{"id":"W4410356985","doi":"10.1145/3672608.3707756","title":"A Machine Learning-Based Approach For Detecting Malicious PyPI Packages","year":2025,"lang":"en","type":"article","venue":"","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary; Concordia University","funders":"","keywords":"Computer science; Artificial intelligence","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":[0.002396711,0.001603873,0.0009661281,0.005478175,0.0008954015,0.001510128,0.001982469,0.001631365,0.001280291],"category_scores_gemma":[0.005516385,0.0003498248,0.001070253,0.001711197,0.0006594977,0.001862495,0.001124653,0.001874186,0.001642566],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001113093,"about_ca_system_score_gemma":0.001371596,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003702951,"about_ca_topic_score_gemma":0.004178883,"domain_scores_codex":[0.9978904,0.0003489747,0.0001554168,0.0006035768,0.0008092819,0.0001924717],"domain_scores_gemma":[0.9958021,0.001382228,0.000500538,0.0004939779,0.001602706,0.0002184],"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":[0.0003015998,0.001295342,0.0476554,0.0001964312,0.000274512,0.0004153954,0.0001951948,0.09262835,0.01879437,0.002705087,0.0156462,0.819892],"study_design_scores_gemma":[0.000008648599,0.0001122203,0.003338473,0.00002144832,0.00004284571,0.0001832038,0.0000361069,0.9854962,0.006351688,0.002380239,0.002006783,0.00002219161],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1781635,0.001205855,0.7953882,0.001160787,0.0003046078,0.0005702314,0.001357855,0.01600499,0.005843988],"genre_scores_gemma":[0.6583272,0.0002944949,0.3315819,0.0004513275,0.0001926593,0.0004004352,0.002915307,0.0002844956,0.005552225],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005478175,"threshold_uncertainty_score":0.01267523,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01211506009077667,"score_gpt":0.2692035489259476,"score_spread":0.2570884888351709,"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."}}