{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XRYDTC3B3CFABD5R3YAUQ3TUA7","short_pith_number":"pith:XRYDTC3B","schema_version":"1.0","canonical_sha256":"bc70398b61d88a008fb1de01486e7407e2759f19806641ae1346847be5a1aa74","source":{"kind":"arxiv","id":"2505.01857","version":1},"attestation_state":"computed","paper":{"title":"DualDiff: Dual-branch Diffusion Model for Autonomous Driving with Semantic Fusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gongpeng Zhao, Haoteng Li, Huazheng Zhou, Jun Yu, Longjun Liu, Yuqi Huang, Zezhong Qian, Zhao Yang","submitted_at":"2025-05-03T16:20:01Z","abstract_excerpt":"Accurate and high-fidelity driving scene reconstruction relies on fully leveraging scene information as conditioning. However, existing approaches, which primarily use 3D bounding boxes and binary maps for foreground and background control, fall short in capturing the complexity of the scene and integrating multi-modal information. In this paper, we propose DualDiff, a dual-branch conditional diffusion model designed to enhance multi-view driving scene generation. We introduce Occupancy Ray Sampling (ORS), a semantic-rich 3D representation, alongside numerical driving scene representation, for"},"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":"2505.01857","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-03T16:20:01Z","cross_cats_sorted":[],"title_canon_sha256":"ace180fe244dc551634eefbd3cf14f4225641262483641ff576cb473065216d5","abstract_canon_sha256":"33d1b9eb8481e744f2b7fe70b917c2ffbdff2370fd00d1e0d5b1947f8b29e670"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:58:06.105721Z","signature_b64":"PvjBPfvoGCPwx/7tuGtx2zxxqOtZxUU459Gk0kkAyJfoienaMPlwCksg5x6yMUdmQrEgTEDjUgEjs3iXi5LuCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc70398b61d88a008fb1de01486e7407e2759f19806641ae1346847be5a1aa74","last_reissued_at":"2026-07-05T10:58:06.105198Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:58:06.105198Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DualDiff: Dual-branch Diffusion Model for Autonomous Driving with Semantic Fusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gongpeng Zhao, Haoteng Li, Huazheng Zhou, Jun Yu, Longjun Liu, Yuqi Huang, Zezhong Qian, Zhao Yang","submitted_at":"2025-05-03T16:20:01Z","abstract_excerpt":"Accurate and high-fidelity driving scene reconstruction relies on fully leveraging scene information as conditioning. However, existing approaches, which primarily use 3D bounding boxes and binary maps for foreground and background control, fall short in capturing the complexity of the scene and integrating multi-modal information. In this paper, we propose DualDiff, a dual-branch conditional diffusion model designed to enhance multi-view driving scene generation. We introduce Occupancy Ray Sampling (ORS), a semantic-rich 3D representation, alongside numerical driving scene representation, for"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.01857","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/2505.01857/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":"2505.01857","created_at":"2026-07-05T10:58:06.105266+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.01857v1","created_at":"2026-07-05T10:58:06.105266+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.01857","created_at":"2026-07-05T10:58:06.105266+00:00"},{"alias_kind":"pith_short_12","alias_value":"XRYDTC3B3CFA","created_at":"2026-07-05T10:58:06.105266+00:00"},{"alias_kind":"pith_short_16","alias_value":"XRYDTC3B3CFABD5R","created_at":"2026-07-05T10:58:06.105266+00:00"},{"alias_kind":"pith_short_8","alias_value":"XRYDTC3B","created_at":"2026-07-05T10:58:06.105266+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"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":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XRYDTC3B3CFABD5R3YAUQ3TUA7","json":"https://pith.science/pith/XRYDTC3B3CFABD5R3YAUQ3TUA7.json","graph_json":"https://pith.science/api/pith-number/XRYDTC3B3CFABD5R3YAUQ3TUA7/graph.json","events_json":"https://pith.science/api/pith-number/XRYDTC3B3CFABD5R3YAUQ3TUA7/events.json","paper":"https://pith.science/paper/XRYDTC3B"},"agent_actions":{"view_html":"https://pith.science/pith/XRYDTC3B3CFABD5R3YAUQ3TUA7","download_json":"https://pith.science/pith/XRYDTC3B3CFABD5R3YAUQ3TUA7.json","view_paper":"https://pith.science/paper/XRYDTC3B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.01857&json=true","fetch_graph":"https://pith.science/api/pith-number/XRYDTC3B3CFABD5R3YAUQ3TUA7/graph.json","fetch_events":"https://pith.science/api/pith-number/XRYDTC3B3CFABD5R3YAUQ3TUA7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XRYDTC3B3CFABD5R3YAUQ3TUA7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XRYDTC3B3CFABD5R3YAUQ3TUA7/action/storage_attestation","attest_author":"https://pith.science/pith/XRYDTC3B3CFABD5R3YAUQ3TUA7/action/author_attestation","sign_citation":"https://pith.science/pith/XRYDTC3B3CFABD5R3YAUQ3TUA7/action/citation_signature","submit_replication":"https://pith.science/pith/XRYDTC3B3CFABD5R3YAUQ3TUA7/action/replication_record"}},"created_at":"2026-07-05T10:58:06.105266+00:00","updated_at":"2026-07-05T10:58:06.105266+00:00"}