{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T07:49:35Z","timestamp":1782287375667,"version":"3.54.5"},"reference-count":69,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems with Applications"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.eswa.2026.132578","type":"journal-article","created":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T23:36:30Z","timestamp":1776900990000},"page":"132578","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Beyond empirical risk: Achieving point cloud robustness through margin refinement and data purification"],"prefix":"10.1016","volume":"326","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-8075-7785","authenticated-orcid":false,"given":"Shurong","family":"Dong","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8678-0348","authenticated-orcid":false,"given":"Jie","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7031-1119","authenticated-orcid":false,"given":"Ruida","family":"Mao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9195-4134","authenticated-orcid":false,"given":"Xuepei","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5123-0833","authenticated-orcid":false,"given":"Shuping","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2348-0532","authenticated-orcid":false,"given":"Guanghui","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.eswa.2026.132578_bib0001","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"9902","article-title":"Crosspoint: Self-supervised cross-modal contrastive learning for 3D point cloud understanding","author":"Afham","year":"2022"},{"key":"10.1016\/j.eswa.2026.132578_bib0002","unstructured":"Baiocchi, A., Spinelli, I., Nicolosi, A., & Scardapane, S. (2024). Adaptive point transformer. arXiv: 2401.14845."},{"key":"10.1016\/j.eswa.2026.132578_bib0003","series-title":"International conference on learning representations","article-title":"Thermometer encoding: One hot way to resist adversarial examples","author":"Buckman","year":"2018"},{"issue":"1","key":"10.1016\/j.eswa.2026.132578_bib0004","doi-asserted-by":"crossref","first-page":"3570","DOI":"10.1038\/s41598-025-86704-6","article-title":"Multi-stage refinement network for point cloud completion based on geodesic attention","volume":"15","author":"Chang","year":"2025","journal-title":"Scientific Reports"},{"key":"10.1016\/j.eswa.2026.132578_bib0005","doi-asserted-by":"crossref","first-page":"29667","DOI":"10.52202\/075280-1291","article-title":"Pointgpt: Auto-regressively generative pre-training from point clouds","volume":"36","author":"Chen","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"2","key":"10.1016\/j.eswa.2026.132578_bib0006","doi-asserted-by":"crossref","DOI":"10.1007\/s11704-023-3455-4","article-title":"Fpsmix: Data augmentation strategy for point cloud classification","volume":"19","author":"Chen","year":"2025","journal-title":"Frontiers of Computer Science"},{"key":"10.1016\/j.eswa.2026.132578_bib0007","series-title":"European conference on computer vision","first-page":"330","article-title":"Pointmixup: Augmentation for point clouds","author":"Chen","year":"2020"},{"key":"10.1016\/j.eswa.2026.132578_bib0008","doi-asserted-by":"crossref","first-page":"4436","DOI":"10.1109\/TIP.2021.3072214","article-title":"Pra-net: Point relation-aware network for 3D point cloud analysis","volume":"30","author":"Cheng","year":"2021","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.eswa.2026.132578_bib0009","unstructured":"DeVries, T., & Taylor, G. W. (2017). Improved regularization of convolutional neural networks with cutout. arXiv: 1708.04552."},{"issue":"2","key":"10.1016\/j.eswa.2026.132578_bib0010","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1007\/s41095-021-0229-5","article-title":"Pct: Point cloud transformer","volume":"7","author":"Guo","year":"2021","journal-title":"Computational Visual Media"},{"key":"10.1016\/j.eswa.2026.132578_bib0011","series-title":"Proceedings of the 32nd ACM international conference on multimedia","first-page":"4995","article-title":"Mamba3d: Enhancing local features for 3D point cloud analysis via state space model","author":"Han","year":"2024"},{"key":"10.1016\/j.eswa.2026.132578_bib0012","series-title":"Proceedings of the IEEE international conference on acoustics, speech and signal processing (ICASSP)","first-page":"1","article-title":"Pcsalmix: Gradient saliency based mix augmentation for point cloud classification","author":"Hong","year":"2023"},{"key":"10.1016\/j.eswa.2026.132578_bib0013","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"548","article-title":"Point cloud augmentation with weighted local transformations","author":"Kim","year":"2021"},{"key":"10.1016\/j.eswa.2026.132578_bib0014","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"15900","article-title":"Regularization