{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T05:03:17Z","timestamp":1755838997131,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":30,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,7,25]],"date-time":"2020-07-25T00:00:00Z","timestamp":1595635200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,7,25]]},"DOI":"10.1145\/3397271.3401212","type":"proceedings-article","created":{"date-parts":[[2020,7,25]],"date-time":"2020-07-25T07:50:08Z","timestamp":1595663408000},"page":"1997-2000","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["Sampling Bias Due to Near-Duplicates in Learning to Rank"],"prefix":"10.1145","author":[{"given":"Maik","family":"Fr\u00f6be","sequence":"first","affiliation":[{"name":"Martin-Luther-Universit\u00e4t Halle-Wittenberg, Halle, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Janek","family":"Bevendorff","sequence":"additional","affiliation":[{"name":"Bauhaus-Universit\u00e4t Weimar, Weimar, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jan Heinrich","family":"Reimer","sequence":"additional","affiliation":[{"name":"Martin-Luther-Universit\u00e4t Halle-Wittenberg, Halle, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Martin","family":"Potthast","sequence":"additional","affiliation":[{"name":"Leipzig University, Leipzig, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matthias","family":"Hagen","sequence":"additional","affiliation":[{"name":"Martin-Luther-Universit\u00e4t Halle-Wittenberg, Halle, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2020,7,25]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Proc. of CIKM","author":"Ai Q.","year":"2018","unstructured":"Q. Ai , J. Mao , Y. Liu , W. B. Croft . 2018 . Unbiased Learning to Rank: Theory and Practice . In Proc. of CIKM 2018. ACM, 2305--2306. Q. Ai, J. Mao, Y. Liu, W. B. Croft. 2018. Unbiased Learning to Rank: Theory and Practice. In Proc. of CIKM 2018. ACM, 2305--2306."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/1099554.1099733"},{"key":"e_1_3_2_2_3_1","volume-title":"Proc. of the Yahoo! Learning to Rank Challenge, held at ICML","author":"Chapelle O.","year":"2011","unstructured":"O. Chapelle , Y. Chang . 2011 . Yahoo! Learning to Rank Challenge Overview . In Proc. of the Yahoo! Learning to Rank Challenge, held at ICML 2010. PMLR, 1--24. O. Chapelle, Y. Chang. 2011. Yahoo! Learning to Rank Challenge Overview. In Proc. of the Yahoo! Learning to Rank Challenge, held at ICML 2010. PMLR, 1--24."},{"key":"e_1_3_2_2_4_1","volume-title":"Proc. of TREC. NIST.","author":"Clarke C. L. A.","year":"2004","unstructured":"C. L. A. Clarke , N. Craswell , I. Soboroff . 2004 . Overview of the TREC 2004 Terabyte Track . In Proc. of TREC. NIST. C. L. A. Clarke, N. Craswell, I. Soboroff. 2004. Overview of the TREC 2004 Terabyte Track. In Proc. of TREC. NIST."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10791-011-9162-z"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3274784.3274788"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331303"},{"key":"e_1_3_2_2_8_1","volume-title":"The Lemur Project-Wiki-RankLib. Lemur Project","author":"Dang V.","year":"2013","unstructured":"V. Dang . 2013. The Lemur Project-Wiki-RankLib. Lemur Project ( 2013 ). Available: https:\/\/sourceforge.net\/p\/lemur\/wiki\/RankLib. V. Dang. 2013. The Lemur Project-Wiki-RankLib. Lemur Project (2013). Available: https:\/\/sourceforge.net\/p\/lemur\/wiki\/RankLib."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/LAWEB.2003.1250280"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.5555\/945365.964285"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-45442-5_2"},{"key":"e_1_3_2_2_12_1","volume-title":"MIREX: MapReduce Information Retrieval Experiments. Tech. Report TR-CTIT-10--15.","author":"Hiemstra D.","year":"2010","unstructured":"D. Hiemstra , C. Hauff . 2010 . MIREX: MapReduce Information Retrieval Experiments. Tech. Report TR-CTIT-10--15. (2010). D. Hiemstra, C. Hauff. 2010. MIREX: MapReduce Information Retrieval Experiments. Tech. Report TR-CTIT-10--15. (2010)."