{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PYCLCPJ34J45V7733UGCBV75PG","short_pith_number":"pith:PYCLCPJ3","schema_version":"1.0","canonical_sha256":"7e04b13d3be279dafffbdd0c20d7fd798a70e3bf6a9665d9462e7a1863ba8e0a","source":{"kind":"arxiv","id":"2502.20108","version":2},"attestation_state":"computed","paper":{"title":"VDT-Auto: End-to-end Autonomous Driving with VLM-Guided Diffusion Transformers","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Dzmitry Tsetserukou, Konstantin Gubernatorov, Selamawit Asfaw, Zakhar Yagudin, Ziang Guo","submitted_at":"2025-02-27T14:02:14Z","abstract_excerpt":"In autonomous driving, dynamic environment and corner cases pose significant challenges to the robustness of ego vehicle's decision-making. To address these challenges, commencing with the representation of state-action mapping in the end-to-end autonomous driving paradigm, we introduce a novel pipeline, VDT-Auto. Leveraging the advancement of the state understanding of Visual Language Model (VLM), incorporating with diffusion Transformer-based action generation, our VDT-Auto parses the environment geometrically and contextually for the conditioning of the diffusion process. Geometrically, we "},"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":"2502.20108","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-27T14:02:14Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"e6c9520ad5fba4af5b59aa23381825caf5330db0b776107bd67b9ba997b182a6","abstract_canon_sha256":"52e253d4f103ac42b8e111f1d20442c103de4b3d3f33d61f822d19043385320a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:22:15.654569Z","signature_b64":"HoUKxyJWjh+fH2uP4wVHY7XSyVd0bdp89zPa6hTWXoWNlOUq4S0mtreP689dQoUUQcyCs5RvZ7HbYuADCUXoBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e04b13d3be279dafffbdd0c20d7fd798a70e3bf6a9665d9462e7a1863ba8e0a","last_reissued_at":"2026-07-05T10:22:15.654039Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:22:15.654039Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VDT-Auto: End-to-end Autonomous Driving with VLM-Guided Diffusion Transformers","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Dzmitry Tsetserukou, Konstantin Gubernatorov, Selamawit Asfaw, Zakhar Yagudin, Ziang Guo","submitted_at":"2025-02-27T14:02:14Z","abstract_excerpt":"In autonomous driving, dynamic environment and corner cases pose significant challenges to the robustness of ego vehicle's decision-making. To address these challenges, commencing with the representation of state-action mapping in the end-to-end autonomous driving paradigm, we introduce a novel pipeline, VDT-Auto. Leveraging the advancement of the state understanding of Visual Language Model (VLM), incorporating with diffusion Transformer-based action generation, our VDT-Auto parses the environment geometrically and contextually for the conditioning of the diffusion process. Geometrically, we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.20108","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/2502.20108/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":"2502.20108","created_at":"2026-07-05T10:22:15.654112+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.20108v2","created_at":"2026-07-05T10:22:15.654112+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.20108","created_at":"2026-07-05T10:22:15.654112+00:00"},{"alias_kind":"pith_short_12","alias_value":"PYCLCPJ34J45","created_at":"2026-07-05T10:22:15.654112+00:00"},{"alias_kind":"pith_short_16","alias_value":"PYCLCPJ34J45V773","created_at":"2026-07-05T10:22:15.654112+00:00"},{"alias_kind":"pith_short_8","alias_value":"PYCLCPJ3","created_at":"2026-07-05T10:22:15.654112+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.20082","citing_title":"VL-DPO: Vision-Language-Guided Finetuning for Preference-Aligned Autonomous Driving","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2507.04049","citing_title":"DIVER: Reinforced Diffusion Breaks Imitation Bottlenecks in End-to-End Autonomous Driving","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PYCLCPJ34J45V7733UGCBV75PG","json":"https://pith.science/pith/PYCLCPJ34J45V7733UGCBV75PG.json","graph_json":"https://pith.science/api/pith-number/PYCLCPJ34J45V7733UGCBV75PG/graph.json","events_json":"https://pith.science/api/pith-number/PYCLCPJ34J45V7733UGCBV75PG/events.json","paper":"https://pith.science/paper/PYCLCPJ3"},"agent_actions":{"view_html":"https://pith.science/pith/PYCLCPJ34J45V7733UGCBV75PG","download_json":"https://pith.science/pith/PYCLCPJ34J45V7733UGCBV75PG.json","view_paper":"https://pith.science/paper/PYCLCPJ3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.20108&json=true","fetch_graph":"https://pith.science/api/pith-number/PYCLCPJ34J45V7733UGCBV75PG/graph.json","fetch_events":"https://pith.science/api/pith-number/PYCLCPJ34J45V7733UGCBV75PG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PYCLCPJ34J45V7733UGCBV75PG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PYCLCPJ34J45V7733UGCBV75PG/action/storage_attestation","attest_author":"https://pith.science/pith/PYCLCPJ34J45V7733UGCBV75PG/action/author_attestation","sign_citation":"https://pith.science/pith/PYCLCPJ34J45V7733UGCBV75PG/action/citation_signature","submit_replication":"https://pith.science/pith/PYCLCPJ34J45V7733UGCBV75PG/action/replication_record"}},"created_at":"2026-07-05T10:22:15.654112+00:00","updated_at":"2026-07-05T10:22:15.654112+00:00"}