{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Z7AS6H33PAWRINNQPJZQDLVYMS","short_pith_number":"pith:Z7AS6H33","schema_version":"1.0","canonical_sha256":"cfc12f1f7b782d1435b07a7301aeb864bed0cb5625c8450e93f677255e5ba0b7","source":{"kind":"arxiv","id":"2412.10373","version":1},"attestation_state":"computed","paper":{"title":"GaussianWorld: Gaussian World Model for Streaming 3D Occupancy Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jie Zhou, Jiwen Lu, Sicheng Zuo, Wenzhao Zheng, Yuanhui Huang","submitted_at":"2024-12-13T18:59:54Z","abstract_excerpt":"3D occupancy prediction is important for autonomous driving due to its comprehensive perception of the surroundings. To incorporate sequential inputs, most existing methods fuse representations from previous frames to infer the current 3D occupancy. However, they fail to consider the continuity of driving scenarios and ignore the strong prior provided by the evolution of 3D scenes (e.g., only dynamic objects move). In this paper, we propose a world-model-based framework to exploit the scene evolution for perception. We reformulate 3D occupancy prediction as a 4D occupancy forecasting problem c"},"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":"2412.10373","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-13T18:59:54Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"9545857757443a43d4912a05c6bf87bdb12c1020a7f3468d611b05bc56b669de","abstract_canon_sha256":"895e8d93fd737f702740dfc0994dae8c7213f66155c0dce0bbfeeb1031d07856"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:48:57.140980Z","signature_b64":"dC6TRxFtG4hanpe2hFgI5ihGtdnUypm/lpRh24iSCfpy9MXSZnTUC1HUcPIRW/dNo8NTKVkLClQxBaMXYHTSBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cfc12f1f7b782d1435b07a7301aeb864bed0cb5625c8450e93f677255e5ba0b7","last_reissued_at":"2026-07-05T09:48:57.140249Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:48:57.140249Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GaussianWorld: Gaussian World Model for Streaming 3D Occupancy Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jie Zhou, Jiwen Lu, Sicheng Zuo, Wenzhao Zheng, Yuanhui Huang","submitted_at":"2024-12-13T18:59:54Z","abstract_excerpt":"3D occupancy prediction is important for autonomous driving due to its comprehensive perception of the surroundings. To incorporate sequential inputs, most existing methods fuse representations from previous frames to infer the current 3D occupancy. However, they fail to consider the continuity of driving scenarios and ignore the strong prior provided by the evolution of 3D scenes (e.g., only dynamic objects move). In this paper, we propose a world-model-based framework to exploit the scene evolution for perception. We reformulate 3D occupancy prediction as a 4D occupancy forecasting problem c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10373","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/2412.10373/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":"2412.10373","created_at":"2026-07-05T09:48:57.140327+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.10373v1","created_at":"2026-07-05T09:48:57.140327+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10373","created_at":"2026-07-05T09:48:57.140327+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z7AS6H33PAWR","created_at":"2026-07-05T09:48:57.140327+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z7AS6H33PAWRINNQ","created_at":"2026-07-05T09:48:57.140327+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z7AS6H33","created_at":"2026-07-05T09:48:57.140327+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06401","citing_title":"A Definition and Roadmap for World Models","ref_index":209,"is_internal_anchor":true},{"citing_arxiv_id":"2606.13460","citing_title":"VISA: VLM-Guided Instance Semantic Auditing for 3D Occupancy World Models","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00746","citing_title":"GaussianFusion: Unified 3D Gaussian Representation for Multi-Modal Fusion Perception","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2412.12870","citing_title":"Physically Interpretable World Models via Weakly Supervised Representation Learning","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2506.09981","citing_title":"ReSim: Reliable World Simulation for Autonomous Driving","ref_index":94,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z7AS6H33PAWRINNQPJZQDLVYMS","json":"https://pith.science/pith/Z7AS6H33PAWRINNQPJZQDLVYMS.json","graph_json":"https://pith.science/api/pith-number/Z7AS6H33PAWRINNQPJZQDLVYMS/graph.json","events_json":"https://pith.science/api/pith-number/Z7AS6H33PAWRINNQPJZQDLVYMS/events.json","paper":"https://pith.science/paper/Z7AS6H33"},"agent_actions":{"view_html":"https://pith.science/pith/Z7AS6H33PAWRINNQPJZQDLVYMS","download_json":"https://pith.science/pith/Z7AS6H33PAWRINNQPJZQDLVYMS.json","view_paper":"https://pith.science/paper/Z7AS6H33","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.10373&json=true","fetch_graph":"https://pith.science/api/pith-number/Z7AS6H33PAWRINNQPJZQDLVYMS/graph.json","fetch_events":"https://pith.science/api/pith-number/Z7AS6H33PAWRINNQPJZQDLVYMS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z7AS6H33PAWRINNQPJZQDLVYMS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z7AS6H33PAWRINNQPJZQDLVYMS/action/storage_attestation","attest_author":"https://pith.science/pith/Z7AS6H33PAWRINNQPJZQDLVYMS/action/author_attestation","sign_citation":"https://pith.science/pith/Z7AS6H33PAWRINNQPJZQDLVYMS/action/citation_signature","submit_replication":"https://pith.science/pith/Z7AS6H33PAWRINNQPJZQDLVYMS/action/replication_record"}},"created_at":"2026-07-05T09:48:57.140327+00:00","updated_at":"2026-07-05T09:48:57.140327+00:00"}