{"id":"W7125588949","doi":"10.1109/cascon66301.2025.00083","title":"Detecting and Fixing API Misuses of Data Science Libraries Using Large Language Models","year":2025,"lang":"","type":"article","venue":"","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Key (lock); Function (biology); Misuse detection; Data access; Application programming interface; Open science","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":[0.01039592,0.002243023,0.001425484,0.004238642,0.001421983,0.003580702,0.003649633,0.001718719,0.001072599],"category_scores_gemma":[0.05694763,0.001678635,0.002618022,0.001796045,0.001127358,0.007115528,0.004163288,0.003912234,0.001387301],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002521196,"about_ca_system_score_gemma":0.005658116,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01458407,"about_ca_topic_score_gemma":0.02210191,"domain_scores_codex":[0.9891395,0.003315988,0.001312567,0.002362761,0.003368126,0.0005010001],"domain_scores_gemma":[0.9541109,0.02324877,0.006269112,0.008652654,0.006810683,0.0009079225],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001539589,0.001719808,0.2083044,0.001330064,0.001073782,0.001289723,0.004279405,0.1098889,0.04824269,0.007258903,0.02934344,0.5857292],"study_design_scores_gemma":[0.00005876207,0.0001819917,0.007594818,0.0000711971,0.0001796411,0.0002696595,0.0004031381,0.9302572,0.04865295,0.00297673,0.009218376,0.0001356413],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3496458,0.0004448316,0.411142,0.0016133,0.0001470313,0.0006730129,0.002395779,0.2307726,0.003165584],"genre_scores_gemma":[0.5319813,0.0002017092,0.4520881,0.0006216674,0.00004748065,0.0004235081,0.007011743,0.005471138,0.002153319],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01458407,"threshold_uncertainty_score":0.0549795,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06177716980078343,"score_gpt":0.3500109255822665,"score_spread":0.2882337557814831,"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."}}