{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T12:04:40Z","timestamp":1784203480387,"version":"3.55.0"},"reference-count":50,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100002635","name":"Inha University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002635","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.neunet.2026.108932","type":"journal-article","created":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T06:14:40Z","timestamp":1776233680000},"page":"108932","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["MultiTabPFN: Codebook-based extensions of TabPFN for high-class-count tabular classification"],"prefix":"10.1016","volume":"202","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1674-7147","authenticated-orcid":false,"given":"Kyungeun","family":"Lee","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.108932_bib0001","unstructured":"Achiam, J., Adler, S., Agarwal, S., Ahmad, L., Akkaya, I., Aleman, F. L., Almeida, D., Altenschmidt, J., Altman, S., Anadkat, S. et al. (2023). GPT-4 technical report. arXiv preprint arXiv: 2303.08774."},{"issue":"Dec","key":"10.1016\/j.neunet.2026.108932_bib0002","first-page":"113","article-title":"Reducing multiclass to binary: A unifying approach for margin classifiers","volume":"1","author":"Allwein","year":"2000","journal-title":"Journal of Machine Learning Research"},{"key":"10.1016\/j.neunet.2026.108932_bib0003","article-title":"An inductive bias for tabular deep learning","volume":"36","author":"Beyazit","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.108932_bib0004","unstructured":"Bommasani, R., Hudson, D. A., Adeli, E., Altman, R., Arora, S., von Arx, S., Bernstein, M. S., Bohg, J., Bosselut, A., Brunskill, E. et al. (2021). On the opportunities and risks of foundation models. arXiv preprint arXiv: 2108.07258."},{"key":"10.1016\/j.neunet.2026.108932_bib0005","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"11114","article-title":"HyperFast: Instant classification for tabular data","volume":"vol. 38","author":"Bonet","year":"2024"},{"key":"10.1016\/j.neunet.2026.108932_bib0006","series-title":"Proceedings of the 22nd ACM sigkdd international conference on knowledge discovery and data mining","first-page":"785","article-title":"XGBoost: A scalable tree boosting system","author":"Chen","year":"2016"},{"key":"10.1016\/j.neunet.2026.108932_bib0007","unstructured":"Cheng, Z.-J., Jia, Z.-Y., Zhou, Z., Li, Y.-F., & Guo, L.-Z. (2025). Realistic evaluation of tabPFN v2 in open environments. arXiv preprint arXiv: 2505.16226."},{"key":"10.1016\/j.neunet.2026.108932_bib0008","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1613\/jair.105","article-title":"Solving multiclass learning problems via error-correcting output codes","volume":"2","author":"Dietterich","year":"1994","journal-title":"Journal of Artificial Intelligence Research"},{"key":"10.1016\/j.neunet.2026.108932_bib0009","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S. et al. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv: 2010.11929."},{"issue":"1","key":"10.1016\/j.neunet.2026.108932_bib0010","doi-asserted-by":"crossref","first-page":"120","DOI":"10.1109\/TPAMI.2008.266","article-title":"On the decoding process in ternary error-correcting output codes","volume":"32","author":"Escalera","year":"2008","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2026.108932_bib0011","series-title":"International conference on artificial intelligence and statistics","first-page":"8053","article-title":"The role of codeword-to-class assignments in error-correcting codes: An empirical study","author":"Evron","year":"2023"},{"key":"10.1016\/j.neunet.2026.108932_bib0012","unstructured":"Feuer, B., Hegde, C., & Cohen, N. (2023). Scaling TabPFN: Sketching and feature selection for tabular prior-data fitted networks. arXiv preprint arXiv: 2311.10609."},{"key":"10.1016\/j.neunet.2026.108932_bib0013","doi-asserted-by":"crossref","first-page":"83430","DOI":"10.52202\/079017-2654","article-title":"TuneTables: Context optimization for scalable prior-data fitted networks","volume":"37","author":"Feuer","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.108932_bib0014","unstructured":"Garg, A., Ali, M., Hollmann, N., Purucker, L., M\u00fcller, S., & Hutter, F. (2025). Real-tabPFN: Improving tabular foundation models via continued pre-training with real-world data. arXiv preprint arXiv: 2507.03971."},{"key":"10.1016\/j.neunet.2026.108932_bib0015","unstructured":"Gorishniy, Y., Rubachev, I., Kartashev, N., Shlenskii, D., Kotelnikov, A., & Babenko, A. (2023). TabR: Unlocking the power of retrieval-augmented tabular deep learning. arXiv preprint arXiv: 2307.14338."