{"id":"https://openalex.org/W7133544844","doi":"https://doi.org/10.1145/3799992","title":"Profiling Minimal Data Dependency Combinations","display_name":"Profiling Minimal Data Dependency Combinations","publication_year":2026,"publication_date":"2026-03-04","ids":{"openalex":"https://openalex.org/W7133544844","doi":"https://doi.org/10.1145/3799992"},"language":"en","primary_location":{"id":"doi:10.1145/3799992","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3799992","pdf_url":null,"source":{"id":"https://openalex.org/S41523882","display_name":"ACM Transactions on Knowledge Discovery from Data","issn_l":"1556-4681","issn":["1556-4681","1556-472X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Knowledge Discovery from Data","raw_type":"journal-article"},"type":"article","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/A5128042608","display_name":"Marcian Seeger","orcid":null},"institutions":[{"id":"https://openalex.org/I161103922","display_name":"Philipps University of Marburg","ror":"https://ror.org/01rdrb571","country_code":"DE","type":"education","lineage":["https://openalex.org/I161103922"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Marcian Seeger","raw_affiliation_strings":["University of Marburg, Marburg, Germany"],"raw_orcid":"https://orcid.org/0009-0001-8483-2212","affiliations":[{"raw_affiliation_string":"University of Marburg, Marburg, Germany","institution_ids":["https://openalex.org/I161103922"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051892912","display_name":"Sebastian Schmidl","orcid":"https://orcid.org/0000-0002-6597-9809"},"institutions":[{"id":"https://openalex.org/I143288331","display_name":"Hasso Plattner Institute","ror":"https://ror.org/058rn5r42","country_code":"DE","type":"facility","lineage":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sebastian Schmidl","raw_affiliation_strings":["Hasso-Plattner-Institut fur Digital Engineering gGmbH, Potsdam, Germany"],"raw_orcid":"https://orcid.org/0000-0002-6597-9809","affiliations":[{"raw_affiliation_string":"Hasso-Plattner-Institut fur Digital Engineering gGmbH, Potsdam, Germany","institution_ids":["https://openalex.org/I143288331"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047144042","display_name":"Thorsten Papenbrock","orcid":"https://orcid.org/0000-0002-4019-8221"},"institutions":[{"id":"https://openalex.org/I161103922","display_name":"Philipps University of Marburg","ror":"https://ror.org/01rdrb571","country_code":"DE","type":"education","lineage":["https://openalex.org/I161103922"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thorsten Papenbrock","raw_affiliation_strings":["University of Marburg, Marburg, Germany"],"raw_orcid":"https://orcid.org/0000-0002-4019-8221","affiliations":[{"raw_affiliation_string":"University of Marburg, Marburg, Germany","institution_ids":["https://openalex.org/I161103922"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21639595,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"20","issue":"4","first_page":"1","last_page":"49"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9779999852180481,"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":0.9779999852180481,"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":0.004000000189989805,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.0035000001080334187,"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/metadata","display_name":"Metadata","score":0.8206999897956848},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.8188999891281128},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.5460000038146973},{"id":"https://openalex.org/keywords/formalism","display_name":"Formalism (music)","score":0.444599986076355},{"id":"https://openalex.org/keywords/data-type","display_name":"Data type","score":0.42910000681877136},{"id":"https://openalex.org/keywords/data-element","display_name":"Data element","score":0.3961000144481659},{"id":"https://openalex.org/keywords/functional-dependency","display_name":"Functional