{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BLWFHEJLSJ3HIOTJFR6OMF2HSE","short_pith_number":"pith:BLWFHEJL","schema_version":"1.0","canonical_sha256":"0aec53912b9276743a692c7ce6174791208cc0978458c679971b956c1478a7cb","source":{"kind":"arxiv","id":"2512.16919","version":2},"attestation_state":"computed","paper":{"title":"DVGT: Driving Visual Geometry Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"Fang Li, Jiwen Lu, Long Chen, Shaoqing Xu, Shengyin Jiang, Sicheng Zuo, Wenzhao Zheng, Zhi-Xin Yang, Zixun Xie","submitted_at":"2025-12-18T18:59:57Z","abstract_excerpt":"Perceiving and reconstructing 3D scene geometry from visual inputs is crucial for autonomous driving. However, there still lacks a driving-targeted dense geometry perception model that can adapt to different scenarios and camera configurations. To bridge this gap, we propose a Driving Visual Geometry Transformer (DVGT), which reconstructs a global dense 3D point map from a sequence of unposed multi-view visual inputs. We first extract visual features for each image using a DINO backbone, and employ alternating intra-view local attention, cross-view spatial attention, and cross-frame temporal a"},"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":"2512.16919","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-12-18T18:59:57Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"4a5618aa0370ca02b2fec26f8f39f69b15319c8a4cf1327a4eeb99b27611a186","abstract_canon_sha256":"6eb2453232c42a25d780a4b1316d49cc38d07f73bd89d166ab4da257dd633b4f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:08:38.136865Z","signature_b64":"EpO/jmMkrURwqZUZ92Xv4OX3Qv6q/mkq4reQSBysgVSDP0IyBSgaYZqE+VecWH5KU4Z4/y8Tke3aIfeSv6PUCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0aec53912b9276743a692c7ce6174791208cc0978458c679971b956c1478a7cb","last_reissued_at":"2026-06-04T01:08:38.136356Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:08:38.136356Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DVGT: Driving Visual Geometry Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"Fang Li, Jiwen Lu, Long Chen, Shaoqing Xu, Shengyin Jiang, Sicheng Zuo, Wenzhao Zheng, Zhi-Xin Yang, Zixun Xie","submitted_at":"2025-12-18T18:59:57Z","abstract_excerpt":"Perceiving and reconstructing 3D scene geometry from visual inputs is crucial for autonomous driving. However, there still lacks a driving-targeted dense geometry perception model that can adapt to different scenarios and camera configurations. To bridge this gap, we propose a Driving Visual Geometry Transformer (DVGT), which reconstructs a global dense 3D point map from a sequence of unposed multi-view visual inputs. We first extract visual features for each image using a DINO backbone, and employ alternating intra-view local attention, cross-view spatial attention, and cross-frame temporal a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.16919","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/2512.16919/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":"2512.16919","created_at":"2026-06-04T01:08:38.136438+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.16919v2","created_at":"2026-06-04T01:08:38.136438+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.16919","created_at":"2026-06-04T01:08:38.136438+00:00"},{"alias_kind":"pith_short_12","alias_value":"BLWFHEJLSJ3H","created_at":"2026-06-04T01:08:38.136438+00:00"},{"alias_kind":"pith_short_16","alias_value":"BLWFHEJLSJ3HIOTJ","created_at":"2026-06-04T01:08:38.136438+00:00"},{"alias_kind":"pith_short_8","alias_value":"BLWFHEJL","created_at":"2026-06-04T01:08:38.136438+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2604.00813","citing_title":"DVGT-2: Vision-Geometry-Action Model for Autonomous Driving at Scale","ref_index":93,"is_internal_anchor":true},{"citing_arxiv_id":"2604.18486","citing_title":"Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation","ref_index":116,"is_internal_anchor":true},{"citing_arxiv_id":"2604.18486","citing_title":"Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation","ref_index":116,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BLWFHEJLSJ3HIOTJFR6OMF2HSE","json":"https://pith.science/pith/BLWFHEJLSJ3HIOTJFR6OMF2HSE.json","graph_json":"https://pith.science/api/pith-number/BLWFHEJLSJ3HIOTJFR6OMF2HSE/graph.json","events_json":"https://pith.science/api/pith-number/BLWFHEJLSJ3HIOTJFR6OMF2HSE/events.json","paper":"https://pith.science/paper/BLWFHEJL"},"agent_actions":{"view_html":"https://pith.science/pith/BLWFHEJLSJ3HIOTJFR6OMF2HSE","download_json":"https://pith.science/pith/BLWFHEJLSJ3HIOTJFR6OMF2HSE.json","view_paper":"https://pith.science/paper/BLWFHEJL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.16919&json=true","fetch_graph":"https://pith.science/api/pith-number/BLWFHEJLSJ3HIOTJFR6OMF2HSE/graph.json","fetch_events":"https://pith.science/api/pith-number/BLWFHEJLSJ3HIOTJFR6OMF2HSE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BLWFHEJLSJ3HIOTJFR6OMF2HSE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BLWFHEJLSJ3HIOTJFR6OMF2HSE/action/storage_attestation","attest_author":"https://pith.science/pith/BLWFHEJLSJ3HIOTJFR6OMF2HSE/action/author_attestation","sign_citation":"https://pith.science/pith/BLWFHEJLSJ3HIOTJFR6OMF2HSE/action/citation_signature","submit_replication":"https://pith.science/pith/BLWFHEJLSJ3HIOTJFR6OMF2HSE/action/replication_record"}},"created_at":"2026-06-04T01:08:38.136438+00:00","updated_at":"2026-06-04T01:08:38.136438+00:00"}