{"id":"https://openalex.org/W4396843721","doi":"https://doi.org/10.1145/3589335.3648327","title":"MS MARCO Web Search: A Large-scale Information-rich Web Dataset with Millions of Real Click Labels","display_name":"MS MARCO Web Search: A Large-scale Information-rich Web Dataset with Millions of Real Click Labels","publication_year":2024,"publication_date":"2024-05-12","ids":{"openalex":"https://openalex.org/W4396843721","doi":"https://doi.org/10.1145/3589335.3648327"},"language":"en","primary_location":{"id":"doi:10.1145/3589335.3648327","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3589335.3648327","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3589335.3648327","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM Web Conference 2024","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3589335.3648327","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070766481","display_name":"Qi Chen","orcid":"https://orcid.org/0009-0006-7394-0185"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qi Chen","raw_affiliation_strings":["Microsoft, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084564357","display_name":"Xiubo Geng","orcid":"https://orcid.org/0000-0001-6477-7933"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiubo Geng","raw_affiliation_strings":["Microsoft, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026219235","display_name":"Corby Rosset","orcid":"https://orcid.org/0000-0001-9167-6214"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Corby Rosset","raw_affiliation_strings":["Microsoft, Redmond, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5097955039","display_name":"Carolyn Buractaon","orcid":"https://orcid.org/0009-0005-2182-5145"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carolyn Buractaon","raw_affiliation_strings":["Microsoft, Redmond, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037626945","display_name":"Jingwen Lu","orcid":"https://orcid.org/0000-0001-8208-898X"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jingwen Lu","raw_affiliation_strings":["Microsoft, Redmond, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100611243","display_name":"Tao Shen","orcid":"https://orcid.org/0000-0003-3315-2468"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Tao Shen","raw_affiliation_strings":["University of Technology Sydney, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"University of Technology Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063459528","display_name":"Kun Zhou","orcid":"https://orcid.org/0000-0003-0650-9521"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Zhou","raw_affiliation_strings":["Microsoft, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006340382","display_name":"Chenyan Xiong","orcid":"https://orcid.org/0000-0002-0392-4183"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chenyan Xiong","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041448669","display_name":"Yeyun Gong","orcid":"https://orcid.org/0000-0001-9954-9674"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yeyun Gong","raw_affiliation_strings":["Microsoft, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105180968","display_name":"Paul J. Bennett","orcid":"https://orcid.org/0009-0006-7852-9651"},"institutions":[{"id":"https://openalex.org/I4210122154","display_name":"Photon Spot (United States)","ror":"https://ror.org/01yxc0v75","country_code":"US","type":"company","lineage":["https://openalex.org/I4210122154"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paul Bennett","raw_affiliation_strings":["Spotify, New York, USA"],"affiliations":[{"raw_affiliation_string":"Spotify, New York, USA","institution_ids":["https://openalex.org/I4210122154"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055132321","display_name":"Nick Craswell","orcid":"https://orcid.org/0000-0002-9351-8137"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nick Craswell","raw_affiliation_strings":["Microsoft, Redmond, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044651577","display_name":"Xing Xie","orcid":"https://orcid.org/0000-0002-8608-8482"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xing Xie","raw_affiliation_strings":["Microsoft, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100346602","display_name":"Fan Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Yang","raw_affiliation_strings":["Microsoft, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102836934","display_name":"Bryan Tower","orcid":"https://orcid.org/0000-0003-3659-6988"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bryan Tower","raw_affiliation_strings":["Microsoft, Redmond, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081428282","display_name":"Nikhil Rao","orcid":"https://orcid.org/0000-0003-0281-932X"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nikhil Rao","raw_affiliation_strings":["Microsoft, Mountain View, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, Mountain View, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028114543","display_name":"Anlei Dong","orcid":"https://orcid.org/0000-0002-8241-4746"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anlei Dong","raw_affiliation_strings":["Microsoft, Mountain View, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, Mountain View, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031344912","display_name":"Wenqi Jiang","orcid":"https://orcid.org/0000-0003-3895-7943"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Wenqi Jiang","raw_affiliation_strings":["ETH Zurich, Z\u00fcrich, Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Zurich, Z\u00fcrich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100423656","display_name":"Zheng Liu","orcid":"https://orcid.org/0000-0001-7765-8466"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Liu","raw_affiliation_strings":["Microsoft, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103208235","display_name":"Mingqin Li","orcid":"https://orcid.org/0009-0002-0270-9489"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mingqin Li","raw_affiliation_strings":["Microsoft, Redmond, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078107851","display_name":"Liu Chuan-jie","orcid":"https://orcid.org/0009-0009-0980-6936"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuanjie Liu","raw_affiliation_strings":["Microsoft, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069703521","display_name":"Zengzhong Li","orcid":"https://orcid.org/0009-0002-8243-7769"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zengzhong Li","raw_affiliation_strings":["Microsoft, Redmond, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090383211","display_name":"Rangan Majumder","orcid":"https://orcid.org/0000-0003-2430-575X"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rangan Majumder","raw_affiliation_strings":["Microsoft, Redmond, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010290944","display_name":"J. Neville","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jennifer Neville","raw_affiliation_strings":["Microsoft, Redmond, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013051953","display_name":"Andy Oakley","orcid":"https://orcid.org/0009-0002-7208-2933"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andy Oakley","raw_affiliation_strings":["Microsoft, Redmond, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083087030","display_name":"Knut Magne Risvik","orcid":null},"institutions":[{"id":"https://openalex.org/I4210135422","display_name":"Microsoft (Norway)","ror":"https://ror.org/03jtz4s80","country_code":"NO","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210135422"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Knut Magne Risvik","raw_affiliation_strings":["Microsoft, Oslo, Norway"],"affiliations":[{"raw_affiliation_string":"Microsoft, Oslo, Norway","institution_ids":["https://openalex.org/I4210135422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079988301","display_name":"Harsha Vardhan Simhadri","orcid":"https://orcid.org/0000-0002-9323-2227"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Harsha Vardhan Simhadri","raw_affiliation_strings":["Microsoft, Redmond, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051880496","display_name":"Manik Varma","orcid":null},"institutions":[{"id":"https://openalex.org/I4210124949","display_name":"Microsoft Research (India)","ror":"https://ror.org/02w7f3w92","country_code":"IN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210124949"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Manik Varma","raw_affiliation_strings":["Microsoft, Bengaluru, India"],"affiliations":[{"raw_affiliation_string":"Microsoft, Bengaluru, India","institution_ids":["https://openalex.org/I4210124949"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100776576","display_name":"Yujing Wang","orcid":"https://orcid.org/0000-0002-7940-5216"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yujing Wang","raw_affiliation_strings":["Microsoft, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036126537","display_name":"Linjun Yang","orcid":"https://orcid.org/0009-0001-1778-7167"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Linjun Yang","raw_affiliation_strings":["Microsoft, Redmond, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100438310","display_name":"Mao Yang","orcid":"https://orcid.org/0009-0009-6455-3898"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mao Yang","raw_affiliation_strings":["Microsoft, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100383731","display_name":"Ce Zhang","orcid":"https://orcid.org/0000-0002-8105-7505"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Ce Zhang","raw_affiliation_strings":["ETH Z\u00fcrich, Z\u00fcrich, Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich, Z\u00fcrich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":6,"institutions_distinct_count":31,"corresponding_author_ids":["https://openalex.org/A5070766481"],"corresponding_institution_ids":["https://openalex.org/I4210113369"],"apc_list":null,"apc_paid":null,"fwci":1.7296,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.85199746,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"292","last_page":"301"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9909999966621399,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9527000188827515,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7649210691452026},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5945354104042053},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5616459250450134},{"id":"https://openalex.org/keywords/web-application","display_name":"Web