{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T06:33:27Z","timestamp":1761806007853,"version":"build-2065373602"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032095268","type":"print"},{"value":"9783032095275","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T00:00:00Z","timestamp":1761696000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T00:00:00Z","timestamp":1761696000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-09527-5_12","type":"book-chapter","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T06:28:30Z","timestamp":1761805710000},"page":"216-234","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Proxy-Enriched Imputation on\u00a0Contextually Incomplete Web Tables"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5832-9154","authenticated-orcid":false,"given":"Denis","family":"Nagel","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jonas","family":"MeiSSner","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1564-9340","authenticated-orcid":false,"given":"Niklas","family":"Kiehne","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5443-1215","authenticated-orcid":false,"given":"Wolf-Tilo","family":"Balke","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,10,29]]},"reference":[{"key":"12_CR1","unstructured":"Angelidakis, H., Kurpisz, A., Sering, L., Zenklusen, R.: Fair and fast k-center clustering for data summarization. In: International Conference on Machine Learning, vol.\u00a0162, pp. 669\u2013702, ICML 2022, 17-23 July 2022, Baltimore. Proceedings of Machine Learning Research. PMLR (2022)"},{"key":"12_CR2","doi-asserted-by":"crossref","unstructured":"Boquet, G., Vicario, J.L., Morell, A., Serrano, J.: Missing data in traffic estimation: a variational autoencoder imputation method. In: ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE (2019)","DOI":"10.1109\/ICASSP.2019.8683011"},{"key":"12_CR3","doi-asserted-by":"crossref","unstructured":"Brickley, D., Burgess, M., Noy, N.: Google dataset search: building a search engine for datasets in an open web ecosystem. In: The World Wide Web Conference, pp. 1365\u20131375. WWW \u201919, Association for Computing Machinery, New York (2019)","DOI":"10.1145\/3308558.3313685"},{"issue":"9","key":"12_CR4","doi-asserted-by":"publisher","first-page":"3212","DOI":"10.1109\/TKDE.2020.2967722","volume":"33","author":"L Caruccio","year":"2021","unstructured":"Caruccio, L., Deufemia, V., Naumann, F., Polese, G.: Discovering relaxed functional dependencies based on multi-attribute dominance. IEEE Trans. Knowl. Data Eng. 33(9), 3212\u20133228 (2021)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"12_CR5","doi-asserted-by":"crossref","unstructured":"Chaudhuri, S., Ding, B., Kandula, S.: Approximate query processing: No silver bullet. In: Proceedings of the 2017 ACM International Conference on Management of Data, SIGMOD Conference 2017, pp. 511\u2013519, Chicago, May 14-19. ACM (2017)","DOI":"10.1145\/3035918.3056097"},{"key":"12_CR6","doi-asserted-by":"publisher","unstructured":"Chen, J., Xu, Y., Wang, P., Yang, Y.: Deep generative imputation model for missing not at random data. In: Proceedings of the 32nd ACM International Conference on Information and Knowledge Management, CIKM 2023, pp. 316\u2013325, Birmingham, October 21-25. ACM (2023). https:\/\/doi.org\/10.1145\/3583780.3614835","DOI":"10.1145\/3583780.3614835"},{"key":"12_CR7","unstructured":"Chen, X., Fain, B., Lyu, L., Munagala, K.: Proportionally fair clustering. In: Proceedings of the 36th International Conference on Machine Learning, vol.