{"id":"W4402706083","doi":"10.1145/3674805.3686685","title":"An Empirical Study of API Misuses of Data-Centric Libraries","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Application programming interface; Workflow; Documentation; World Wide Web; Software; Data science; Database; Programming language","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":[],"consensus_categories":[],"category_scores_codex":[0.009600929,0.0006798141,0.000522977,0.006496279,0.001166335,0.001929132,0.001203979,0.001171826,0.001016063],"category_scores_gemma":[0.1116217,0.0007693871,0.0006172039,0.005268841,0.001882461,0.007119655,0.002519075,0.002412037,0.0006308228],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001043435,"about_ca_system_score_gemma":0.001669671,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003855292,"about_ca_topic_score_gemma":0.005741047,"domain_scores_codex":[0.9782655,0.005513006,0.003368481,0.002249937,0.009545409,0.001057564],"domain_scores_gemma":[0.7356675,0.1441517,0.06688772,0.01808506,0.03167395,0.003534021],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000266717,0.0004635484,0.9094501,0.0006002135,0.0001389324,0.001143412,0.01306715,0.0008065425,0.002859166,0.0008507615,0.003438976,0.06691454],"study_design_scores_gemma":[0.00004292836,0.0007751953,0.90998,0.0008691771,0.0002406785,0.006084564,0.02055182,0.02137664,0.01198944,0.001637293,0.02628345,0.0001687023],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9929825,0.0005910667,0.003054096,0.0004102724,0.00001791212,0.0000814926,0.0007131732,0.0003902162,0.001759411],"genre_scores_gemma":[0.9909714,0.0006789746,0.005257132,0.0002439427,0.00002922539,0.0001225894,0.001615625,0.0002222957,0.0008588238],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009600929,"threshold_uncertainty_score":0.05077511,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1144202484834596,"score_gpt":0.3921641979897521,"score_spread":0.2777439495062926,"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."}}