{"id":"https://openalex.org/W7166813135","doi":"https://doi.org/10.18653/v1/2026.acl-long.1795","title":"SciCoQA: Quality Assurance for Scientific Paper\u2013Code Alignment","display_name":"SciCoQA: Quality Assurance for Scientific Paper\u2013Code Alignment","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166813135","doi":"https://doi.org/10.18653/v1/2026.acl-long.1795"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.1795","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1795","pdf_url":"https://aclanthology.org/2026.acl-long.1795.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.1795.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139792715","display_name":"Tim Baumg\u00e4rtner","orcid":null},"institutions":[{"id":"https://openalex.org/I4210102840","display_name":"Ubiquitous Energy (United States)","ror":"https://ror.org/01b06j989","country_code":"US","type":"company","lineage":["https://openalex.org/I4210102840"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tim Baumg\u00e4rtner","raw_affiliation_strings":["Ubiquitous Knowledge Processing Lab (UKP Lab) , Department of Computer Science , TU Darmstadt and National Research Center for Applied Cybersecurity ATHENE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ubiquitous Knowledge Processing Lab (UKP Lab) , Department of Computer Science , TU Darmstadt and National Research Center for Applied Cybersecurity ATHENE","institution_ids":["https://openalex.org/I4210102840"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139767996","display_name":"Iryna Gurevych","orcid":null},"institutions":[{"id":"https://openalex.org/I4210102840","display_name":"Ubiquitous Energy (United States)","ror":"https://ror.org/01b06j989","country_code":"US","type":"company","lineage":["https://openalex.org/I4210102840"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Iryna Gurevych","raw_affiliation_strings":["Ubiquitous Knowledge Processing Lab (UKP Lab) , Department of Computer Science , TU Darmstadt and National Research Center for Applied Cybersecurity ATHENE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ubiquitous Knowledge Processing Lab (UKP Lab) , Department of Computer Science , TU Darmstadt and National Research Center for Applied Cybersecurity ATHENE","institution_ids":["https://openalex.org/I4210102840"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210102840"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87021382,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"38740","last_page":"38770"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13607","display_name":"Academic Publishing and Open Access","score":0.11100000143051147,"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/T13607","display_name":"Academic Publishing and Open Access","score":0.11100000143051147,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.09019999951124191,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11937","display_name":"Research Data Management Practices","score":0.06880000233650208,"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/quality-assurance","display_name":"Quality assurance","score":0.6629999876022339},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4146000146865845},{"id":"https://openalex.org/keywords/qa/qc","display_name":"QA/QC","score":0.2775000035762787},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.2524999976158142},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.24560000002384186}],"concepts":[{"id":"https://openalex.org/C106436119","wikidata":"https://www.wikidata.org/wiki/Q836575","display_name":"Quality assurance","level":3,"score":0.6629999876022339},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4794999957084656},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4146000146865845},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.37540000677108765},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.3237999975681305},{"id":"https://openalex.org/C51687143","wikidata":"https://www.wikidata.org/wiki/Q295600","display_name":"QA/QC","level":5,"score":0.2775000035762787},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.2524999976158142},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.24560000002384186},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.24240000545978546},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.23510000109672546}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.1795","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1795","pdf_url":"https://aclanthology.org/2026.acl-long.1795.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.1795","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1795","pdf_url":"https://aclanthology.org/2026.acl-long.1795.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166813135.pdf","grobid_xml":"https://content.openalex.org/works/W7166813135.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Discrepancies":[0],"between":[1],"scientific":[2,18,80],"papers":[3,136],"and":[4,65,88,91,105,116,135],"their":[5,138],"code":[6],"undermine":[7],"reproducibility,":[8],"a":[9,40,75,93,111],"concern":[10],"that":[11,125],"grows":[12],"as":[13],"automated":[14,79],"research":[15],"agents":[16],"scale":[17,98],"output":[19],"beyond":[20,99],"human":[21],"review":[22],"capacity.Whether":[23],"LLMs":[24],"can":[25],"reliably":[26],"detect":[27,68],"such":[28],"discrepancies":[29,45],"has":[30],"not":[31],"been":[32],"systematically":[33],"measured.To":[34],"this":[35,51],"end,":[36],"we":[37],"present":[38],"SCICOQA,":[39],"dataset":[41],"of":[42,71,113],"635":[43],"paper-code":[44],"(92":[46],"real,":[47],"543":[48],"synthetic)":[49],"for":[50],"cross-modal":[52],"verification":[53],"task.Across":[54],"22":[55],"evaluated":[56],"models,":[57],"even":[58],"the":[59,120],"best-performing":[60],"LLMs,":[61],"Gemini":[62],"3.1":[63],"Pro":[64],"GPT-5":[66],"Mini,":[67],"only":[69],"46.7%":[70],"real-world":[72],"discrepancies,":[73],"revealing":[74],"critical":[76],"gap":[77],"in":[78],"quality":[81],"assurance.We":[82],"construct":[83],"SCICOQA":[84],"from":[85],"GitHub":[86],"issues":[87],"reproducibility":[89],"papers,":[90],"propose":[92],"synthetic":[94],"generation":[95],"pipeline":[96],"to":[97,101,118],"AI":[100],"Physics,":[102],"Quantitative":[103],"Biology,":[104],"other":[106],"computational":[107],"sciences.We":[108],"further":[109],"introduce":[110],"taxonomy":[112],"discrepancy":[114],"types":[115],"categories":[117],"characterize":[119],"occurring":[121],"mismatches.Our":[122],"analysis":[123],"shows":[124],"models":[126],"particularly":[127],"struggle":[128],"with":[129],"omitted":[130],"paper":[131],"details,":[132],"long-context":[133],"inputs,":[134],"outside":[137],"pre-training":[139],"corpus.":[140],"1":[141]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}