{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:JQIDHRRGJAWNCAFUH27F2YIVVF","short_pith_number":"pith:JQIDHRRG","canonical_record":{"source":{"id":"2305.16683","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-26T07:05:08Z","cross_cats_sorted":[],"title_canon_sha256":"bb06da3f5f8e66324d8ee0b8bae948ee033ce57dd5db989689bd289845d65e78","abstract_canon_sha256":"c5300a9242025f7a990fd11e8e8845c88f4e3914d116745a2964a8bff0e6f1e2"},"schema_version":"1.0"},"canonical_sha256":"4c1033c626482cd100b43ebe5d6115a95d5be790e7770670e68abd00e91c45dc","source":{"kind":"arxiv","id":"2305.16683","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.16683","created_at":"2026-07-05T06:14:16Z"},{"alias_kind":"arxiv_version","alias_value":"2305.16683v1","created_at":"2026-07-05T06:14:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.16683","created_at":"2026-07-05T06:14:16Z"},{"alias_kind":"pith_short_12","alias_value":"JQIDHRRGJAWN","created_at":"2026-07-05T06:14:16Z"},{"alias_kind":"pith_short_16","alias_value":"JQIDHRRGJAWNCAFU","created_at":"2026-07-05T06:14:16Z"},{"alias_kind":"pith_short_8","alias_value":"JQIDHRRG","created_at":"2026-07-05T06:14:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:JQIDHRRGJAWNCAFUH27F2YIVVF","target":"record","payload":{"canonical_record":{"source":{"id":"2305.16683","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-26T07:05:08Z","cross_cats_sorted":[],"title_canon_sha256":"bb06da3f5f8e66324d8ee0b8bae948ee033ce57dd5db989689bd289845d65e78","abstract_canon_sha256":"c5300a9242025f7a990fd11e8e8845c88f4e3914d116745a2964a8bff0e6f1e2"},"schema_version":"1.0"},"canonical_sha256":"4c1033c626482cd100b43ebe5d6115a95d5be790e7770670e68abd00e91c45dc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:14:16.206592Z","signature_b64":"kpgspnfo3RJYn6wAlQuyoM7UGGsiXU5jAQaoToArUWpgi2GgkdwP2tZwnSLKn5ZQpUddBXDoBGle26Mf3pFYDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c1033c626482cd100b43ebe5d6115a95d5be790e7770670e68abd00e91c45dc","last_reissued_at":"2026-07-05T06:14:16.206163Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:14:16.206163Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.16683","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:14:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fEe9fKsCck2vi3AN44MTyq/5ecrW2lnj06v7BSrN42HQ0jei0pv59yhX2Y9nPnIHfgkP7uWTS5azVqAAkZiBBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T16:24:47.416179Z"},"content_sha256":"d047e62ba8cdc5efdfb021f26c3157c79f9606f681bc741273227131bd823766","schema_version":"1.0","event_id":"sha256:d047e62ba8cdc5efdfb021f26c3157c79f9606f681bc741273227131bd823766"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:JQIDHRRGJAWNCAFUH27F2YIVVF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Future-conditioned Unsupervised Pretraining for Decision Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Deheng Ye, Qiang Fu, Shuai Li, Wei Yang, Zhihui Xie, Zichuan Lin","submitted_at":"2023-05-26T07:05:08Z","abstract_excerpt":"Recent research in offline reinforcement learning (RL) has demonstrated that return-conditioned supervised learning is a powerful paradigm for decision-making problems. While promising, return conditioning is limited to training data labeled with rewards and therefore faces challenges in learning from unsupervised data. In this work, we aim to utilize generalized future conditioning to enable efficient unsupervised pretraining from reward-free and sub-optimal offline data. We propose Pretrained Decision Transformer (PDT), a conceptually simple approach for unsupervised RL pretraining. PDT leve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.16683","kind":"arxiv","version":1},"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/2305.16683/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":"2026-07-05T06:14:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RqUm/ePDpPIbZHk2KGlXKhCsC9werkDV0J8MvyBlng29oMROpS2bxHRL3keWhG5Gd5eUvjbZTJECNHjkVetzAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T16:24:47.416997Z"},"content_sha256":"70b657bc9797c08b7706ff232b22ae2b0234bfa36e953e4d9014e861fdc355e9","schema_version":"1.0","event_id":"sha256:70b657bc9797c08b7706ff232b22ae2b0234bfa36e953e4d9014e861fdc355e9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JQIDHRRGJAWNCAFUH27F2YIVVF/bundle.json","state_url":"https://pith.science