strategy for point cloud via rigidly mixed sample","author":"Lee","year":"2021"},{"key":"10.1016\/j.eswa.2026.132578_bib0015","doi-asserted-by":"crossref","first-page":"23580","DOI":"10.52202\/068431-1713","article-title":"Sagemix: Saliency-guided mixup for point clouds","volume":"35","author":"Lee","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.132578_bib0016","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"6378","article-title":"Pointaugment: An auto-augmentation framework for point cloud classification","author":"Li","year":"2020"},{"key":"10.1016\/j.eswa.2026.132578_bib0017","article-title":"Pointcnn: Convolution on x-transformed points","volume":"31","author":"Li","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.132578_bib0018","doi-asserted-by":"crossref","unstructured":"Liang, D., Zhou, X., Xu, W., Zhu, X., Zou, Z., Ye, X., & Bai, X. (2024). Pointmamba: A simple state space model for point cloud analysis. arXiv: 2402.10739.","DOI":"10.52202\/079017-1026"},{"key":"10.1016\/j.eswa.2026.132578_bib0019","series-title":"Proceedings of the 33rd ACM international conference on multimedia","first-page":"8517","article-title":"Graph-guided dual-level augmentation for 3D scene segmentation","author":"Lin","year":"2025"},{"key":"10.1016\/j.eswa.2026.132578_bib0020","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"4293","article-title":"Fpconv: Learning local flattening for point convolution","author":"Lin","year":"2020"},{"key":"10.1016\/j.eswa.2026.132578_bib0021","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"1800","article-title":"Convolution in the cloud: Learning deformable kernels in 3D graph convolution networks for point cloud analysis","author":"Lin","year":"2020"},{"issue":"8","key":"10.1016\/j.eswa.2026.132578_bib0022","first-page":"4212","article-title":"Learning of 3d graph convolution networks for point cloud analysis","volume":"44","author":"Lin","year":"2021","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.eswa.2026.132578_bib0023","series-title":"European conference on computer vision","first-page":"657","article-title":"Masked discrimination for self-supervised learning on point clouds","author":"Liu","year":"2022"},{"key":"10.1016\/j.eswa.2026.132578_bib0024","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"8895","article-title":"Relation-shape convolutional neural network for point cloud analysis","author":"Liu","year":"2019"},{"key":"10.1016\/j.eswa.2026.132578_bib0025","series-title":"European conference on computer vision","first-page":"326","article-title":"A closer look at local aggregation operators in point cloud analysis","author":"Liu","year":"2020"},{"key":"10.1016\/j.eswa.2026.132578_bib0026","unstructured":"Ma, X., Qin, C., You, H., Ran, H., & Fu, Y. (2022a). Rethinking network design and local geometry in point cloud: A simple residual MLP framework. arXiv: 2202.07123."},{"key":"10.1016\/j.eswa.2026.132578_bib0027","unstructured":"Ma, X., Qin, C., You, H., Ran, H., & Fu, Y. (2022b). Rethinking network design and local geometry in point cloud: A simple residual MLP framework. arXiv: 2202.07123."},{"key":"10.1016\/j.eswa.2026.132578_bib0028","unstructured":"Madry, A., Makelov, A., Schmidt, L., Tsipras, D., & Vladu, A. (2017). Towards deep learning models resistant to adversarial attacks. arXiv: 1706.06083."},{"key":"10.1016\/j.eswa.2026.132578_bib0029","article-title":"Masked autoencoders for 3d point cloud self-supervised learning","volume":"1","author":"Pang","year":"2023","journal-title":"World Scientific Annual Review of Artificial Intelligence"},{"key":"10.1016\/j.eswa.2026.132578_bib0030","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"652","article-title":"Pointnet: Deep learning on point sets for 3D classification and segmentation","author":"Qi","year":"2017"},{"key":"10.1016\/j.eswa.2026.132578_bib0031","article-title":"Pointnet++: Deep hierarchical feature learning on point sets in a metric space","volume":"30","author":"Qi","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.132578_bib0032","doi-asserted-by":"crossref","first-page":"23192","DOI":"10.52202\/068431-1685","article-title":"Pointnext: Revisiting pointnet++ with improved training and scaling strategies","volume":"35","author":"Qian","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.132578_bib0033","doi-asserted-by":"crossref","first-page":"1943","DOI":"10.1109\/TMM.2021.3074240","article-title":"Geometric back-projection network for point cloud classification","volume":"24","author":"Qiu","year":"2021","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.eswa.2026.132578_bib0034","series-title":"Proceedings of the 39th international