{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:AJBQR2QJALQE3XPIIERBTGSAYM","short_pith_number":"pith:AJBQR2QJ","schema_version":"1.0","canonical_sha256":"024308ea0902e04ddde84122199a40c324ef1371c7240663fbb5baa1e8d6784b","source":{"kind":"arxiv","id":"2303.03747","version":1},"attestation_state":"computed","paper":{"title":"Graph Decision Transformer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Dacheng Tao, Li Shen, Shengchao Hu, Ya Zhang","submitted_at":"2023-03-07T09:10:34Z","abstract_excerpt":"Offline reinforcement learning (RL) is a challenging task, whose objective is to learn policies from static trajectory data without interacting with the environment. Recently, offline RL has been viewed as a sequence modeling problem, where an agent generates a sequence of subsequent actions based on a set of static transition experiences. However, existing approaches that use transformers to attend to all tokens naively can overlook the dependencies between different tokens and limit long-term dependency learning. In this paper, we propose the Graph Decision Transformer (GDT), a novel offline"},"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":"2303.03747","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-07T09:10:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7a1db06dec82fe18e4e2bdab920a659d3c979e3065571d73b6fb9c0539830bf4","abstract_canon_sha256":"f7a3762b67d8d8471ee1d323b3655d08409eb3e7ce885feb02be84d816518e0a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:48:58.689580Z","signature_b64":"Tw2+a9zTEbQouiS2HEsAB/xcSTLwLb8MDJTPNJ+8oucZvO3fft5mHO3hePcAxCSuKVM6JJKxPK920RFZEKtnDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"024308ea0902e04ddde84122199a40c324ef1371c7240663fbb5baa1e8d6784b","last_reissued_at":"2026-07-05T05:48:58.689080Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:48:58.689080Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Graph Decision Transformer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Dacheng Tao, Li Shen, Shengchao Hu, Ya Zhang","submitted_at":"2023-03-07T09:10:34Z","abstract_excerpt":"Offline reinforcement learning (RL) is a challenging task, whose objective is to learn policies from static trajectory data without interacting with the environment. Recently, offline RL has been viewed as a sequence modeling problem, where an agent generates a sequence of subsequent actions based on a set of static transition experiences. However, existing approaches that use transformers to attend to all tokens naively can overlook the dependencies between different tokens and limit long-term dependency learning. In this paper, we propose the Graph Decision Transformer (GDT), a novel offline"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.03747","kind":"arxiv","version":1},"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/2303.03747/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":"2303.03747","created_at":"2026-07-05T05:48:58.689140+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.03747v1","created_at":"2026-07-05T05:48:58.689140+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.03747","created_at":"2026-07-05T05:48:58.689140+00:00"},{"alias_kind":"pith_short_12","alias_value":"AJBQR2QJALQE","created_at":"2026-07-05T05:48:58.689140+00:00"},{"alias_kind":"pith_short_16","alias_value":"AJBQR2QJALQE3XPI","created_at":"2026-07-05T05:48:58.689140+00:00"},{"alias_kind":"pith_short_8","alias_value":"AJBQR2QJ","created_at":"2026-07-05T05:48:58.689140+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.10174","citing_title":"Should We Ever Prefer Decision Transformer for Offline Reinforcement Learning?","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AJBQR2QJALQE3XPIIERBTGSAYM","json":"https://pith.science/pith/AJBQR2QJALQE3XPIIERBTGSAYM.json","graph_json":"https://pith.science/api/pith-number/AJBQR2QJALQE3XPIIERBTGSAYM/graph.json","events_json":"https://pith.science/api/pith-number/AJBQR2QJALQE3XPIIERBTGSAYM/events.json","paper":"https://pith.science/paper/AJBQR2QJ"},"agent_actions":{"view_html":"https://pith.science/pith/AJBQR2QJALQE3XPIIERBTGSAYM","download_json":"https://pith.science/pith/AJBQR2QJALQE3XPIIERBTGSAYM.json","view_paper":"https://pith.science/paper/AJBQR2QJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.03747&json=true","fetch_graph":"https://pith.science/api/pith-number/AJBQR2QJALQE3XPIIERBTGSAYM/graph.json","fetch_events":"https://pith.science/api/pith-number/AJBQR2QJALQE3XPIIERBTGSAYM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AJBQR2QJALQE3XPIIERBTGSAYM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AJBQR2QJALQE3XPIIERBTGSAYM/action/storage_attestation","attest_author":"https://pith.science/pith/AJBQR2QJALQE3XPIIERBTGSAYM/action/author_attestation","sign_citation":"https://pith.science/pith/AJBQR2QJALQE3XPIIERBTGSAYM/action/citation_signature","submit_replication":"https://pith.science/pith/AJBQR2QJALQE3XPIIERBTGSAYM/action/replication_record"}},"created_at":"2026-07-05T05:48:58.689140+00:00","updated_at":"2026-07-05T05:48:58.689140+00:00"}