{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:APQIWZ3QWMAYP7S3KJSCTZKRBY","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":"99f17c25c5273922d88adabe351192e1f79bb6c65e2a880501d44e09c9192f73","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-31T08:38:25Z","title_canon_sha256":"d663e8acd565e907334af4c558f2f35aa15a1b1f98cecc5d2488611192ed57f6"},"schema_version":"1.0","source":{"id":"2405.20692","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.20692","created_at":"2026-07-05T08:25:41Z"},{"alias_kind":"arxiv_version","alias_value":"2405.20692v1","created_at":"2026-07-05T08:25:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.20692","created_at":"2026-07-05T08:25:41Z"},{"alias_kind":"pith_short_12","alias_value":"APQIWZ3QWMAY","created_at":"2026-07-05T08:25:41Z"},{"alias_kind":"pith_short_16","alias_value":"APQIWZ3QWMAYP7S3","created_at":"2026-07-05T08:25:41Z"},{"alias_kind":"pith_short_8","alias_value":"APQIWZ3Q","created_at":"2026-07-05T08:25:41Z"}],"graph_snapshots":[{"event_id":"sha256:d3d6f9453c68db4b182fde8d031bee7c9ef680602e3bb35b4dfbb0981784e8da","target":"graph","created_at":"2026-07-05T08:25:41Z","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/2405.20692/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In-context learning is a promising approach for offline reinforcement learning (RL) to handle online tasks, which can be achieved by providing task prompts. Recent works demonstrated that in-context RL could emerge with self-improvement in a trial-and-error manner when treating RL tasks as an across-episodic sequential prediction problem. Despite the self-improvement not requiring gradient updates, current works still suffer from high computational costs when the across-episodic sequence increases with task horizons. To this end, we propose an In-context Decision Transformer (IDT) to achieve s","authors_text":"Bo Yang, Hechang Chen, Jifeng Hu, Lichao Sun, Sili Huang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-31T08:38:25Z","title":"In-Context Decision Transformer: Reinforcement Learning via Hierarchical Chain-of-Thought"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.20692","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":"sha256:0a18dccff7437a80f26c8cba4e14f5cef96634cd71525f8a820c784ccfc16875","target":"record","created_at":"2026-07-05T08:25:41Z","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":"99f17c25c5273922d88adabe351192e1f79bb6c65e2a880501d44e09c9192f73","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-31T08:38:25Z","title_canon_sha256":"d663e8acd565e907334af4c558f2f35aa15a1b1f98cecc5d2488611192ed57f6"},"schema_version":"1.0","source":{"id":"2405.20692","kind":"arxiv","version":1}},"canonical_sha256":"03e08b6770b30187fe5b526429e5510e1b89713f45fdaef9df5e5a0ebb0373e0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"03e08b6770b30187fe5b526429e5510e1b89713f45fdaef9df5e5a0ebb0373e0","first_computed_at":"2026-07-05T08:25:41.026048Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:25:41.026048Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"H9YQpYxPxf+ti79lbDMprDW18HnesSTgwbUhPyrYyG14oUkpXZhBr4d9SZe4Poy4CrvY1ZABOxDj/HEPEGr2Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:25:41.026592Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.20692","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0a18dccff7437a80f26c8cba4e14f5cef96634cd71525f8a820c784ccfc16875","sha256:d3d6f9453c68db4b182fde8d031bee7c9ef680602e3bb35b4dfbb0981784e8da"],"state_sha256":"1ae8fed07748003c72f0a757d76e27db8db7e2a639e55391fcbaf309c177e283"}