{"id":"https://openalex.org/W4415036041","doi":"https://doi.org/10.48550/arxiv.2510.09031","title":"Web Crawler Restrictions, AI Training Datasets \\& Political Biases","display_name":"Web Crawler Restrictions, AI Training Datasets \\& Political Biases","publication_year":2025,"publication_date":"2025-10-10","ids":{"openalex":"https://openalex.org/W4415036041","doi":"https://doi.org/10.48550/arxiv.2510.09031"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2510.09031","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.09031","pdf_url":"https://arxiv.org/pdf/2510.09031","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2510.09031","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027021407","display_name":"Paul Bouchaud","orcid":"https://orcid.org/0000-0002-0310-8194","observed_orcids":["https://orcid.org/0000-0002-0310-8194"]},"institutions":[{"id":"https://openalex.org/I205092303","display_name":"Institut d'Etudes Politiques de Paris","ror":"https://ror.org/05fe7ax82","country_code":"FR","type":"facility","lineage":["https://openalex.org/I205092303"]},{"id":"https://openalex.org/I4403386758","display_name":"Institut des Syst\u00e8mes Complexes Paris \u00cele-de-France","ror":"https://ror.org/04k1akk19","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I204730241","https://openalex.org/I4403386758"]},{"id":"https://openalex.org/I4405256168","display_name":"m\u00e9dialab Sciences Po","ror":"https://ror.org/03vk15693","country_code":"FR","type":"facility","lineage":["https://openalex.org/I205092303","https://openalex.org/I4405256168"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Bouchaud, Paul","raw_affiliation_strings":["ISC-PIF, m\u00e9dialab","ISC-PIF - Institut des Syst\u00e8mes Complexes - Paris Ile-de-France (57-59 rue Lhomond 75005 Paris - France)","m\u00e9dialab - m\u00e9dialab (Sciences Po) (27 rue Saint-Guillaume - 75337 Paris Cedex 07 - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ISC-PIF, m\u00e9dialab","institution_ids":["https://openalex.org/I4403386758"]},{"raw_affiliation_string":"ISC-PIF - Institut des Syst\u00e8mes Complexes - Paris Ile-de-France (57-59 rue Lhomond 75005 Paris - France)","institution_ids":["https://openalex.org/I4403386758"]},{"raw_affiliation_string":"m\u00e9dialab - m\u00e9dialab (Sciences Po) (27 rue Saint-Guillaume - 75337 Paris Cedex 07 - France)","institution_ids":["https://openalex.org/I205092303","https://openalex.org/I4405256168"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032431129","display_name":"Pedro Ramaciotti Morales","orcid":"https://orcid.org/0000-0002-3649-4503","observed_orcids":["https://orcid.org/0000-0002-3649-4503"]},"institutions":[{"id":"https://openalex.org/I205092303","display_name":"Institut d'Etudes Politiques de Paris","ror":"https://ror.org/05fe7ax82","country_code":"FR","type":"facility","lineage":["https://openalex.org/I205092303"]},{"id":"https://openalex.org/I4210098463","display_name":"Learning Planet Institute","ror":"https://ror.org/00zbj9525","country_code":"FR","type":"facility","lineage":["https://openalex.org/I154526488","https://openalex.org/I204730241","https://openalex.org/I4210098463"]},{"id":"https://openalex.org/I4403386758","display_name":"Institut des Syst\u00e8mes Complexes Paris \u00cele-de-France","ror":"https://ror.org/04k1akk19","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I204730241","https://openalex.org/I4403386758"]},{"id":"https://openalex.org/I4405256168","display_name":"m\u00e9dialab Sciences Po","ror":"https://ror.org/03vk15693","country_code":"FR","type":"facility","lineage":["https://openalex.org/I205092303","https://openalex.org/I4405256168"]},{"id":"https://openalex.org/I4405256744","display_name":"Learning Transitions","ror":"https://ror.org/04gac9b55","country_code":"FR","type":"facility","lineage":["https://openalex.org/I4210142324","https://openalex.org/I4405256744"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Ramaciotti, Pedro","raw_affiliation_strings":["ISC-PIF, m\u00e9dialab","ISC-PIF - Institut des