\u00a097, pp. 1032\u20131041, ICML 2019, 9-15 June 2019, Long Beach. Proceedings of Machine Learning Research. PMLR (2019)"},{"key":"12_CR8","doi-asserted-by":"crossref","unstructured":"Domeniconi, C., Yan, B.: Nearest neighbor ensemble. In: 17th International Conference on Pattern Recognition, pp. 228\u2013231, ICPR 2004, Cambridge, August 23-26, 2004. IEEE Computer Society (2004)","DOI":"10.1109\/ICPR.2004.1334065"},{"issue":"9","key":"12_CR9","doi-asserted-by":"publisher","first-page":"938","DOI":"10.14778\/2777598.2777603","volume":"8","author":"XL Dong","year":"2015","unstructured":"Dong, X.L., et al.: Knowledge-based trust: estimating the trustworthiness of web sources. Proc. VLDB Endow. 8(9), 938\u2013949 (2015)","journal-title":"Proc. VLDB Endow."},{"key":"12_CR10","doi-asserted-by":"crossref","unstructured":"Dong, Y., Takeoka, K., Xiao, C., Oyamada, M.: Efficient joinable table discovery in data lakes: a high-dimensional similarity-based approach. In: 37th IEEE International Conference on Data Engineering, pp. 456\u2013467, ICDE 2021, Chania, Greece, April 19-22, 2021. IEEE (2021)","DOI":"10.1109\/ICDE51399.2021.00046"},{"issue":"10","key":"12_CR11","doi-asserted-by":"publisher","first-page":"2458","DOI":"10.14778\/3603581.3603587","volume":"16","author":"Y Dong","year":"2023","unstructured":"Dong, Y., Xiao, C., Nozawa, T., Enomoto, M., Oyamada, M.: Deepjoin: joinable table discovery with pre-trained language models. Proc. VLDB Endow. 16(10), 2458\u20132470 (2023)","journal-title":"Proc. VLDB Endow."},{"key":"12_CR12","unstructured":"Elhamifar, E., Kaluza, M.C.D.P.: Subset selection and summarization in sequential data. In: Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, pp. 1035\u20131045, December 4-9, 2017, Long Beach (2017)"},{"key":"12_CR13","doi-asserted-by":"publisher","first-page":"1945","DOI":"10.14778\/3137765.3137815","volume":"10","author":"N Hassan","year":"2017","unstructured":"Hassan, N., et al.: Claimbuster: the first-ever end-to-end fact-checking system. Proc. VLDB Endowment 10, 1945\u20131948 (2017)","journal-title":"Proc. VLDB Endowment"},{"key":"12_CR14","doi-asserted-by":"publisher","unstructured":"Heymans, M.W., Twisk, J.W.: Handling missing data in clinical research. J. Clin. Epidemiol. 151, 185\u2013188 (2022). https:\/\/doi.org\/10.1016\/j.jclinepi.2022.08.016, https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0895435622002189","DOI":"10.1016\/j.jclinepi.2022.08.016"},{"key":"12_CR15","doi-asserted-by":"crossref","unstructured":"Jo, S., et al.: Verifying text summaries of relational data sets. In: Proceedings of the 2019 International Conference on Management of Data, p. 299\u2013316. SIGMOD \u201919, Association for Computing Machinery, New York (2019)","DOI":"10.1145\/3299869.3300074"},{"issue":"12","key":"12_CR16","doi-asserted-by":"publisher","first-page":"2965","DOI":"10.14778\/3415478.3415520","volume":"13","author":"G Karagiannis","year":"2020","unstructured":"Karagiannis, G., Saeed, M., Papotti, P., Trummer, I.: Scrutinizer: fact checking statistical claims. Proc. VLDB Endowment 13(12), 2965\u20132968 (2020)","journal-title":"Proc. VLDB Endowment"},{"key":"12_CR17","doi-asserted-by":"crossref","unstructured":"Li, Q., Li, Y., Gao, J., Zhao, B., Fan, W., Han, J.: Resolving conflicts in heterogeneous data by truth discovery and source reliability estimation. In: Proceedings of the 2014 ACM SIGMOD International Conference on Management of Data, pp. 1187\u20131198. SIGMOD \u201914, Association for Computing Machinery, New York (2014)","DOI":"10.1145\/2588555.2610509"},{"key":"12_CR18","unstructured":"Ma, C., Zhang, C.: Identifiable generative models for missing not at random data imputation. In: Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, pp. 27645\u201327658, December 6-14, 2021, virtual (2021). https:\/\/proceedings.neurips.cc\/paper\/2021\/hash\/e8a642ed6a9ad20fb159472950db3d65-Abstract.html"},{"key":"12_CR19","doi-asserted-by":"crossref","unstructured":"Mall, R., Jumutc, V., Langone, R., Suykens, J.A.K.: Representative subsets for big data learning using k-NN graphs. In: 2014 IEEE International Conference on Big Data (IEEE BigData 2014), pp. 37\u201342, Washington, October 27-30. IEEE Computer Society (2014)","DOI":"10.1109\/BigData.2014.7004210"},{"key":"12_CR20","unstructured":"Mattei, P., Frellsen, J.: MIWAE: deep generative modelling and imputation of incomplete data sets. In: Proceedings of the 36th International Conference on Machine Learning, ICML 2019, 9-15 June 2019, Long Beach, California. Proceedings of Machine Learning Research, PMLR (2019)"},{"key":"12_CR21","doi-asserted-by":"crossref","unstructured":"Mei, Y., Song, S., Fang, C., Yang, H., Fang, J., Long, J.: Capturing semantics for imputation with pre-trained language models. In: 37th IEEE International Conference on Data Engineering, ICDE 2021, Chania, Greece, April 19-22, 2021. IEEE (2021)","DOI":"10.1109\/ICDE51399.2021.00013"},{"key":"12_CR22","doi-asserted-by":"crossref","unstructured":"Nagel, D., Affeldt, T., Voges, N., G\u00fcntzer, U., Balke, W.T.: Binding data narrations - corroborating the plausibility of scientific narratives by open research data. In: 2023 ACM\/IEEE Joint Conference on Digital Libraries (JCDL). Santa Fe (2023)","DOI":"10.1109\/JCDL57899.2023.00028"},{"issue":"12","key":"12_CR23","doi-asserted-by":"publisher","first-page":"1986","DOI":"10.14778\/3352063.3352116","volume":"12","author":"F Nargesian","year":"2019","unstructured":"Nargesian, F., Zhu, E., Miller, R.J., Pu, K.Q., Arocena, P.C.: Data lake management: challenges and opportunities. Proc. VLDB Endow. 12(12), 1986\u20131989 (2019)","journal-title":"Proc. VLDB Endow."},{"issue":"7","key":"12_CR24","doi-asserted-by":"publisher","first-page":"813","DOI":"10.14778\/3192965.3192973","volume":"11","author":"F Nargesian","year":"2018","unstructured":"Nargesian, F., Zhu, E., Pu, K.Q., Miller, R.J.: Table union search on open data. Proc. VLDB Endow. 11(7), 813\u2013825 (2018)","journal-title":"Proc. VLDB Endow."},{"key":"12_CR25","doi-asserted-by":"crossref","unstructured":"Paton, N.W., Chen, J., Wu, Z.: Dataset discovery and exploration: a survey. ACM Comput. Surv. 56(4) (2023)","DOI":"10.1145\/3626521"},{"key":"12_CR26","doi-asserted-by":"publisher","unstructured":"Pereira, R.C., Abreu, P.H., Rodrigues, P.P., Figueiredo, M.A.: Imputation of data missing not at random: Artificial generation and benchmark analysis. Expert Syst. Appl. 249, 123654 (2024). https:\/\/doi.org\/10.1016\/j.eswa.2024.123654, https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0957417424005207","DOI":"10.1016\/j.eswa.2024.123654"},{"key":"12_CR27","doi-asserted-by":"crossref","unstructured":"Psychogyios, K., Ilias, L., Askounis, D.: Comparison of missing data imputation methods using the framingham heart study dataset. In: IEEE-EMBS International Conference on Biomedical and Health Informatics, BHI 2022, pp.\u00a01\u20135, Ioannina, Greece, September 27-30, 2022. IEEE (2022)","DOI":"10.1109\/BHI56158.2022.9926882"},{"key":"12_CR28","doi-asserted-by":"crossref","unstructured":"Reimers, N., Gurevych, I.: Sentence-BERT: Sentence embeddings using siamese BERT-networks. CoRR abs\/1908.10084 (2019)","DOI":"10.18653\/v1\/D19-1410"},{"key":"12_CR29","unstructured":"Robinson, J., Wingate, D.: Leveraging large language models for multiple choice question answering. In: The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. OpenReview.net (2023)"},{"issue":"1","key":"12_CR30","doi-asserted-by":"publisher","first-page":"112","DOI":"10.1093\/bioinformatics\/btr597","volume":"28","author":"DJ Stekhoven","year":"2012","unstructured":"Stekhoven, D.J., B\u00fchlmann, P.: Missforest - non-parametric missing value imputation for mixed-type data. Bioinform. 28(1), 112\u2013118 (2012)","journal-title":"Bioinform."