{"id":"https://openalex.org/W4394047473","doi":"https://doi.org/10.5281/zenodo.5883456","title":"Webis-MS-MARCO-Anchor-Texts-22","display_name":"Webis-MS-MARCO-Anchor-Texts-22","publication_year":2022,"publication_date":"2022-01-20","ids":{"openalex":"https://openalex.org/W4394047473","doi":"https://doi.org/10.5281/zenodo.5883456"},"language":"en","primary_location":{"id":"pmh:oai:zenodo.org:5883456","is_oa":true,"landing_page_url":"https://zenodo.org/record/5883456","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"dataset"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://zenodo.org/record/5883456","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068616222","display_name":"Maik Fr\u00f6be","orcid":"https://orcid.org/0000-0002-1003-981X"},"institutions":[{"id":"https://openalex.org/I68956291","display_name":"Martin Luther University Halle-Wittenberg","ror":"https://ror.org/05gqaka33","country_code":"DE","type":"education","lineage":["https://openalex.org/I68956291"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Fr\u00f6be, Maik","raw_affiliation_strings":["Martin-Luther-Universit\u00e4t Halle-Wittenberg"],"raw_orcid":"https://orcid.org/0000-0002-1003-981X","affiliations":[{"raw_affiliation_string":"Martin-Luther-Universit\u00e4t Halle-Wittenberg","institution_ids":["https://openalex.org/I68956291"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101535412","display_name":"Sebastian G\u00fcnther","orcid":"https://orcid.org/0000-0003-0371-3594"},"institutions":[{"id":"https://openalex.org/I68956291","display_name":"Martin Luther University Halle-Wittenberg","ror":"https://ror.org/05gqaka33","country_code":"DE","type":"education","lineage":["https://openalex.org/I68956291"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"G\u00fcnther, Sebastian","raw_affiliation_strings":["Martin-Luther-Universit\u00e4t Halle-Wittenberg"],"raw_orcid":"https://orcid.org/0000-0003-0371-3594","affiliations":[{"raw_affiliation_string":"Martin-Luther-Universit\u00e4t Halle-Wittenberg","institution_ids":["https://openalex.org/I68956291"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015325792","display_name":"Maximilian Probst Gutenberg","orcid":"https://orcid.org/0000-0003-3522-156X"},"institutions":[{"id":"https://openalex.org/I68956291","display_name":"Martin Luther University Halle-Wittenberg","ror":"https://ror.org/05gqaka33","country_code":"DE","type":"education","lineage":["https://openalex.org/I68956291"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Probst, Maximilian","raw_affiliation_strings":["Martin-Luther-Universit\u00e4t Halle-Wittenberg"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Martin-Luther-Universit\u00e4t Halle-Wittenberg","institution_ids":["https://openalex.org/I68956291"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083712311","display_name":"Martin Potthast","orcid":"https://orcid.org/0000-0003-2451-0665"},"institutions":[{"id":"https://openalex.org/I926574661","display_name":"Leipzig University","ror":"https://ror.org/03s7gtk40","country_code":"DE","type":"education","lineage":["https://openalex.org/I926574661"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Potthast, Martin","raw_affiliation_strings":["Leipzig University"],"raw_orcid":"https://orcid.org/0000-0003-2451-0665","affiliations":[{"raw_affiliation_string":"Leipzig University","institution_ids":["https://openalex.org/I926574661"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014322854","display_name":"Matthias Hagen","orcid":"https://orcid.org/0000-0002-9733-2890"},"institutions":[{"id":"https://openalex.org/I68956291","display_name":"Martin Luther University Halle-Wittenberg","ror":"https://ror.org/05gqaka33","country_code":"DE","type":"education","lineage":["https://openalex.org/I68956291"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hagen, Matthias","raw_affiliation_strings":["Martin-Luther-Universit\u00e4t Halle-Wittenberg"],"raw_orcid":"https://orcid.org/0000-0002-9733-2890","affiliations":[{"raw_affiliation_string":"Martin-Luther-Universit\u00e4t