{"id":"https://openalex.org/W4281391100","doi":"https://doi.org/10.1145/3530800.3534534","title":"Measuring information gain using provenance","display_name":"Measuring information gain using provenance","publication_year":2022,"publication_date":"2022-05-23","ids":{"openalex":"https://openalex.org/W4281391100","doi":"https://doi.org/10.1145/3530800.3534534"},"language":"en","primary_location":{"id":"doi:10.1145/3530800.3534534","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3530800.3534534","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th International Workshop on the Theory and Practice of Provenance","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/A5019643678","display_name":"Shemon Rawat","orcid":null},"institutions":[{"id":"https://openalex.org/I63135867","display_name":"University of Cincinnati","ror":"https://ror.org/01e3m7079","country_code":"US","type":"education","lineage":["https://openalex.org/I63135867"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shemon Rawat","raw_affiliation_strings":["University of Cincinnati"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Cincinnati","institution_ids":["https://openalex.org/I63135867"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079405484","display_name":"Seokki Lee","orcid":"https://orcid.org/0000-0002-5637-252X"},"institutions":[{"id":"https://openalex.org/I63135867","display_name":"University of Cincinnati","ror":"https://ror.org/01e3m7079","country_code":"US","type":"education","lineage":["https://openalex.org/I63135867"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Seokki Lee","raw_affiliation_strings":["University of Cincinnati"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Cincinnati","institution_ids":["https://openalex.org/I63135867"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000818365","display_name":"Taeho Jung","orcid":"https://orcid.org/0000-0002-9082-0357"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Taeho Jung","raw_affiliation_strings":["University of Notre Dame"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Notre Dame","institution_ids":["https://openalex.org/I107639228"]}]}],"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":0.08327518,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9998000264167786,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.991599977016449,"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/T11937","display_name":"Research Data Management Practices","score":0.9839000105857849,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8053611516952515},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.7007942199707031},{"id":"https://openalex.org/keywords/provenance","display_name":"Provenance","score":0.6099165081977844},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5749322772026062},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.46710601449012756},{"id":"https://openalex.org/keywords/information-gain","display_name":"Information gain","score":0.45677274465560913},{"id":"https://openalex.org/keywords/replicate","display_name":"Replicate","score":0.440848171710968},{"id":"https://openalex.org/keywords/information-sharing","display_name":"Information sharing","score":0.42384621500968933},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.39591968059539795},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.13193011283874512},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.06735217571258545}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8053611516952515},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.7007942199707031},{"id":"https://openalex.org/C2780049196","wikidata":"https://www.wikidata.org/wiki/Q23582628","display_name":"Provenance","level":2,"score":0.6099165081977844},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5749322772026062},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.46710601449012756},{"id":"https://openalex.org/C2983203078","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Information gain","level":2,"score":0.45677274465560913},{"id":"https://openalex.org/C2781162219","wikidata":"https://www.wikidata.org/wiki/Q26250693","display_name":"Replicate","level":2,"score":0.440848171710968},{"id":"https://openalex.org/C2776854237","wikidata":"https://www.wikidata.org/wiki/Q6031064","display_name":"Information sharing","level":2,"score":0.42384621500968933},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.39591968059539795},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.13193011283874512},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.06735217571258545},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C5900021","wikidata":"https://www.wikidata.org/wiki/Q163082","display_name":"Petrology","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3530800.3534534","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3530800.3534534","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th International Workshop on the Theory and Practice of Provenance","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","score":0.46000000834465027,"display_name":"Partnerships for the goals"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1552694902","https://openalex.org/W2001108980","https://openalex.org/W2077525424","https://openalex.org/W2293299776","https://openalex.org/W2613577383","https://openalex.org/W2763243434","https://openalex.org/W2889548904","https://openalex.org/W2949033485","https://openalex.org/W3011197833","https://openalex.org/W4238104076","https://openalex.org/W4251269742"],"related_works":["https://openalex.org/W2384888906","https://openalex.org/W2376314740","https://openalex.org/W2366644548","https://openalex.org/W2357241418","https://openalex.org/W2119214692","https://openalex.org/W2086064646","https://openalex.org/W2119135658","https://openalex.org/W2115485936","https://openalex.org/W2153015554","https://openalex.org/W2146184373"],"abstract_inverted_index":{"In":[0,50],"recent":[1],"years,":[2],"a":[3,26,55,103,114],"large":[4],"amount":[5],"of":[6,29,65,110],"data":[7,19,74],"is":[8,25],"collected":[9],"from":[10,47],"multiple":[11],"sources":[12],"and":[13,32,39,87,93],"the":[14,37,63,83,96,108],"demands":[15],"for":[16,61],"analyzing":[17],"these":[18],"have":[20],"increased":[21],"enormously.":[22],"Data":[23],"sharing":[24],"valuable":[27],"part":[28],"this":[30,51],"data-intensive":[31],"collaborative":[33],"environment":[34],"due":[35],"to":[36,106],"synergies":[38],"added":[40],"values":[41],"created":[42],"by":[43],"multi-modal":[44],"datasets":[45],"generated":[46],"different":[48],"sources.":[49],"work,":[52],"we":[53],"introduce":[54],"technique":[56],"that":[57,69],"can":[58],"be":[59,71],"used":[60],"quantifying":[62],"degree":[64],"information":[66],"gain":[67],"(IG)":[68],"may":[70],"obtained":[72],"over":[73,85,113],"sharing.":[75],"Our":[76],"method":[77],"captures":[78],"both":[79],"where-":[80],"(to":[81,89],"compute":[82],"IG":[84,97],"values)":[86],"how-provenance":[88],"find":[90],"matching":[91],"records)":[92],"accurately":[94],"computes":[95],"based":[98],"on":[99],"them.":[100],"We":[101],"conduct":[102],"preliminary":[104],"evaluation":[105],"show":[107],"runtime":[109],"our":[111],"approach":[112],"real-world":[115],"dataset.":[116]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}