{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:VRNGVMNPRN72JDPH7RYQQDT6QF","short_pith_number":"pith:VRNGVMNP","schema_version":"1.0","canonical_sha256":"ac5a6ab1af8b7fa48de7fc71080e7e815d4ff58313b2c744bcf8d6afb21d5326","source":{"kind":"arxiv","id":"2202.07123","version":2},"attestation_state":"computed","paper":{"title":"Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Can Qin, Haoxi Ran, Haoxuan You, Xu Ma, Yun Fu","submitted_at":"2022-02-15T01:39:07Z","abstract_excerpt":"Point cloud analysis is challenging due to irregularity and unordered data structure. To capture the 3D geometries, prior works mainly rely on exploring sophisticated local geometric extractors using convolution, graph, or attention mechanisms. These methods, however, incur unfavorable latency during inference, and the performance saturates over the past few years. In this paper, we present a novel perspective on this task. We notice that detailed local geometrical information probably is not the key to point cloud analysis -- we introduce a pure residual MLP network, called PointMLP, which in"},"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":"2202.07123","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2022-02-15T01:39:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6a016fcf22c50d3d54aa477b0ba324b609d560a76d29b77c13a30d000288d231","abstract_canon_sha256":"ce3fd2f0705dab3281cc81e14392d9441d1bc5a8d48f9a1bfde01df1018b1dbf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:20:10.027585Z","signature_b64":"bc5L7uKKMCAKfT7XCC1ZATZFyisbhnn4UVNZ28/IdOxLQ5rWdtknEjvXxBcnDsg+OXmnWW/zOvFmPm92FXaiCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac5a6ab1af8b7fa48de7fc71080e7e815d4ff58313b2c744bcf8d6afb21d5326","last_reissued_at":"2026-07-05T05:20:10.027105Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:20:10.027105Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Can Qin, Haoxi Ran, Haoxuan You, Xu Ma, Yun Fu","submitted_at":"2022-02-15T01:39:07Z","abstract_excerpt":"Point cloud analysis is challenging due to irregularity and unordered data structure. To capture the 3D geometries, prior works mainly rely on exploring sophisticated local geometric extractors using convolution, graph, or attention mechanisms. These methods, however, incur unfavorable latency during inference, and the performance saturates over the past few years. In this paper, we present a novel perspective on this task. We notice that detailed local geometrical information probably is not the key to point cloud analysis -- we introduce a pure residual MLP network, called PointMLP, which in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.07123","kind":"arxiv","version":2},"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/2202.07123/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":"2202.07123","created_at":"2026-07-05T05:20:10.027167+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.07123v2","created_at":"2026-07-05T05:20:10.027167+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.07123","created_at":"2026-07-05T05:20:10.027167+00:00"},{"alias_kind":"pith_short_12","alias_value":"VRNGVMNPRN72","created_at":"2026-07-05T05:20:10.027167+00:00"},{"alias_kind":"pith_short_16","alias_value":"VRNGVMNPRN72JDPH","created_at":"2026-07-05T05:20:10.027167+00:00"},{"alias_kind":"pith_short_8","alias_value":"VRNGVMNP","created_at":"2026-07-05T05:20:10.027167+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":15,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25278","citing_title":"Heterogeneous and Adept Snapshot Distillation for 3D Semantic Segmentation","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09604","citing_title":"DAP: Doppler-aware Point Network for Heterogeneous mmWave Action Recognition","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01573","citing_title":"$\\text{VG}^2$GT: Voxel-Gaussian Splatting Visual Geometry Grounded Transformer","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30375","citing_title":"Full-field prediction for engineering-scale three-dimensional aircraft with multigrid-hierarchical learning","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07590","citing_title":"Beyond Defenses: Manifold-Aligned Regularization for Intrinsic 3D Point Cloud Robustness","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22997","citing_title":"Scene Reconstruction as Mapping Priors for 3D Detection","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22090","citing_title":"A Camera-Cooperative ISAC Framework for Multimodal Non-Cooperative UAVs Sensing","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2512.08323","citing_title":"Detecting Dental Landmarks from Intraoral 3D Scans: the 3DTeethLand challenge","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2602.00937","citing_title":"CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2303.16199","citing_title":"LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention","ref_index":247,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02497","citing_title":"Delaunay Canopy: Building Wireframe Reconstruction from Airborne LiDAR Point Clouds via Delaunay Graph","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09604","citing_title":"DAP: Doppler-aware Point Network for Heterogeneous mmWave Action Recognition","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09606","citing_title":"On the Generation and Mitigation of Harmful Geometry in Image-to-3D Models","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10706","citing_title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07590","citing_title":"Beyond Defenses: Manifold-Aligned Regularization for Intrinsic 3D Point Cloud Robustness","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VRNGVMNPRN72JDPH7RYQQDT6QF","json":"https://pith.science/pith/VRNGVMNPRN72JDPH7RYQQDT6QF.json","graph_json":"https://pith.science/api/pith-number/VRNGVMNPRN72JDPH7RYQQDT6QF/graph.json","events_json":"https://pith.science/api/pith-number/VRNGVMNPRN72JDPH7RYQQDT6QF/events.json","paper":"https://pith.science/paper/VRNGVMNP"},"agent_actions":{"view_html":"https://pith.science/pith/VRNGVMNPRN72JDPH7RYQQDT6QF","download_json":"https://pith.science/pith/VRNGVMNPRN72JDPH7RYQQDT6QF.json","view_paper":"https://pith.science/paper/VRNGVMNP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.07123&json=true","fetch_graph":"https://pith.science/api/pith-number/VRNGVMNPRN72JDPH7RYQQDT6QF/graph.json","fetch_events":"https://pith.science/api/pith-number/VRNGVMNPRN72JDPH7RYQQDT6QF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VRNGVMNPRN72JDPH7RYQQDT6QF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VRNGVMNPRN72JDPH7RYQQDT6QF/action/storage_attestation","attest_author":"https://pith.science/pith/VRNGVMNPRN72JDPH7RYQQDT6QF/action/author_attestation","sign_citation":"https://pith.science/pith/VRNGVMNPRN72JDPH7RYQQDT6QF/action/citation_signature","submit_replication":"https://pith.science/pith/VRNGVMNPRN72JDPH7RYQQDT6QF/action/replication_record"}},"created_at":"2026-07-05T05:20:10.027167+00:00","updated_at":"2026-07-05T05:20:10.027167+00:00"}