{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:AP6D7QNTBSOCZTZ2FOHP46XYKU","short_pith_number":"pith:AP6D7QNT","schema_version":"1.0","canonical_sha256":"03fc3fc1b30c9c2ccf3a2b8efe7af8550b71be128ab9d0de4a591576ca57a4b7","source":{"kind":"arxiv","id":"2309.16397","version":3},"attestation_state":"computed","paper":{"title":"Uncertainty-Aware Decision Transformer for Stochastic Driving Environments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Fang Da, Fan Nie, Hang Zhao, Qiao Sun, Zenan Li","submitted_at":"2023-09-28T12:44:51Z","abstract_excerpt":"Offline Reinforcement Learning (RL) enables policy learning without active interactions, making it especially appealing for self-driving tasks. Recent successes of Transformers inspire casting offline RL as sequence modeling, which, however, fails in stochastic environments with incorrect assumptions that identical actions can consistently achieve the same goal. In this paper, we introduce an UNcertainty-awaRE deciSion Transformer (UNREST) for planning in stochastic driving environments without introducing additional transition or complex generative models. Specifically, UNREST estimates uncer"},"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":"2309.16397","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-28T12:44:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f573c42fcee87d2d4805b0f32d6956f52c3282b16e84e8933f0908ac37e37b7e","abstract_canon_sha256":"dcbf580d6482cfc001abbcb599e4e6541cdb30276761d7a5b2057bc6aee1352f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:16:44.818124Z","signature_b64":"C+KVWj2x6lKCI0/JSYnTR9kC7SgZLxwdKhczOFGYp0WMiCk0NpCb5N/9nJq9AsGSJNBXPEkt7/Be9OHWGzaMAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03fc3fc1b30c9c2ccf3a2b8efe7af8550b71be128ab9d0de4a591576ca57a4b7","last_reissued_at":"2026-07-05T09:16:44.817660Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:16:44.817660Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Uncertainty-Aware Decision Transformer for Stochastic Driving Environments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Fang Da, Fan Nie, Hang Zhao, Qiao Sun, Zenan Li","submitted_at":"2023-09-28T12:44:51Z","abstract_excerpt":"Offline Reinforcement Learning (RL) enables policy learning without active interactions, making it especially appealing for self-driving tasks. Recent successes of Transformers inspire casting offline RL as sequence modeling, which, however, fails in stochastic environments with incorrect assumptions that identical actions can consistently achieve the same goal. In this paper, we introduce an UNcertainty-awaRE deciSion Transformer (UNREST) for planning in stochastic driving environments without introducing additional transition or complex generative models. Specifically, UNREST estimates uncer"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.16397","kind":"arxiv","version":3},"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/2309.16397/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":"2309.16397","created_at":"2026-07-05T09:16:44.817721+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.16397v3","created_at":"2026-07-05T09:16:44.817721+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.16397","created_at":"2026-07-05T09:16:44.817721+00:00"},{"alias_kind":"pith_short_12","alias_value":"AP6D7QNTBSOC","created_at":"2026-07-05T09:16:44.817721+00:00"},{"alias_kind":"pith_short_16","alias_value":"AP6D7QNTBSOCZTZ2","created_at":"2026-07-05T09:16:44.817721+00:00"},{"alias_kind":"pith_short_8","alias_value":"AP6D7QNT","created_at":"2026-07-05T09:16:44.817721+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2402.12289","citing_title":"DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AP6D7QNTBSOCZTZ2FOHP46XYKU","json":"https://pith.science/pith/AP6D7QNTBSOCZTZ2FOHP46XYKU.json","graph_json":"https://pith.science/api/pith-number/AP6D7QNTBSOCZTZ2FOHP46XYKU/graph.json","events_json":"https://pith.science/api/pith-number/AP6D7QNTBSOCZTZ2FOHP46XYKU/events.json","paper":"https://pith.science/paper/AP6D7QNT"},"agent_actions":{"view_html":"https://pith.science/pith/AP6D7QNTBSOCZTZ2FOHP46XYKU","download_json":"https://pith.science/pith/AP6D7QNTBSOCZTZ2FOHP46XYKU.json","view_paper":"https://pith.science/paper/AP6D7QNT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.16397&json=true","fetch_graph":"https://pith.science/api/pith-number/AP6D7QNTBSOCZTZ2FOHP46XYKU/graph.json","fetch_events":"https://pith.science/api/pith-number/AP6D7QNTBSOCZTZ2FOHP46XYKU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AP6D7QNTBSOCZTZ2FOHP46XYKU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AP6D7QNTBSOCZTZ2FOHP46XYKU/action/storage_attestation","attest_author":"https://pith.science/pith/AP6D7QNTBSOCZTZ2FOHP46XYKU/action/author_attestation","sign_citation":"https://pith.science/pith/AP6D7QNTBSOCZTZ2FOHP46XYKU/action/citation_signature","submit_replication":"https://pith.science/pith/AP6D7QNTBSOCZTZ2FOHP46XYKU/action/replication_record"}},"created_at":"2026-07-05T09:16:44.817721+00:00","updated_at":"2026-07-05T09:16:44.817721+00:00"}