{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MVIYLLK7EGIVM2ZEGII4QE74TD","short_pith_number":"pith:MVIYLLK7","schema_version":"1.0","canonical_sha256":"655185ad5f2191566b243211c813fc98c65a8c3a24f238cb5bb89920d7022d1f","source":{"kind":"arxiv","id":"2410.10429","version":1},"attestation_state":"computed","paper":{"title":"DOME: Taming Diffusion Model into High-Fidelity Controllable Occupancy World Model","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bu Jin, Haodong Li, Junming Wang, Qian Zhang, Songen Gu, Wei Yin, Xiaoxiao Long, Xiaoyang Guo","submitted_at":"2024-10-14T12:24:32Z","abstract_excerpt":"We propose DOME, a diffusion-based world model that predicts future occupancy frames based on past occupancy observations. The ability of this world model to capture the evolution of the environment is crucial for planning in autonomous driving. Compared to 2D video-based world models, the occupancy world model utilizes a native 3D representation, which features easily obtainable annotations and is modality-agnostic. This flexibility has the potential to facilitate the development of more advanced world models. Existing occupancy world models either suffer from detail loss due to discrete toke"},"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":"2410.10429","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-14T12:24:32Z","cross_cats_sorted":[],"title_canon_sha256":"74f9a18bc2a5f937b2cb483d1e00b0361de6900c3fedbbce01d6e50178e0b30c","abstract_canon_sha256":"6f41fb7818ed5e34f0705a60784ce5c7bd51a40fc0592aebfbcd99fbc0a4d333"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:20:16.182932Z","signature_b64":"Zy/Xa3Yee6XY3NP5U5l0OQO5O7KmN94/I00qpJ9KA2HN5iDkZJWA6khgpC6g6fRL1hJzyALDVmIoBVDLIeBVDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"655185ad5f2191566b243211c813fc98c65a8c3a24f238cb5bb89920d7022d1f","last_reissued_at":"2026-07-05T09:20:16.182511Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:20:16.182511Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DOME: Taming Diffusion Model into High-Fidelity Controllable Occupancy World Model","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bu Jin, Haodong Li, Junming Wang, Qian Zhang, Songen Gu, Wei Yin, Xiaoxiao Long, Xiaoyang Guo","submitted_at":"2024-10-14T12:24:32Z","abstract_excerpt":"We propose DOME, a diffusion-based world model that predicts future occupancy frames based on past occupancy observations. The ability of this world model to capture the evolution of the environment is crucial for planning in autonomous driving. Compared to 2D video-based world models, the occupancy world model utilizes a native 3D representation, which features easily obtainable annotations and is modality-agnostic. This flexibility has the potential to facilitate the development of more advanced world models. Existing occupancy world models either suffer from detail loss due to discrete toke"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.10429","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/2410.10429/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":"2410.10429","created_at":"2026-07-05T09:20:16.182567+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.10429v1","created_at":"2026-07-05T09:20:16.182567+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.10429","created_at":"2026-07-05T09:20:16.182567+00:00"},{"alias_kind":"pith_short_12","alias_value":"MVIYLLK7EGIV","created_at":"2026-07-05T09:20:16.182567+00:00"},{"alias_kind":"pith_short_16","alias_value":"MVIYLLK7EGIVM2ZE","created_at":"2026-07-05T09:20:16.182567+00:00"},{"alias_kind":"pith_short_8","alias_value":"MVIYLLK7","created_at":"2026-07-05T09:20:16.182567+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20189","citing_title":"HilDA: Hierarchical Distillation with Diffusion for Advancing Self-Supervised LiDAR Pre-training","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30421","citing_title":"OWMDrive: Causality-Aware End-to-End Autonomous Driving via 4D Occupancy World Model","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26113","citing_title":"AnyScene: Towards Highly Controllable Driving Scene Generation at Anywhere and Beyond","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27038","citing_title":"TPS-Drive: Task-Guided Representation Purification for VLM-based Autonomous Driving","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2504.18576","citing_title":"DriVerse: Navigation World Model for Driving Simulation via Multimodal Trajectory Prompting and Motion Alignment","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2512.01030","citing_title":"Lotus-2: Advancing Geometric Dense Prediction with Powerful Image Generative Model","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17682","citing_title":"GEM: Gaussian Evolution Model for Occupancy Forecasting and Motion Planning","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2511.22039","citing_title":"SparseWorld-TC: Trajectory-Conditioned Sparse Occupancy World Model","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2602.07775","citing_title":"Rolling Sink: Bridging Limited-Horizon Training and Open-Ended Testing in Autoregressive Video Diffusion","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.28196","citing_title":"HERMES++: Toward a Unified Driving World Model for 3D Scene Understanding and Generation","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12857","citing_title":"Artificial Intelligence for Modeling and Simulation of Mixed Automated and Human Traffic","ref_index":149,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07326","citing_title":"GEM: Generating LiDAR World Model via Deformable Mamba","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MVIYLLK7EGIVM2ZEGII4QE74TD","json":"https://pith.science/pith/MVIYLLK7EGIVM2ZEGII4QE74TD.json","graph_json":"https://pith.science/api/pith-number/MVIYLLK7EGIVM2ZEGII4QE74TD/graph.json","events_json":"https://pith.science/api/pith-number/MVIYLLK7EGIVM2ZEGII4QE74TD/events.json","paper":"https://pith.science/paper/MVIYLLK7"},"agent_actions":{"view_html":"https://pith.science/pith/MVIYLLK7EGIVM2ZEGII4QE74TD","download_json":"https://pith.science/pith/MVIYLLK7EGIVM2ZEGII4QE74TD.json","view_paper":"https://pith.science/paper/MVIYLLK7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.10429&json=true","fetch_graph":"https://pith.science/api/pith-number/MVIYLLK7EGIVM2ZEGII4QE74TD/graph.json","fetch_events":"https://pith.science/api/pith-number/MVIYLLK7EGIVM2ZEGII4QE74TD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MVIYLLK7EGIVM2ZEGII4QE74TD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MVIYLLK7EGIVM2ZEGII4QE74TD/action/storage_attestation","attest_author":"https://pith.science/pith/MVIYLLK7EGIVM2ZEGII4QE74TD/action/author_attestation","sign_citation":"https://pith.science/pith/MVIYLLK7EGIVM2ZEGII4QE74TD/action/citation_signature","submit_replication":"https://pith.science/pith/MVIYLLK7EGIVM2ZEGII4QE74TD/action/replication_record"}},"created_at":"2026-07-05T09:20:16.182567+00:00","updated_at":"2026-07-05T09:20:16.182567+00:00"}