conference on machine learning","first-page":"18559","article-title":"Benchmarking and analyzing point cloud classification under corruptions","volume":"162","author":"Ren","year":"2022"},{"key":"10.1016\/j.eswa.2026.132578_bib0035","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"4548","article-title":"Mining point cloud local structures by kernel correlation and graph pooling","author":"Shen","year":"2018"},{"key":"10.1016\/j.eswa.2026.132578_bib0036","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"2118","article-title":"Patchaugment: Local neighborhood augmentation in point cloud classification","author":"Sheshappanavar","year":"2021"},{"key":"10.1016\/j.eswa.2026.132578_bib0037","unstructured":"Shi, Y., He, Q., Liu, Y., Liu, X., & Su, J. (2025). Kan or mlp? point cloud shows the way forward. arXiv: 2504.13593."},{"key":"10.1016\/j.eswa.2026.132578_bib0038","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"3693","article-title":"Dynamic edge-conditioned filters in convolutional neural networks on graphs","author":"Simonovsky","year":"2017"},{"key":"10.1016\/j.eswa.2026.132578_bib0039","series-title":"Proceedings of the european conference on computer vision (ECCV)","first-page":"631","article-title":"Is robustness the cost of accuracy?\u2013A comprehensive study on the robustness of 18 deep image classification models","author":"Su","year":"2018"},{"key":"10.1016\/j.eswa.2026.132578_bib0040","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"6411","article-title":"Kpconv: Flexible and deformable convolution for point clouds","author":"Thomas","year":"2019"},{"key":"10.1016\/j.eswa.2026.132578_bib0041","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"1588","article-title":"Revisiting point cloud classification: A new benchmark dataset and classification model on real-world data","author":"Uy","year":"2019"},{"key":"10.1016\/j.eswa.2026.132578_bib0042","series-title":"International conference on machine learning","first-page":"6438","article-title":"Manifold mixup: Better representations by interpolating hidden states","author":"Verma","year":"2019"},{"key":"10.1016\/j.eswa.2026.132578_bib0043","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"9782","article-title":"Unsupervised point cloud pre-training via occlusion completion","author":"Wang","year":"2021"},{"key":"10.1016\/j.eswa.2026.132578_bib0044","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"14330","article-title":"Sample-adaptive augmentation for point cloud recognition against real-world corruptions","author":"Wang","year":"2023"},{"key":"10.1016\/j.eswa.2026.132578_bib0045","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"10296","article-title":"Graph attention convolution for point cloud semantic segmentation","author":"Wang","year":"2019"},{"issue":"5","key":"10.1016\/j.eswa.2026.132578_bib0046","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3326362","article-title":"Dynamic graph cnn for learning on point clouds","volume":"38","author":"Wang","year":"2019","journal-title":"ACM Transactions on Graphics (tog)"},{"key":"10.1016\/j.eswa.2026.132578_bib0047","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"5686","article-title":"Pointpatchmix: Point cloud mixing with patch scoring","volume":"38","author":"Wang","year":"2024"},{"key":"10.1016\/j.eswa.2026.132578_bib0048","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision (ICCV)","article-title":"Take-a-photo: 3D-to-2D generative pre-training of point cloud models","author":"Wang","year":"2023"},{"key":"10.1016\/j.eswa.2026.132578_bib0049","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"9621","article-title":"Pointconv: Deep convolutional networks on 3D point clouds","author":"Wu","year":"2019"},{"key":"10.1016\/j.eswa.2026.132578_bib0050","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"5251","article-title":"Spatiotemporal self-supervised learning for point clouds in the wild","author":"Wu","year":"2023"},{"key":"10.1016\/j.eswa.2026.132578_bib0051","doi-asserted-by":"crossref","first-page":"11035","DOI":"10.52202\/068431-0802","article-title":"Polarmix: A general data augmentation technique for lidar point clouds","volume":"35","author":"Xiao","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.132578_bib0052","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"3173","article-title":"Paconv: Position adaptive convolution with dynamic kernel assembling on point clouds","author":"Xu","year":"2021"},{"key":"10.1016\/j.eswa.2026.132578_bib0053","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"3056","article-title":"Learning geometry-disentangled representation for complementary understanding of 3D object point cloud","volume":"35","author":"Xu","year":"2021"},{"key":"10.1016\/j.eswa.2026.132578_bib0054","series-title":"Proceedings