{"id":"https://openalex.org/W2892938424","doi":"https://doi.org/10.1109/bigdata.2018.8622095","title":"Predicting computational reproducibility of data analysis pipelines in large population studies using collaborative filtering","display_name":"Predicting computational reproducibility of data analysis pipelines in large population studies using collaborative filtering","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2892938424","doi":"https://doi.org/10.1109/bigdata.2018.8622095","mag":"2892938424"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2018.8622095","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2018.8622095","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1809.10139","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079267174","display_name":"Soudabeh Barghi","orcid":null},"institutions":[{"id":"https://openalex.org/I60158472","display_name":"Concordia University","ror":"https://ror.org/0420zvk78","country_code":"CA","type":"education","lineage":["https://openalex.org/I60158472"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Soudabeh Barghi","raw_affiliation_strings":["Department of Computer Science and Software Engineering, Concordia University, Montreal, Quebec, Canada","[Department of Computer Science and Software Engineering, Concordia University Montreal, Qu\u00e9bec, Canada]"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Software Engineering, Concordia University, Montreal, Quebec, Canada","institution_ids":["https://openalex.org/I60158472"]},{"raw_affiliation_string":"[Department of Computer Science and Software Engineering, Concordia University Montreal, Qu\u00e9bec, Canada]","institution_ids":["https://openalex.org/I60158472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058953336","display_name":"Lalet Scaria","orcid":null},"institutions":[{"id":"https://openalex.org/I60158472","display_name":"Concordia University","ror":"https://ror.org/0420zvk78","country_code":"CA","type":"education","lineage":["https://openalex.org/I60158472"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Lalet Scaria","raw_affiliation_strings":["Department of Computer Science and Software Engineering, Concordia University, Montreal, Quebec, Canada","[Department of Computer Science and Software Engineering, Concordia University Montreal, Qu\u00e9bec, Canada]"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Software Engineering, Concordia University, Montreal, Quebec, Canada","institution_ids":["https://openalex.org/I60158472"]},{"raw_affiliation_string":"[Department of Computer Science and Software Engineering, Concordia University Montreal, Qu\u00e9bec, Canada]","institution_ids":["https://openalex.org/I60158472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001806407","display_name":"Ali Salari","orcid":"https://orcid.org/0000-0002-7426-918X"},"institutions":[{"id":"https://openalex.org/I60158472","display_name":"Concordia University","ror":"https://ror.org/0420zvk78","country_code":"CA","type":"education","lineage":["https://openalex.org/I60158472"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ali Salari","raw_affiliation_strings":["Department of Computer Science and Software Engineering, Concordia University, Montreal, Quebec, Canada","[Department of Computer Science and Software Engineering, Concordia University Montreal, Qu\u00e9bec, Canada]"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Software Engineering, Concordia University, Montreal, Quebec, Canada","institution_ids":["https://openalex.org/I60158472"]},{"raw_affiliation_string":"[Department of Computer Science and Software Engineering, Concordia University Montreal, Qu\u00e9bec, Canada]","institution_ids":["https://openalex.org/I60158472"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075952219","display_name":"Tristan Glatard","orcid":"https://orcid.org/0000-0003-2620-5883"},"institutions":[{"id":"https://openalex.org/I60158472","display_name":"Concordia University","ror":"https://ror.org/0420zvk78","country_code":"CA","type":"education","lineage":["https://openalex.org/I60158472"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Tristan Glatard","raw_affiliation_strings":["Department of Computer Science and Software Engineering, Concordia University, Montreal, Quebec, Canada","[Department of Computer Science and Software Engineering, Concordia University Montreal, Qu\u00e9bec, Canada]"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Software Engineering, Concordia University, Montreal, Quebec, Canada","institution_ids":["https://openalex.org/I60158472"]},{"raw_affiliation_string":"[Department of Computer Science and Software Engineering, Concordia University Montreal, Qu\u00e9bec, Canada]","institution_ids":["https://openalex.org/I60158472"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5079267174"],"corresponding_institution_ids":["https://openalex.org/I60158472"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10331614,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"943","last_page":"950"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10799","display_name":"Data Visualization and Analytics","score":0.9887999892234802,"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"}},"topics":[{"id":"https://openalex.org/T10799","display_name":"Data Visualization and Analytics","score":0.9887999892234802,"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"}},{"id":"https://openalex.org/T10241","display_name":"Functional Brain Connectivity Studies","score":0.9847000241279602,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T13283","display_name":"Mental Health Research Topics","score":0.9824000000953674,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reproducibility","display_name":"Reproducibility","score":0.802676260471344},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7673598527908325},{"id":"https://openalex.org/keywords/pipeline-transport","display_name":"Pipeline