Syst\u00e8mes Complexes - Paris Ile-de-France (57-59 rue Lhomond 75005 Paris - France)","Learning Transitions - Learning Planet Institute (LPI) - RNSR: 202324521H (8bis Rue Charles V - 75004 Paris - France)","m\u00e9dialab - m\u00e9dialab (Sciences Po) (27 rue Saint-Guillaume - 75337 Paris Cedex 07 - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ISC-PIF, m\u00e9dialab","institution_ids":["https://openalex.org/I4403386758"]},{"raw_affiliation_string":"ISC-PIF - Institut des Syst\u00e8mes Complexes - Paris Ile-de-France (57-59 rue Lhomond 75005 Paris - France)","institution_ids":["https://openalex.org/I4403386758"]},{"raw_affiliation_string":"Learning Transitions - Learning Planet Institute (LPI) - RNSR: 202324521H (8bis Rue Charles V - 75004 Paris - France)","institution_ids":["https://openalex.org/I4210098463","https://openalex.org/I4405256744"]},{"raw_affiliation_string":"m\u00e9dialab - m\u00e9dialab (Sciences Po) (27 rue Saint-Guillaume - 75337 Paris Cedex 07 - France)","institution_ids":["https://openalex.org/I205092303","https://openalex.org/I4405256168"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.5102999806404114,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.5102999806404114,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.3513000011444092,"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/T11147","display_name":"Misinformation and Its Impacts","score":0.06679999828338623,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/large-language-model-training-data","display_name":"large language model training data","score":0.8840000033378601},{"id":"https://openalex.org/keywords/factual-reporting","display_name":"factual reporting","score":0.527999997138977},{"id":"https://openalex.org/keywords/website-popularity","display_name":"website popularity","score":0.6399999856948853},{"id":"https://openalex.org/keywords/content-types","display_name":"content types","score":0.4059999883174896}],"concepts":[{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.8646000027656555},{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.7767000198364258},{"id":"https://openalex.org/C2780586970","wikidata":"https://www.wikidata.org/wiki/Q1357284","display_name":"Popularity","level":2,"score":0.7569000124931335},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5982999801635742},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5583000183105469},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5252000093460083},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.5120000243186951},{"id":"https://openalex.org/C43711488","wikidata":"https://www.wikidata.org/wiki/Q7534783","display_name":"Skew","level":2,"score":0.4207000136375427},{"id":"https://openalex.org/C85079727","wikidata":"https://www.wikidata.org/wiki/Q3560114","display_name":"Quarter (Canadian coin)","level":2,"score":0.4011000096797943},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.38519999384880066},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.38089999556541443},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3458000123500824},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.34209999442100525},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3393000066280365},{"id":"https://openalex.org/C108827166","wikidata":"https://www.wikidata.org/wiki/Q175975","display_name":"Internet privacy","level":1,"score":0.3271999955177307},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2881999909877777},{"id":"https://openalex.org/C112698675","wikidata":"https://www.wikidata.org/wiki/Q37038","display_name":"Advertising","level":1,"score":0.26350000500679016},{"id":"https://openalex.org/C101293273","wikidata":"https://www.wikidata.org/wiki/Q579716","display_name":"User-generated content","level":3,"score":0.26089999079704285},{"id":"https://openalex.org/C162446236","wikidata":"https://www.wikidata.org/wiki/Q653137","display_name":"Content