{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:YQAGUQNGI32IZY6ZSTRRPLSAYL","short_pith_number":"pith:YQAGUQNG","canonical_record":{"source":{"id":"2404.10393","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-16T08:48:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a9a85d5868e4b7ebdd3135ef4500a51d3b94518d719efeb1c959c8748ce1a974","abstract_canon_sha256":"4c5e42644aacf2697e1535b32b9b94e2ff585d91483d44b0ce719499597587be"},"schema_version":"1.0"},"canonical_sha256":"c4006a41a646f48ce3d994e317ae40c2c76896b046bbb3fbb54260f333c90300","source":{"kind":"arxiv","id":"2404.10393","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.10393","created_at":"2026-07-05T11:34:41Z"},{"alias_kind":"arxiv_version","alias_value":"2404.10393v2","created_at":"2026-07-05T11:34:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.10393","created_at":"2026-07-05T11:34:41Z"},{"alias_kind":"pith_short_12","alias_value":"YQAGUQNGI32I","created_at":"2026-07-05T11:34:41Z"},{"alias_kind":"pith_short_16","alias_value":"YQAGUQNGI32IZY6Z","created_at":"2026-07-05T11:34:41Z"},{"alias_kind":"pith_short_8","alias_value":"YQAGUQNG","created_at":"2026-07-05T11:34:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:YQAGUQNGI32IZY6ZSTRRPLSAYL","target":"record","payload":{"canonical_record":{"source":{"id":"2404.10393","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-16T08:48:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a9a85d5868e4b7ebdd3135ef4500a51d3b94518d719efeb1c959c8748ce1a974","abstract_canon_sha256":"4c5e42644aacf2697e1535b32b9b94e2ff585d91483d44b0ce719499597587be"},"schema_version":"1.0"},"canonical_sha256":"c4006a41a646f48ce3d994e317ae40c2c76896b046bbb3fbb54260f333c90300","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:41.817539Z","signature_b64":"gVyiAeyVvPILVUW+70WxvAYmTxV7fJuJCYNAU8rMDA3AK1w2rjV+M/TJeqDipQOzXXOHJIbUeAtYZYlFAe5/AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c4006a41a646f48ce3d994e317ae40c2c76896b046bbb3fbb54260f333c90300","last_reissued_at":"2026-07-05T11:34:41.817091Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:41.817091Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.10393","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":"2026-07-05T11:34:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O0VTmlNcWViKArVMoQ5LF88Y+vL9I4HRQxDpji+oCLj5UUWDU2hbWf61O1Blnj7R4f1BEvNsyL17uROl9YZ+Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T22:33:03.107190Z"},"content_sha256":"4da5519011c3022502b64f9fefa3996585fe2bdcedde099c85247036c2bae2c8","schema_version":"1.0","event_id":"sha256:4da5519011c3022502b64f9fefa3996585fe2bdcedde099c85247036c2bae2c8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:YQAGUQNGI32IZY6ZSTRRPLSAYL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Offline Trajectory Optimization for Offline Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Fajie Yuan, Jun Ma, Liu Yang, Pengjie Ren, Xin Xin, Yunsen Liang, Zhaochun Ren, Zhumin Chen, Ziqi Zhao","submitted_at":"2024-04-16T08:48:46Z","abstract_excerpt":"Offline reinforcement learning (RL) aims to learn policies without online explorations. To enlarge the training data, model-based offline RL learns a dynamics model which is utilized as a virtual environment to generate simulation data and enhance policy learning. However, existing data augmentation methods for offline RL suffer from (i) trivial improvement from short-horizon simulation; and (ii) the lack of evaluation and correction for generated data, leading to low-qualified augmentation.\n  In this paper, we propose offline trajectory optimization for offline reinforcement learning (OTTO). "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.10393","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/2404.10393/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":"2026-07-05T11:34:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nmV3a8PN1GOMr3k+iTYfrqByT9LTWjGa8JT3J+iNuizGDQj7GHSV5trdN3e27p+MKOyPl1ONfeOmn21wFnNrCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T22:33:03.108084Z"},"content_sha256":"00b748e0ee0436ec2a3af76511790faac9dac3288da61141882df9a8c274b740","schema_version":"1.0","event_id":"sha256:00b748e0ee0436ec2a3af76511790faac9dac3288da61141882df9a8c274b740"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YQAGUQNGI32IZY6ZSTRRPLSAYL/bundle.json","state_url":