{"id":"W4411271665","doi":"10.1109/msr66628.2025.00069","title":"It Works (only) on My Machine: A Study on Reproducibility Smells in Ansible Scripts","year":2025,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Scripting language; Computer science; Reproducibility; Programming language; Mathematics; Statistics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01270561,0.000372082,0.0003913012,0.002241383,0.001542402,0.002939877,0.001117538,0.0007520399,0.001279275],"category_scores_gemma":[0.08281388,0.0004185818,0.0004868883,0.002326442,0.001907546,0.004762307,0.002015816,0.001384416,0.0005414397],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001167437,"about_ca_system_score_gemma":0.001546942,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003405503,"about_ca_topic_score_gemma":0.005898283,"domain_scores_codex":[0.9911361,0.004229423,0.0009284857,0.0009475871,0.002258602,0.0004998125],"domain_scores_gemma":[0.8271181,0.1107638,0.03385239,0.009828706,0.01462742,0.003809521],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0005952899,0.001132616,0.6900249,0.0009279441,0.0001395555,0.00236414,0.1820337,0.001052132,0.006057764,0.00242783,0.004958302,0.1082859],"study_design_scores_gemma":[0.00004398283,0.001522352,0.8460306,0.0007607705,0.000181871,0.001719755,0.1126908,0.008577446,0.005158152,0.002463539,0.02066462,0.0001861264],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9969282,0.0001801537,0.001062055,0.0002048826,0.00000855193,0.00003008844,0.00007284214,0.00005203058,0.001461132],"genre_scores_gemma":[0.9965779,0.0001930791,0.001718105,0.0001529372,0.00001388264,0.00006034389,0.0002744566,0.0001070608,0.000902192],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9872944,"threshold_uncertainty_score":0.06719446,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02988152605488271,"score_gpt":0.3231813417224383,"score_spread":0.2932998156675556,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}