of the european conference on computer vision (ECCV)","first-page":"87","article-title":"Spidercnn: Deep learning on point sets with parameterized convolutional filters","author":"Xu","year":"2018"},{"key":"10.1016\/j.eswa.2026.132578_bib0055","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"14530","article-title":"Implicit autoencoder for point-cloud self-supervised representation learning","author":"Yan","year":"2023"},{"key":"10.1016\/j.eswa.2026.132578_bib0056","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"19313","article-title":"Point-bert: Pre-training 3D point cloud transformers with masked point modeling","author":"Yu","year":"2022"},{"key":"10.1016\/j.eswa.2026.132578_bib0057","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"6023","article-title":"Cutmix: Regularization strategy to train strong classifiers with localizable features","author":"Yun","year":"2019"},{"issue":"1","key":"10.1016\/j.eswa.2026.132578_bib0058","article-title":"Pcalign: A general data augmentation framework for point clouds","volume":"14","author":"Zhang","year":"2024","journal-title":"Scientific Reports"},{"issue":"12","key":"10.1016\/j.eswa.2026.132578_bib0059","doi-asserted-by":"crossref","first-page":"11985","DOI":"10.1002\/int.23073","article-title":"Pvt: Point-voxel transformer for point cloud learning","volume":"37","author":"Zhang","year":"2022","journal-title":"International Journal of Intelligent Systems"},{"key":"10.1016\/j.eswa.2026.132578_bib0060","unstructured":"Zhang, H., Cisse, M., Dauphin, Y. N., & Lopez-Paz, D. (2017). mixup: Beyond empirical risk minimization. arXiv: 1710.09412."},{"key":"10.1016\/j.eswa.2026.132578_bib0061","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1016\/j.neucom.2022.07.049","article-title":"Pointcutmix: Regularization strategy for point cloud classification","volume":"505","author":"Zhang","year":"2022","journal-title":"Neurocomputing"},{"key":"10.1016\/j.eswa.2026.132578_bib0062","doi-asserted-by":"crossref","unstructured":"Zhang, R., Wang, L., Guo, Z., Wang, Y., Gao, P., Li, H., & Shi, J. (2023). Parameter is not all you need: Starting from non-parametric networks for 3D point cloud analysis. arXiv: 2303.08134.","DOI":"10.1109\/CVPR52729.2023.00517"},{"key":"10.1016\/j.eswa.2026.132578_bib0063","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"10121","article-title":"Point cloud mamba: Point cloud learning via state space model","volume":"39","author":"Zhang","year":"2025"},{"key":"10.1016\/j.eswa.2026.132578_bib0064","doi-asserted-by":"crossref","first-page":"2247","DOI":"10.3390\/rs16122247","article-title":"LiDAR point cloud augmentation for adverse conditions using conditional generative models","volume":"16","author":"Zhang","year":"2024","journal-title":"Remote Sensing"},{"key":"10.1016\/j.eswa.2026.132578_bib0065","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"16259","article-title":"Point transformer","author":"Zhao","year":"2021"},{"key":"10.1016\/j.eswa.2026.132578_bib0066","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"22935","article-title":"Point cloud pre-training with diffusion models","author":"Zheng","year":"2024"},{"key":"10.1016\/j.eswa.2026.132578_bib0067","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"13001","article-title":"Random erasing data augmentation","volume":"34","author":"Zhong","year":"2020"},{"key":"10.1016\/j.eswa.2026.132578_bib0068","series-title":"36Th british machine vision conference 2025, BMVC 2025, sheffield, uk, november 24\u201327, 2025","article-title":"Generative data augmentation for object point cloud segmentation","author":"Zhu","year":"2025"},{"key":"10.1016\/j.eswa.2026.132578_bib0069","series-title":"European conference on computer vision","first-page":"633","article-title":"Automix: Mixup networks for sample interpolation via cooperative barycenter learning","author":"Zhu","year":"2020"}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426014910?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426014910?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T07:29:03Z","timestamp":1782286143000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0957417426014910"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":69,"alternative-id":["S0957417426014910"],"URL":"https:\/\/doi.org\/10.1016\/j.eswa.2026.132578","relation":{},"ISSN":["0957-4174"],"issn-type":[{"value":"0957-4174","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Beyond empirical risk: Achieving point cloud robustness through margin refinement and data purification","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.eswa.2026.132578","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"132578"}}