"https://pith.science/pith/YQAGUQNGI32IZY6ZSTRRPLSAYL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YQAGUQNGI32IZY6ZSTRRPLSAYL/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":"2026-08-05T22:33:03Z","links":{"resolver":"https://pith.science/pith/YQAGUQNGI32IZY6ZSTRRPLSAYL","bundle":"https://pith.science/pith/YQAGUQNGI32IZY6ZSTRRPLSAYL/bundle.json","state":"https://pith.science/pith/YQAGUQNGI32IZY6ZSTRRPLSAYL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YQAGUQNGI32IZY6ZSTRRPLSAYL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YQAGUQNGI32IZY6ZSTRRPLSAYL","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":"4c5e42644aacf2697e1535b32b9b94e2ff585d91483d44b0ce719499597587be","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-16T08:48:46Z","title_canon_sha256":"a9a85d5868e4b7ebdd3135ef4500a51d3b94518d719efeb1c959c8748ce1a974"},"schema_version":"1.0","source":{"id":"2404.10393","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.10393","created_at":"2026-07-05T11:34:41Z"},{"alias_kind":"arxiv_version","alias_value":"2404.10393v2","created_at":"2026-07-05T11:34:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.10393","created_at":"2026-07-05T11:34:41Z"},{"alias_kind":"pith_short_12","alias_value":"YQAGUQNGI32I","created_at":"2026-07-05T11:34:41Z"},{"alias_kind":"pith_short_16","alias_value":"YQAGUQNGI32IZY6Z","created_at":"2026-07-05T11:34:41Z"},{"alias_kind":"pith_short_8","alias_value":"YQAGUQNG","created_at":"2026-07-05T11:34:41Z"}],"graph_snapshots":[{"event_id":"sha256:00b748e0ee0436ec2a3af76511790faac9dac3288da61141882df9a8c274b740","target":"graph","created_at":"2026-07-05T11:34:41Z","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/2404.10393/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning (RL) aims to learn policies without online explorations. To enlarge the training data, model-based offline RL learns a dynamics model which is utilized as a virtual environment to generate simulation data and enhance policy learning. However, existing data augmentation methods for offline RL suffer from (i) trivial improvement from short-horizon simulation; and (ii) the lack of evaluation and correction for generated data, leading to low-qualified augmentation.\n  In this paper, we propose offline trajectory optimization for offline reinforcement learning (OTTO). ","authors_text":"Fajie Yuan, Jun Ma, Liu Yang, Pengjie Ren, Xin Xin, Yunsen Liang, Zhaochun Ren, Zhumin Chen, Ziqi Zhao","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-16T08:48:46Z","title":"Offline Trajectory Optimization for Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.10393","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":"sha256:4da5519011c3022502b64f9fefa3996585fe2bdcedde099c85247036c2bae2c8","target":"record","created_at":"2026-07-05T11:34:41Z","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":"4c5e42644aacf2697e1535b32b9b94e2ff585d91483d44b0ce719499597587be","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-16T08:48:46Z","title_canon_sha256":"a9a85d5868e4b7ebdd3135ef4500a51d3b94518d719efeb1c959c8748ce1a974"},"schema_version":"1.0","source":{"id":"2404.10393","kind":"arxiv","version":2}},"canonical_sha256":"c4006a41a646f48ce3d994e317ae40c2c76896b046bbb3fbb54260f333c90300","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c4006a41a646f48ce3d994e317ae40c2c76896b046bbb3fbb54260f333c90300","first_computed_at":"2026-07-05T11:34:41.817091Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:34:41.817091Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gVyiAeyVvPILVUW+70WxvAYmTxV7fJuJCYNAU8rMDA3AK1w2rjV+M/TJeqDipQOzXXOHJIbUeAtYZYlFAe5/AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:34:41.817539Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.10393","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4da5519011c3022502b64f9fefa3996585fe2bdcedde099c85247036c2bae2c8","sha256:00b748e0ee0436ec2a3af76511790faac9dac3288da61141882df9a8c274b740"],"state_sha256":"66510a0321090ca5eb73b0d284e1aeb7e96eff878bd67d2c861e67280628808d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K63J1oTrLELst+RqUBLRpFO143nvQPLDhJv6SFVr7ncTdtobr/jDJ5aN4dk52mY1U/PeBYCsFFhr93VRnpAQAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T22:33:03.121455Z","bundle_sha256":"84c7870adfe6210151af36b08298a7d34702f1d4ddd50e3a03c295aa8c12a345"}}