{"id":"https://openalex.org/W1732744741","doi":"https://doi.org/10.48550/arxiv.0909.1769","title":"Interactive Data Integration through Smart Copy & Paste","display_name":"Interactive Data Integration through Smart Copy & Paste","publication_year":2009,"publication_date":"2009-09-09","ids":{"openalex":"https://openalex.org/W1732744741","doi":"https://doi.org/10.48550/arxiv.0909.1769","mag":"1732744741"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:0909.1769","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/0909.1769","pdf_url":"https://arxiv.org/pdf/0909.1769","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/0909.1769","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063822723","display_name":"Zachary G. Ives","orcid":"https://orcid.org/0000-0001-7527-2957","observed_orcids":["https://orcid.org/0000-0001-7527-2957"]},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ives, Zachary","raw_affiliation_strings":["University Of Pennsylvania","#N#               * University of Pennsylvania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University Of Pennsylvania","institution_ids":["https://openalex.org/I79576946"]},{"raw_affiliation_string":"#N#               * University of Pennsylvania","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089542402","display_name":"Craig A. Knoblock","orcid":"https://orcid.org/0000-0002-6371-4807","observed_orcids":["https://orcid.org/0000-0002-6371-4807"]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Knoblock, Craig","raw_affiliation_strings":["University of Southern California - Information Sciences Institute","#N#               * University of Pennsylvania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California - Information Sciences Institute","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"#N#               * University of Pennsylvania","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045363082","display_name":"Steven Minton","orcid":"https://orcid.org/0000-0001-8640-2905","observed_orcids":["https://orcid.org/0000-0001-8640-2905"]},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Minton, Steve","raw_affiliation_strings":["Fetch Technologies","#N#               * University of Pennsylvania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fetch Technologies","institution_ids":[]},{"raw_affiliation_string":"#N#               * University of Pennsylvania","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086888117","display_name":"Marie Jacob","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jacob, Marie","raw_affiliation_strings":["University of Pennsylvania","[Information Sciences Institute]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pennsylvania","institution_ids":["https://openalex.org/I79576946"]},{"raw_affiliation_string":"[Information Sciences Institute]","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113507177","display_name":"Partha Pratim Talukdar","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Talukdar, Partha","raw_affiliation_strings":["University of Pennsylvania","[Information Sciences Institute]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pennsylvania","institution_ids":["https://openalex.org/I79576946"]},{"raw_affiliation_string":"[Information Sciences Institute]","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009564354","display_name":"Rattapoom Tuchinda","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tuchinda, Rattapoom","raw_affiliation_strings":["University of Southern California - Information Sciences Institute","[Information Sciences Institute]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California - Information Sciences Institute","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"[Information Sciences Institute]","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033175043","display_name":"Jos\u00e9 Luis Ambite","orcid":"https://orcid.org/0000-0003-0087-080X","observed_orcids":["https://orcid.org/0000-0003-0087-080X"]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ambite, Jose Luis","raw_affiliation_strings":["University of Southern California - Information Sciences Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California - Information Sciences Institute","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085785023","display_name":"Maria Muslea","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Muslea, Maria","raw_affiliation_strings":["University of Southern California - Information Sciences Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California - Information Sciences Institute","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019089688","display_name":"Bora Cenk Gazen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gazen, Cenk","raw_affiliation_strings":["Fetch Technologies"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fetch Technologies","institution_ids":[]}]}],"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":true,"cited_by_count":20,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.49410000443458557,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.49410000443458557,"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":0.10329999774694443,"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/T13197","display_name":"Spreadsheets and End-User Computing","score":0.09830000251531601,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/copycat","display_name":"copycats","score":0.8460000157356262},{"id":"https://openalex.org/keywords/schema-mapping","display_name":"schema mapping","score":0.44999998807907104},{"id":"https://openalex.org/keywords/provenance","display_name":"provenance","score":0.5540000200271606},{"id":"https://openalex.org/keywords/ad-hoc-collaboration","display_name":"ad-hoc collaboration","score":0.6359999775886536},{"id":"https://openalex.org/keywords/emergency-response","display_name":"emergency