dependency","score":0.3921000063419342},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.35749998688697815}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.8206999897956848},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.8188999891281128},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7390999794006348},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5691999793052673},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.5460000038146973},{"id":"https://openalex.org/C73301696","wikidata":"https://www.wikidata.org/wiki/Q5469984","display_name":"Formalism (music)","level":3,"score":0.444599986076355},{"id":"https://openalex.org/C138958017","wikidata":"https://www.wikidata.org/wiki/Q190087","display_name":"Data type","level":2,"score":0.42910000681877136},{"id":"https://openalex.org/C30872290","wikidata":"https://www.wikidata.org/wiki/Q1172389","display_name":"Data element","level":3,"score":0.3961000144481659},{"id":"https://openalex.org/C26320393","wikidata":"https://www.wikidata.org/wiki/Q597053","display_name":"Functional dependency","level":3,"score":0.3921000063419342},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.35749998688697815},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3456999957561493},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.3391000032424927},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.3174000084400177},{"id":"https://openalex.org/C137314826","wikidata":"https://www.wikidata.org/wiki/Q2330408","display_name":"Data mapping","level":2,"score":0.3075000047683716},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.2930000126361847},{"id":"https://openalex.org/C153048206","wikidata":"https://www.wikidata.org/wiki/Q3454922","display_name":"Metadata repository","level":3,"score":0.29089999198913574},{"id":"https://openalex.org/C1668388","wikidata":"https://www.wikidata.org/wiki/Q1149776","display_name":"Data management","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C110326360","wikidata":"https://www.wikidata.org/wiki/Q17149476","display_name":"Metadata modeling","level":4,"score":0.27799999713897705},{"id":"https://openalex.org/C33762810","wikidata":"https://www.wikidata.org/wiki/Q461671","display_name":"Data integrity","level":2,"score":0.27090001106262207},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2513999938964844},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2506999969482422}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3799992","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3799992","pdf_url":null,"source":{"id":"https://openalex.org/S41523882","display_name":"ACM Transactions on Knowledge Discovery from Data","issn_l":"1556-4681","issn":["1556-4681","1556-472X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Knowledge Discovery from Data","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.5548948645591736,"id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G1992983452","display_name":null,"funder_award_id":"BMWK.IIB5","funder_id":"https://openalex.org/F4303701741","funder_display_name":"Bundesministerium f\u00fcr Wirtschaft und Klimaschutz"}],"funders":[{"id":"https://openalex.org/F4303701741","display_name":"Bundesministerium f\u00fcr Wirtschaft und Klimaschutz","ror":"https://ror.org/02vgg2808"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W760598031","https://openalex.org/W1569370144","https://openalex.org/W1573373104","https://openalex.org/W1975125888","https://openalex.org/W1980185632","https://openalex.org/W1982556167","https://openalex.org/W1999227640","https://openalex.org/W2001560228","https://openalex.org/W2005735417","https://openalex.org/W2008896880","https://openalex.org/W2018639042","https://openalex.org/W2042412119","https://openalex.org/W2061290719","https://openalex.org/W2063645305","https://openalex.org/W2067025709","https://openalex.org/W2077922582","https://openalex.org/W2094407133","https://openalex.org/W2110810394","https://openalex.org/W2125223317","https://openalex.org/W2125552274","https://openalex.org/W2135105491","https://openalex.org/W2142412033","https://openalex.org/W2155709245","https://openalex.org/W2159186077","https://openalex.org/W2166549982","https://openalex.org/W2182148130","https://openalex.org/W2232417456","https://openalex.org/W2241277057","https://openalex.org/W2266772167","https://openalex.org/W2403919992","https://openalex.org/W2439326083","https://openalex.org/W2551370001","https://openalex.org/W2732517469","https://openalex.org/W2767992