{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7WXXNOR5XM5OMTL5UAAAVXTMIL","short_pith_number":"pith:7WXXNOR5","schema_version":"1.0","canonical_sha256":"fdaf76ba3dbb3ae64d7da0000ade6c42dfa82059d87cbbc29b103bcb1b22c58a","source":{"kind":"arxiv","id":"2608.13147","version":1},"attestation_state":"computed","paper":{"title":"Geometry-Grounded Unified 3D Perception for Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Han Li, Longfei Xu, Naiyan Wang, Si Liu, Xiaohui Wang, Ya Yang, Zehao Huang","submitted_at":"2026-08-13T12:17:50Z","abstract_excerpt":"Camera-based autonomous driving perception requires a shared representation that preserves metric 3D structure across synchronized multi-camera streams. However, existing image-based frameworks often rely on backbones pretrained for semantic recognition, and introduce 3D geometry through downstream task-specific modules. As a result, their shared representations may fail to preserve explicit metric geometry and consistent 3D scene structure. In this paper, we present a Geometry-grounded Unified 3D Perception (GeoUP) framework that adapts the reconstruction-oriented latent of VGGT to calibrated"},"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":"2608.13147","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-13T12:17:50Z","cross_cats_sorted":[],"title_canon_sha256":"d495998ed16df6e6f2ed6174914585796a6272fbc89199c62f3f454bb4b35253","abstract_canon_sha256":"7e124a1f41d32e7a6c086fa4194a7bb8a63f18f40bd4a11d9eaa86ae9a97c1bb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-14T01:00:29.140749Z","signature_b64":"HgIse2Nks7FGbKXhM3LmlPnzoXhrlrylPAduOatj3HsqfMbaZfhw6mZCrOZJtZqoEh/PAsPhvk3tK+H6m+beDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fdaf76ba3dbb3ae64d7da0000ade6c42dfa82059d87cbbc29b103bcb1b22c58a","last_reissued_at":"2026-08-14T01:00:29.138795Z","signature_status":"signed_v1","first_computed_at":"2026-08-14T01:00:29.138795Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Geometry-Grounded Unified 3D Perception for Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Han Li, Longfei Xu, Naiyan Wang, Si Liu, Xiaohui Wang, Ya Yang, Zehao Huang","submitted_at":"2026-08-13T12:17:50Z","abstract_excerpt":"Camera-based autonomous driving perception requires a shared representation that preserves metric 3D structure across synchronized multi-camera streams. However, existing image-based frameworks often rely on backbones pretrained for semantic recognition, and introduce 3D geometry through downstream task-specific modules. As a result, their shared representations may fail to preserve explicit metric geometry and consistent 3D scene structure. In this paper, we present a Geometry-grounded Unified 3D Perception (GeoUP) framework that adapts the reconstruction-oriented latent of VGGT to calibrated"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.13147","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/2608.13147/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":"2608.13147","created_at":"2026-08-14T01:00:29.139771+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.13147v1","created_at":"2026-08-14T01:00:29.139771+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.13147","created_at":"2026-08-14T01:00:29.139771+00:00"},{"alias_kind":"pith_short_12","alias_value":"7WXXNOR5XM5O","created_at":"2026-08-14T01:00:29.139771+00:00"},{"alias_kind":"pith_short_16","alias_value":"7WXXNOR5XM5OMTL5","created_at":"2026-08-14T01:00:29.139771+00:00"},{"alias_kind":"pith_short_8","alias_value":"7WXXNOR5","created_at":"2026-08-14T01:00:29.139771+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7WXXNOR5XM5OMTL5UAAAVXTMIL","json":"https://pith.science/pith/7WXXNOR5XM5OMTL5UAAAVXTMIL.json","graph_json":"https://pith.science/api/pith-number/7WXXNOR5XM5OMTL5UAAAVXTMIL/graph.json","events_json":"https://pith.science/api/pith-number/7WXXNOR5XM5OMTL5UAAAVXTMIL/events.json","paper":"https://pith.science/paper/7WXXNOR5"},"agent_actions":{"view_html":"https://pith.science/pith/7WXXNOR5XM5OMTL5UAAAVXTMIL","download_json":"https://pith.science/pith/7WXXNOR5XM5OMTL5UAAAVXTMIL.json","view_paper":"https://pith.science/paper/7WXXNOR5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.13147&json=true","fetch_graph":"https://pith.science/api/pith-number/7WXXNOR5XM5OMTL5UAAAVXTMIL/graph.json","fetch_events":"https://pith.science/api/pith-number/7WXXNOR5XM5OMTL5UAAAVXTMIL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7WXXNOR5XM5OMTL5UAAAVXTMIL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7WXXNOR5XM5OMTL5UAAAVXTMIL/action/storage_attestation","attest_author":"https://pith.science/pith/7WXXNOR5XM5OMTL5UAAAVXTMIL/action/author_attestation","sign_citation":"https://pith.science/pith/7WXXNOR5XM5OMTL5UAAAVXTMIL/action/citation_signature","submit_replication":"https://pith.science/pith/7WXXNOR5XM5OMTL5UAAAVXTMIL/action/replication_record"}},"created_at":"2026-08-14T01:00:29.139771+00:00","updated_at":"2026-08-14T01:00:29.139771+00:00"}