analysis","level":2,"score":0.2587999999523163}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:2510.09031","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.09031","pdf_url":"https://arxiv.org/pdf/2510.09031","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:HAL:hal-05302425v1","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/hal-05302425","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"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":"2025","raw_type":"info:eu-repo/semantics/preprint"},{"id":"doi:10.48550/arxiv.2510.09031","doi":"https://doi.org/10.48550/arxiv.2510.09031","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.09031","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2510.09031","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.09031","pdf_url":"https://arxiv.org/pdf/2510.09031","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415036041.pdf","grobid_xml":"https://content.openalex.org/works/W4415036041.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1614298861","https://openalex.org/W2483215953","https://openalex.org/W2893425640","https://openalex.org/W2896457183","https://openalex.org/W2898883664","https://openalex.org/W2922862135","https://openalex.org/W2972668795","https://openalex.org/W3016719704","https://openalex.org/W3030163527","https://openalex.org/W3133702157","https://openalex.org/W3158822421","https://openalex.org/W4307020316","https://openalex.org/W4307020339","https://openalex.org/W4322718191","https://openalex.org/W4362557450","https://openalex.org/W4379468930","https://openalex.org/W4385564993","https://openalex.org/W4386246120","https://openalex.org/W4393968095","https://openalex.org/W4415222182","https://openalex.org/W4415798387","https://openalex.org/W7106250948"],"related_works":["https://openalex.org/W7223297186","https://openalex.org/W4415272390","https://openalex.org/W7162199073","https://openalex.org/W7221465563","https://openalex.org/W7222882762","https://openalex.org/W7203458031","https://openalex.org/W7208756530","https://openalex.org/W4416530742","https://openalex.org/W7111935053","https://openalex.org/W7214772368"],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2,152],"rely":[3],"on":[4,42],"web-scraped":[5],"text":[6],"for":[7,93],"training;":[8],"concurrently,":[9],"content":[10,59],"creators":[11],"are":[12],"increasingly":[13],"blocking":[14,52,136],"AI":[15,69],"crawlers":[16],"to":[17,72,91,129],"retain":[18],"control":[19],"over":[20],"their":[21,38],"data.":[22],"We":[23],"analyze":[24],"crawler":[25],"restrictions":[26,108,121],"across":[27,74],"the":[28,64,75,106,149],"top":[29,65,77],"one":[30],"million":[31],"most-visited":[32],"websites":[33,67,112],"since":[34],"2023":[35],"and":[36,58,113],"examine":[37],"potential":[39],"downstream":[40],"effects":[41],"training":[43,140],"data":[44],"composition.":[45],"Our":[46,131],"analysis":[47],"reveals":[48],"growing":[49],"restrictions,":[50],"with":[51,95,101,115],"patterns":[53,137],"varying":[54],"by":[55,154],"website":[56],"popularity":[57],"type.":[60],"A":[61],"quarter":[62],"of":[63,84,124,151],"thousand":[66],"restrict":[68],"crawlers,":[70],"decreasing":[71],"one-tenth":[73],"broader":[76],"million.":[78],"Content":[79],"type":[80],"matters":[81],"significantly:":[82],"34.2%":[83],"news":[85],"outlets":[86,94,100,126],"disallow":[87],"OpenAI's":[88],"GPTBot,":[89],"rising":[90],"55%":[92],"high":[96],"factual":[97,117],"reporting.":[98],"Additionally,":[99],"neutral":[102],"political":[103],"positions":[104],"impose":[105,119],"strongest":[107],"(58%),":[109],"whereas":[110],"hyperpartisan":[111],"those":[114],"low":[116],"reporting":[118],"fewer":[120],"-only":[122],"4.1%":[123],"right-leaning":[125],"block":[127],"access":[128],"OpenAI.":[130],"findings":[132],"suggest":[133],"that":[134],"heterogeneous":[135],"may":[138],"skew":[139],"datasets":[141],"toward":[142],"low-quality":[143],"or":[144],"polarized":[145],"content,":[146],"potentially":[147],"affecting":[148],"capabilities":[150],"served":[153],"prominent":[155],"AI-as-a-Service":[156],"providers.":[157]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-10T00:00:00"}
