{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:D5Q6ABKZC4DEVQ3RWQDRCBHMA6","short_pith_number":"pith:D5Q6ABKZ","schema_version":"1.0","canonical_sha256":"1f61e0055917064ac371b4071104ec078cab06591b56f320cd16259919930710","source":{"kind":"arxiv","id":"2312.17118","version":5},"attestation_state":"computed","paper":{"title":"Fully Sparse 3D Occupancy Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haiguang Wang, Haisong Liu, Hongyang Li, Jia Zeng, Li Chen, Limin Wang, Tianyu Li, Yang Chen, Zetong Yang","submitted_at":"2023-12-28T16:54:53Z","abstract_excerpt":"Occupancy prediction plays a pivotal role in autonomous driving. Previous methods typically construct dense 3D volumes, neglecting the inherent sparsity of the scene and suffering from high computational costs. To bridge the gap, we introduce a novel fully sparse occupancy network, termed SparseOcc. SparseOcc initially reconstructs a sparse 3D representation from camera-only inputs and subsequently predicts semantic/instance occupancy from the 3D sparse representation by sparse queries. A mask-guided sparse sampling is designed to enable sparse queries to interact with 2D features in a fully s"},"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":"2312.17118","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-28T16:54:53Z","cross_cats_sorted":[],"title_canon_sha256":"3652b134d528414e202626981c58119cac7677f476fc31abb174e5a953c20221","abstract_canon_sha256":"b3b8643e3c16f42d1323b4c92195dfcb4e6d07a31d0d21f811f7d86dafab5583"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:45:47.604162Z","signature_b64":"jh970DoIn61JCvWSUsGazSYEHvt+hnBF2Q4N2ssXgKyLQICpNPRtnAecn8Xr6ddac4eH9pRV63cpfWvsEepPDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f61e0055917064ac371b4071104ec078cab06591b56f320cd16259919930710","last_reissued_at":"2026-07-05T08:45:47.603723Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:45:47.603723Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fully Sparse 3D Occupancy Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haiguang Wang, Haisong Liu, Hongyang Li, Jia Zeng, Li Chen, Limin Wang, Tianyu Li, Yang Chen, Zetong Yang","submitted_at":"2023-12-28T16:54:53Z","abstract_excerpt":"Occupancy prediction plays a pivotal role in autonomous driving. Previous methods typically construct dense 3D volumes, neglecting the inherent sparsity of the scene and suffering from high computational costs. To bridge the gap, we introduce a novel fully sparse occupancy network, termed SparseOcc. SparseOcc initially reconstructs a sparse 3D representation from camera-only inputs and subsequently predicts semantic/instance occupancy from the 3D sparse representation by sparse queries. A mask-guided sparse sampling is designed to enable sparse queries to interact with 2D features in a fully s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.17118","kind":"arxiv","version":5},"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/2312.17118/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":"2312.17118","created_at":"2026-07-05T08:45:47.603779+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.17118v5","created_at":"2026-07-05T08:45:47.603779+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.17118","created_at":"2026-07-05T08:45:47.603779+00:00"},{"alias_kind":"pith_short_12","alias_value":"D5Q6ABKZC4DE","created_at":"2026-07-05T08:45:47.603779+00:00"},{"alias_kind":"pith_short_16","alias_value":"D5Q6ABKZC4DEVQ3R","created_at":"2026-07-05T08:45:47.603779+00:00"},{"alias_kind":"pith_short_8","alias_value":"D5Q6ABKZ","created_at":"2026-07-05T08:45:47.603779+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00746","citing_title":"GaussianFusion: Unified 3D Gaussian Representation for Multi-Modal Fusion Perception","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31688","citing_title":"Semantic Occupancy Prediction with Dual Range-Voxel Representation","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D5Q6ABKZC4DEVQ3RWQDRCBHMA6","json":"https://pith.science/pith/D5Q6ABKZC4DEVQ3RWQDRCBHMA6.json","graph_json":"https://pith.science/api/pith-number/D5Q6ABKZC4DEVQ3RWQDRCBHMA6/graph.json","events_json":"https://pith.science/api/pith-number/D5Q6ABKZC4DEVQ3RWQDRCBHMA6/events.json","paper":"https://pith.science/paper/D5Q6ABKZ"},"agent_actions":{"view_html":"https://pith.science/pith/D5Q6ABKZC4DEVQ3RWQDRCBHMA6","download_json":"https://pith.science/pith/D5Q6ABKZC4DEVQ3RWQDRCBHMA6.json","view_paper":"https://pith.science/paper/D5Q6ABKZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.17118&json=true","fetch_graph":"https://pith.science/api/pith-number/D5Q6ABKZC4DEVQ3RWQDRCBHMA6/graph.json","fetch_events":"https://pith.science/api/pith-number/D5Q6ABKZC4DEVQ3RWQDRCBHMA6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D5Q6ABKZC4DEVQ3RWQDRCBHMA6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D5Q6ABKZC4DEVQ3RWQDRCBHMA6/action/storage_attestation","attest_author":"https://pith.science/pith/D5Q6ABKZC4DEVQ3RWQDRCBHMA6/action/author_attestation","sign_citation":"https://pith.science/pith/D5Q6ABKZC4DEVQ3RWQDRCBHMA6/action/citation_signature","submit_replication":"https://pith.science/pith/D5Q6ABKZC4DEVQ3RWQDRCBHMA6/action/replication_record"}},"created_at":"2026-07-05T08:45:47.603779+00:00","updated_at":"2026-07-05T08:45:47.603779+00:00"}