{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WRLPPCMFB7D55U4KNATDR4CGVT","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":"c313077d3e8f68e72f2e80258e1ca6953b948007c8fc4941cd0294c6bf722f6d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-01T22:02:07Z","title_canon_sha256":"5e267ce43c4b96f3a6d1eb667baedb401ec3f32a28e5ec1469529944f746d4e9"},"schema_version":"1.0","source":{"id":"2412.00979","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.00979","created_at":"2026-07-05T09:48:37Z"},{"alias_kind":"arxiv_version","alias_value":"2412.00979v2","created_at":"2026-07-05T09:48:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.00979","created_at":"2026-07-05T09:48:37Z"},{"alias_kind":"pith_short_12","alias_value":"WRLPPCMFB7D5","created_at":"2026-07-05T09:48:37Z"},{"alias_kind":"pith_short_16","alias_value":"WRLPPCMFB7D55U4K","created_at":"2026-07-05T09:48:37Z"},{"alias_kind":"pith_short_8","alias_value":"WRLPPCMF","created_at":"2026-07-05T09:48:37Z"}],"graph_snapshots":[{"event_id":"sha256:e91b63e1d4b89e1d46b0cfd5f0d69a3628184018b2554ac3e3b236f46c297ed4","target":"graph","created_at":"2026-07-05T09:48:37Z","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/2412.00979/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Decision transformers recast reinforcement learning as a conditional sequence generation problem, offering a simple but effective alternative to traditional value or policy-based methods. A recent key development in this area is the integration of prompting in decision transformers to facilitate few-shot policy generalization. However, current methods mainly use static prompt segments to guide rollouts, limiting their ability to provide context-specific guidance. Addressing this, we introduce a hierarchical prompting approach enabled by retrieval augmentation. Our method learns two layers of s","authors_text":"Haozhu Wang, Yanjun Qi, Zhe Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-01T22:02:07Z","title":"Hierarchical Prompt Decision Transformer: Improving Few-Shot Policy Generalization with Global and Adaptive Guidance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.00979","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":"sha256:3dcd121aedcd14f053eb1c8e31b38e9b94cc41fbac2c530af75f8ee5a06b8290","target":"record","created_at":"2026-07-05T09:48:37Z","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":"c313077d3e8f68e72f2e80258e1ca6953b948007c8fc4941cd0294c6bf722f6d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-01T22:02:07Z","title_canon_sha256":"5e267ce43c4b96f3a6d1eb667baedb401ec3f32a28e5ec1469529944f746d4e9"},"schema_version":"1.0","source":{"id":"2412.00979","kind":"arxiv","version":2}},"canonical_sha256":"b456f789850fc7ded38a682638f046ace94180aa051f9704124e59a31d95c6a5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b456f789850fc7ded38a682638f046ace94180aa051f9704124e59a31d95c6a5","first_computed_at":"2026-07-05T09:48:37.563692Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:48:37.563692Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Dr1XAVTlLg+deeUiGKLyh9CCaUHqzNRp3kZQUlGj9YRxgJi9vfma8BPzkeBLXEQDWJeLYQOib/AxWvlwo6x9DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:48:37.564191Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.00979","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3dcd121aedcd14f053eb1c8e31b38e9b94cc41fbac2c530af75f8ee5a06b8290","sha256:e91b63e1d4b89e1d46b0cfd5f0d69a3628184018b2554ac3e3b236f46c297ed4"],"state_sha256":"1cbfbb7fe2e77a79ac92edb72fc8900c818d45df82c9637a355ed8c48925c153"}