{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HS6GJMBNHQ4NJT53XRBMHJOJ6N","short_pith_number":"pith:HS6GJMBN","schema_version":"1.0","canonical_sha256":"3cbc64b02d3c38d4cfbbbc42c3a5c9f3419e7788e1dd220219a372394203f0dd","source":{"kind":"arxiv","id":"2503.15208","version":1},"attestation_state":"computed","paper":{"title":"DiST-4D: Disentangled Spatiotemporal Diffusion with Metric Depth for 4D Driving Scene Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bohan Li, Feiyang Tan, Hao Zhao, Jiazhe Guo, Shuo Chen, Xiaojuan Qi, Xiaoyang Lyu, Xiwu Chen, Yikang Ding, Yingshuang Zou, Zhiheng Li","submitted_at":"2025-03-19T13:49:48Z","abstract_excerpt":"Current generative models struggle to synthesize dynamic 4D driving scenes that simultaneously support temporal extrapolation and spatial novel view synthesis (NVS) without per-scene optimization. A key challenge lies in finding an efficient and generalizable geometric representation that seamlessly connects temporal and spatial synthesis. To address this, we propose DiST-4D, the first disentangled spatiotemporal diffusion framework for 4D driving scene generation, which leverages metric depth as the core geometric representation. DiST-4D decomposes the problem into two diffusion processes: Di"},"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":"2503.15208","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-19T13:49:48Z","cross_cats_sorted":[],"title_canon_sha256":"c64ee3ce137e3acb05da64c43a5cb8804eff040358efa049511307e4987b27df","abstract_canon_sha256":"920d229e7b535822eb5a36677ae2ddfc6cc02f94882208aa07ec2aaff213cee9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:34:48.517796Z","signature_b64":"eeDbygOijsB0BJzrtmAcTSmuzuFBdRmf0NSeJgLj9vn3gGQHOS6FzBWXNlIqJyxRjaO8SQ5JOKd+0SzIVZccBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3cbc64b02d3c38d4cfbbbc42c3a5c9f3419e7788e1dd220219a372394203f0dd","last_reissued_at":"2026-07-05T10:34:48.517303Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:34:48.517303Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DiST-4D: Disentangled Spatiotemporal Diffusion with Metric Depth for 4D Driving Scene Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bohan Li, Feiyang Tan, Hao Zhao, Jiazhe Guo, Shuo Chen, Xiaojuan Qi, Xiaoyang Lyu, Xiwu Chen, Yikang Ding, Yingshuang Zou, Zhiheng Li","submitted_at":"2025-03-19T13:49:48Z","abstract_excerpt":"Current generative models struggle to synthesize dynamic 4D driving scenes that simultaneously support temporal extrapolation and spatial novel view synthesis (NVS) without per-scene optimization. A key challenge lies in finding an efficient and generalizable geometric representation that seamlessly connects temporal and spatial synthesis. To address this, we propose DiST-4D, the first disentangled spatiotemporal diffusion framework for 4D driving scene generation, which leverages metric depth as the core geometric representation. DiST-4D decomposes the problem into two diffusion processes: Di"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.15208","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/2503.15208/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":"2503.15208","created_at":"2026-07-05T10:34:48.517366+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.15208v1","created_at":"2026-07-05T10:34:48.517366+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.15208","created_at":"2026-07-05T10:34:48.517366+00:00"},{"alias_kind":"pith_short_12","alias_value":"HS6GJMBNHQ4N","created_at":"2026-07-05T10:34:48.517366+00:00"},{"alias_kind":"pith_short_16","alias_value":"HS6GJMBNHQ4NJT53","created_at":"2026-07-05T10:34:48.517366+00:00"},{"alias_kind":"pith_short_8","alias_value":"HS6GJMBN","created_at":"2026-07-05T10:34:48.517366+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20110","citing_title":"FrozenDrive: Zero-Shot Text-Guided Driving Scene Generation and Data Augmentation with Parameter-Free Frozen Diffusion Model","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2512.23180","citing_title":"GaussianDWM: 3D Gaussian Driving World Model for Unified Scene Understanding and Multi-Modal Generation","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2512.23421","citing_title":"DriveLaW:Unifying Planning and Video Generation in a Latent Driving World","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08712","citing_title":"From Articulated Kinematics to Routed Visual Control for Action-Conditioned Surgical Video Generation","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06658","citing_title":"Relit-LiVE: Relight Video by Jointly Learning Environment Video","ref_index":106,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HS6GJMBNHQ4NJT53XRBMHJOJ6N","json":"https://pith.science/pith/HS6GJMBNHQ4NJT53XRBMHJOJ6N.json","graph_json":"https://pith.science/api/pith-number/HS6GJMBNHQ4NJT53XRBMHJOJ6N/graph.json","events_json":"https://pith.science/api/pith-number/HS6GJMBNHQ4NJT53XRBMHJOJ6N/events.json","paper":"https://pith.science/paper/HS6GJMBN"},"agent_actions":{"view_html":"https://pith.science/pith/HS6GJMBNHQ4NJT53XRBMHJOJ6N","download_json":"https://pith.science/pith/HS6GJMBNHQ4NJT53XRBMHJOJ6N.json","view_paper":"https://pith.science/paper/HS6GJMBN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.15208&json=true","fetch_graph":"https://pith.science/api/pith-number/HS6GJMBNHQ4NJT53XRBMHJOJ6N/graph.json","fetch_events":"https://pith.science/api/pith-number/HS6GJMBNHQ4NJT53XRBMHJOJ6N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HS6GJMBNHQ4NJT53XRBMHJOJ6N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HS6GJMBNHQ4NJT53XRBMHJOJ6N/action/storage_attestation","attest_author":"https://pith.science/pith/HS6GJMBNHQ4NJT53XRBMHJOJ6N/action/author_attestation","sign_citation":"https://pith.science/pith/HS6GJMBNHQ4NJT53XRBMHJOJ6N/action/citation_signature","submit_replication":"https://pith.science/pith/HS6GJMBNHQ4NJT53XRBMHJOJ6N/action/replication_record"}},"created_at":"2026-07-05T10:34:48.517366+00:00","updated_at":"2026-07-05T10:34:48.517366+00:00"}