response","score":0.7820000052452087}],"concepts":[{"id":"https://openalex.org/C130191384","wikidata":"https://www.wikidata.org/wiki/Q2996887","display_name":"Copycat","level":2,"score":0.950144350528717},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.843191385269165},{"id":"https://openalex.org/C2780767217","wikidata":"https://www.wikidata.org/wiki/Q5532421","display_name":"Generality","level":2,"score":0.6290267705917358},{"id":"https://openalex.org/C58581272","wikidata":"https://www.wikidata.org/wiki/Q12741163","display_name":"Workspace","level":3,"score":0.6029306650161743},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.5368751883506775},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.4726152718067169},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4390484690666199},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4131702780723572},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.33577802777290344},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.13852640986442566},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1360313892364502},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.09638714790344238},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:arXiv.org:0909.1769","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/0909.1769","pdf_url":"https://arxiv.org/pdf/0909.1769","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":"mag:2949066031","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/0909.1769","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.0909.1769","doi":"https://doi.org/10.48550/arxiv.0909.1769","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.0909.1769","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"mag:1732744741","doi":null,"is_oa":false,"landing_page_url":"https://www.cis.upenn.edu/~zives/research/cidr.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306418070","display_name":"Conference on Innovative Data Systems Research","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Conference on Innovative Data Systems Research","raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:0909.1769","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/0909.1769","pdf_url":"https://arxiv.org/pdf/0909.1769","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":[{"id":"https://openalex.org/G2015090911","display_name":"II: Data Cooperatives:  Rapid and Incremental Data Sharing with Applications to Bioinformatics","funder_award_id":"0513778","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2792195988","display_name":"Preserving Constraints in XML Data Exchange","funder_award_id":"0415810","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1732744741.pdf","grobid_xml":"https://content.openalex.org/works/W1732744741.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W179050280","https://openalex.org/W181136906","https://openalex.org/W1502767928","https://openalex.org/W1519573073","https://openalex.org/W1531552153","https://openalex.org/W1553019137","https://openalex.org/W1616576116","https://openalex.org/W1908950999","https://openalex.org/W1927338256","https://openalex.org/W1996300450","https://openalex.org/W2008896880","https://openalex.org/W2035072056","https://openalex.org/W2055515830","https://openalex.org/W2059268928","https://openalex.org/W2069897123","https://openalex.org/W2097360199","https://openalex.org/W2103219113","https://openalex.org/W2106659693","https://openalex.org/W2113547889","https://openalex.org/W2113970290","https://openalex.org/W2122483056","https://openalex.org/W2123390832","https://openalex.org/W2126444157","https://openalex.org/W2127753549","https://openalex.org/W2131165428","https://openalex.org/W2147026797","https://openalex.org/W2148210463","https://openalex.org/W2153508518","https://openalex.org/W2156454791","https://openalex.org/W2160218441","https://openalex.org/W2162463342","https://openalex.org/W2166376630","https://openalex.org/W2171244245","https://openalex.org/W2171262729","https://openalex.org/W2171874178"],"related_works":["https://openalex.org/W1997281874","https://openalex.org/W1510113589","https://openalex.org/W7095616831","https://openalex.org/W90660802","https://openalex.org/W2766455614","https://openalex.org/W2048282669","https://openalex.org/W7095526235","https://openalex.org/W2024774552","https://openalex.org/W7061698932","https://openalex.org/W2129889089"],"abstract_inverted_index":{"In":[0,96],"many":[1],"scenarios,":[2],"such":[3],"as":[4,115],"emergency":[5],"response":[6],"or":[7,162],"ad":[8],"hoc":[9],"collaboration,":[10],"it":[11],"is":[12],"critical":[13],"to":[14],"reduce":[15],"the":[16,25,53,57,61,79,93,98,106,112,116,123,146,168],"overhead":[17],"in":[18,145,188,191],"integrating":[19],"data.":[20],"Ideally,":[21],"one":[22,30],"could":[23],"perform":[24],"entire":[26],"process":[27],"interactively":[28],"under":[29],"unified":[31],"interface:":[32],"defining":[33],"extractors":[34],"and":[35,43,59,70,74,81,87,126,137,167,183],"wrappers":[36],"for":[37,76,105],"sources,":[38],"creating":[39],"a":[40,66],"mediated":[41],"schema,":[42],"adding":[44],"schema":[45],"mappings":[46],"?":[47,157,166],"while":[48],"seeing":[49],"how":[50],"these":[51,135,155],"impact":[52],"integrated":[54],"view":[55],"of":[56,84,109,148,179],"data,":[58],"refining":[60],"design":[62],"accordingly.":[63],"We":[64],"propose":[65],"novel":[67],"smart":[68],"copy":[69],"paste":[71],"(SCP)":[72],"model":[73],"architecture":[75],"seamlessly":[77],"combining":[78],"design-time":[80],"run-time":[82],"aspects":[83],"data":[85,119],"integration,":[86],"we":[88],"describe":[89],"an":[90,143,177],"initial":[91],"prototype,":[92],"CopyCat":[94,133],"system.":[95],"CopyCat,":[97],"user":[99,117,151],"does":[100],"not":[101],"need":[102],"special":[103],"tools":[104],"different":[107],"stages":[108],"integration:":[110],"instead,":[111],"system":[113,169],"watches":[114],"copies":[118],"from":[120,171],"applications":[121],"(including":[122],"Web":[124],"browser)":[125],"pastes":[127],"them":[128],"into":[129],"CopyCat?s":[130],"spreadsheet-like":[131],"workspace.":[132],"generalizes":[134],"actions":[136],"presents":[138],"proposed":[139],"auto-completions,":[140],"each":[141],"with":[142],"explanation":[144],"form":[147],"provenance.":[149],"The":[150],"provides":[152,176],"feedback":[153],"on":[154],"suggestions":[156],"through":[158],"either":[159],"direct":[160],"interactions":[161],"further":[163],"copy-and-paste":[164],"operations":[165],"learns":[170],"this":[172],"feedback.":[173],"This":[174],"paper":[175],"overview":[178],"our":[180],"prototype":[181],"system,":[182],"identifies":[184],"key":[185],"research":[186],"challenges":[187],"achieving":[189],"SCP":[190],"its":[192],"full":[193],"generality.":[194]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2016-06-24T00:00:00"}