112","https://openalex.org/W2772675153","https://openalex.org/W2801277931","https://openalex.org/W2952611840","https://openalex.org/W2963803628","https://openalex.org/W2988782038","https://openalex.org/W2991341431","https://openalex.org/W2996500300","https://openalex.org/W3022794709","https://openalex.org/W3040722616","https://openalex.org/W3081970771","https://openalex.org/W3171487259","https://openalex.org/W3175201267","https://openalex.org/W3194211785","https://openalex.org/W4210979382","https://openalex.org/W4226367749","https://openalex.org/W4242142158","https://openalex.org/W4380433179","https://openalex.org/W4393202813","https://openalex.org/W4408529014","https://openalex.org/W6925379511"],"related_works":[],"abstract_inverted_index":{"Data":[0],"profiling":[1,31,150,188,282,296,313],"describes":[2],"the":[3,51,78,120,129,148,171,187,197,221,262,265,275,295,307],"activity":[4],"of":[5,53,68,83,105,131,151,157,174,201,223,230,264,274,297,309],"inferring":[6],"structural":[7,23,54],"metadata,":[8],"such":[9],"as":[10,117,119,142,211],"functional":[11],"dependencies,":[12,14,60],"inclusion":[13],"and":[15,47,70,137,140,161,184,191,269,277,291,301],"unique":[16],"column":[17],"combinations,":[18,176,203],"from":[19,112],"(relational)":[20],"datasets.":[21],"Because":[22],"metadata":[24,55,69,84,115,122,254,284,318],"is":[25,116,167,302],"often":[26],"not":[27],"stored":[28],"explicitly,":[29],"data":[30,38,42,59,106,132,152,225,298,312],"plays":[32],"a":[33,93,168,207,212,239,271,303,310],"crucial":[34],"role":[35],"in":[36,57,89,134,228],"various":[37],"management":[39],"tasks,":[40],"including":[41],"discovery,":[43],"cleaning,":[44],"integration,":[45],"normalization,":[46],"querying.":[48],"Due":[49,195],"to":[50,96,189,196,245],"importance":[52],"and,":[56],"particular,":[58],"researchers":[61],"have":[62],"been":[63,86],"actively":[64],"exploring":[65],"new":[66],"types":[67],"efficient":[71],"algorithms":[72],"for":[73,170,251,294],"their":[74],"automatic":[75,149],"discovery.":[76,123],"In":[77,124,256],"past,":[79],"however,":[80],"each":[81],"type":[82],"has":[85],"considered":[87],"mostly":[88],"isolation.":[90],"This":[91,218],"poses":[92],"serious":[94],"challenge":[95],"many":[97],"use":[98],"cases":[99],"that":[100,146,279,315],"actually":[101],"require":[102],"specific":[103],"combinations":[104,111,136,160,300],"dependencies":[107,133],"because":[108,177],"deriving":[109],"these":[110,178],"individually":[113],"profiled":[114],"difficult":[118],"initial":[121],"this":[125],"article,":[126],"we":[127,204,237,260],"investigate":[128],"interaction":[130],"(complex)":[135,283],"define":[138],"minimality":[139,208,222,234,249,267],"completeness":[141],"two":[143],"essential":[144],"properties":[145,179],"enable":[147,180],"dependency":[153,159,163,175,202,226,299],"combinations.":[154],"A":[155],"notion":[156],"minimal":[158],"complete":[162],"combination":[164,227],"result":[165,193],"sets":[166],"prerequisite":[169],"(automatic)":[172],"discovery":[173],"search":[181,199,214],"space":[182,200,215],"pruning":[183,216],"effectively":[185],"restrict":[186],"manageable":[190],"meaningful":[192],"sizes.":[194],"enormous":[198],"also":[205],"propose":[206],"constraint":[209,242],"formalism":[210],"novel":[213],"technique.":[217],"technique":[219],"expresses":[220],"any":[224,252],"terms":[229],"already":[231],"well-known,":[232],"type-specific":[233],"constraints.":[235],"Furthermore,":[236],"apply":[238],"practical,":[240],"graph-based":[241],"inference":[243],"algorithm":[244],"automatically":[246],"derive":[247],"query-specific":[248],"constraints":[250,268],"given":[253],"query.":[255],"an":[257],"experimental":[258],"evaluation,":[259],"assess":[261],"effectiveness":[263],"derived":[266],"provide":[270],"first":[272],"impression":[273],"possibilities":[276],"challenges":[278],"arise":[280],"when":[281],"patterns.":[285],"Our":[286],"study":[287],"covers":[288],"both":[289],"theoretical":[290],"practical":[292],"aspects":[293],"necessary":[304],"step":[305],"towards":[306],"development":[308],"holistic":[311],"system":[314],"efficiently":[316],"answers":[317],"pattern":[319],"queries.":[320]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-03-05T00:00:00"}