{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:E4E67XOER4SAC7NKTZMN33SGOH","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":"b7bdab17212520fe85855bc7ed699b2d4070874c35fc00a26d9a48285e845ef7","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-14T19:30:53Z","title_canon_sha256":"ea5b671525aec145bbc02cca35563e0661fc635daa3143b72f0f70206168f9f7"},"schema_version":"1.0","source":{"id":"2409.09513","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.09513","created_at":"2026-07-05T09:07:10Z"},{"alias_kind":"arxiv_version","alias_value":"2409.09513v1","created_at":"2026-07-05T09:07:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.09513","created_at":"2026-07-05T09:07:10Z"},{"alias_kind":"pith_short_12","alias_value":"E4E67XOER4SA","created_at":"2026-07-05T09:07:10Z"},{"alias_kind":"pith_short_16","alias_value":"E4E67XOER4SAC7NK","created_at":"2026-07-05T09:07:10Z"},{"alias_kind":"pith_short_8","alias_value":"E4E67XOE","created_at":"2026-07-05T09:07:10Z"}],"graph_snapshots":[{"event_id":"sha256:830070ac3d96c7be89acb19ffae7f2e586d7af0b6f3df23e4e8816f844077fc7","target":"graph","created_at":"2026-07-05T09:07:10Z","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/2409.09513/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Supervised learning approaches to offline reinforcement learning, particularly those utilizing the Decision Transformer, have shown effectiveness in continuous environments and for sparse rewards. However, they often struggle with long-horizon tasks due to the high compounding error of auto-regressive models. To overcome this limitation, we go beyond next-token prediction and introduce Planning Tokens, which contain high-level, long time-scale information about the agent's future. Predicting dual time-scale tokens at regular intervals enables our model to use these long-horizon Planning Tokens","authors_text":"Joseph Clinton, Robert Lieck","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-14T19:30:53Z","title":"Planning Transformer: Long-Horizon Offline Reinforcement Learning with Planning Tokens"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.09513","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":"sha256:336033bf4398e843846330c8171af8b312548bd173318d437adf5a60bca4bc01","target":"record","created_at":"2026-07-05T09:07:10Z","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":"b7bdab17212520fe85855bc7ed699b2d4070874c35fc00a26d9a48285e845ef7","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-14T19:30:53Z","title_canon_sha256":"ea5b671525aec145bbc02cca35563e0661fc635daa3143b72f0f70206168f9f7"},"schema_version":"1.0","source":{"id":"2409.09513","kind":"arxiv","version":1}},"canonical_sha256":"2709efddc48f24017daa9e58ddee4671c5b4a169d40f43dd1c342ab5cfeb70a0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2709efddc48f24017daa9e58ddee4671c5b4a169d40f43dd1c342ab5cfeb70a0","first_computed_at":"2026-07-05T09:07:10.709260Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:07:10.709260Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2++WQtOWbMcsDXu2mNmZ/Lug4MZQpcw8xzxlehrggQquIGd1ukrgCQ11VfCRtX1Owpe4fWlGngrlv+40DaxpAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:07:10.709695Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.09513","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:336033bf4398e843846330c8171af8b312548bd173318d437adf5a60bca4bc01","sha256:830070ac3d96c7be89acb19ffae7f2e586d7af0b6f3df23e4e8816f844077fc7"],"state_sha256":"68a8f10d649b65da4a14924a289fee4dbe40d5be1d66b18b7e1384565b301735"}