},{"key":"10.1016\/j.neunet.2026.108932_bib0016","first-page":"18932","article-title":"Revisiting deep learning models for tabular data","volume":"34","author":"Gorishniy","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.108932_bib0017","series-title":"Uncertainty in artificial intelligence","first-page":"1724","article-title":"Integer programming-based error-correcting output code design for robust classification","author":"Gupta","year":"2021"},{"key":"10.1016\/j.neunet.2026.108932_bib0018","doi-asserted-by":"crossref","first-page":"10094","DOI":"10.52202\/068431-0733","article-title":"Scalable design of error-correcting output codes using discrete optimization with graph coloring","volume":"35","author":"Gupta","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.108932_bib0019","article-title":"Classification by pairwise coupling","volume":"10","author":"Hastie","year":"1997","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.108932_bib0020","unstructured":"Hollmann, N., M\u00fcller, S., Eggensperger, K., & Hutter, F. (2022). TabPFN: A transformer that solves small tabular classification problems in a second. arXiv preprint arXiv: 2207.01848."},{"key":"10.1016\/j.neunet.2026.108932_bib0021","doi-asserted-by":"crossref","DOI":"10.1038\/s41586-024-08328-6","article-title":"Accurate predictions on small data with a tabular foundation model","author":"Hollmann","year":"2025","journal-title":"Nature"},{"issue":"6","key":"10.1016\/j.neunet.2026.108932_bib0022","doi-asserted-by":"crossref","first-page":"11298","DOI":"10.1109\/TNNLS.2024.3454598","article-title":"Instance-specific loss-weighted decoding for decomposition-based multiclass classification","volume":"36","author":"Jia","year":"2024","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.neunet.2026.108932_bib0023","article-title":"LightGBM: A highly efficient gradient boosting decision tree","volume":"30","author":"Ke","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.108932_bib0024","series-title":"Machine learning proceedings 1995","first-page":"313","article-title":"Error-correcting output coding corrects bias and variance","author":"Kong","year":"1995"},{"key":"10.1016\/j.neunet.2026.108932_bib0025","unstructured":"Lee, K., Eo, M., Cho, H.-S., Kim, D., Sim, Y. S., Kim, S., Suh, M.-K., & Lim, W. (2025). MultiTab: A comprehensive benchmark suite for multi-dimensional evaluation in tabular domains. arXiv preprint arXiv: 2505.14312."},{"key":"10.1016\/j.neunet.2026.108932_bib0026","doi-asserted-by":"crossref","unstructured":"Lee, K., Eo,M., Cho, H.-S., Suh, M.-K., Kim, S., Sim, Y. S, yoon, S., yoon, S., Lim, W. (2025). Range-limited augmentation for few-shot learning in tabular data with comprehensive benchmark. In Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V. 2, 1262\u20131273.","DOI":"10.1145\/3711896.3737098"},{"key":"10.1016\/j.neunet.2026.108932_bib0027","unstructured":"Lee, K., Sim, Y. S., Cho, H.-S., Eo, M., Yoon, S., Yoon, S., & Lim, W. (2024). Binning as a pretext task: Improving self-supervised learning in tabular domains. arXiv preprint arXiv: 2405.07414."},{"key":"10.1016\/j.neunet.2026.108932_bib0028","unstructured":"Liu, S.-Y., & Ye, H.-J. (2025). TabPFN unleashed: A scalable and effective solution to tabular classification problems. arXiv preprint arXiv: 2502.02527."},{"key":"10.1016\/j.neunet.2026.108932_bib0029","unstructured":"Ma, J., Thomas, V., Hosseinzadeh, R., Kamkari, H., Labach, A., Cresswell, J. C., Golestan, K., Yu, G., Volkovs, M., & Caterini, A. L. (2024a). TabDPT: Scaling tabular foundation models. arXiv preprint arXiv: 2410.18164."},{"key":"10.1016\/j.neunet.2026.108932_bib0030","unstructured":"Ma, J., Thomas, V., Yu, G., & Caterini, A. (2024b). In-context data distillation with tabPFN. arXiv preprint arXiv: 2402.06971."},{"key":"10.1016\/j.neunet.2026.108932_bib0031","series-title":"The theory of error-correcting codes","volume":"volume 16","author":"MacWilliams","year":"1977"},{"key":"10.1016\/j.neunet.2026.108932_bib0032","article-title":"When do neural nets outperform boosted trees on tabular data?","volume":"36","author":"McElfresh","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.108932_bib0033","unstructured":"M\u00fcller, S., Hollmann, N., Arango, S. P., Grabocka, J., & Hutter, F. (2021). Transformers can do Bayesian inference. arXiv preprint arXiv: 2112.10510."