},{"key":"12_CR31","doi-asserted-by":"crossref","unstructured":"Tabibian, B., Valera, I., Farajtabar, M., Song, L., Sch\u00f6lkopf, B., Gomez-Rodriguez, M.: Distilling information reliability and source trustworthiness from digital traces. In: Proceedings of the 26th International Conference on World Wide Web, pp. 847\u2013855. WWW \u201917, International World Wide Web Conferences Steering Committee, Republic and Canton of Geneva, CHE (2017)","DOI":"10.1145\/3038912.3052672"},{"key":"12_CR32","unstructured":"Touvron, H., et al.: Llama 2: Open foundation and fine-tuned chat models (2023)"},{"key":"12_CR33","doi-asserted-by":"crossref","unstructured":"Vrande\u010di\u0107, D., Kr\u00f6tzsch, M.: Wikidata: a free collaborative knowledgebase. Commun. ACM 57(10), 78\u201385 (2014)","DOI":"10.1145\/2629489"},{"key":"12_CR34","unstructured":"Wei, K., Iyer, R.K., Bilmes, J.A.: Submodularity in data subset selection and active learning. In: Proceedings of the 32nd International Conference on Machine Learning, ICML 2015, Lille, France, 6-11 July 2015 (2015)"},{"key":"12_CR35","unstructured":"World Health Organization: Global health observatory (2023). https:\/\/www.who.int\/data\/gho"},{"key":"12_CR36","unstructured":"World Health Organization: Health equity assessment toolkit (2023). https:\/\/www.who.int\/data\/inequality-monitor\/assessment_toolkit"},{"key":"12_CR37","doi-asserted-by":"crossref","unstructured":"Wang, Y., Francesco\u00a0Fabbri, M.M.: Fair and representative subset selection from data streams. In: WWW \u201921: The Web Conference 2021, Virtual Event \/ Ljubljana, Slovenia, April 19-23, 2021 (2021)","DOI":"10.1145\/3442381.3449799"},{"key":"12_CR38","unstructured":"Yoon, J., Jordon, J., van\u00a0der Schaar, M.: GAIN: missing data imputation using generative adversarial nets. In: Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsm\u00e4ssan, vol.\u00a080, pp. 5675\u20135684, Stockholm, July 10-15, 2018. Proceedings of Machine Learning Research. PMLR (2018)"},{"key":"12_CR39","doi-asserted-by":"crossref","unstructured":"Zhang, M., Mundra, P., Chikweze, C., Nargesian, F., Weikum, G.: Approximate query answering over open data. In: Proceedings of the Workshop on Human-In-the-Loop Data Analytics, HILDA 2023, pp. 11:1\u201311:3, Seattle, 18 June 2023. ACM (2023)","DOI":"10.1145\/3597465.3605227"},{"key":"12_CR40","unstructured":"Zheng, C., Zhou, H., Meng, F., Zhou, J., Huang, M.: Large language models are not robust multiple choice selectors. In: The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, May 7-11, 2024. OpenReview.net (2024)"}],"container-title":["Lecture Notes in Computer Science","The Semantic Web \u2013 ISWC 2025"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-09527-5_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T06:28:41Z","timestamp":1761805721000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-09527-5_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,29]]},"ISBN":["9783032095268","9783032095275"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-09527-5_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,29]]},"assertion":[{"value":"29 October 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The code, including\u00a0all data sets and narratives, can be found on\n                      \n                      .","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Supplemental Material Statement"}},{"value":"ISWC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Semantic Web Conference","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Nara","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 November 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"semweb2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iswc2025.semanticweb.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}