{"id":"https://openalex.org/W7168588591","doi":"https://doi.org/10.1145/3814940.3815327","title":"Deal with it! Towards Self-Organizing Data Schemas from Semi-Structured Inserts","display_name":"Deal with it! Towards Self-Organizing Data Schemas from Semi-Structured Inserts","publication_year":2026,"publication_date":"2026-05-31","ids":{"openalex":"https://openalex.org/W7168588591","doi":"https://doi.org/10.1145/3814940.3815327"},"language":null,"primary_location":{"id":"doi:10.1145/3814940.3815327","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3814940.3815327","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Ninth International Workshop on Exploiting Artificial Intelligence Techniques for Data Management","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3814940.3815327","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021190212","display_name":"Benjamin H\u00e4ttasch","orcid":"https://orcid.org/0000-0001-8949-3611"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Benjamin H\u00e4ttasch","raw_affiliation_strings":["German Research Center for Artificial Intelligence (DFKI), Darmstadt, Germany, and Technical University of Darmstadt, Darmstadt, Germany"],"raw_orcid":"https://orcid.org/0000-0001-8949-3611","affiliations":[{"raw_affiliation_string":"German Research Center for Artificial Intelligence (DFKI), Darmstadt, Germany, and Technical University of Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141000939","display_name":"Leon Kr\u00fcger","orcid":"https://orcid.org/0009-0009-6866-6371"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Leon Kr\u00fcger","raw_affiliation_strings":["Technical University of Darmstadt, Darmstadt, Germany"],"raw_orcid":"https://orcid.org/0009-0009-6866-6371","affiliations":[{"raw_affiliation_string":"Technical University of Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073504200","display_name":"Carsten Binnig","orcid":"https://orcid.org/0000-0002-2744-7836"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Carsten Binnig","raw_affiliation_strings":["Technical University of Darmstadt, Darmstadt, Germany, and German Research Center for Artificial Intelligence (DFKI), Darmstadt, Germany"],"raw_orcid":"https://orcid.org/0000-0002-2744-7836","affiliations":[{"raw_affiliation_string":"Technical University of Darmstadt, Darmstadt, Germany, and German Research Center for Artificial Intelligence (DFKI), Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I31512782"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"31","last_page":"40"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.7851999998092651},{"id":"https://openalex.org/keywords/information-schema","display_name":"Information schema","score":0.7202000021934509},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.6320000290870667},{"id":"https://openalex.org/keywords/database-schema","display_name":"Database schema","score":0.5374000072479248},{"id":"https://openalex.org/keywords/conceptual-schema","display_name":"Conceptual schema","score":0.5304999947547913},{"id":"https://openalex.org/keywords/semi-structured-model","display_name":"Semi-structured model","score":0.40709999203681946},{"id":"https://openalex.org/keywords/schema-migration","display_name":"Schema migration","score":0.3982999920845032},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.35850000381469727},{"id":"https://openalex.org/keywords/star-schema","display_name":"Star schema","score":0.353300005197525}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8306999802589417},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.7851999998092651},{"id":"https://openalex.org/C150012506","wikidata":"https://www.wikidata.org/wiki/Q6031185","display_name":"Information schema","level":5,"score":0.7202000021934509},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.6320000290870667},{"id":"https://openalex.org/C30775581","wikidata":"https://www.wikidata.org/wiki/Q632285","display_name":"Database schema","level":3,"score":0.5374000072479248},{"id":"https://openalex.org/C29275276","wikidata":"https://www.wikidata.org/wiki/Q2268965","display_name":"Conceptual schema","level":3,"score":0.5304999947547913},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.43810001015663147},{"id":"https://openalex.org/C56310702","wikidata":"https://www.wikidata.org/wiki/Q2269281","display_name":"Semi-structured model","level":4,"score":0.40709999203681946},{"id":"https://openalex.org/C153440673","wikidata":"https://www.wikidata.org/wiki/Q7431119","display_name":"Schema migration","level":5,"score":0.3982999920845032},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3878999948501587},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38119998574256897},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.35850000381469727},{"id":"https://openalex.org/C190703929","wikidata":"https://www.wikidata.org/wiki/Q1331138","display_name":"Star schema","level":4,"score":0.353300005197525},{"id":"https://openalex.org/C2777327318","wikidata":"https://www.wikidata.org/wiki/Q1408390","display_name":"Schema