{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WZ65AQPVHBSFUNZEJQEIU2C6L6","short_pith_number":"pith:WZ65AQPV","schema_version":"1.0","canonical_sha256":"b67dd041f538645a37244c088a685e5faaff661acdfb5ec9eef54b3a5bed7bfc","source":{"kind":"arxiv","id":"2405.20337","version":1},"attestation_state":"computed","paper":{"title":"OccSora: 4D Occupancy Generation Models as World Simulators for Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Haiyang Yu, Han Jiang, Jiwen Lu, Lening Wang, Wenzhao Zheng, Yilong Ren, Zhiyong Cui","submitted_at":"2024-05-30T17:59:42Z","abstract_excerpt":"Understanding the evolution of 3D scenes is important for effective autonomous driving. While conventional methods mode scene development with the motion of individual instances, world models emerge as a generative framework to describe the general scene dynamics. However, most existing methods adopt an autoregressive framework to perform next-token prediction, which suffer from inefficiency in modeling long-term temporal evolutions. To address this, we propose a diffusion-based 4D occupancy generation model, OccSora, to simulate the development of the 3D world for autonomous driving. We emplo"},"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":"2405.20337","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-30T17:59:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"438166a0215c19567e72ac34972bec45d2b6f906c0eee90f3c9d1a29708bbbce","abstract_canon_sha256":"4a36ba05ba12274c80be5f324c645d336de9d994203b7ded66e40f98e0c0d368"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:24.499461Z","signature_b64":"hetEXAypO2H2XsVs4ymSjF8i4HQQYJPipm/rOUzHDGxGabUvZ6iuvxM0PfK2bUt+Y7o5ccqkrxNe3I0AsZb7BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b67dd041f538645a37244c088a685e5faaff661acdfb5ec9eef54b3a5bed7bfc","last_reissued_at":"2026-07-05T08:25:24.498924Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:24.498924Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OccSora: 4D Occupancy Generation Models as World Simulators for Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Haiyang Yu, Han Jiang, Jiwen Lu, Lening Wang, Wenzhao Zheng, Yilong Ren, Zhiyong Cui","submitted_at":"2024-05-30T17:59:42Z","abstract_excerpt":"Understanding the evolution of 3D scenes is important for effective autonomous driving. While conventional methods mode scene development with the motion of individual instances, world models emerge as a generative framework to describe the general scene dynamics. However, most existing methods adopt an autoregressive framework to perform next-token prediction, which suffer from inefficiency in modeling long-term temporal evolutions. To address this, we propose a diffusion-based 4D occupancy generation model, OccSora, to simulate the development of the 3D world for autonomous driving. We emplo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.20337","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/2405.20337/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":"2405.20337","created_at":"2026-07-05T08:25:24.498983+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.20337v1","created_at":"2026-07-05T08:25:24.498983+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.20337","created_at":"2026-07-05T08:25:24.498983+00:00"},{"alias_kind":"pith_short_12","alias_value":"WZ65AQPVHBSF","created_at":"2026-07-05T08:25:24.498983+00:00"},{"alias_kind":"pith_short_16","alias_value":"WZ65AQPVHBSFUNZE","created_at":"2026-07-05T08:25:24.498983+00:00"},{"alias_kind":"pith_short_8","alias_value":"WZ65AQPV","created_at":"2026-07-05T08:25:24.498983+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06401","citing_title":"A Definition and Roadmap for World Models","ref_index":206,"is_internal_anchor":true},{"citing_arxiv_id":"2606.18888","citing_title":"Generative-Model Predictive Planning for Navigation in Partially Observable Environments","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12189","citing_title":"DynaTok: Token-Based 4D Reconstruction from Partial Point Clouds","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24354","citing_title":"SparseWorld: Enhancing End-to-End Autonomous Driving via World Models with Sparse Scene Representation","ref_index":28,"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":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26113","citing_title":"AnyScene: Towards Highly Controllable Driving Scene Generation at Anywhere and Beyond","ref_index":45,"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":56,"is_internal_anchor":false},{"citing_arxiv_id":"2511.22039","citing_title":"SparseWorld-TC: Trajectory-Conditioned Sparse Occupancy World Model","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2512.23421","citing_title":"DriveLaW:Unifying Planning and Video Generation in a Latent Driving World","ref_index":67,"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":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09701","citing_title":"DriveFuture: Future-Aware Latent World Models for Autonomous Driving","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22240","citing_title":"OccDirector: Language-Guided Behavior and Interaction Generation in 4D Occupancy Space","ref_index":11,"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":148,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WZ65AQPVHBSFUNZEJQEIU2C6L6","json":"https://pith.science/pith/WZ65AQPVHBSFUNZEJQEIU2C6L6.json","graph_json":"https://pith.science/api/pith-number/WZ65AQPVHBSFUNZEJQEIU2C6L6/graph.json","events_json":"https://pith.science/api/pith-number/WZ65AQPVHBSFUNZEJQEIU2C6L6/events.json","paper":"https://pith.science/paper/WZ65AQPV"},"agent_actions":{"view_html":"https://pith.science/pith/WZ65AQPVHBSFUNZEJQEIU2C6L6","download_json":"https://pith.science/pith/WZ65AQPVHBSFUNZEJQEIU2C6L6.json","view_paper":"https://pith.science/paper/WZ65AQPV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.20337&json=true","fetch_graph":"https://pith.science/api/pith-number/WZ65AQPVHBSFUNZEJQEIU2C6L6/graph.json","fetch_events":"https://pith.science/api/pith-number/WZ65AQPVHBSFUNZEJQEIU2C6L6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WZ65AQPVHBSFUNZEJQEIU2C6L6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WZ65AQPVHBSFUNZEJQEIU2C6L6/action/storage_attestation","attest_author":"https://pith.science/pith/WZ65AQPVHBSFUNZEJQEIU2C6L6/action/author_attestation","sign_citation":"https://pith.science/pith/WZ65AQPVHBSFUNZEJQEIU2C6L6/action/citation_signature","submit_replication":"https://pith.science/pith/WZ65AQPVHBSFUNZEJQEIU2C6L6/action/replication_record"}},"created_at":"2026-07-05T08:25:24.498983+00:00","updated_at":"2026-07-05T08:25:24.498983+00:00"}