{"id":"https://openalex.org/W7225835662","doi":"https://doi.org/10.5281/zenodo.24134198","title":"Pre-registration: paired decision eval (\"right for the wrong reasons\") \u2013 EuConform, stage 1","display_name":"Pre-registration: paired decision eval (\"right for the wrong reasons\") \u2013 EuConform, stage 1","publication_year":2026,"publication_date":"2026-11-11","ids":{"openalex":"https://openalex.org/W7225835662","doi":"https://doi.org/10.5281/zenodo.24134198"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.24134198","doi":"https://doi.org/10.5281/zenodo.24134198","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24134198","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":"article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.24134198","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5161447446","display_name":"Benedikt Hiepler","orcid":"https://orcid.org/0009-0005-2068-0415","observed_orcids":["https://orcid.org/0009-0005-2068-0415"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hiepler, Benedikt","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0005-2068-0415","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5161447446"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.5605000257492065,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.5605000257492065,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.36550000309944153,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.014999999664723873,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[],"concepts":[{"id":"https://openalex.org/C153180980","wikidata":"https://www.wikidata.org/wiki/Q19776675","display_name":"Commit","level":2,"score":0.6934999823570251},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4700999855995178},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.46380001306533813},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4406999945640564},{"id":"https://openalex.org/C2780922921","wikidata":"https://www.wikidata.org/wiki/Q255189","display_name":"Paraphrase","level":2,"score":0.41510000824928284},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.41339999437332153},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4108999967575073},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.3481999933719635},{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.32989999651908875},{"id":"https://openalex.org/C146357865","wikidata":"https://www.wikidata.org/wiki/Q1123245","display_name":"Stage (stratigraphy)","level":2,"score":0.32199999690055847},{"id":"https://openalex.org/C186282968","wikidata":"https://www.wikidata.org/wiki/Q1434261","display_name":"McNemar's test","level":2,"score":0.3179999887943268},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.31459999084472656},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3109999895095825},{"id":"https://openalex.org/C56666940","wikidata":"https://www.wikidata.org/wiki/Q788790","display_name":"Documentation","level":2,"score":0.27869999408721924},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.25780001282691956}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.24134198","doi":"https://doi.org/10.5281/zenodo.24134198","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24134198","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":"article"},{"id":"doi:10.5281/zenodo.24134199","doi":"https://doi.org/10.5281/zenodo.24134199","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24134199","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":"article"}],"best_oa_location":{"id":"doi:10.5281/zenodo.24134198","doi":"https://doi.org/10.5281/zenodo.24134198","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24134198","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":"article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W4386555476","https://openalex.org/W4415795507","https://openalex.org/W7160313080"],"related_works":[],"abstract_inverted_index":{"Pre-registration":[0],"(stage":[1],"1)":[2],"of":[3,101,191],"the":[4,27,49,73,90,95,99,102,120,130,173,182,192,204],"paired":[5,35],"decision":[6],"eval":[7],"in":[8,44,129,199,203],"EuConform,":[9],"an":[10],"open-source":[11],"evidence":[12],"toolkit":[13],"for":[14,26],"AI":[15],"compliance.":[16],"The":[17,151,196],"instrument":[18],"asks":[19],"whether":[20],"a":[21,143],"language":[22],"model":[23,63,92],"is":[24,34,153,159],"right":[25,28],"reason:":[29],"every":[30],"synthetic":[31,144],"base":[32],"case":[33],"with":[36,54,69,78,98,132,147,177,184,210],"decisive,":[37],"irrelevant,":[38],"placebo":[39],"and":[40,48,94,104,110,117,163,206],"paraphrase":[41],"variants,":[42],"scored":[43],"both":[45],"option":[46],"orders,":[47],"analysis":[50],"compares":[51],"accuracy":[52,56],"(Acc)":[53],"grounded":[55],"(GA).":[57],"This":[58],"deposit":[59],"fixes,":[60],"before":[61],"any":[62],"has":[64],"been":[65],"run:":[66],"hypotheses":[67],"H0\u2013H4":[68],"refutation":[70],"criteria,":[71],"metrics,":[72],"six":[74,138],"open":[75,139],"0.5\u20132B":[76,140],"models":[77,141],"Hugging":[79],"Face":[80],"revisions,":[81],"rule":[82,149],"families,":[83],"frozen":[84],"prompt":[85,106],"wording,":[86],"name":[87],"lists,":[88],"seeds,":[89],"pre-registered":[91],"pairs,":[93],"generator":[96],"manifests":[97],"SHA-256":[100,190],"dev":[103],"pilot":[105],"sets.":[107],"Stages":[108],"2":[109],"3":[111],"(label":[112],"tokens":[113],"per":[114],"model,":[115],"N":[116],"k":[118],"from":[119],"power":[121],"simulation,":[122],"test":[123],"split":[124],"hashes)":[125],"are":[126],"recorded":[127],"later":[128],"repository,":[131],"deviations":[133],"dated.":[134],"Claim":[135],"boundary:":[136],"\"for":[137],"on":[142,172],"rule-following":[145],"task":[146,152],"eight":[148],"families\".":[150],"clinically":[154],"motivated":[155],"but":[156],"synthetic;":[157],"it":[158],"not":[160],"medical":[161],"advice":[162],"makes":[164],"no":[165],"clinical":[166],"claim.":[167],"Source:":[168],"github.com/Hiepler/EuConform,":[169],"commit":[170,179],"650cf91f78fef68533e4c4c3d08f8b3b794be82c":[171],"main":[174],"branch":[175],"(merged":[176],"merge":[178],"ac8c1f2c3666cfca8039ed53409ff88f4b04a431).":[180],"Verify":[181],"archive":[183,193],"shasum":[185],"-a":[186],"256":[187],"-c":[188],"SHA256SUMS.":[189],"euconform-paired-eval-prereg-stage1.zip:":[194],"93d6f94854a6d93bac331a7335e2be578ae5cb955464ba77e626d188e355bd85.":[195],"prompt-set":[197],"hashes":[198],"manifests/":[200],"equal":[201],"those":[202],"pre-registration":[205],"can":[207],"be":[208],"reproduced":[209],"euconform":[211],"paired-eval":[212],"generate.":[213]},"counts_by_year":[],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2026-11-12T00:00:00"}