/pith/JQIDHRRGJAWNCAFUH27F2YIVVF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JQIDHRRGJAWNCAFUH27F2YIVVF/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":"2026-08-06T16:24:47Z","links":{"resolver":"https://pith.science/pith/JQIDHRRGJAWNCAFUH27F2YIVVF","bundle":"https://pith.science/pith/JQIDHRRGJAWNCAFUH27F2YIVVF/bundle.json","state":"https://pith.science/pith/JQIDHRRGJAWNCAFUH27F2YIVVF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JQIDHRRGJAWNCAFUH27F2YIVVF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:JQIDHRRGJAWNCAFUH27F2YIVVF","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":"c5300a9242025f7a990fd11e8e8845c88f4e3914d116745a2964a8bff0e6f1e2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-26T07:05:08Z","title_canon_sha256":"bb06da3f5f8e66324d8ee0b8bae948ee033ce57dd5db989689bd289845d65e78"},"schema_version":"1.0","source":{"id":"2305.16683","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.16683","created_at":"2026-07-05T06:14:16Z"},{"alias_kind":"arxiv_version","alias_value":"2305.16683v1","created_at":"2026-07-05T06:14:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.16683","created_at":"2026-07-05T06:14:16Z"},{"alias_kind":"pith_short_12","alias_value":"JQIDHRRGJAWN","created_at":"2026-07-05T06:14:16Z"},{"alias_kind":"pith_short_16","alias_value":"JQIDHRRGJAWNCAFU","created_at":"2026-07-05T06:14:16Z"},{"alias_kind":"pith_short_8","alias_value":"JQIDHRRG","created_at":"2026-07-05T06:14:16Z"}],"graph_snapshots":[{"event_id":"sha256:70b657bc9797c08b7706ff232b22ae2b0234bfa36e953e4d9014e861fdc355e9","target":"graph","created_at":"2026-07-05T06:14:16Z","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/2305.16683/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent research in offline reinforcement learning (RL) has demonstrated that return-conditioned supervised learning is a powerful paradigm for decision-making problems. While promising, return conditioning is limited to training data labeled with rewards and therefore faces challenges in learning from unsupervised data. In this work, we aim to utilize generalized future conditioning to enable efficient unsupervised pretraining from reward-free and sub-optimal offline data. We propose Pretrained Decision Transformer (PDT), a conceptually simple approach for unsupervised RL pretraining. PDT leve","authors_text":"Deheng Ye, Qiang Fu, Shuai Li, Wei Yang, Zhihui Xie, Zichuan Lin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-26T07:05:08Z","title":"Future-conditioned Unsupervised Pretraining for Decision Transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.16683","kind":"arxiv","version":1},"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:d047e62ba8cdc5efdfb021f26c3157c79f9606f681bc741273227131bd823766","target":"record","created_at":"2026-07-05T06:14:16Z","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":"c5300a9242025f7a990fd11e8e8845c88f4e3914d116745a2964a8bff0e6f1e2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-26T07:05:08Z","title_canon_sha256":"bb06da3f5f8e66324d8ee0b8bae948ee033ce57dd5db989689bd289845d65e78"},"schema_version":"1.0","source":{"id":"2305.16683","kind":"arxiv","version":1}},"canonical_sha256":"4c1033c626482cd100b43ebe5d6115a95d5be790e7770670e68abd00e91c45dc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4c1033c626482cd100b43ebe5d6115a95d5be790e7770670e68abd00e91c45dc","first_computed_at":"2026-07-05T06:14:16.206163Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:14:16.206163Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kpgspnfo3RJYn6wAlQuyoM7UGGsiXU5jAQaoToArUWpgi2GgkdwP2tZwnSLKn5ZQpUddBXDoBGle26Mf3pFYDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:14:16.206592Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.16683","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d047e62ba8cdc5efdfb021f26c3157c79f9606f681bc741273227131bd823766","sha256:70b657bc9797c08b7706ff232b22ae2b0234bfa36e953e4d9014e861fdc355e9"],"state_sha256":"cfb6b139488ccd9508e616dad999b62a6aa16fb1fa4d1d961d08d6587b56e181"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xQYFiyZc9YDiy/pD6xTlEKODSgyMWC7Wb9IzXp/bXgV33ABnxP7htazgIH5mvD6ZRzmMgzmuK4QDfFWzxMGGBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T16:24:47.422116Z","bundle_sha256":"079f7bc4e8031c4fcb92aa458747fe3528161e3888dbbb675ebadf449da5a66f"}}