{"id":"https://openalex.org/W7225430803","doi":"https://doi.org/10.5281/zenodo.23991506","title":"What extraction cannot slim, and whether function injection can: a pre-registered study of 580 Java repositories","display_name":"What extraction cannot slim, and whether function injection can: a pre-registered study of 580 Java repositories","publication_year":2026,"publication_date":"2026-11-06","ids":{"openalex":"https://openalex.org/W7225430803","doi":"https://doi.org/10.5281/zenodo.23991506"},"language":"en","primary_location":{"id":"doi:10.48550/arxiv.2611.10545","doi":"https://doi.org/10.48550/arxiv.2611.10545","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.10545","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2611.10545","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076594477","display_name":"Daniel Sagenschneider","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Sagenschneider, Daniel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5076594477"],"corresponding_institution_ids":[],"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":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9994999766349792,"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/T10430","display_name":"Software Engineering Techniques and Practices","score":0.00019999999494757503,"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/T10639","display_name":"Advanced Software Engineering Methodologies","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/long-method","display_name":"Long Method","score":0.7850000262260437},{"id":"https://openalex.org/keywords/extract-method-refactoring","display_name":"extract method refactoring","score":0.7170000076293945},{"id":"https://openalex.org/keywords/early-returns","display_name":"early returns","score":0.6200000047683716},{"id":"https://openalex.org/keywords/java-code","display_name":"Java code","score":0.4860000014305115},{"id":"https://openalex.org/keywords/open-source-software-repositories","display_name":"open-source repositories","score":0.5889999866485596},{"id":"https://openalex.org/keywords/ai-coding-assistants","display_name":"AI coding assistants","score":0.574999988079071}],"concepts":[{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5440999865531921},{"id":"https://openalex.org/C548217200","wikidata":"https://www.wikidata.org/wiki/Q251","display_name":"Java","level":2,"score":0.5389000177383423},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5196999907493591},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.4043000042438507},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3970000147819519},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.36719998717308044},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3659000098705292},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3515999913215637},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.3116999864578247},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2992999851703644},{"id":"https://openalex.org/C135598885","wikidata":"https://www.wikidata.org/wiki/Q1366302","display_name":"Row","level":2,"score":0.28769999742507935},{"id":"https://openalex.org/C2776836400","wikidata":"https://www.wikidata.org/wiki/Q31087","display_name":"Calculator","level":2,"score":0.28540000319480896},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.2838999927043915},{"id":"https://openalex.org/C85079727","wikidata":"https://www.wikidata.org/wiki/Q3560114","display_name":"Quarter (Canadian coin)","level":2,"score":0.2818000018596649},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2628999948501587},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C199519371","wikidata":"https://www.wikidata.org/wiki/Q942695","display_name":"Source lines of code","level":3,"score":0.26179999113082886},{"id":"https://openalex.org/C3018260909","wikidata":"https://www.wikidata.org/wiki/Q1322871","display_name":"Exploratory