{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QAQZ33IUPTYYI3W2QSX5QMNJQR","short_pith_number":"pith:QAQZ33IU","schema_version":"1.0","canonical_sha256":"80219ded147cf1846eda84afd831a9844bbf9bcde38a0ef2d27712607495f614","source":{"kind":"arxiv","id":"2307.02484","version":6},"attestation_state":"computed","paper":{"title":"Elastic Decision Transformer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Masashi Hamaya, Xiaolong Wang, Yueh-Hua Wu","submitted_at":"2023-07-05T17:58:21Z","abstract_excerpt":"This paper introduces Elastic Decision Transformer (EDT), a significant advancement over the existing Decision Transformer (DT) and its variants. Although DT purports to generate an optimal trajectory, empirical evidence suggests it struggles with trajectory stitching, a process involving the generation of an optimal or near-optimal trajectory from the best parts of a set of sub-optimal trajectories. The proposed EDT differentiates itself by facilitating trajectory stitching during action inference at test time, achieved by adjusting the history length maintained in DT. Further, the EDT optimi"},"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":"2307.02484","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-05T17:58:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"83476acb23d5e2812853e51caa513c311e496057ef5c7548246f634f985a47cf","abstract_canon_sha256":"6b11ebc75d6930c83a6c946e6d3c22d2a1a7932ac656b9424241658d8fd4e1d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:02:51.870039Z","signature_b64":"VSDwt8xNvPPSUssUeAAgJCjLlcKt0BGlhb+Qgm4EsnMGkTG7KmjSakI/rq2HBaNO8l6KH2lwA/RP4rP1VEVIBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80219ded147cf1846eda84afd831a9844bbf9bcde38a0ef2d27712607495f614","last_reissued_at":"2026-07-05T07:02:51.869609Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:02:51.869609Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Elastic Decision Transformer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Masashi Hamaya, Xiaolong Wang, Yueh-Hua Wu","submitted_at":"2023-07-05T17:58:21Z","abstract_excerpt":"This paper introduces Elastic Decision Transformer (EDT), a significant advancement over the existing Decision Transformer (DT) and its variants. Although DT purports to generate an optimal trajectory, empirical evidence suggests it struggles with trajectory stitching, a process involving the generation of an optimal or near-optimal trajectory from the best parts of a set of sub-optimal trajectories. The proposed EDT differentiates itself by facilitating trajectory stitching during action inference at test time, achieved by adjusting the history length maintained in DT. Further, the EDT optimi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.02484","kind":"arxiv","version":6},"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/2307.02484/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":"2307.02484","created_at":"2026-07-05T07:02:51.869667+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.02484v6","created_at":"2026-07-05T07:02:51.869667+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.02484","created_at":"2026-07-05T07:02:51.869667+00:00"},{"alias_kind":"pith_short_12","alias_value":"QAQZ33IUPTYY","created_at":"2026-07-05T07:02:51.869667+00:00"},{"alias_kind":"pith_short_16","alias_value":"QAQZ33IUPTYYI3W2","created_at":"2026-07-05T07:02:51.869667+00:00"},{"alias_kind":"pith_short_8","alias_value":"QAQZ33IU","created_at":"2026-07-05T07:02:51.869667+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.01862","citing_title":"QHyer: Q-conditioned Hybrid Attention-mamba Transformer for Offline Goal-conditioned RL","ref_index":207,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QAQZ33IUPTYYI3W2QSX5QMNJQR","json":"https://pith.science/pith/QAQZ33IUPTYYI3W2QSX5QMNJQR.json","graph_json":"https://pith.science/api/pith-number/QAQZ33IUPTYYI3W2QSX5QMNJQR/graph.json","events_json":"https://pith.science/api/pith-number/QAQZ33IUPTYYI3W2QSX5QMNJQR/events.json","paper":"https://pith.science/paper/QAQZ33IU"},"agent_actions":{"view_html":"https://pith.science/pith/QAQZ33IUPTYYI3W2QSX5QMNJQR","download_json":"https://pith.science/pith/QAQZ33IUPTYYI3W2QSX5QMNJQR.json","view_paper":"https://pith.science/paper/QAQZ33IU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.02484&json=true","fetch_graph":"https://pith.science/api/pith-number/QAQZ33IUPTYYI3W2QSX5QMNJQR/graph.json","fetch_events":"https://pith.science/api/pith-number/QAQZ33IUPTYYI3W2QSX5QMNJQR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QAQZ33IUPTYYI3W2QSX5QMNJQR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QAQZ33IUPTYYI3W2QSX5QMNJQR/action/storage_attestation","attest_author":"https://pith.science/pith/QAQZ33IUPTYYI3W2QSX5QMNJQR/action/author_attestation","sign_citation":"https://pith.science/pith/QAQZ33IUPTYYI3W2QSX5QMNJQR/action/citation_signature","submit_replication":"https://pith.science/pith/QAQZ33IUPTYYI3W2QSX5QMNJQR/action/replication_record"}},"created_at":"2026-07-05T07:02:51.869667+00:00","updated_at":"2026-07-05T07:02:51.869667+00:00"}