{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AZBENW3562PNJ6BHRL5C545GXQ","short_pith_number":"pith:AZBENW35","schema_version":"1.0","canonical_sha256":"064246db7df69ed4f8278afa2ef3a6bc23c190580586892597afcf3ee9426980","source":{"kind":"arxiv","id":"2412.08643","version":1},"attestation_state":"computed","paper":{"title":"GPD-1: Generative Pre-training for Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Dalong Du, Jie Zhou, Jiwen Lu, Shanghang Zhang, Sicheng Zuo, Wenzhao Zheng, Yunpeng Zhang, Zixun Xie","submitted_at":"2024-12-11T18:59:51Z","abstract_excerpt":"Modeling the evolutions of driving scenarios is important for the evaluation and decision-making of autonomous driving systems. Most existing methods focus on one aspect of scene evolution such as map generation, motion prediction, and trajectory planning. In this paper, we propose a unified Generative Pre-training for Driving (GPD-1) model to accomplish all these tasks altogether without additional fine-tuning. We represent each scene with ego, agent, and map tokens and formulate autonomous driving as a unified token generation problem. We adopt the autoregressive transformer architecture and"},"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":"2412.08643","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-11T18:59:51Z","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"title_canon_sha256":"d425727a0655bd905c8431a9097c27c8c64fe62fbdde97ba3073a36831f9fbf3","abstract_canon_sha256":"a425d80180260d06f80c7e952eee48dd37340c200c95e9dae9c85de3a4ec514d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:47:52.852756Z","signature_b64":"osYc5otDmm+qMQrjwfeuhjLDhRdYEhDndYiey/018cvRYwioj9GmIhczMh8rDdjG+SXPB/O9skixUeGWx+kgDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"064246db7df69ed4f8278afa2ef3a6bc23c190580586892597afcf3ee9426980","last_reissued_at":"2026-07-05T09:47:52.852270Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:47:52.852270Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GPD-1: Generative Pre-training for Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Dalong Du, Jie Zhou, Jiwen Lu, Shanghang Zhang, Sicheng Zuo, Wenzhao Zheng, Yunpeng Zhang, Zixun Xie","submitted_at":"2024-12-11T18:59:51Z","abstract_excerpt":"Modeling the evolutions of driving scenarios is important for the evaluation and decision-making of autonomous driving systems. Most existing methods focus on one aspect of scene evolution such as map generation, motion prediction, and trajectory planning. In this paper, we propose a unified Generative Pre-training for Driving (GPD-1) model to accomplish all these tasks altogether without additional fine-tuning. We represent each scene with ego, agent, and map tokens and formulate autonomous driving as a unified token generation problem. We adopt the autoregressive transformer architecture and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.08643","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/2412.08643/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":"2412.08643","created_at":"2026-07-05T09:47:52.852341+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.08643v1","created_at":"2026-07-05T09:47:52.852341+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.08643","created_at":"2026-07-05T09:47:52.852341+00:00"},{"alias_kind":"pith_short_12","alias_value":"AZBENW3562PN","created_at":"2026-07-05T09:47:52.852341+00:00"},{"alias_kind":"pith_short_16","alias_value":"AZBENW3562PNJ6BH","created_at":"2026-07-05T09:47:52.852341+00:00"},{"alias_kind":"pith_short_8","alias_value":"AZBENW35","created_at":"2026-07-05T09:47:52.852341+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.10371","citing_title":"GaussianAD: Gaussian-Centric End-to-End Autonomous Driving","ref_index":58,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AZBENW3562PNJ6BHRL5C545GXQ","json":"https://pith.science/pith/AZBENW3562PNJ6BHRL5C545GXQ.json","graph_json":"https://pith.science/api/pith-number/AZBENW3562PNJ6BHRL5C545GXQ/graph.json","events_json":"https://pith.science/api/pith-number/AZBENW3562PNJ6BHRL5C545GXQ/events.json","paper":"https://pith.science/paper/AZBENW35"},"agent_actions":{"view_html":"https://pith.science/pith/AZBENW3562PNJ6BHRL5C545GXQ","download_json":"https://pith.science/pith/AZBENW3562PNJ6BHRL5C545GXQ.json","view_paper":"https://pith.science/paper/AZBENW35","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.08643&json=true","fetch_graph":"https://pith.science/api/pith-number/AZBENW3562PNJ6BHRL5C545GXQ/graph.json","fetch_events":"https://pith.science/api/pith-number/AZBENW3562PNJ6BHRL5C545GXQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AZBENW3562PNJ6BHRL5C545GXQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AZBENW3562PNJ6BHRL5C545GXQ/action/storage_attestation","attest_author":"https://pith.science/pith/AZBENW3562PNJ6BHRL5C545GXQ/action/author_attestation","sign_citation":"https://pith.science/pith/AZBENW3562PNJ6BHRL5C545GXQ/action/citation_signature","submit_replication":"https://pith.science/pith/AZBENW3562PNJ6BHRL5C545GXQ/action/replication_record"}},"created_at":"2026-07-05T09:47:52.852341+00:00","updated_at":"2026-07-05T09:47:52.852341+00:00"}