{"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":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0004907052,0.0002041257,0.0004197604,0.0004850185,0.00001721799,0.0002665742,0.006003688,0.0001346258,0.00004043882],"category_scores_gemma":[0.0003951615,0.0001686444,0.00005183581,0.000793758,0.00006245202,0.0003688612,0.01592577,0.000592447,0.00001824377],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002409211,"about_ca_system_score_gemma":0.0005052903,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002141061,"about_ca_topic_score_gemma":0.000009116864,"domain_scores_codex":[0.997469,0.0001166461,0.0004428459,0.0009070824,0.0008209567,0.0002434443],"domain_scores_gemma":[0.9949993,0.000857481,0.00007856848,0.003820294,0.0001293552,0.0001149639],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001015371,0.01586041,0.6855554,0.01103772,0.002580602,0.0007955026,0.03765205,0.02385698,0.0003875278,0.01752262,0.1017444,0.1029052],"study_design_scores_gemma":[0.001588205,0.002860499,0.2129317,0.0007824682,0.0002403598,0.00002934302,0.001490719,0.7455769,0.007097597,0.02241845,0.003013732,0.001970022],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8143003,0.001607569,0.1809008,0.0002634406,0.0009462645,0.0007450887,0.00006688082,0.0009305722,0.0002390432],"genre_scores_gemma":[0.9486092,0.00001774442,0.05110554,0.000009990659,0.0000721551,0.00001565148,0.00002285984,0.00002323797,0.0001236551],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.72172,"threshold_uncertainty_score":0.9993743,"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."}}