"id":"2201.12122","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-28T13:55:35Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"245c40c896a40bc32d79fa1f77cef45ef65524c994e60e5e62e9b3264912a32e","abstract_canon_sha256":"2ce8a2da72c13a5ba882f4a28ea4faba4dca66c7727927cc3b2eb76cbbc5d806"},"schema_version":"1.0"},"canonical_sha256":"0f486f00f25d3cf283cddb9bb3264b0652a91617fe0d0294f2161040666c8849","source":{"kind":"arxiv","id":"2201.12122","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.12122","created_at":"2026-07-05T04:42:59Z"},{"alias_kind":"arxiv_version","alias_value":"2201.12122v3","created_at":"2026-07-05T04:42:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.12122","created_at":"2026-07-05T04:42:59Z"},{"alias_kind":"pith_short_12","alias_value":"B5EG6AHSLU6P","created_at":"2026-07-05T04:42:59Z"},{"alias_kind":"pith_short_16","alias_value":"B5EG6AHSLU6PFA6N","created_at":"2026-07-05T04:42:59Z"},{"alias_kind":"pith_short_8","alias_value":"B5EG6AHS","created_at":"2026-07-05T04:42:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:B5EG6AHSLU6PFA6N3ON3GJSLAZ","target":"record","payload":{"canonical_record":{"source":{"id":"2201.12122","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-28T13:55:35Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"245c40c896a40bc32d79fa1f77cef45ef65524c994e60e5e62e9b3264912a32e","abstract_canon_sha256":"2ce8a2da72c13a5ba882f4a28ea4faba4dca66c7727927cc3b2eb76cbbc5d806"},"schema_version":"1.0"},"canonical_sha256":"0f486f00f25d3cf283cddb9bb3264b0652a91617fe0d0294f2161040666c8849","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:42:59.014058Z","signature_b64":"ihIZndCuxaDvMGXwYnANd8LTIWHmoFJan/1KzX4Fri9xq84eSToCio6P4rW+hFwDHD/0WVveC2ue+CsL399xCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f486f00f25d3cf283cddb9bb3264b0652a91617fe0d0294f2161040666c8849","last_reissued_at":"2026-07-05T04:42:59.013555Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:42:59.013555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2201.12122","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:42:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F7A5bM9WBiVyM3KN0tvSz7xsdI+55YZ0KKTFrzf4xpUtmGNVGiqDt/IWAojY0h14Wccr6qW4XxPbB4mpDKDoDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-27T23:02:42.562577Z"},"content_sha256":"a11a93cfe6a599e94fc0174aa1e6ecf6236bba93e88891397f023109a231f99d","schema_version":"1.0","event_id":"sha256:a11a93cfe6a599e94fc0174aa1e6ecf6236bba93e88891397f023109a231f99d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:B5EG6AHSLU6PFA6N3ON3GJSLAZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Can Wikipedia Help Offline Reinforcement Learning?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Machel Reid, Shixiang Shane Gu, Yutaro Yamada","submitted_at":"2022-01-28T13:55:35Z","abstract_excerpt":"Fine-tuning reinforcement learning (RL) models has been challenging because of a lack of large scale off-the-shelf datasets as well as high variance in transferability among different environments. Recent work has looked at tackling offline RL from the perspective of sequence modeling with improved results as result of the introduction of the Transformer architecture. However, when the model is trained from scratch, it suffers from slow convergence speeds. In this paper, we look to take advantage of this formulation of reinforcement learning as sequence modeling and investigate the transferabi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.12122","kind":"arxiv","version":3},"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/2201.12122/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":"2026-07-05T04:42:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0ViM34gJqPQAr8iJGTWQ5WuW9hYPHksXQoUgnX999Mn3c34phJzYX+TN1V2dXsl7hB6gyUZGNqW+SCqsDDw3AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-27T23:02:42.562960Z"},"content_sha256":"d1628ec2bc1f41424c302ef15f22c575409553ac37f00e0f2d5e60c57ccc043a","schema_version":"1.0","event_id":"sha256:d1628ec2bc1f41424c302ef15f22c575409553ac37f00e0f2d5e60c57ccc043a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/B5EG6AHSLU6PFA6N3ON3GJSLAZ/bundle.json","state_url":"https://pith.science/pith/B5EG6AHSLU6PFA6N3ON3GJSLAZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