{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,15]],"date-time":"2025-07-15T03:18:43Z","timestamp":1752549523098,"version":"3.41.2"},"reference-count":15,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2002,4,1]],"date-time":"2002-04-01T00:00:00Z","timestamp":1017619200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2002,4,1]],"date-time":"2002-04-01T00:00:00Z","timestamp":1017619200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Data Mining and Knowledge Discovery"],"published-print":{"date-parts":[[2002,4]]},"DOI":"10.1023\/a:1014095614948","type":"journal-article","created":{"date-parts":[[2002,12,28]],"date-time":"2002-12-28T14:42:56Z","timestamp":1041086576000},"page":"173-190","source":"Crossref","is-referenced-by-count":34,"title":["Likelihood-Based Data Squashing: A Modeling Approach to Instance Construction"],"prefix":"10.1007","volume":"6","author":[{"given":"David","family":"Madigan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nandini","family":"Raghavan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"William","family":"Dumouchel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Martha","family":"Nason","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christian","family":"Posse","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Greg","family":"Ridgeway","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"394823_CR1","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1023\/A:1022689900470","volume":"6","author":"D.W. Aha","year":"1991","unstructured":"Aha, D.W., Kilber, D., and Albert, M. K. 1991. Instance-based learning algorithms. Machine Learning, 6:37\u201366.","journal-title":"Machine Learning"},{"key":"394823_CR2","volume-title":"Empirical Model Building and Response Surfaces","author":"G.E.P. Box","year":"1987","unstructured":"Box, G.E.P. and Draper, N.R. 1987. Empirical Model Building and Response Surfaces. New York, USA: John Wiley & Sons."},{"key":"394823_CR3","volume-title":"Statistics for Experimenters: An Introduction to Design, Data Analysis, and Model Building","author":"C.E.P. Box","year":"1978","unstructured":"Box, C.E.P., Hunter, W.G., and Hunter, J.S. 1978. Statistics for Experimenters: An Introduction to Design, Data Analysis, and Model Building. New York, USA: John Wiley & Sons."},{"key":"394823_CR4","unstructured":"Bradley, P.S., Fayyad, U., and Reina, C. 1998. Scaling clustering algorithms to large databases. In Proceedings of the Fourth International Conference on Knowledge Discovery and Data Mining, pp. 9\u201315."},{"key":"394823_CR5","first-page":"191","volume-title":"Statistical Signal Processing","author":"L. Breiman","year":"1984","unstructured":"Breiman, L. and Friedman, J. 1984. Tools for large data set analysis. In Statistical Signal Processing, Edward J. Wegman and James G. Smith (Eds). New York: M. Dekker, pp. 191\u2013197."},{"key":"394823_CR6","doi-asserted-by":"crossref","unstructured":"Catlett, J. Megainduction: A test flight. 1991. In Proceedings of the Eighth International Workshop on Machine Learning, pp. 596\u2013599.","DOI":"10.1016\/B978-1-55860-200-7.50121-5"},{"key":"394823_CR7","doi-asserted-by":"crossref","unstructured":"DuMouchel, W., Volinsky, C., Johnson, T., Cortes, C., and Pregibon, D. 1999. Squashing flat files flatter. In Proceedings of the Fifth ACM Conference on Knowledge Discovery and Data Mining, pp. 6\u201315.","DOI":"10.1145\/312129.312184"},{"key":"394823_CR8","doi-asserted-by":"crossref","first-page":"499","DOI":"10.1080\/00401706.1974.10489231","volume":"16","author":"G.M. Furnival","year":"1974","unstructured":"Furnival, G.M. and Wilson, R.W. 1974. Regression by leaps and bounds. Technometrics, 16: 499\u2013511.","journal-title":"Technometrics"},{"key":"394823_CR9","doi-asserted-by":"crossref","first-page":"779","DOI":"10.1145\/242223.242300","volume":"28","author":"G.A. Gibson","year":"1996","unstructured":"Gibson, G.A., Vitter, J.S., and Wilkes, J. 1996. Report of the working group on storage I\/O issues in large-scale computing. ACM Computing Surveys, 28:779\u2013793.","journal-title":"ACM Computing Surveys"},{"key":"394823_CR10","doi-asserted-by":"crossref","first-page":"318","DOI":"10.2307\/2530022","volume":"34","author":"J. Lawless","year":"1978","unstructured":"Lawless, J. and Singhal, K. 1978. Efficient screening of nonnormal regression models. Biometrics, 34, pp. 318\u2013327.","journal-title":"Biometrics"},{"key":"394823_CR11","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1023\/A:1009876119989","volume":"3","author":"F. Provost","year":"1989","unstructured":"Provost, F. and Kolluri, V. 1989. A survey of methods for scaling up inductive algorithms. Journal of Data Mining and Knowledge Discovery, 3: 131\u2013169.","journal-title":"Journal of Data Mining and Knowledge Discovery"},{"key":"394823_CR12","doi-asserted-by":"crossref","first-page":"461","DOI":"10.1214\/aos\/1176344136","volume":"6","author":"G. Schwarz","year":"1978","unstructured":"Schwarz, G. 1978. Estimating the dimension of a model. Annals of Statistics, 6: 461\u2013464.","journal-title":"Annals of Statistics"},{"key":"394823_CR13","doi-asserted-by":"crossref","unstructured":"Syed, N.A., Liu, H., and Sung, K.K. 1999. A study of support vectors on model independent example selection. In Proceedings of the Fifth ACM Conference on Knowledge Discovery and Data Mining, pp. 272\u2013276.","DOI":"10.1145\/312129.312245"},{"key":"394823_CR14","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4757-2719-7","volume-title":"Modern Applied Statistics with S-PLUS","author":"W.N. Venables","year":"1997","unstructured":"Venables, W.N. and Ripley, B.D. 1997. Modern Applied Statistics with S-PLUS. New York: Springer-Verlag."},{"key":"394823_CR15","doi-asserted-by":"crossref","unstructured":"Zhang, T., Ramakrishnan, R., and Livny, M. 1996. Birch: An efficient data clustering method for large databases. In Proceedings of the 1996 ACM SIGMOD International Conference on Management of Data, pp. 103\u2013114.","DOI":"10.1145\/233269.233324"}],"container-title":["Data Mining and Knowledge Discovery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1023\/A:1014095614948.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1023\/A:1014095614948\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1023\/A:1014095614948.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,14]],"date-time":"2025-07-14T02:41:50Z","timestamp":1752460910000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1023\/A:1014095614948"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2002,4]]},"references-count":15,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2002,4]]}},"alternative-id":["394823"],"URL":"https:\/\/doi.org\/10.1023\/a:1014095614948","relation":{},"ISSN":["1384-5810","1573-756X"],"issn-type":[{"type":"print","value":"1384-5810"},{"type":"electronic","value":"1573-756X"}],"subject":[],"published":{"date-parts":[[2002,4]]}}}