{"id":"https://openalex.org/W2146807852","doi":"https://doi.org/10.1109/itw.2008.4578672","title":"Contextual information retrieval based on algorithmic information theory and statistical outlier detection","display_name":"Contextual information retrieval based on algorithmic information theory and statistical outlier detection","publication_year":2008,"publication_date":"2008-05-01","ids":{"openalex":"https://openalex.org/W2146807852","doi":"https://doi.org/10.1109/itw.2008.4578672","mag":"2146807852"},"language":"en","primary_location":{"id":"doi:10.1109/itw.2008.4578672","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itw.2008.4578672","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE Information Theory Workshop","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/0711.4388","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100732117","display_name":"R. Mart\u00ednez","orcid":"https://orcid.org/0000-0003-2336-9145"},"institutions":[{"id":"https://openalex.org/I88060688","display_name":"Universidad Polit\u00e9cnica de Madrid","ror":"https://ror.org/03n6nwv02","country_code":"ES","type":"education","lineage":["https://openalex.org/I88060688"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Rafael Martinez","raw_affiliation_strings":["Departamento de Ingenier\u00eda Inform\u00e1tica, Universidad Polit\u00e9cirica de Madrid, Spain"],"affiliations":[{"raw_affiliation_string":"Departamento de Ingenier\u00eda Inform\u00e1tica, Universidad Polit\u00e9cirica de Madrid, Spain","institution_ids":["https://openalex.org/I88060688"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017095669","display_name":"Manuel Cebri\u00e1n","orcid":"https://orcid.org/0000-0002-3681-7982"},"institutions":[{"id":"https://openalex.org/I175594653","display_name":"John Brown University","ror":"https://ror.org/02ct41q97","country_code":"US","type":"education","lineage":["https://openalex.org/I175594653"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Manuel Cebrian","raw_affiliation_strings":["Department of Computer Science, Brown University, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Brown University, USA","institution_ids":["https://openalex.org/I175594653"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000844533","display_name":"Francisco B. Rodr\u0131\u0301guez","orcid":"https://orcid.org/0000-0003-4053-099X"},"institutions":[{"id":"https://openalex.org/I88060688","display_name":"Universidad Polit\u00e9cnica de Madrid","ror":"https://ror.org/03n6nwv02","country_code":"ES","type":"education","lineage":["https://openalex.org/I88060688"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Francisco de Borja Rodriguez","raw_affiliation_strings":["Departamento de Ingenier\u00eda Inform\u00e1tica, Universidad Polit\u00e9cirica de Madrid, Spain"],"affiliations":[{"raw_affiliation_string":"Departamento de Ingenier\u00eda Inform\u00e1tica, Universidad Polit\u00e9cirica de Madrid, Spain","institution_ids":["https://openalex.org/I88060688"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025314362","display_name":"David Camacho","orcid":"https://orcid.org/0000-0002-5051-3475"},"institutions":[{"id":"https://openalex.org/I88060688","display_name":"Universidad Polit\u00e9cnica de Madrid","ror":"https://ror.org/03n6nwv02","country_code":"ES","type":"education","lineage":["https://openalex.org/I88060688"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"David Camacho","raw_affiliation_strings":["Departamento de Ingenier\u00eda Inform\u00e1tica, Universidad Polit\u00e9cirica de Madrid, Spain"],"affiliations":[{"raw_affiliation_string":"Departamento de Ingenier\u00eda Inform\u00e1tica, Universidad Polit\u00e9cirica de Madrid, Spain","institution_ids":["https://openalex.org/I88060688"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100732117"],"corresponding_institution_ids":["https://openalex.org/I88060688"],"apc_list":null,"apc_paid":null,"fwci":0.8256,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.77227151,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"5","issue":null,"first_page":"292","last_page":"297"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12002","display_name":"Computability, Logic, AI Algorithms","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T12002","display_name":"Computability, Logic, AI Algorithms","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11269","display_name":"Algorithms and Data Compression","score":0.9945999979972839,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9944999814033508,"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/computer-science","display_name":"Computer