{"id":"https://openalex.org/W4399364148","doi":"https://doi.org/10.1145/3630106.3659033","title":"A Critical Analysis of the Largest Source for Generative AI Training Data: Common Crawl","display_name":"A Critical Analysis of the Largest Source for Generative AI Training Data: Common Crawl","publication_year":2024,"publication_date":"2024-06-03","ids":{"openalex":"https://openalex.org/W4399364148","doi":"https://doi.org/10.1145/3630106.3659033"},"language":"en","primary_location":{"id":"doi:10.1145/3630106.3659033","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3630106.3659033","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 2024 ACM Conference on Fairness, Accountability, and Transparency","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014487236","display_name":"Stefan Baack","orcid":"https://orcid.org/0000-0002-2464-7699"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Stefan Baack","raw_affiliation_strings":["Mozilla Foundation, Germany"],"raw_orcid":"https://orcid.org/0000-0002-2464-7699","affiliations":[{"raw_affiliation_string":"Mozilla Foundation, Germany","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5014487236"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":15.5757,"has_fulltext":false,"cited_by_count":47,"citation_normalized_percentile":{"value":0.99452526,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2199","last_page":"2208"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10028","display_name":"Topic Modeling","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10260","display_name":"Software Engineering Research","score":0.9972000122070312,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9925000071525574,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/transparency","display_name":"Transparency (behavior)","score":0.6012172698974609},{"id":"https://openalex.org/keywords/popularity","display_name":"Popularity","score":0.5929499864578247},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5724303126335144},{"id":"https://openalex.org/keywords/reflection","display_name":"Reflection (computer programming)","score":0.5662049651145935},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5515506267547607},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5086151361465454},{"id":"https://openalex.org/keywords/accountability","display_name":"Accountability","score":0.45902472734451294},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3651334345340729},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3363149166107178},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1455153524875641},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.11158096790313721},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.10223028063774109}],"concepts":[{"id":"https://openalex.org/C2780233690","wikidata":"https://www.wikidata.org/wiki/Q535347","display_name":"Transparency (behavior)","level":2,"score":0.6012172698974609},{"id":"https://openalex.org/C2780586970","wikidata":"https://www.wikidata.org/wiki/Q1357284","display_name":"Popularity","level":2,"score":0.5929499864578247},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5724303126335144},{"id":"https://openalex.org/C65682993","wikidata":"https://www.wikidata.org/wiki/Q1056451","display_name":"Reflection (computer programming)","level":2,"score":0.5662049651145935},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5515506267547607},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5086151361465454},{"id":"https://openalex.org/C2776007630","wikidata":"https://www.wikidata.org/wiki/Q2798912","display_name":"Accountability","level":2,"score":0.45902472734451294},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3651334345340729},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3363149166107178},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1455153524875641},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.11158096790313721},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.10223028063774109},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3630106.3659033","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3630106.3659033","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 2024 ACM Conference on Fairness, Accountability, and Transparency","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2301953046","https://openalex.org/W2325014739","https://openalex.org/W2989539713","https://openalex.org/W3001128645","https://openalex.org/W3043315258","https://openalex.org/W3118781290","https://openalex.org/W3133702157","https://openalex.org/W3169705981","https://openalex.org/W3189849087","https://openalex.org/W3198173902","https://openalex.org/W3207830467","https://openalex.org/W4200514127","https://openalex.org/W4232488826","https://openalex.org/W4250532311","https://openalex.org/W4287752787","https://openalex.org/W4288089799","https://openalex.org/W4292779060","https://openalex.org/W4307225507","https://openalex.org/W4308586485","https://openalex.org/W4308760226","https://openalex.org/W4311642023","https://openalex.org/W4322718191","https://openalex.org/W4327743697","https://openalex.org/W4327860312","https://openalex.org/W4362655426","https://openalex.org/W4379468930","https://openalex.org/W4382140993","https://openalex.org/W4385245566","https://openalex.org/W6948966457"],"related_works":["https://openalex.org/W2368605798","https://openalex.org/W2518037665","https://openalex.org/W2348524959","https://openalex.org/W2477036161","https://openalex.org/W2368049389","https://openalex.org/W2384861574","https://openalex.org/W4294565801","https://openalex.org/W2170801710","https://openalex.org/W2952704802","https://openalex.org/W3199802296"],"abstract_inverted_index":{"Common":[0,72,93,100,144],"Crawl":[1,73,145],"is":[2,28,75,80,138],"the":[3,15,39,89,117,132],"largest":[4],"freely":[5],"available":[6],"collection":[7],"of":[8,14,19,38,66,91],"web":[9],"crawl":[10],"data":[11,21,42],"and":[12,32,58,110,120,147],"one":[13],"most":[16],"important":[17],"sources":[18],"pre-training":[20,41],"for":[22,55,103,107],"large":[23,36],"language":[24],"models":[25],"(LLMs).":[26],"It":[27],"used":[29],"so":[30],"frequently":[31],"makes":[33],"up":[34],"such":[35],"proportions":[37],"overall":[40],"in":[43,112],"many":[44],"cases":[45],"that":[46],"it":[47,126],"arguably":[48],"has":[49],"become":[50],"a":[51],"foundational":[52],"building":[53],"block":[54],"LLM":[56,86,104],"development,":[57],"subsequently":[59],"generative":[60,113],"AI":[61,114,133],"products":[62],"built":[63],"on":[64,140],"top":[65],"LLMs.":[67],"Despite":[68],"its":[69,128],"pivotal":[70],"role,":[71],"itself":[74],"not":[76],"widely":[77],"understood,":[78],"nor":[79],"there":[81],"much":[82],"reflection":[83],"evident":[84],"among":[85],"builders":[87],"about":[88],"implications":[90],"using":[92],"Crawl's":[94,101],"data.":[95],"This":[96],"paper":[97],"discusses":[98],"what":[99],"popularity":[102],"development":[105],"means":[106],"fairness,":[108],"accountability,":[109],"transparency":[111],"by":[115],"highlighting":[116],"organization's":[118],"values":[119],"practices,":[121],"as":[122,124],"well":[123],"how":[125],"views":[127],"own":[129],"role":[130],"within":[131],"ecosystem.":[134],"Our":[135],"qualitative":[136],"analysis":[137],"based":[139],"in-depth":[141],"interviews":[142],"with":[143],"staffers":[146],"relevant":[148],"online":[149],"documents.":[150]},"counts_by_year":[{"year":2026,"cited_by_count":16},{"year":2025,"cited_by_count":29},{"year":2024,"cited_by_count":2}],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-10-10T00:00:00"}