{"id":"https://openalex.org/W4394745369","doi":"https://doi.org/10.1145/3597503.3639146","title":"DeepLSH: Deep Locality-Sensitive Hash Learning for Fast and Efficient Near-Duplicate Crash Report Detection","display_name":"DeepLSH: Deep Locality-Sensitive Hash Learning for Fast and Efficient Near-Duplicate Crash Report Detection","publication_year":2024,"publication_date":"2024-04-12","ids":{"openalex":"https://openalex.org/W4394745369","doi":"https://doi.org/10.1145/3597503.3639146"},"language":"en","primary_location":{"id":"doi:10.1145/3597503.3639146","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3597503.3639146","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the IEEE/ACM 46th International Conference on Software Engineering","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/A5008078788","display_name":"Youcef Remil","orcid":"https://orcid.org/0000-0001-5305-3526"},"institutions":[{"id":"https://openalex.org/I48430043","display_name":"Institut National des Sciences Appliqu\u00e9es de Lyon","ror":"https://ror.org/050jn9y42","country_code":"FR","type":"education","lineage":["https://openalex.org/I203339264","https://openalex.org/I48430043"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Youcef Remil","raw_affiliation_strings":["INSA Lyon, Villeurbanne, France","Infologic, Lyon, France","INSA Lyon, Villeurbanne, France Infologic, Lyon, France"],"raw_orcid":"https://orcid.org/0000-0001-5305-3526","affiliations":[{"raw_affiliation_string":"INSA Lyon, Villeurbanne, France","institution_ids":["https://openalex.org/I48430043"]},{"raw_affiliation_string":"Infologic, Lyon, France","institution_ids":[]},{"raw_affiliation_string":"INSA Lyon, Villeurbanne, France Infologic, Lyon, France","institution_ids":["https://openalex.org/I48430043"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045908789","display_name":"Anes Bendimerad","orcid":"https://orcid.org/0000-0002-3347-6094"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anes Bendimerad","raw_affiliation_strings":["Infologic, Lyon, France"],"raw_orcid":"https://orcid.org/0000-0002-3347-6094","affiliations":[{"raw_affiliation_string":"Infologic, Lyon, France","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028606518","display_name":"Romain Mathonat","orcid":"https://orcid.org/0000-0003-1158-4702"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Romain Mathonat","raw_affiliation_strings":["Infologic, Lyon, France"],"raw_orcid":"https://orcid.org/0000-0003-1158-4702","affiliations":[{"raw_affiliation_string":"Infologic, Lyon, France","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066869710","display_name":"Chedy Ra\u00efssi","orcid":"https://orcid.org/0000-0002-6100-7519"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chedy Ra\u00efssi","raw_affiliation_strings":["Riot Games, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-6100-7519","affiliations":[{"raw_affiliation_string":"Riot Games, Singapore, Singapore","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057395190","display_name":"Mehdi Kaytoue","orcid":"https://orcid.org/0000-0002-1569-5242"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mehdi Kaytoue","raw_affiliation_strings":["Infologic, Lyon, France"],"raw_orcid":"https://orcid.org/0000-0002-1569-5242","affiliations":[{"raw_affiliation_string":"Infologic, Lyon, France","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9980999827384949,"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"}},"topics":[{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9980999827384949,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.994700014591217,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.991100013256073,"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/locality-sensitive-hashing","display_name":"Locality-sensitive hashing","score":0.9409148693084717},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8159235715866089},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.6748530864715576},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.557554304599762},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.554672122001648},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.5519006252288818},{"id":"https://openalex.org/keywords/crash","display_name":"Crash","score":0.5219499468803406},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5113844275474548},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.47485828399658203},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4701017737388611},{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.4295628070831299},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.40347206592559814},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33191442489624023},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.178777277469635},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0968911349773407}],"concepts":[{"id":"https://openalex.org/C74270461","wikidata":"https://www.wikidata.org/wiki/Q1625299","display_name":"Locality-sensitive