{"id":"https://openalex.org/W2911424454","doi":"https://doi.org/10.14778/3291264.3291268","title":"Snuba","display_name":"Snuba","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2911424454","doi":"https://doi.org/10.14778/3291264.3291268","mag":"2911424454"},"language":"en","primary_location":{"id":"doi:10.14778/3291264.3291268","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3291264.3291268","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"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":"Proceedings of the VLDB Endowment","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/A5020645010","display_name":"Paroma Varma","orcid":"https://orcid.org/0000-0002-9035-2506"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Paroma Varma","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103852640","display_name":"Christopher R\u00e9","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher R\u00e9","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5020645010"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":10.1536,"has_fulltext":false,"cited_by_count":119,"citation_normalized_percentile":{"value":0.98447357,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"12","issue":"3","first_page":"223","last_page":"236"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9998000264167786,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9998000264167786,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9983000159263611,"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/heuristics","display_name":"Heuristics","score":0.9056327939033508},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8121234178543091},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6814906001091003},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6519313454627991},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6043341755867004},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5968359112739563},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5802881717681885},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5417523980140686},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5159803032875061},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.47284701466560364},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3340206742286682},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07540565729141235}],"concepts":[{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.9056327939033508},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8121234178543091},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6814906001091003},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6519313454627991},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6043341755867004},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5968359112739563},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5802881717681885},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5417523980140686},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5159803032875061},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.47284701466560364},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3340206742286682},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07540565729141235},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.14778/3291264.3291268","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3291264.3291268","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"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":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},{"id":"pmh:oai:europepmc.org:5835668","is_oa":false,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/6879381","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"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"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.4300000071525574,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":73,"referenced_works":["https://openalex.org/W9014458","https://openalex.org/W108763474","https://openalex.org/W1479807131","https://openalex.org/W1516184288","https://openalex.org/W1526922602","https://openalex.org/W1541280084","https://openalex.org/W1686810756","https://openalex.org/W1726806267","https://openalex.org/W1861492603","https://openalex.org/W1872614887","https://openalex.org/W1954715867","https://openalex.org/W1968969471","https://openalex.org/W1983320747","https://openalex.org/W2001619934","https://openalex.org/W2015159529","https://openalex.org/W2029249040","https://openalex.org/W2048679005","https://openalex.org/W2064675550","https://openalex.org/W2065394549","https://openalex.org/W2068737686","https://openalex.org/W2079735306","https://openalex.org/W2089334447","https://openalex.org/W2094878426","https://openalex.org/W2097