{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.001366467,0.0002815181,0.0003848313,0.000771571,0.0009037665,0.0007258434,0.002765781,0.0001097074,0.00001597111],"category_scores_gemma":[0.0006337001,0.0002912523,0.0000403434,0.002783229,0.0008232852,0.01352656,0.008679338,0.0002868826,5.202876e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007163612,"about_ca_system_score_gemma":0.0006891572,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002378207,"about_ca_topic_score_gemma":0.00004040973,"domain_scores_codex":[0.9969358,0.00008016099,0.0006167965,0.001282159,0.0004512354,0.0006338183],"domain_scores_gemma":[0.9969473,0.000339681,0.0003132875,0.002036565,0.0002507195,0.0001124538],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005366067,0.0001984451,0.0007710698,0.0009974119,0.00007883146,0.00003454031,0.00778251,0.001844293,0.3078983,0.2070173,0.00005701505,0.4732666],"study_design_scores_gemma":[0.0001452212,0.00003121446,0.00002287614,0.0002858771,0.00001575796,0.00001334823,0.0009249298,0.6045454,0.3838269,0.009938053,0.00006686844,0.0001835856],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05476588,0.002987774,0.9391059,0.00008777079,0.0002758596,0.0002973439,0.00002674746,0.0004221207,0.00203056],"genre_scores_gemma":[0.6079085,0.00008416973,0.391753,0.0001163523,0.00001845749,0.000002115155,5.718983e-7,0.000009453778,0.0001072955],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6027011,"threshold_uncertainty_score":0.999954,"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."}}