hashing","level":4,"score":0.9409148693084717},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8159235715866089},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.6748530864715576},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.557554304599762},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.554672122001648},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.5519006252288818},{"id":"https://openalex.org/C183469790","wikidata":"https://www.wikidata.org/wiki/Q333501","display_name":"Crash","level":2,"score":0.5219499468803406},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5113844275474548},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.47485828399658203},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4701017737388611},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.4295628070831299},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.40347206592559814},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33191442489624023},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.178777277469635},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0968911349773407},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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":1,"locations":[{"id":"doi:10.1145/3597503.3639146","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3597503.3639146","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the IEEE/ACM 46th International Conference on Software Engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.550000011920929,"display_name":"Climate action","id":"https://metadata.un.org/sdg/13"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1672197616","https://openalex.org/W1913628733","https://openalex.org/W1939575207","https://openalex.org/W1956333070","https://openalex.org/W1967936510","https://openalex.org/W1985514943","https://openalex.org/W2012833704","https://openalex.org/W2022995284","https://openalex.org/W2074231493","https://openalex.org/W2096598529","https://openalex.org/W2127176799","https://openalex.org/W2128782367","https://openalex.org/W2145725688","https://openalex.org/W2147717514","https://openalex.org/W2149234515","https://openalex.org/W2165558283","https://openalex.org/W2169597130","https://openalex.org/W2803341875","https://openalex.org/W2963305974","https://openalex.org/W3097305689","https://openalex.org/W3149901392","https://openalex.org/W4225992987"],"related_works":["https://openalex.org/W2000601968","https://openalex.org/W2135779989","https://openalex.org/W2144265691","https://openalex.org/W2033383639","https://openalex.org/W2754607325","https://openalex.org/W3108918257","https://openalex.org/W144856782","https://openalex.org/W2080135560","https://openalex.org/W3016124764","https://openalex.org/W2147226516"],"abstract_inverted_index":{"Automatic":[0],"crash":[1,102,124],"bucketing":[2,103,125],"is":[3,57,106],"a":[4,48,156,188],"crucial":[5],"phase":[6],"in":[7,20,100,130,150],"the":[8,39,43,71,90,101,116,121,145,151,168],"software":[9],"development":[10],"process":[11],"for":[12,120,137,172,177],"efficiently":[13,53],"triaging":[14],"bug":[15,31],"reports.":[16],"It":[17,56,105],"generally":[18],"consists":[19],"grouping":[21],"similar":[22,45],"reports":[23],"through":[24],"clustering":[25],"techniques.":[26],"However,":[27],"with":[28,78,160,187],"real-time":[29],"streaming":[30],"collection,":[32],"systems":[33],"are":[34,42],"needed":[35],"to":[36,47,60,65,76,82,110,134,143],"quickly":[37],"answer":[38],"question:":[40],"What":[41],"most":[44,122,146],"bugs":[46],"new":[49],"one?,":[50],"that":[51,114,165],"is,":[52],"find":[54],"near-duplicates.":[55],"thus":[58],"natural":[59],"consider":[61,144],"nearest":[62],"neighbors":[63],"search":[64,92],"tackle":[66],"this":[67,131,138,185],"problem":[68],"and":[69,86,174],"especially":[70],"well-known":[72],"locality-sensitive":[73,118],"hashing":[74],"(LSH)":[75],"deal":[77],"large":[79],"datasets":[80],"due":[81],"its":[83],"sublinear":[84],"performance":[85],"theoretical":[87],"guarantees":[88],"on":[89,192],"similarity":[91],"accuracy.":[93],"Surprisingly,":[94],"LSH":[95,136,180],"has":[96],"not":[97,108],"been":[98],"considered":[99],"literature.":[104],"indeed":[107],"trivial":[109],"derive":[111],"hash":[112],"functions":[113],"satisfy":[115],"so-called":[117],"property":[119,170],"advanced":[123],"metrics.":[126],"Consequently,":[127],"we":[128,153,197],"study":[129],"paper":[132],"how":[133],"leverage":[135],"task.":[139],"To":[140],"be":[141],"able":[142],"relevant":[147],"metrics":[148,176],"used":[149],"literature,":[152],"introduce":[154],"DeepLSH,":[155],"Siamese":[157],"DNN":[158],"architecture":[159],"an":[161,193],"original":[162,194],"loss":[163],"function,":[164],"perfectly":[166],"approximates":[167],"locality-sensitivity":[169],"even":[171],"Jaccard":[173],"Cosine":[175],"which":[178,196],"exact":[179],"solutions":[181],"exist.":[182],"We":[183],"support":[184],"claim":[186],"series":[189],"of":[190],"experiments":[191],"dataset,":[195],"make":[198],"available.":[199]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}