{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WRLPPCMFB7D55U4KNATDR4CGVT","short_pith_number":"pith:WRLPPCMF","schema_version":"1.0","canonical_sha256":"b456f789850fc7ded38a682638f046ace94180aa051f9704124e59a31d95c6a5","source":{"kind":"arxiv","id":"2412.00979","version":2},"attestation_state":"computed","paper":{"title":"Hierarchical Prompt Decision Transformer: Improving Few-Shot Policy Generalization with Global and Adaptive Guidance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Haozhu Wang, Yanjun Qi, Zhe Wang","submitted_at":"2024-12-01T22:02:07Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2412.00979","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-01T22:02:07Z","cross_cats_sorted":[],"title_canon_sha256":"5e267ce43c4b96f3a6d1eb667baedb401ec3f32a28e5ec1469529944f746d4e9","abstract_canon_sha256":"c313077d3e8f68e72f2e80258e1ca6953b948007c8fc4941cd0294c6bf722f6d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:48:37.564191Z","signature_b64":"Dr1XAVTlLg+deeUiGKLyh9CCaUHqzNRp3kZQUlGj9YRxgJi9vfma8BPzkeBLXEQDWJeLYQOib/AxWvlwo6x9DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b456f789850fc7ded38a682638f046ace94180aa051f9704124e59a31d95c6a5","last_reissued_at":"2026-07-05T09:48:37.563692Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:48:37.563692Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchical Prompt Decision Transformer: Improving Few-Shot Policy Generalization with Global and Adaptive Guidance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Haozhu Wang, Yanjun Qi, Zhe Wang","submitted_at":"2024-12-01T22:02:07Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.00979","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/2412.00979/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2412.00979","created_at":"2026-07-05T09:48:37.563753+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.00979v2","created_at":"2026-07-05T09:48:37.563753+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.00979","created_at":"2026-07-05T09:48:37.563753+00:00"},{"alias_kind":"pith_short_12","alias_value":"WRLPPCMFB7D5","created_at":"2026-07-05T09:48:37.563753+00:00"},{"alias_kind":"pith_short_16","alias_value":"WRLPPCMFB7D55U4K","created_at":"2026-07-05T09:48:37.563753+00:00"},{"alias_kind":"pith_short_8","alias_value":"WRLPPCMF","created_at":"2026-07-05T09:48:37.563753+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WRLPPCMFB7D55U4KNATDR4CGVT","json":"https://pith.science/pith/WRLPPCMFB7D55U4KNATDR4CGVT.json","graph_json":"https://pith.science/api/pith-number/WRLPPCMFB7D55U4KNATDR4CGVT/graph.json","events_json":"https://pith.science/api/pith-number/WRLPPCMFB7D55U4KNATDR4CGVT/events.json","paper":"https://pith.science/paper/WRLPPCMF"},"agent_actions":{"view_html":"https://pith.science/pith/WRLPPCMFB7D55U4KNATDR4CGVT","download_json":"https://pith.science/pith/WRLPPCMFB7D55U4KNATDR4CGVT.json","view_paper":"https://pith.science/paper/WRLPPCMF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.00979&json=true","fetch_graph":"https://pith.science/api/pith-number/WRLPPCMFB7D55U4KNATDR4CGVT/graph.json","fetch_events":"https://pith.science/api/pith-number/WRLPPCMFB7D55U4KNATDR4CGVT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WRLPPCMFB7D55U4KNATDR4CGVT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WRLPPCMFB7D55U4KNATDR4CGVT/action/storage_attestation","attest_author":"https://pith.science/pith/WRLPPCMFB7D55U4KNATDR4CGVT/action/author_attestation","sign_citation":"https://pith.science/pith/WRLPPCMFB7D55U4KNATDR4CGVT/action/citation_signature","submit_replication":"https://pith.science/pith/WRLPPCMFB7D55U4KNATDR4CGVT/action/replication_record"}},"created_at":"2026-07-05T09:48:37.563753+00:00","updated_at":"2026-07-05T09:48:37.563753+00:00"}