{"id":"https://openalex.org/W4385990940","doi":"https://doi.org/10.1007/978-3-031-41682-8_22","title":"CCpdf: Building a\u00a0High Quality Corpus for\u00a0Visually Rich Documents from\u00a0Web Crawl Data","display_name":"CCpdf: Building a\u00a0High Quality Corpus for\u00a0Visually Rich Documents from\u00a0Web Crawl Data","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4385990940","doi":"https://doi.org/10.1007/978-3-031-41682-8_22"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-41682-8_22","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-41682-8_22","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","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/A5011962351","display_name":"Micha\u0142 Turski","orcid":"https://orcid.org/0000-0002-4341-3062"},"institutions":[{"id":"https://openalex.org/I59411706","display_name":"Adam Mickiewicz University in Pozna\u0144","ror":"https://ror.org/04g6bbq64","country_code":"PL","type":"education","lineage":["https://openalex.org/I59411706"]}],"countries":["PL"],"is_corresponding":true,"raw_author_name":"Micha\u0142 Turski","raw_affiliation_strings":["Adam Mickiewicz University, Pozna\u0144, Poland","Snowflake, Warsaw, Poland"],"affiliations":[{"raw_affiliation_string":"Adam Mickiewicz University, Pozna\u0144, Poland","institution_ids":["https://openalex.org/I59411706"]},{"raw_affiliation_string":"Snowflake, Warsaw, Poland","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054685387","display_name":"Tomasz Stanis\u0142awek","orcid":"https://orcid.org/0000-0003-1046-7563"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tomasz Stanis\u0142awek","raw_affiliation_strings":["Snowflake, Warsaw, Poland"],"affiliations":[{"raw_affiliation_string":"Snowflake, Warsaw, Poland","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008212803","display_name":"Karol Kaczmarek","orcid":"https://orcid.org/0009-0008-4287-305X"},"institutions":[{"id":"https://openalex.org/I59411706","display_name":"Adam Mickiewicz University in Pozna\u0144","ror":"https://ror.org/04g6bbq64","country_code":"PL","type":"education","lineage":["https://openalex.org/I59411706"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Karol Kaczmarek","raw_affiliation_strings":["Adam Mickiewicz University, Pozna\u0144, Poland","Snowflake, Warsaw, Poland"],"affiliations":[{"raw_affiliation_string":"Adam Mickiewicz University, Pozna\u0144, Poland","institution_ids":["https://openalex.org/I59411706"]},{"raw_affiliation_string":"Snowflake, Warsaw, Poland","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079629977","display_name":"Pawe\u0142 Dyda","orcid":null},"institutions":[{"id":"https://openalex.org/I59411706","display_name":"Adam Mickiewicz University in Pozna\u0144","ror":"https://ror.org/04g6bbq64","country_code":"PL","type":"education","lineage":["https://openalex.org/I59411706"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Pawe\u0142 Dyda","raw_affiliation_strings":["Adam Mickiewicz University, Pozna\u0144, Poland","Snowflake, Warsaw, Poland"],"affiliations":[{"raw_affiliation_string":"Adam Mickiewicz University, Pozna\u0144, Poland","institution_ids":["https://openalex.org/I59411706"]},{"raw_affiliation_string":"Snowflake, Warsaw, Poland","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077188385","display_name":"Filip Grali\u0144ski","orcid":"https://orcid.org/0000-0001-8066-4533"},"institutions":[{"id":"https://openalex.org/I59411706","display_name":"Adam Mickiewicz University in Pozna\u0144","ror":"https://ror.org/04g6bbq64","country_code":"PL","type":"education","lineage":["https://openalex.org/I59411706"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Filip Grali\u0144ski","raw_affiliation_strings":["Adam Mickiewicz University, Pozna\u0144, Poland","Snowflake, Warsaw, Poland"],"affiliations":[{"raw_affiliation_string":"Adam Mickiewicz University, Pozna\u0144, Poland","institution_ids":["https://openalex.org/I59411706"]},{"raw_affiliation_string":"Snowflake, Warsaw, Poland","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5011962351"],"corresponding_institution_ids":["https://openalex.org/I59411706"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":1.5997,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.84662862,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"348","last_page":"365"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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":0.9998000264167786,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9997000098228455,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9944000244140625,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.9009153842926025},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.767533004283905},{"id":"https://openalex.org/keywords/upload","display_name":"Upload","score":0.760988175868988},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6511222124099731},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.5605543255805969},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5381056070327759},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5303343534469604},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5045152902603149},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46953117847442627},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.46442878246307373},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4516644775867462},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.41001784801483154},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3547047972679138}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9009153842926025},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.767533004283905},{"id":"https://openalex.org/C71901391","wikidata":"https://www.wikidata.org/wiki/Q7126699","display_name":"Upload","level":2,"score":0.760988175868988},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6511222124099731},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.5605543255805969},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5381056070327759},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5303343534469604},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5045152902603149},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46953117847442627},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.46442878246307373},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4516644775867462},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.41001784801483154},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3547047972679138},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"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/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-031-41682-8_22","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-41682-8_22","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6499999761581421,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1966382373","https://openalex.org/W2123766055","https://openalex.org/W2801930304","https://openalex.org/W2962772269","https://openalex.org/W2965373594","https://openalex.org/W2981852735","https://openalex.org/W2989539713","https://openalex.org/W2997154779","https://openalex.org/W3003711898","https://openalex.org/W3034238904","https://openalex.org/W3104953317","https://openalex.org/W3113497636","https://openalex.org/W3113753692","https://openalex.org/W3156891177","https://openalex.org/W3169483174","https://openalex.org/W3174269049","https://openalex.org/W3175301726","https://openalex.org/W3176851559","https://openalex.org/W3202839357","https://openalex.org/W3204562006","https://openalex.org/W3206996280","https://openalex.org/W3213241618","https://openalex.org/W4320482280","https://openalex.org/W6778883912","https://openalex.org/W6832598865"],"related_works":["https://openalex.org/W4321258516","https://openalex.org/W2051833850","https://openalex.org/W4287845917","https://openalex.org/W3156164993","https://openalex.org/W2385015894","https://openalex.org/W2171573941","https://openalex.org/W2144007828","https://openalex.org/W3040878054","https://openalex.org/W3119324922","https://openalex.org/W1542790140"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-01-20T23:28:44.954186","created_date":"2025-10-10T00:00:00"}