Halle-Wittenberg","institution_ids":["https://openalex.org/I68956291"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.37439998984336853,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.37439998984336853,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.03840000182390213,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.038100000470876694,"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":0.37103980779647827}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.37103980779647827}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:zenodo.org:5883456","is_oa":true,"landing_page_url":"https://zenodo.org/record/5883456","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"dataset"},{"id":"doi:10.5281/zenodo.5883456","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.5883456","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Dataset"}],"best_oa_location":{"id":"pmh:oai:zenodo.org:5883456","is_oa":true,"landing_page_url":"https://zenodo.org/record/5883456","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"dataset"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829"],"abstract_inverted_index":{"The":[0,29,137,160],"Webis":[1,167],"MS":[2,18,98,123,168],"MARCO":[3,19,99,124,169],"Anchor":[4,100,125,170,268],"Text":[5,101,126,171,269],"2022":[6,102,127,172],"dataset":[7,103,128,139,173],"enriches":[8,104],"Version":[9,87,94,108,114],"1":[10,88,109],"and":[11,60,89,110,134,143,158,198,201,204,207,228,231,234,237,240,243],"2":[12,115],"of":[13,17,83,91,121,162,165,267],"the":[14,35,84,97,122,147,163,166,177,271],"document":[15],"collection":[16],"with":[20,52,66,116,140],"anchor":[21,48,56,62,70,77,117,149],"text":[22,78],"extracted":[23,148],"from":[24],"six":[25,30],"Common":[26,31],"Crawl":[27,32],"snapshots.":[28],"snapshots":[33],"cover":[34],"years":[36],"2016":[37],"to":[38],"2021":[39],"(between":[40],"1.7-3.4":[41],"billion":[42],"documents":[43,51,65,85,92,106,112],"each).":[44],"We":[45],"sampled":[46],"1,000":[47,55,69],"texts":[49,57,63,71,150],"for":[50,64,81,93,107,113,146],"more":[53],"than":[54,68],"at":[58],"random":[59],"all":[61,76,144],"less":[67],"(this":[72],"sampling":[73],"yields":[74],"that":[75],"is":[79,153],"included":[80],"94%":[82],"in":[86,131,176,213,256,270],"97%":[90],"2).":[95],"Overall,":[96],"1,703,834":[105],"4,821,244":[111],"text.":[118],"Cleaned":[119],"versions":[120],"are":[129,174],"available":[130,154],"ir_datasets,":[132],"Zenodo":[133],"Hugging":[135,156],"Face.":[136],"raw":[138],"additional":[141],"information":[142],"metadata":[145],"(roughly":[151],"100GB)":[152],"on":[155,219],"Face":[157],"files.webis.de.":[159],"details":[161],"construction":[164],"described":[175],"associated":[178],"paper.":[179],"If":[180],"you":[181],"use":[182],"this":[183],"dataset,":[184],"please":[185],"cite<br>":[186],"<code>@InProceedings{froebe:2022a,<br>":[187],"address":[188],"=":[189,195,211,225,247,250,253,260,264,276],"{Berlin":[190],"Heidelberg":[191],"New":[192],"York},<br>":[193],"author":[194],"{Maik":[196],"Fr{\\\"o}be":[197],"Sebastian":[199],"G{\\\"u}nther":[200],"Maximilian":[202],"Probst":[203],"Martin":[205],"Potthast":[206],"Matthias":[208],"Hagen},<br>":[209],"booktitle":[210],"{Advances":[212],"Information":[214],"Retrieval.":[215],"44th":[216],"European":[217],"Conference":[218],"IR":[220],"Research":[221],"(ECIR":[222],"2022)},<br>":[223],"editor":[224],"{Matthias":[226],"Hagen":[227],"Suzan":[229],"Verberne":[230],"Craig":[232],"Macdonald":[233],"Christin":[235],"Seifert":[236],"Krisztian":[238],"Balog":[239],"Kjetil":[241],"N{\\o}rv\\r{a}g":[242],"Vinay":[244],"Setty},<br>":[245],"month":[246],"apr,<br>":[248],"publisher":[249],"{Springer},<br>":[251],"series":[252],"{Lecture":[254],"Notes":[255],"Computer":[257],"Science},<br>":[258],"site":[259],"{Stavanger,":[261],"Norway},<br>":[262],"title":[263],"{{The":[265],"Power":[266],"Neural":[272],"Retrieval":[273],"Era}},<br>":[274],"year":[275],"2022<br>":[277],"}</code>":[278]},"counts_by_year":[],"updated_date":"2026-07-23T13:24:44.402172","created_date":"2025-10-10T00:00:00"}