117768","https://openalex.org/W2101234009","https://openalex.org/W2101654853","https://openalex.org/W2107254606","https://openalex.org/W2107598941","https://openalex.org/W2108598243","https://openalex.org/W2116064496","https://openalex.org/W2117173982","https://openalex.org/W2125027602","https://openalex.org/W2125283600","https://openalex.org/W2134734244","https://openalex.org/W2142126234","https://openalex.org/W2143349571","https://openalex.org/W2149236697","https://openalex.org/W2149713870","https://openalex.org/W2150588363","https://openalex.org/W2154455818","https://openalex.org/W2162340487","https://openalex.org/W2165698076","https://openalex.org/W2250539671","https://openalex.org/W2252115292","https://openalex.org/W2277195237","https://openalex.org/W2323506184","https://openalex.org/W2404161646","https://openalex.org/W2404544029","https://openalex.org/W2559655401","https://openalex.org/W2561715562","https://openalex.org/W2584281025","https://openalex.org/W2590501763","https://openalex.org/W2592362528","https://openalex.org/W2604259521","https://openalex.org/W2604272474","https://openalex.org/W2612690371","https://openalex.org/W2612972698","https://openalex.org/W2614062172","https://openalex.org/W2618530766","https://openalex.org/W2622759881","https://openalex.org/W2725395424","https://openalex.org/W2753688405","https://openalex.org/W2769041395","https://openalex.org/W2911424454","https://openalex.org/W2915806464","https://openalex.org/W2949312134","https://openalex.org/W2953132584","https://openalex.org/W2959716049","https://openalex.org/W2962778704","https://openalex.org/W2962915384","https://openalex.org/W2964134873","https://openalex.org/W3008793775","https://openalex.org/W6929990038"],"related_works":["https://openalex.org/W1657880117","https://openalex.org/W2595172197","https://openalex.org/W2127970246","https://openalex.org/W2084856301","https://openalex.org/W1001352512","https://openalex.org/W4382618745","https://openalex.org/W2885125400","https://openalex.org/W1989889224","https://openalex.org/W2748922771","https://openalex.org/W1987128138"],"abstract_inverted_index":{"As":[0],"deep":[1],"learning":[2,205],"models":[3],"are":[4],"applied":[5],"to":[6,20,26,44,84,93,97,169,208],"increasingly":[7],"diverse":[8],"problems,":[9],"a":[10,82,89,98,132,141],"key":[11],"bottleneck":[12],"is":[13,119],"gathering":[14],"enough":[15],"high-quality":[16],"training":[17,95,155],"labels":[18,34,96,112],"tailored":[19],"each":[21,49,111],"task.":[22,50],"Users":[23],"therefore":[24],"turn":[25],"weak":[27,104],"supervision,":[28],"relying":[29],"on":[30,194],"imperfect":[31],"sources":[32,47],"of":[33,115,135],"like":[35,65,203],"pattern":[36],"matching":[37],"and":[38,57,70,122,166,193],"user-defined":[39,178],"heuristics.":[40],"Unfortunately,":[41],"users":[42,187],"have":[43],"design":[45],"these":[46,77],"for":[48],"This":[51],"process":[52,126,148],"can":[53],"be":[54],"time":[55],"consuming":[56],"expensive:":[58],"domain":[59],"experts":[60],"often":[61],"perform":[62],"repetitive":[63],"steps":[64],"guessing":[66],"optimal":[67],"numerical":[68],"thresholds":[69],"developing":[71],"informative":[72],"text":[73],"patterns.":[74],"To":[75],"address":[76],"challenges,":[78],"we":[79],"present":[80],"Snuba,":[81],"system":[83],"automatically":[85,150,159],"generate":[86],"heuristics":[87,109,129,161,179],"using":[88],"small":[90],"labeled":[91],"dataset":[92,101],"assign":[94],"large,":[99],"unlabeled":[100,137],"in":[102,162],"the":[103,113,116,128,136,146,175],"supervision":[105],"setting.":[106],"Snuba":[107,158,198],"generates":[108,160],"that":[110,144],"subset":[114],"data":[117],"it":[118,153],"accurate":[120],"for,":[121],"iteratively":[123],"repeats":[124],"this":[125],"until":[127],"together":[130],"label":[131,156],"large":[133],"portion":[134],"data.":[138],"We":[139],"develop":[140],"statistical":[142],"measure":[143],"guarantees":[145],"iterative":[147],"will":[149],"terminate":[151],"before":[152],"degrades":[154],"quality.":[157],"under":[163],"five":[164],"minutes":[165],"performs":[167],"up":[168,207],"9.74":[170],"F1":[171,210],"points":[172],"better":[173],"than":[174],"best":[176],"known":[177],"developed":[180],"over":[181],"many":[182],"days.":[183],"In":[184],"collaborations":[185],"with":[186],"at":[188],"research":[189],"labs,":[190],"Stanford":[191],"Hospital,":[192],"open":[195],"source":[196],"datasets,":[197],"outperforms":[199],"other":[200],"automated":[201],"approaches":[202],"semi-supervised":[204],"by":[206],"14.35":[209],"points.":[211]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":18},{"year":2021,"cited_by_count":29},{"year":2020,"cited_by_count":20},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2019-02-21T00:00:00"}