},{"key":"10.1016\/j.neunet.2026.108932_bib0034","article-title":"CatBoost: Unbiased boosting with categorical features","volume":"31","author":"Prokhorenkova","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"6","key":"10.1016\/j.neunet.2026.108932_bib0035","doi-asserted-by":"crossref","first-page":"1007","DOI":"10.1109\/TPAMI.2006.116","article-title":"Discriminant ECOC: A heuristic method for application dependent design of error correcting output codes","volume":"28","author":"Pujol","year":"2006","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2026.108932_bib0036","unstructured":"Qu, J., Holzm\u00c3\u017eller, D., Varoquaux, G., & Morvan, M. L. (2025). TabICL: A tabular foundation model for in-context learning on large data. arXiv preprint arXiv: 2502.05564."},{"key":"10.1016\/j.neunet.2026.108932_bib0037","series-title":"International conference on machine learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"issue":"140","key":"10.1016\/j.neunet.2026.108932_bib0038","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of Machine Learning Research"},{"issue":"Jan","key":"10.1016\/j.neunet.2026.108932_bib0039","first-page":"101","article-title":"In defense of one-vs-all classification","volume":"5","author":"Rifkin","year":"2004","journal-title":"Journal of Machine Learning Research"},{"key":"10.1016\/j.neunet.2026.108932_bib0040","unstructured":"Rubachev, I., Kartashev, N., Gorishniy, Y., & Babenko, A. (2024). TabReD: Analyzing pitfalls and filling the gaps in tabular deep learning benchmarks. arXiv preprint arXiv: 2406.19380."},{"key":"10.1016\/j.neunet.2026.108932_bib0041","doi-asserted-by":"crossref","first-page":"108439","DOI":"10.52202\/079017-3442","article-title":"Retrieval & fine-tuning for in-context tabular models","volume":"37","author":"Thomas","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.108932_bib0042","unstructured":"Touvron, H., Martin, L., Stone, K., Albert, P., Almahairi, A., Babaei, Y., Bashlykov, N., Batra, S., Bhargava, P., Bhosale, S. et al. (2023). Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv: 2307.09288."},{"key":"10.1016\/j.neunet.2026.108932_bib0043","unstructured":"Van Breugel, B., & Van Der Schaar, M. (2024). Why tabular foundation models should be a research priority. arXiv preprint arXiv: 2405.01147."},{"key":"10.1016\/j.neunet.2026.108932_bib0044","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106180","article-title":"Graph neural network contextual embedding for deep learning on tabular data","volume":"173","author":"Villaiz\u00e1n-Vallelado","year":"2024","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.108932_bib0045","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2025.107208","article-title":"Deterministic autoencoder using wasserstein loss for tabular data generation","volume":"185","author":"Wang","year":"2025","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.108932_bib0046","doi-asserted-by":"crossref","first-page":"73098","DOI":"10.52202\/079017-2327","article-title":"Towards heterogeneous long-tailed learning: benchmarking, metrics, and toolbox","volume":"37","author":"Wang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.108932_bib0047","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109957","article-title":"An adaptive error-correcting output codes algorithm based on gene expression programming and similarity measurement matrix","volume":"145","author":"Xie","year":"2024","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.neunet.2026.108932_bib0048","unstructured":"Xu, D., Cirit, O., Asadi, R., Sun, Y., & Wang, W. (2024). Mixture of in-context prompters for tabular pfns. arXiv preprint arXiv: 2405.16156."},{"key":"10.1016\/j.neunet.2026.108932_bib0049","unstructured":"Ye, H.-J., Liu, S.-Y., Cai, H.-R., Zhou, Q.-L., & Zhan, D.-C. (2024a). A closer look at deep learning on tabular data. arXiv preprint arXiv: 2407.00956."},{"key":"10.1016\/j.neunet.2026.108932_bib0050","unstructured":"Ye, H.-J., Yin, H.-H., & Zhan, D.-C. (2024b). Modern neighborhood components analysis: A deep tabular baseline two decades later. arXiv preprint arXiv: 2407.03257."}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S089360802600393X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S089360802600393X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T11:13:50Z","timestamp":1784200430000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S089360802600393X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":50,"alternative-id":["S089360802600393X"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.108932","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"MultiTabPFN: Codebook-based extensions of TabPFN for high-class-count tabular classification","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.108932","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"108932"}}