{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6EGBMZGVNPDFP2WEJSP65GHTQ7","short_pith_number":"pith:6EGBMZGV","schema_version":"1.0","canonical_sha256":"f10c1664d56bc657eac44c9fee98f387ff6fc77403bcf9cb84a1cf20ea82997f","source":{"kind":"arxiv","id":"2607.12214","version":1},"attestation_state":"computed","paper":{"title":"Beyond Perfect Priors: Adaptive Gaussian Graph for 4D Driving Reconstruction in the Wild","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jen-Ming Wu, Jianping Wang, Qian Xu, Xiaoyun Dong, Yang Lu, Yun Wang","submitted_at":"2026-07-07T04:35:58Z","abstract_excerpt":"Reconstructing 4D driving scenes in the wild (e.g., internet and AI-generated videos) is critical for diverse autonomous driving simulation. While recent Gaussian Scene Graph (GSG) methods achieve impressive visual quality, they heavily rely on precise priors, such as accurate camera poses and LiDAR depth, or manual annotations. When initialized with noisy priors estimated from in-the-wild videos, existing GSG methods suffer from optimization ambiguity (e.g., entangling camera and agent poses) and topological failures (e.g., missing objects), causing severe rendering artifacts. To enable robus"},"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":"2607.12214","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-07T04:35:58Z","cross_cats_sorted":[],"title_canon_sha256":"9e9a6c4e088e0df86befd1163fae1944ff1f826810b2ac5d59ce7c8f3f4538e7","abstract_canon_sha256":"4b19eb19d778aa6d8a669bbb038e148d15a34975743902e7ee3b018e804e89e7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-15T00:21:38.937573Z","signature_b64":"/KfmgN6D3G/In7HCTL5bBA7L5Q5pPCn8itGiXg7RnzpgrIBUiJBRQ6syPeApy00D/O38SkJZ+Fq/E7DHgNASBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f10c1664d56bc657eac44c9fee98f387ff6fc77403bcf9cb84a1cf20ea82997f","last_reissued_at":"2026-07-15T00:21:38.936809Z","signature_status":"signed_v1","first_computed_at":"2026-07-15T00:21:38.936809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Perfect Priors: Adaptive Gaussian Graph for 4D Driving Reconstruction in the Wild","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jen-Ming Wu, Jianping Wang, Qian Xu, Xiaoyun Dong, Yang Lu, Yun Wang","submitted_at":"2026-07-07T04:35:58Z","abstract_excerpt":"Reconstructing 4D driving scenes in the wild (e.g., internet and AI-generated videos) is critical for diverse autonomous driving simulation. While recent Gaussian Scene Graph (GSG) methods achieve impressive visual quality, they heavily rely on precise priors, such as accurate camera poses and LiDAR depth, or manual annotations. When initialized with noisy priors estimated from in-the-wild videos, existing GSG methods suffer from optimization ambiguity (e.g., entangling camera and agent poses) and topological failures (e.g., missing objects), causing severe rendering artifacts. To enable robus"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.12214","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/2607.12214/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":"2607.12214","created_at":"2026-07-15T00:21:38.937234+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.12214v1","created_at":"2026-07-15T00:21:38.937234+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.12214","created_at":"2026-07-15T00:21:38.937234+00:00"},{"alias_kind":"pith_short_12","alias_value":"6EGBMZGVNPDF","created_at":"2026-07-15T00:21:38.937234+00:00"},{"alias_kind":"pith_short_16","alias_value":"6EGBMZGVNPDFP2WE","created_at":"2026-07-15T00:21:38.937234+00:00"},{"alias_kind":"pith_short_8","alias_value":"6EGBMZGV","created_at":"2026-07-15T00:21:38.937234+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/6EGBMZGVNPDFP2WEJSP65GHTQ7","json":"https://pith.science/pith/6EGBMZGVNPDFP2WEJSP65GHTQ7.json","graph_json":"https://pith.science/api/pith-number/6EGBMZGVNPDFP2WEJSP65GHTQ7/graph.json","events_json":"https://pith.science/api/pith-number/6EGBMZGVNPDFP2WEJSP65GHTQ7/events.json","paper":"https://pith.science/paper/6EGBMZGV"},"agent_actions":{"view_html":"https://pith.science/pith/6EGBMZGVNPDFP2WEJSP65GHTQ7","download_json":"https://pith.science/pith/6EGBMZGVNPDFP2WEJSP65GHTQ7.json","view_paper":"https://pith.science/paper/6EGBMZGV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.12214&json=true","fetch_graph":"https://pith.science/api/pith-number/6EGBMZGVNPDFP2WEJSP65GHTQ7/graph.json","fetch_events":"https://pith.science/api/pith-number/6EGBMZGVNPDFP2WEJSP65GHTQ7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6EGBMZGVNPDFP2WEJSP65GHTQ7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6EGBMZGVNPDFP2WEJSP65GHTQ7/action/storage_attestation","attest_author":"https://pith.science/pith/6EGBMZGVNPDFP2WEJSP65GHTQ7/action/author_attestation","sign_citation":"https://pith.science/pith/6EGBMZGVNPDFP2WEJSP65GHTQ7/action/citation_signature","submit_replication":"https://pith.science/pith/6EGBMZGVNPDFP2WEJSP65GHTQ7/action/replication_record"}},"created_at":"2026-07-15T00:21:38.937234+00:00","updated_at":"2026-07-15T00:21:38.937234+00:00"}