/B5EG6AHSLU6PFA6N3ON3GJSLAZ/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":"2026-07-27T23:02:42Z","links":{"resolver":"https://pith.science/pith/B5EG6AHSLU6PFA6N3ON3GJSLAZ","bundle":"https://pith.science/pith/B5EG6AHSLU6PFA6N3ON3GJSLAZ/bundle.json","state":"https://pith.science/pith/B5EG6AHSLU6PFA6N3ON3GJSLAZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/B5EG6AHSLU6PFA6N3ON3GJSLAZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:B5EG6AHSLU6PFA6N3ON3GJSLAZ","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":"2ce8a2da72c13a5ba882f4a28ea4faba4dca66c7727927cc3b2eb76cbbc5d806","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-28T13:55:35Z","title_canon_sha256":"245c40c896a40bc32d79fa1f77cef45ef65524c994e60e5e62e9b3264912a32e"},"schema_version":"1.0","source":{"id":"2201.12122","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.12122","created_at":"2026-07-05T04:42:59Z"},{"alias_kind":"arxiv_version","alias_value":"2201.12122v3","created_at":"2026-07-05T04:42:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.12122","created_at":"2026-07-05T04:42:59Z"},{"alias_kind":"pith_short_12","alias_value":"B5EG6AHSLU6P","created_at":"2026-07-05T04:42:59Z"},{"alias_kind":"pith_short_16","alias_value":"B5EG6AHSLU6PFA6N","created_at":"2026-07-05T04:42:59Z"},{"alias_kind":"pith_short_8","alias_value":"B5EG6AHS","created_at":"2026-07-05T04:42:59Z"}],"graph_snapshots":[{"event_id":"sha256:d1628ec2bc1f41424c302ef15f22c575409553ac37f00e0f2d5e60c57ccc043a","target":"graph","created_at":"2026-07-05T04:42:59Z","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/2201.12122/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fine-tuning reinforcement learning (RL) models has been challenging because of a lack of large scale off-the-shelf datasets as well as high variance in transferability among different environments. Recent work has looked at tackling offline RL from the perspective of sequence modeling with improved results as result of the introduction of the Transformer architecture. However, when the model is trained from scratch, it suffers from slow convergence speeds. In this paper, we look to take advantage of this formulation of reinforcement learning as sequence modeling and investigate the transferabi","authors_text":"Machel Reid, Shixiang Shane Gu, Yutaro Yamada","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-28T13:55:35Z","title":"Can Wikipedia Help Offline Reinforcement Learning?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.12122","kind":"arxiv","version":3},"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:a11a93cfe6a599e94fc0174aa1e6ecf6236bba93e88891397f023109a231f99d","target":"record","created_at":"2026-07-05T04:42:59Z","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":"2ce8a2da72c13a5ba882f4a28ea4faba4dca66c7727927cc3b2eb76cbbc5d806","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-28T13:55:35Z","title_canon_sha256":"245c40c896a40bc32d79fa1f77cef45ef65524c994e60e5e62e9b3264912a32e"},"schema_version":"1.0","source":{"id":"2201.12122","kind":"arxiv","version":3}},"canonical_sha256":"0f486f00f25d3cf283cddb9bb3264b0652a91617fe0d0294f2161040666c8849","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0f486f00f25d3cf283cddb9bb3264b0652a91617fe0d0294f2161040666c8849","first_computed_at":"2026-07-05T04:42:59.013555Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:42:59.013555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ihIZndCuxaDvMGXwYnANd8LTIWHmoFJan/1KzX4Fri9xq84eSToCio6P4rW+hFwDHD/0WVveC2ue+CsL399xCg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:42:59.014058Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.12122","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a11a93cfe6a599e94fc0174aa1e6ecf6236bba93e88891397f023109a231f99d","sha256:d1628ec2bc1f41424c302ef15f22c575409553ac37f00e0f2d5e60c57ccc043a"],"state_sha256":"9056665e2c19502d5a5ac59ffdcc5189022c00c3b64b3db2edf463ab55855b29"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bHRqkvjT+kh0SM3QzbGI1VD6hZe11W9no8QPf4YRcaBTIi4chv55c0eFyJFzaxda/8otqOynfZbLZqbYvQKNBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-27T23:02:42.565422Z","bundle_sha256":"fc5e6c090b57db25a897d99d090df8c34dc8e106e03b5f70c0b31d07049732a2"}}