{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PDRVQXEREGIU4QIMTPXM73EBB2","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":"6cad9317d915d5229da45e34169f5e782804f52186e34d3141adb1fe1c41145f","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-05-27T07:55:45Z","title_canon_sha256":"e2e989cc98e08801163e8ee8a3d4718735f4cadcfb1c2fe4b1738f14358983c5"},"schema_version":"1.0","source":{"id":"2405.16907","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.16907","created_at":"2026-07-05T09:32:09Z"},{"alias_kind":"arxiv_version","alias_value":"2405.16907v5","created_at":"2026-07-05T09:32:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16907","created_at":"2026-07-05T09:32:09Z"},{"alias_kind":"pith_short_12","alias_value":"PDRVQXEREGIU","created_at":"2026-07-05T09:32:09Z"},{"alias_kind":"pith_short_16","alias_value":"PDRVQXEREGIU4QIM","created_at":"2026-07-05T09:32:09Z"},{"alias_kind":"pith_short_8","alias_value":"PDRVQXER","created_at":"2026-07-05T09:32:09Z"}],"graph_snapshots":[{"event_id":"sha256:b2bae29c32f51bf84e6fcf267c661636ccac7869565b6c14ab9bf31f21122243","target":"graph","created_at":"2026-07-05T09:32:09Z","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/2405.16907/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline Reinforcement Learning (Offline RL) presents challenges of learning effective decision-making policies from static datasets without any online interactions. Data augmentation techniques, such as noise injection and data synthesizing, aim to improve Q-function approximation by smoothing the learned state-action region. However, these methods often fall short of directly improving the quality of offline datasets, leading to suboptimal results. In response, we introduce GTA, Generative Trajectory Augmentation, a novel generative data augmentation approach designed to enrich offline data b","authors_text":"Jaewoo Lee, Jinkyoo Park, Sujin Yun, Taeyoung Yun","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-05-27T07:55:45Z","title":"GTA: Generative Trajectory Augmentation with Guidance for Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16907","kind":"arxiv","version":5},"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":"sha256:1992cd5c9f387b3b1be06df7da097053f0dff966bf48d99ac49fd2bd7d87eb0e","target":"record","created_at":"2026-07-05T09:32:09Z","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":"6cad9317d915d5229da45e34169f5e782804f52186e34d3141adb1fe1c41145f","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-05-27T07:55:45Z","title_canon_sha256":"e2e989cc98e08801163e8ee8a3d4718735f4cadcfb1c2fe4b1738f14358983c5"},"schema_version":"1.0","source":{"id":"2405.16907","kind":"arxiv","version":5}},"canonical_sha256":"78e3585c9121914e410c9beecfec810e809a1bd33d013b8040ea18f557301739","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"78e3585c9121914e410c9beecfec810e809a1bd33d013b8040ea18f557301739","first_computed_at":"2026-07-05T09:32:09.456928Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:32:09.456928Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jInaU+XRKlEfwOxhPkSn2qcjGmvWKUvZ9PXLU/OMA58Itw0g0RkY8HUoKYyGBkFaFKJzZft5TR69lRZg36bgBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:32:09.457402Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.16907","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1992cd5c9f387b3b1be06df7da097053f0dff966bf48d99ac49fd2bd7d87eb0e","sha256:b2bae29c32f51bf84e6fcf267c661636ccac7869565b6c14ab9bf31f21122243"],"state_sha256":"6ce0db83a6da7c0e4d3be2c52e6207b87a4ff5a087dc86f8fc63562b4763fbd9"}