{"id":"https://openalex.org/W6931814279","doi":"https://doi.org/10.5281/zenodo.7900059","title":"How to Train Your Neural Bug Detector: Artificial vs Real Bugs","display_name":"How to Train Your Neural Bug Detector: Artificial vs Real Bugs","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W6931814279","doi":"https://doi.org/10.5281/zenodo.7900059"},"language":"en","primary_location":{"id":"pmh:oai:zenodo.org:7900059","is_oa":true,"landing_page_url":"https://zenodo.org/record/7900059","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/other"},"type":"other","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://zenodo.org/record/7900059","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Richter, Cedric","orcid":"https://orcid.org/0000-0003-2906-6508"},"institutions":[{"id":"https://openalex.org/I129877168","display_name":"Carl von Ossietzky Universit\u00e4t Oldenburg","ror":"https://ror.org/033n9gh91","country_code":"DE","type":"education","lineage":["https://openalex.org/I129877168"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Richter, Cedric","raw_affiliation_strings":["University of Oldenburg"],"affiliations":[{"raw_affiliation_string":"University of Oldenburg","institution_ids":["https://openalex.org/I129877168"]}]},{"author_position":"last","author":{"id":null,"display_name":"Wehrheim, Heike","orcid":"https://orcid.org/0000-0002-2385-7512"},"institutions":[{"id":"https://openalex.org/I129877168","display_name":"Carl von Ossietzky Universit\u00e4t Oldenburg","ror":"https://ror.org/033n9gh91","country_code":"DE","type":"education","lineage":["https://openalex.org/I129877168"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Wehrheim, Heike","raw_affiliation_strings":["University of Oldenburg"],"affiliations":[{"raw_affiliation_string":"University of Oldenburg","institution_ids":["https://openalex.org/I129877168"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I129877168"],"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.635699987411499},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.5687000155448914},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5475999712944031},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5054000020027161},{"id":"https://openalex.org/keywords/software-bug","display_name":"Software bug","score":0.5037999749183655},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.46320000290870667}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6654999852180481},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.635699987411499},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5932000279426575},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.5687000155448914},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5475999712944031},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5054000020027161},{"id":"https://openalex.org/C1009929","wikidata":"https://www.wikidata.org/wiki/Q179550","display_name":"Software bug","level":3,"score":0.5037999749183655},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49779999256134033},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.46320000290870667},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.39809998869895935},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.3614000082015991},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.3206000030040741},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.29980000853538513},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2768999934196472},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26460000872612}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:zenodo.org:7900059","is_oa":true,"landing_page_url":"https://zenodo.org/record/7900059","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/other"},{"id":"doi:10.5281/zenodo.7900059","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.7900059","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:zenodo.org:7900059","is_oa":true,"landing_page_url":"https://zenodo.org/record/7900059","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/other"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Real":[0],"bug":[1,27,40,65,93,102,107,141,160,189],"fixes":[2,94],"found":[3],"in":[4,169],"open":[5],"source":[6,13,54],"repositories":[7],"seem":[8],"to":[9,16,85,146,164],"be":[10,180],"the":[11,23,87,155,184,187,193],"perfect":[12],"for":[14,34,197],"learning":[15],"localize":[17],"and":[18,56,111,115,122],"repair":[19],"real":[20,76,92,106,114,140,188],"bugs.":[21,77,200],"Yet,":[22],"scale":[24],"of":[25,89,113,138,152,157,186],"existing":[26,53,158],"fix":[28,190],"collections":[29],"is":[30],"typically":[31],"too":[32],"small":[33],"training":[35,90,125,133,149],"data-intensive":[36],"neural":[37,64,101,159],"approaches.":[38],"Neural":[39],"detectors":[41,66,103,161],"are":[42],"hence":[43],"almost":[44],"exclusively":[45],"trained":[46,67,104],"on":[47,68,91,105,128,134,166],"artificial":[48,69,109,116,199],"bugs,":[49],"produced":[50],"by":[51,162,182],"mutating":[52],"code":[55,194],"thus":[57],"easily":[58],"obtainable":[59],"at":[60,95,118],"large":[61],"scales.":[62],"However,":[63],"bugs":[70,110,117,168],"usually":[71],"underperform":[72],"when":[73],"faced":[74],"with":[75,123],"To":[78],"address":[79],"this":[80],"shortcoming,":[81],"we":[82,143],"set":[83],"out":[84],"explore":[86],"impact":[88],"scale.":[96],"Our":[97],"systematic":[98],"study":[99],"compares":[100],"fixes,":[108,142],"mixtures":[112],"various":[119],"dataset":[120,137,191,195],"scales":[121],"varying":[124],"techniques.":[126],"Based":[127],"our":[129,173],"insights":[130],"gained":[131],"from":[132],"a":[135,148],"novel":[136],"33k":[139],"were":[144],"able":[145],"identify":[147],"setting":[150],"capable":[151],"significantly":[153],"improving":[154],"performance":[156],"up":[163],"170%":[165],"simple":[167],"Python.":[170],"In":[171],"addition,":[172],"evaluation":[174],"shows":[175],"that":[176],"further":[177],"gains":[178],"can":[179],"expected":[181],"increasing":[183],"size":[185],"or":[192],"used":[196],"generating":[198]},"counts_by_year":[],"updated_date":"2026-02-05T00:54:17.221276","created_date":"2025-10-10T00:00:00"}