{"id":"https://openalex.org/W1977714272","doi":"https://doi.org/10.1145/2618243.2618263","title":"Helping scientists reconnect their datasets","display_name":"Helping scientists reconnect their datasets","publication_year":2014,"publication_date":"2014-06-24","ids":{"openalex":"https://openalex.org/W1977714272","doi":"https://doi.org/10.1145/2618243.2618263","mag":"1977714272"},"language":"en","primary_location":{"id":"doi:10.1145/2618243.2618263","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2618243.2618263","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th International Conference on Scientific and Statistical Database Management","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/A5014235464","display_name":"Abdussalam Alawini","orcid":"https://orcid.org/0000-0003-1106-7190"},"institutions":[{"id":"https://openalex.org/I126345244","display_name":"Portland State University","ror":"https://ror.org/00yn2fy02","country_code":"US","type":"education","lineage":["https://openalex.org/I126345244"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abdussalam Alawini","raw_affiliation_strings":["Portland State University","PORTLAND STATE UNIVERSITY,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Portland State University","institution_ids":["https://openalex.org/I126345244"]},{"raw_affiliation_string":"PORTLAND STATE UNIVERSITY,","institution_ids":["https://openalex.org/I126345244"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014301644","display_name":"David Maier","orcid":"https://orcid.org/0000-0003-4790-5619"},"institutions":[{"id":"https://openalex.org/I126345244","display_name":"Portland State University","ror":"https://ror.org/00yn2fy02","country_code":"US","type":"education","lineage":["https://openalex.org/I126345244"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Maier","raw_affiliation_strings":["Portland State University","PORTLAND STATE UNIVERSITY,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Portland State University","institution_ids":["https://openalex.org/I126345244"]},{"raw_affiliation_string":"PORTLAND STATE UNIVERSITY,","institution_ids":["https://openalex.org/I126345244"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001807961","display_name":"Kristin Tufte","orcid":null},"institutions":[{"id":"https://openalex.org/I126345244","display_name":"Portland State University","ror":"https://ror.org/00yn2fy02","country_code":"US","type":"education","lineage":["https://openalex.org/I126345244"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kristin Tufte","raw_affiliation_strings":["Portland State University","PORTLAND STATE UNIVERSITY,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Portland State University","institution_ids":["https://openalex.org/I126345244"]},{"raw_affiliation_string":"PORTLAND STATE UNIVERSITY,","institution_ids":["https://openalex.org/I126345244"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007124763","display_name":"Bill Howe","orcid":"https://orcid.org/0000-0001-8588-8472"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bill Howe","raw_affiliation_strings":["University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11891","display_name":"Big Data and Business Intelligence","score":0.9941999912261963,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.788520097732544},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.5713749527931213},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.5411168932914734},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.5398908853530884},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5008680820465088},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5004947185516357},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4970288574695587},{"id":"https://openalex.org/keywords/connection","display_name":"Connection (principal bundle)","score":0.4855451285839081},{"id":"https://openalex.org/keywords/publishing","display_name":"Publishing","score":0.45237645506858826},{"id":"https://openalex.org/keywords/data-sharing","display_name":"Data sharing","score":0.4403449296951294},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4383430480957031},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07615968585014343}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.788520097732544},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.5713749527931213},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.5411168932914734},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.5398908853530884},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5008680820465088},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5004947185516357},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4970288574695587},{"id":"https://openalex.org/C13355873","wikidata":"https://www.wikidata.org/wiki/Q2920850","display_name":"Connection (principal bundle)","level":2,"score":0.4855451285839081},{"id":"https://openalex.org/C151719136","wikidata":"https://www.wikidata.org/wiki/Q3972943","display_name":"Publishing","level":2,"score":0.45237645506858826},{"id":"https://openalex.org/C2779965156","wikidata":"https://www.wikidata.org/wiki/Q5227350","display_name":"Data sharing","level":3,"score":0.4403449296951294},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4383430480957031},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07615968585014343},{"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/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C204787440","wikidata":"https://www.wikidata.org/wiki/Q188504","display_name":"Alternative medicine","level":2,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2618243.2618263","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2618243.2618263","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th International Conference on Scientific and Statistical Database Management","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.465.801","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.465.801","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://web.cecs.pdx.edu/~tufte/papers/HelpingScientistsReconnectTheirDatasets.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7257401546","display_name":null,"funder_award_id":"IIS 1064685","funder_id":"https://openalex.org/F4320337389","funder_display_name":"Division of Information and Intelligent Systems"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337389","display_name":"Division of Information and Intelligent Systems","ror":"https://ror.org/053a2cp42"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W168287280","https://openalex.org/W1510220247","https://openalex.org/W1514391626","https://openalex.org/W1608814077","https://openalex.org/W1610496399","https://openalex.org/W1679882079","https://openalex.org/W1966514306","https://openalex.org/W1980397870","https://openalex.org/W1981951557","https://openalex.org/W1984566373","https://openalex.org/W2059299892","https://openalex.org/W2093189534","https://openalex.org/W2100830825","https://openalex.org/W2108991785","https://openalex.org/W2116544254","https://openalex.org/W2135473121","https://openalex.org/W2156859522","https://openalex.org/W3008751704","https://openalex.org/W4239429564","https://openalex.org/W4252058675","https://openalex.org/W6630648165"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W4312814274","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358294942","https://openalex.org/W4367460280"],"abstract_inverted_index":{"It":[0],"seems":[1],"inevitable":[2],"that":[3,60],"the":[4,57],"datasets":[5,17,46,86],"associated":[6],"with":[7,18,31],"a":[8,109],"research":[9],"project":[10],"proliferate":[11],"over":[12,50],"time:":[13],"collaborators":[14],"may":[15,107],"extend":[16],"new":[19,22,24,29],"measurements":[20],"and":[21,34,68,115],"attributes,":[23],"experimental":[25],"runs":[26],"result":[27],"in":[28,77,103],"files":[30],"similar":[32],"structures,":[33],"subsets":[35],"of":[36,56,113],"data":[37,64,76],"are":[38],"extracted":[39],"for":[40],"independent":[41],"analysis.":[42],"As":[43],"these":[44],"\"residual\"":[45],"begin":[47],"to":[48],"accrete":[49],"time,":[51],"scientists":[52,89],"can":[53,87],"lose":[54],"track":[55],"derivation":[58,93],"history":[59],"connects":[61],"them,":[62],"complicating":[63],"sharing,":[65],"provenance":[66],"tracking,":[67],"scientific":[69],"reproducibility.":[70],"In":[71],"this":[72],"paper,":[73],"focusing":[74],"on":[75],"spreadsheets,":[78],"we":[79],"consider":[80],"how":[81],"observable":[82],"relationships":[83],"between":[84],"two":[85],"help":[88],"recall":[90],"their":[91],"original":[92],"connection.":[94],"For":[95],"instance,":[96],"if":[97],"dataset":[98,104],"A":[99,114],"is":[100],"wholly":[101],"contained":[102],"B,":[105],"B":[106],"be":[108,117],"more":[110],"recent":[111],"version":[112],"should":[116],"preferred":[118],"when":[119],"archiving":[120],"or":[121],"publishing.":[122]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