application","score":0.4895723760128021},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4638206362724304},{"id":"https://openalex.org/keywords/click-through-rate","display_name":"Click-through rate","score":0.42312347888946533},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.1079396903514862},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.06894400715827942}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7649210691452026},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5945354104042053},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5616459250450134},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.4895723760128021},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4638206362724304},{"id":"https://openalex.org/C115174607","wikidata":"https://www.wikidata.org/wiki/Q1100934","display_name":"Click-through rate","level":2,"score":0.42312347888946533},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.1079396903514862},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.06894400715827942}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3589335.3648327","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3589335.3648327","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3589335.3648327","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM Web Conference 2024","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2405.07526","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.07526","pdf_url":"https://arxiv.org/pdf/2405.07526","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3589335.3648327","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3589335.3648327","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3589335.3648327","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM Web Conference 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5299999713897705,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4396843721.pdf"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W2124509324","https://openalex.org/W2132234208","https://openalex.org/W2133995768","https://openalex.org/W2136189984","https://openalex.org/W2142920810","https://openalex.org/W2144684817","https://openalex.org/W2186845332","https://openalex.org/W2560674852","https://openalex.org/W2757662681","https://openalex.org/W2803620078","https://openalex.org/W2912924812","https://openalex.org/W2913954081","https://openalex.org/W2950729111","https://openalex.org/W2963213349","https://openalex.org/W2998702515","https://openalex.org/W3093655911","https://openalex.org/W3094444847","https://openalex.org/W3137305332","https://openalex.org/W3148323213","https://openalex.org/W3153094109","https://openalex.org/W3188983256","https://openalex.org/W4221166196","https://openalex.org/W4224438163","https://openalex.org/W4251326898","https://openalex.org/W4284685333","https://openalex.org/W4284691825","https://openalex.org/W4306317399","https://openalex.org/W4320465836","https://openalex.org/W4322617770","https://openalex.org/W4385572804","https://openalex.org/W6810139940","https://openalex.org/W6850138286"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W4286419063","https://openalex.org/W2011720192","https://openalex.org/W3189010682","https://openalex.org/W4213212078","https://openalex.org/W2890330992","https://openalex.org/W3011869339","https://openalex.org/W3152321673","https://openalex.org/W4377236619","https://openalex.org/W2580385364"],"abstract_inverted_index":{"Recent":[0],"breakthroughs":[1],"in":[2,60,100,132],"large":[3,80],"models":[4],"have":[5],"highlighted":[6],"the":[7,25,111,127],"critical":[8],"significance":[9],"of":[10,33,54],"data":[11,120],"scale,":[12],"labels":[13],"and":[14,45,57,73,104,118,134],"modals.":[15],"In":[16],"this":[17],"paper,":[18],"we":[19],"introduce":[20],"MS":[21,83,122,137],"MARCO":[22,84,123,138],"Web":[23,85,124,139],"Search,":[24],"first":[26,112],"large-scale":[27],"information-rich":[28],"web":[29,43,93],"dataset,":[30],"featuring":[31],"millions":[32],"real":[34,117],"clicked":[35],"query-document":[36],"labels.":[37],"This":[38],"dataset":[39,113,141],"closely":[40],"mimics":[41],"real-world":[42],"document":[44],"query":[46],"distribution,":[47],"provides":[48],"rich":[49,119],"information":[50,76,105],"for":[51,129],"various":[52,61],"kinds":[53],"downstream":[55],"tasks":[56,96],"encourages":[58],"research":[59,108],"areas,":[62],"such":[63],"as":[64],"generic":[65,70],"end-to-end":[66],"neural":[67],"indexer":[68],"models,":[69,72],"embedding":[71],"next":[74],"generation":[75],"access":[77],"system":[78,107,135],"with":[79,91],"language":[81],"models.":[82],"Search":[86,125,140],"offers":[87],"a":[88],"retrieval":[89,94,106],"benchmark":[90],"three":[92],"challenge":[95],"that":[97,114],"demands":[98],"innovations":[99],"both":[101],"machine":[102],"learning":[103],"domains.":[109],"As":[110],"meets":[115],"large,":[116],"requirements,":[121],"paves":[126],"way":[128],"future":[130],"advancements":[131],"AI":[133],"research.":[136],"is":[142],"available":[143],"at:":[144],"https://github.com/microsoft/MS-MARCO-Web-Search.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}