matching","level":3,"score":0.34700000286102295},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.32499998807907104},{"id":"https://openalex.org/C54239708","wikidata":"https://www.wikidata.org/wiki/Q1329910","display_name":"View","level":3,"score":0.32409998774528503},{"id":"https://openalex.org/C40207289","wikidata":"https://www.wikidata.org/wiki/Q755662","display_name":"Relational model","level":3,"score":0.31290000677108765},{"id":"https://openalex.org/C33762810","wikidata":"https://www.wikidata.org/wiki/Q461671","display_name":"Data integrity","level":2,"score":0.2881999909877777},{"id":"https://openalex.org/C135572916","wikidata":"https://www.wikidata.org/wiki/Q193351","display_name":"Data warehouse","level":2,"score":0.2854999899864197},{"id":"https://openalex.org/C180198813","wikidata":"https://www.wikidata.org/wiki/Q121182","display_name":"Information system","level":2,"score":0.28130000829696655},{"id":"https://openalex.org/C148840519","wikidata":"https://www.wikidata.org/wiki/Q1049878","display_name":"Database design","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C103593891","wikidata":"https://www.wikidata.org/wiki/Q624546","display_name":"Entity\u2013relationship model","level":3,"score":0.26170000433921814},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C193519340","wikidata":"https://www.wikidata.org/wiki/Q891179","display_name":"Data loss","level":2,"score":0.2531999945640564}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3814940.3815327","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3814940.3815327","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Ninth International Workshop on Exploiting Artificial Intelligence Techniques for Data Management","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3814940.3815327","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3814940.3815327","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Ninth International Workshop on Exploiting Artificial Intelligence Techniques for Data Management","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1999133515","https://openalex.org/W2008896880","https://openalex.org/W2424304400","https://openalex.org/W2890431379","https://openalex.org/W3014616325","https://openalex.org/W4322718191","https://openalex.org/W4375869868","https://openalex.org/W4379390735","https://openalex.org/W4414241780","https://openalex.org/W4415797147"],"related_works":[],"abstract_inverted_index":{"In":[0,55],"scenarios":[1],"where":[2,158],"the":[3,68,102,128,138,142,147,151,156,169,178,196],"structure":[4],"of":[5,65,95,130,171,229],"information":[6],"to":[7,61,78,150,167,190,206],"store":[8,62,118],"is":[9,213],"not":[10,47,175],"known":[11],"upfront":[12],"or":[13,123,126,164,173],"changes":[14],"over":[15],"time,":[16],"neither":[17],"traditional":[18],"relational":[19,97],"databases":[20,27,98],"nor":[21],"schemaless":[22,57],"approaches":[23,58],"are":[24,28],"well-suited.":[25],"Relational":[26],"great":[29],"for":[30,70,218,225,251],"data":[31,66,119,149,243],"analysis":[32],"and":[33,99,154,194,222],"exploration,":[34],"but":[35,73],"require":[36,74],"a":[37,71,183,204,219,238],"carefully":[38],"crafted":[39],"schema,":[40,72,133,185,221],"which":[41,134],"causes":[42],"high":[43],"manual":[44],"overhead.":[45],"Entities":[46],"considered":[48],"during":[49],"schema":[50,103,153,157,179,197],"design":[51],"cannot":[52],"be":[53,235],"stored.":[54],"contrast,":[56],"allow":[59],"users":[60],"all":[63],"kinds":[64],"without":[67],"need":[69],"schema-checking":[75],"on":[76,93,105],"read":[77,83],"ensure":[79,182],"that":[80,91],"queries":[81],"can":[82,117],"certain":[84],"attributes.":[85],"Therefore,":[86],"we":[87,246],"present":[88],"an":[89,226,248],"approach":[90,233],"works":[92],"top":[94],"existing":[96,152],"autonomously":[100],"organizes":[101],"based":[104],"incoming":[106,148],"data.":[107],"We":[108,202],"call":[109],"our":[110,186,230],"system":[111,145,187],"JUSTINE":[112],"(JUST":[113],"INsert":[114],"Engine).":[115],"Users":[116],"while":[120],"omitting":[121],"table":[122],"column":[124],"names":[125],"using":[127],"wording":[129],"their":[131],"mental":[132],"might":[135],"deviate":[136],"from":[137],"real":[139],"one":[140],"in":[141,177],"database.":[143],"Our":[144,232],"maps":[146],"adjusts":[155],"needed":[159],"(i.e.,":[160],"by":[161,199],"adding":[162],"columns":[163],"new":[165],"tables)":[166],"handle":[168],"insertion":[170],"attributes":[172],"entities":[174],"represented":[176],"yet.":[180],"To":[181],"high-quality":[184],"provides":[188],"operations":[189],"periodically":[191],"fix":[192],"mistakes":[193],"optimize":[195],"(e.g.,":[198],"combining":[200],"tables).":[201],"propose":[203],"way":[205],"evaluate":[207],"such":[208],"systems,":[209],"even":[210],"though":[211],"there":[212],"no":[214],"single":[215],"gold":[216],"standard":[217],"suitable":[220],"use":[223],"this":[224],"initial":[227],"evaluation":[228],"approach.":[231],"should":[234],"seen":[236],"as":[237],"first":[239],"step":[240],"towards":[241],"self-organizing":[242],"schemas,":[244],"therefore,":[245],"provide":[247],"extensive":[249],"roadmap":[250],"further":[252],"research.":[253]},"counts_by_year":[],"updated_date":"2026-07-17T05:58:32.477365","created_date":"2026-07-17T00:00:00"}