science","score":0.7814353704452515},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.7197327017784119},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6077170372009277},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5984765291213989},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5486300587654114},{"id":"https://openalex.org/keywords/false-positive-paradox","display_name":"False positive paradox","score":0.4417390823364258},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3474525809288025},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.11181178689002991}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7814353704452515},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.7197327017784119},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6077170372009277},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5984765291213989},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5486300587654114},{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.4417390823364258},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3474525809288025},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.11181178689002991}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/itw.2008.4578672","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itw.2008.4578672","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE Information Theory Workshop","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:0711.4388","is_oa":true,"landing_page_url":"http://arxiv.org/abs/0711.4388","pdf_url":"https://arxiv.org/pdf/0711.4388","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:0711.4388","is_oa":true,"landing_page_url":"http://arxiv.org/abs/0711.4388","pdf_url":"https://arxiv.org/pdf/0711.4388","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.4399999976158142,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W61804265","https://openalex.org/W596943770","https://openalex.org/W1496818883","https://openalex.org/W1564436890","https://openalex.org/W1602667807","https://openalex.org/W1660390307","https://openalex.org/W1970655212","https://openalex.org/W1982402725","https://openalex.org/W1987389174","https://openalex.org/W2026087380","https://openalex.org/W2035225306","https://openalex.org/W2037646798","https://openalex.org/W2043909051","https://openalex.org/W2108587916","https://openalex.org/W2128859735","https://openalex.org/W2130444042","https://openalex.org/W2165612380","https://openalex.org/W2313469048","https://openalex.org/W2331052961","https://openalex.org/W4300528607","https://openalex.org/W6602591098","https://openalex.org/W6986189286"],"related_works":["https://openalex.org/W1557094818","https://openalex.org/W2183246718","https://openalex.org/W2099261052","https://openalex.org/W3209204065","https://openalex.org/W3006513224","https://openalex.org/W2046456988","https://openalex.org/W2105707930","https://openalex.org/W1755711892","https://openalex.org/W2357409937","https://openalex.org/W2160907113"],"abstract_inverted_index":{"This":[0],"work":[1],"presents":[2],"an":[3,119],"Information":[4],"Retrieval":[5],"technique":[6],"based":[7],"on":[8],"algorithmic":[9],"information":[10,37],"theory":[11],"(using":[12],"the":[13,51,60,70,85,94,98,105,108,111],"normalized":[14],"compression":[15],"distance),":[16],"statistical":[17],"data":[18],"outlier":[19],"detection,":[20],"and":[21,56],"a":[22,63,90],"novel":[23],"database":[24,95],"structure.":[25],"The":[26],"paper":[27],"shows":[28],"how":[29],"they":[30],"all":[31],"can":[32],"be":[33],"integrated":[34],"to":[35,58,92],"retrieve":[36],"from":[38],"generic":[39],"databases":[40],"using":[41],"long":[42],"text-based":[43],"queries.":[44],"Two":[45],"important":[46],"problems":[47],"are":[48,116],"addressed.":[49],"On":[50,84],"one":[52],"hand,":[53,87],"we":[54,88],"analyze":[55],"tyr":[57],"solve":[59],"detection":[61],"of":[62,66,107,110],"particular":[64],"case":[65],"false":[67],"positives:":[68],"when":[69],"distance":[71,100],"among":[72],"two":[73],"documents":[74],"is":[75,80],"outlyingly":[76],"low":[77],"but":[78],"there":[79],"not":[81],"actual":[82],"similarity.":[83],"other":[86],"propose":[89],"way":[91],"structure":[93],"such":[96],"that":[97],"similarity":[99],"estimation":[101],"scales":[102],"well":[103],"with":[104,118],"length":[106],"size":[109],"query.":[112],"All":[113],"design":[114],"choices":[115],"justified":[117],"experimental":[120],"evaluation.":[121]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}