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-12844-3_38"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3018661.3018699"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2396761.2398691"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/2348283.2348464"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10791-006-9019-z"},{"key":"e_1_3_2_2_18_1","volume-title":"Selection Bias in the LETOR Datasets. In SIGIR Workshop on Learning to Rank for Information Retrieval. ACM, 48--51","author":"Minka T.","year":"2008","unstructured":"T. Minka , S. Robertson . 2008 . Selection Bias in the LETOR Datasets. In SIGIR Workshop on Learning to Rank for Information Retrieval. ACM, 48--51 . T. Minka, S. Robertson. 2008. Selection Bias in the LETOR Datasets. In SIGIR Workshop on Learning to Rank for Information Retrieval. ACM, 48--51."},{"key":"e_1_3_2_2_19_1","volume-title":"Proc. of the Workshop on Cognitive Computation at NIPS","author":"Nguyen T.","year":"2016","unstructured":"T. Nguyen , M. Rosenberg , X. Song , J. Gao , S. Tiwary , R. Majumder , L. Deng . 2016 . MS MARCO: A Human Generated MAchine Reading COmprehension Dataset . In Proc. of the Workshop on Cognitive Computation at NIPS 2016. CEUR-WS.org. T. Nguyen, M. Rosenberg, X. Song, J. Gao, S. Tiwary, R. Majumder, L. Deng. 2016. MS MARCO: A Human Generated MAchine Reading COmprehension Dataset. In Proc. of the Workshop on Cognitive Computation at NIPS 2016. CEUR-WS.org."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380255"},{"key":"e_1_3_2_2_21_1","volume-title":"abs\/1306.2597","author":"Qin T.","year":"2013","unstructured":"T. Qin , T. Liu . 2013. Introducing LETOR 4.0 Datasets . Co RR , Vol . abs\/1306.2597 ( 2013 ). T. Qin, T. Liu. 2013. Introducing LETOR 4.0 Datasets. CoRR, Vol. abs\/1306.2597 (2013)."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/2124295.2124396"},{"key":"e_1_3_2_2_23_1","volume-title":"Overly Optimistic Prediction Results on Imbalanced Data: Flaws and Benefits of Applying Over-sampling. CoRR","author":"Vandewiele G.","year":"2020","unstructured":"G. Vandewiele , I. Dehaene , G. Kov\u00e1cs , L. Sterckx , O. Janssens , F. Ongenae , F. De Backere , F. De Turck , K. Roelens , J. Decruyenaere , S. Van Hoecke , T. Demeester . 2020. Overly Optimistic Prediction Results on Imbalanced Data: Flaws and Benefits of Applying Over-sampling. CoRR , Vol. abs\/ 2001 .06296 ( 2020 ). G. Vandewiele, I. Dehaene, G. Kov\u00e1cs, L. Sterckx, O. Janssens, F. Ongenae, F. De Backere, F. De Turck, K. Roelens, J. Decruyenaere, S. Van Hoecke, T. Demeester. 2020. Overly Optimistic Prediction Results on Imbalanced Data: Flaws and Benefits of Applying Over-sampling. CoRR, Vol. abs\/2001.06296 (2020)."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0306-4573(03)00063-3"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/2911451.2911537"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3159652.3159732"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10791-009-9112-1"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080721"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015425"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/2600428.2609634"}],"event":{"name":"SIGIR '20: The 43rd International ACM SIGIR conference on research and development in Information Retrieval","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"],"location":"Virtual Event China","acronym":"SIGIR '20"},"container-title":["Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3397271.3401212","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3397271.3401212","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:41:43Z","timestamp":1750200103000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3397271.3401212"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7,25]]},"references-count":30,"alternative-id":["10.1145\/3397271.3401212","10.1145\/3397271"],"URL":"https:\/\/doi.org\/10.1145\/3397271.3401212","relation":{},"subject":[],"published":{"date-parts":[[2020,7,25]]},"assertion":[{"value":"2020-07-25","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}