transport","score":0.6037232875823975},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.6004226803779602},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5491518974304199},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5133851766586304},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5014348030090332},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4933144152164459},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.46706849336624146},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.45188108086586},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.41722372174263},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1871035099029541},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1327635943889618},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.11415708065032959},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09784108400344849}],"concepts":[{"id":"https://openalex.org/C9893847","wikidata":"https://www.wikidata.org/wiki/Q1425625","display_name":"Reproducibility","level":2,"score":0.802676260471344},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7673598527908325},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.6037232875823975},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.6004226803779602},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5491518974304199},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5133851766586304},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5014348030090332},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4933144152164459},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.46706849336624146},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.45188108086586},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.41722372174263},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1871035099029541},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1327635943889618},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.11415708065032959},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09784108400344849},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"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/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C87717796","wikidata":"https://www.wikidata.org/wiki/Q146326","display_name":"Environmental engineering","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/bigdata.2018.8622095","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2018.8622095","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},{"id":"pmh:oai:https://spectrum.library.concordia.ca:984854","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306400871","display_name":"Spectrum Research Repository (Concordia University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I60158472","host_organization_name":"Concordia University","host_organization_lineage":["https://openalex.org/I60158472"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Thesis"},{"id":"pmh:oai:arXiv.org:1809.10139","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1809.10139","pdf_url":"https://arxiv.org/pdf/1809.10139","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"},{"id":"mag:2892938424","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1809.10139v1","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1809.10139","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1809.10139","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1809.10139","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1809.10139","pdf_url":"https://arxiv.org/pdf/1809.10139","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":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320314000","display_name":"Compute Canada","ror":"https://ror.org/03ty8yr27"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2892938424.pdf","grobid_xml":"https://content.openalex.org/works/W2892938424.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W1979051296","https://openalex.org/W1983208069","https://openalex.org/W1992288515","https://openalex.org/W1998085570","https://openalex.org/W2008985174","https://openalex.org/W2024729467","https://openalex.org/W2054141820","https://openalex.org/W2159094788","https://openalex.org/W2406493898","https://openalex.org/W2950480787","https://openalex.org/W4300601563","https://openalex.org/W6676522543","https://openalex.org/W6749472895"],"related_works":["https://openalex.org/W2962866071","https://openalex.org/W2798575764","https://openalex.org/W2105727087","https://openalex.org/W3008499500","https://openalex.org/W2326356868","https://openalex.org/W3154190849","https://openalex.org/W1857425027","https://openalex.org/W2184831092","https://openalex.org/W2899250548","https://openalex.org/W2144641356","https://openalex.org/W2401031807","https://openalex.org/W118588265","https://openalex.org/W142644365","https://openalex.org/W3187632904","https://openalex.org/W2963560899","https://openalex.org/W3135625980","https://openalex.org/W1966695753","https://openalex.org/W2910285766","https://openalex.org/W3177201091","https://openalex.org/W2172445210"],"abstract_inverted_index":{"Evaluating":[0],"the":[1,42,55,65,68,78,131,140,147],"computational":[2,32,43,122],"reproducibility":[3,44,123,154],"of":[4,27,45,67,97,133],"data":[5,23,46],"analysis":[6,47],"pipelines":[7,48],"has":[8],"become":[9],"a":[10,16,38,58,87,91,94,101,125,158],"critical":[11],"issue.":[12],"It":[13],"is,":[14],"however,":[15],"cumbersome":[17],"process":[18],"for":[19],"analyses":[20],"that":[21,110,146],"involve":[22],"from":[24],"large":[25,50],"populations":[26],"subjects,":[28],"due":[29],"to":[30,40,76,120,152],"their":[31],"and":[33,100,136],"storage":[34],"requirements.":[35],"We":[36,53,71,128,144],"present":[37],"method":[39,149],"predict":[41,121],"in":[49,139],"population":[51,92],"studies.":[52],"formulate":[54],"problem":[56],"as":[57],"collaborative":[59,141],"filtering":[60,142],"process,":[61],"with":[62,93,105,124,157],"constraints":[63],"on":[64,84],"construction":[66],"training":[69,79],"set.":[70],"propose":[72],"6":[73],"different":[74],"strategies":[75],"build":[77],"set,":[80],"which":[81],"we":[82],"evaluate":[83],"2":[85],"datasets,":[86],"synthetic":[88],"one":[89,103,111],"modeling":[90],"growing":[95],"number":[96],"subject":[98,137],"types,":[99],"real":[102],"obtained":[104],"neuroinformatics":[106],"pipelines.":[107],"Results":[108],"show":[109],"sampling":[112],"method,":[113],"\"Random":[114],"File":[115],"Numbers":[116],"(Uniform)\"":[117],"is":[118,150],"able":[119,151],"good":[126],"accuracy.":[127],"also":[129],"analyze":[130],"relevance":[132],"including":[134],"file":[135],"biases":[138],"model.":[143],"conclude":[145],"proposed":[148],"speedup":[153],"evaluations":[155],"substantially,":[156],"reduced":[159],"accuracy":[160],"loss.":[161]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}