{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4JSXFJSBSUR2A6C4OUNUZSAOQL","short_pith_number":"pith:4JSXFJSB","schema_version":"1.0","canonical_sha256":"e26572a6419523a0785c751b4cc80e82d3700c89fdc1f82d89875b4a7e09862a","source":{"kind":"arxiv","id":"2303.11301","version":1},"attestation_state":"computed","paper":{"title":"VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Tracking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianhui Liu, Jiaya Jia, Xiangyu Zhang, Xiaojuan Qi, Yukang Chen","submitted_at":"2023-03-20T17:40:44Z","abstract_excerpt":"3D object detectors usually rely on hand-crafted proxies, e.g., anchors or centers, and translate well-studied 2D frameworks to 3D. Thus, sparse voxel features need to be densified and processed by dense prediction heads, which inevitably costs extra computation. In this paper, we instead propose VoxelNext for fully sparse 3D object detection. Our core insight is to predict objects directly based on sparse voxel features, without relying on hand-crafted proxies. Our strong sparse convolutional network VoxelNeXt detects and tracks 3D objects through voxel features entirely. It is an elegant and"},"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":"2303.11301","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-20T17:40:44Z","cross_cats_sorted":[],"title_canon_sha256":"8c1242fb9cac86a7cc23d846bc99dde1bf8810a5a3e4df94a738e39124f79545","abstract_canon_sha256":"5f232cfb5a0a67a4261f159e8f50abc34ba21409b8bf0ba874394838067eb1f2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:52:47.809713Z","signature_b64":"A6Rru4Xr6iT4ol0PgQTj7/oh6zGAOKHgXZjNV6WmPiEMwh2qASg7qk3JGXiT53cnin6D9IhWCefb+frL8x0TCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e26572a6419523a0785c751b4cc80e82d3700c89fdc1f82d89875b4a7e09862a","last_reissued_at":"2026-07-05T05:52:47.809282Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:52:47.809282Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Tracking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianhui Liu, Jiaya Jia, Xiangyu Zhang, Xiaojuan Qi, Yukang Chen","submitted_at":"2023-03-20T17:40:44Z","abstract_excerpt":"3D object detectors usually rely on hand-crafted proxies, e.g., anchors or centers, and translate well-studied 2D frameworks to 3D. Thus, sparse voxel features need to be densified and processed by dense prediction heads, which inevitably costs extra computation. In this paper, we instead propose VoxelNext for fully sparse 3D object detection. Our core insight is to predict objects directly based on sparse voxel features, without relying on hand-crafted proxies. Our strong sparse convolutional network VoxelNeXt detects and tracks 3D objects through voxel features entirely. It is an elegant and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.11301","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/2303.11301/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":"2303.11301","created_at":"2026-07-05T05:52:47.809332+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.11301v1","created_at":"2026-07-05T05:52:47.809332+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.11301","created_at":"2026-07-05T05:52:47.809332+00:00"},{"alias_kind":"pith_short_12","alias_value":"4JSXFJSBSUR2","created_at":"2026-07-05T05:52:47.809332+00:00"},{"alias_kind":"pith_short_16","alias_value":"4JSXFJSBSUR2A6C4","created_at":"2026-07-05T05:52:47.809332+00:00"},{"alias_kind":"pith_short_8","alias_value":"4JSXFJSB","created_at":"2026-07-05T05:52:47.809332+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31109","citing_title":"InfiniVerse: Occupancy Guided Unbounded Scene Generation for Autonomous Driving","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20033","citing_title":"A Nash Equilibrium Framework For Training-Free Multimodal Step Verification","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4JSXFJSBSUR2A6C4OUNUZSAOQL","json":"https://pith.science/pith/4JSXFJSBSUR2A6C4OUNUZSAOQL.json","graph_json":"https://pith.science/api/pith-number/4JSXFJSBSUR2A6C4OUNUZSAOQL/graph.json","events_json":"https://pith.science/api/pith-number/4JSXFJSBSUR2A6C4OUNUZSAOQL/events.json","paper":"https://pith.science/paper/4JSXFJSB"},"agent_actions":{"view_html":"https://pith.science/pith/4JSXFJSBSUR2A6C4OUNUZSAOQL","download_json":"https://pith.science/pith/4JSXFJSBSUR2A6C4OUNUZSAOQL.json","view_paper":"https://pith.science/paper/4JSXFJSB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.11301&json=true","fetch_graph":"https://pith.science/api/pith-number/4JSXFJSBSUR2A6C4OUNUZSAOQL/graph.json","fetch_events":"https://pith.science/api/pith-number/4JSXFJSBSUR2A6C4OUNUZSAOQL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4JSXFJSBSUR2A6C4OUNUZSAOQL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4JSXFJSBSUR2A6C4OUNUZSAOQL/action/storage_attestation","attest_author":"https://pith.science/pith/4JSXFJSBSUR2A6C4OUNUZSAOQL/action/author_attestation","sign_citation":"https://pith.science/pith/4JSXFJSBSUR2A6C4OUNUZSAOQL/action/citation_signature","submit_replication":"https://pith.science/pith/4JSXFJSBSUR2A6C4OUNUZSAOQL/action/replication_record"}},"created_at":"2026-07-05T05:52:47.809332+00:00","updated_at":"2026-07-05T05:52:47.809332+00:00"}