{"id":"W4394745299","doi":"10.1145/3597503.3639177","title":"Demystifying and Detecting Misuses of Deep Learning APIs","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University; York University","funders":"","keywords":"Computer science; Software; Artificial intelligence; Focus (optics); World Wide Web; Computer security; 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":[],"consensus_categories":[],"category_scores_codex":[0.0002957313,0.00005201379,0.00006463287,0.0001342965,0.00004329632,0.0001412953,0.0001893803,0.00002371608,0.00001170211],"category_scores_gemma":[0.0007310749,0.00004610564,0.00001819747,0.0003405567,0.00001670168,0.0001881923,0.0001949941,0.0001548395,0.00001132264],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001430779,"about_ca_system_score_gemma":0.00001366018,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002443064,"about_ca_topic_score_gemma":0.00000237089,"domain_scores_codex":[0.9994107,0.00001864535,0.00008797054,0.000183681,0.0001484582,0.0001505843],"domain_scores_gemma":[0.998583,0.001229322,0.000008227187,0.0001122945,0.00002523429,0.00004188322],"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":[0.000001132532,0.000005757869,0.02502608,0.0004777022,0.00003435002,0.00004663686,0.002130863,0.0023818,0.02089315,0.006840806,0.00002345165,0.9421383],"study_design_scores_gemma":[0.00006937969,0.0000554394,0.007424727,0.0001316051,0.000003223557,0.0000601703,0.00009817659,0.9512273,0.03962201,0.0005282735,0.0006385406,0.0001411469],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2224832,0.001603062,0.7750508,0.00007442867,0.00009341435,0.00002839832,3.205026e-8,0.0004710704,0.0001955735],"genre_scores_gemma":[0.9477868,0.00001664094,0.05204151,0.000004359828,0.00001953941,0.000002531838,4.576055e-8,0.000007134493,0.0001214485],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9488455,"threshold_uncertainty_score":0.1880133,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02022102989289797,"score_gpt":0.2798789748483475,"score_spread":0.2596579449554495,"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."}}