{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:XWFJABMAIGCZBZI3WTOXLM7M3Y","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":"6a16363983044e81209f76ba9e820953d4678e4f40bcbbd14e554604b1a3979c","cross_cats_sorted":["cs.AI","cs.CV","cs.RO"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-17T17:59:32Z","title_canon_sha256":"ec440fa4c1da7e7ced8da60ba3290efa56ba810cdb32733f2a4e18dbf593a218"},"schema_version":"1.0","source":{"id":"2304.08487","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.08487","created_at":"2026-07-05T06:01:52Z"},{"alias_kind":"arxiv_version","alias_value":"2304.08487v1","created_at":"2026-07-05T06:01:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.08487","created_at":"2026-07-05T06:01:52Z"},{"alias_kind":"pith_short_12","alias_value":"XWFJABMAIGCZ","created_at":"2026-07-05T06:01:52Z"},{"alias_kind":"pith_short_16","alias_value":"XWFJABMAIGCZBZI3","created_at":"2026-07-05T06:01:52Z"},{"alias_kind":"pith_short_8","alias_value":"XWFJABMA","created_at":"2026-07-05T06:01:52Z"}],"graph_snapshots":[{"event_id":"sha256:cb6de10e068ecd0563842a5c4e9a557969840acfb36ce23de37f228988ff28c5","target":"graph","created_at":"2026-07-05T06:01:52Z","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/2304.08487/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Decision Transformers (DT) have demonstrated strong performances in offline reinforcement learning settings, but quickly adapting to unseen novel tasks remains challenging. To address this challenge, we propose a new framework, called Hyper-Decision Transformer (HDT), that can generalize to novel tasks from a handful of demonstrations in a data- and parameter-efficient manner. To achieve such a goal, we propose to augment the base DT with an adaptation module, whose parameters are initialized by a hyper-network. When encountering unseen tasks, the hyper-network takes a handful of demonstration","authors_text":"Chuang Gan, Ding Zhao, Mengdi Xu, Shun Zhang, Yikang Shen, Yuchen Lu","cross_cats":["cs.AI","cs.CV","cs.RO"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-17T17:59:32Z","title":"Hyper-Decision Transformer for Efficient Online Policy Adaptation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.08487","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:e216b4f9e91aa87f1f2b2d969e25fb3fb7c4f068ed971e2f89b47016c8a63057","target":"record","created_at":"2026-07-05T06:01:52Z","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":"6a16363983044e81209f76ba9e820953d4678e4f40bcbbd14e554604b1a3979c","cross_cats_sorted":["cs.AI","cs.CV","cs.RO"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-17T17:59:32Z","title_canon_sha256":"ec440fa4c1da7e7ced8da60ba3290efa56ba810cdb32733f2a4e18dbf593a218"},"schema_version":"1.0","source":{"id":"2304.08487","kind":"arxiv","version":1}},"canonical_sha256":"bd8a900580418590e51bb4dd75b3ecde16dabb2556af6c6afaf21be0a158111a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bd8a900580418590e51bb4dd75b3ecde16dabb2556af6c6afaf21be0a158111a","first_computed_at":"2026-07-05T06:01:52.968387Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:01:52.968387Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nF9y2SuJhbW25JpjPIOpJYAAfRQBN9SXiPgWKE6M7LY7jICCI09zTcsoFN9Ge8p0JUMMWmupc4vUFHrwLE/qBA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:01:52.968844Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.08487","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e216b4f9e91aa87f1f2b2d969e25fb3fb7c4f068ed971e2f89b47016c8a63057","sha256:cb6de10e068ecd0563842a5c4e9a557969840acfb36ce23de37f228988ff28c5"],"state_sha256":"f703f51111d57280431c507f14d48e1af909958a52e78cd247cb3c97d4657b03"}