analysis","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25380000472068787}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.48550/arxiv.2611.10545","doi":"https://doi.org/10.48550/arxiv.2611.10545","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.10545","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.5281/zenodo.23991506","doi":"https://doi.org/10.5281/zenodo.23991506","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23991506","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,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.5281/zenodo.23991507","doi":"https://doi.org/10.5281/zenodo.23991507","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23991507","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,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2611.10545","doi":"https://doi.org/10.48550/arxiv.2611.10545","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.10545","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2566214410","https://openalex.org/W3012957750","https://openalex.org/W2275949219","https://openalex.org/W3012287791","https://openalex.org/W7097654406","https://openalex.org/W2103015420","https://openalex.org/W2337561238","https://openalex.org/W6958113027","https://openalex.org/W4212909689","https://openalex.org/W2769294560"],"abstract_inverted_index":{"A":[0,98],"method":[1],"of":[2,90,102,135,143,155,176,196,232,237,240,251,266],"26":[3],"code":[4,313],"lines":[5],"or":[6,284],"more":[7],"reads":[8],"as":[9,53,186,199,218,228,299],"a":[10,27,34,64,75,78,88,153,229,249,271,274,277,304],"Long":[11],"Method,":[12],"and":[13,40,69,77,189,210,221,254,264,308],"Extract":[14],"Method":[15],"is":[16,49,166],"the":[17,54,66,128,144,177,183,190,206,238,241,267,297,302,309],"usual":[18],"fix.":[19],"Some":[20],"long":[21,145,256],"methods":[22,42,158,179,182,243],"have":[23],"no":[24],"single-exit":[25],"fix:":[26],"return":[28,73],"cannot":[29,140],"leave":[30],"an":[31,71],"extracted":[32],"piece,":[33],"piece":[35,62],"hands":[36,80],"back":[37],"one":[38,219],"value,":[39],"some":[41],"are":[43,159,180,295],"knotted":[44],"so":[45],"that":[46,150,244],"every":[47],"cut":[48],"blocked.":[50],"Function":[51],"injection,":[52],"OfficeFloor":[55],"framework":[56,67],"does":[57],"it,":[58],"cuts":[59],"differently:":[60],"each":[61,107],"becomes":[63],"function":[65,79,162,220],"injects":[68],"sequences,":[70],"early":[72],"ends":[74],"function,":[76],"on":[81,312],"several":[82],"values.":[83],"The":[84,147],"framework's":[85],"author":[86],"pre-registered":[87],"test":[89],"whether":[91],"it":[92,252],"takes":[93,164,192,246],"apart":[94,198,247],"what":[95],"extraction":[96,139,203,216],"cannot.":[97],"stratified":[99],"random":[100],"sample":[101,129],"580":[103],"open-source":[104],"Java":[105],"repositories,":[106],"pinned":[108],"before":[109,127],"AI":[110,316],"coding":[111],"assistants":[112],"were":[113,125],"in":[114,194,301],"general":[115],"use,":[116],"was":[117,130],"scanned":[118],"by":[119,270,276,285],"released":[120],"tools":[121],"whose":[122],"cost":[123],"models":[124],"fixed":[126],"drawn:":[131],"3,026,902":[132],"methods,":[133],"168,466":[134],"them":[136],"long.":[137],"Single-exit":[138],"slim":[141],"22.8%":[142],"methods.":[146],"registered":[148,293],"hypothesis,":[149],"at":[151],"least":[152],"quarter":[154,239],"those":[156,197],"stuck":[157,178,242],"ones":[160],"only":[161],"injection":[163,209],"apart,":[165],"refuted:":[167],"22.2%":[168],"(95%":[169],"CI":[170],"20.3":[171],"to":[172,282],"24.3).":[173],"Nearly":[174],"half":[175],"early-return":[181],"plan":[184],"counts":[185],"conventionally":[187],"fixable,":[188],"split":[191,207],"three":[193],"four":[195],"they":[200],"stand.":[201],"Where":[202],"would":[204],"do,":[205],"chooses":[208],"costs":[211],"less":[212],"for":[213,257,289],"29.0%":[214],"against":[215,223],"wrapped":[217],"17.2%":[222],"plain":[224],"extraction,":[225],"almost":[226],"always":[227],"straight":[230],"sequence":[231],"functions.":[233],"An":[234],"exploratory":[235],"reading":[236],"neither":[245],"finds":[248],"third":[250],"tables":[253],"literals,":[255],"their":[258,262],"data":[259],"rather":[260],"than":[261],"logic,":[263],"most":[265],"rest":[268],"blocked":[269],"jump":[272],"inside":[273],"loop,":[275],"nested":[278],"statement":[279],"too":[280,287],"large":[281],"cut,":[283],"values":[286],"many":[288],"any":[290],"cut.":[291],"Three":[292],"studies":[294],"proposed:":[296],"classes":[298],"rules":[300],"tools,":[303],"refinement":[305],"per":[306],"class,":[307],"same":[310],"measures":[311],"written":[314],"with":[315],"assistants.":[317]},"counts_by_year":[],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2026-11-07T00:00:00"}