{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003895563,0.0001500568,0.0001619526,0.0002425081,0.0002496911,0.0001048712,0.0005180615,0.00007410908,0.000005111188],"category_scores_gemma":[0.0003870834,0.0001375802,0.00009251143,0.0005345321,0.00002708586,0.000190691,0.0001530905,0.0001952777,0.000002536608],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008332993,"about_ca_system_score_gemma":0.00005557623,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003809042,"about_ca_topic_score_gemma":0.0000127831,"domain_scores_codex":[0.9988933,0.00005191209,0.0001946425,0.00043968,0.0001514214,0.0002690601],"domain_scores_gemma":[0.9990835,0.0002205894,0.00007895535,0.0004156087,0.0001600182,0.0000413241],"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":[0.0001235688,0.0003621508,0.001857872,0.0004981283,0.00009418799,0.00001101253,0.0002802927,0.04130531,0.01784713,0.09878201,0.002047867,0.8367904],"study_design_scores_gemma":[0.0003784214,0.0001701171,0.0000390017,0.00001332978,0.000005538766,0.000004561384,0.000020908,0.7540047,0.2239528,0.004891538,0.01632916,0.0001899325],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000144397,0.0000892492,0.990437,0.0003643142,0.00009090299,0.0004373944,0.000001248197,0.002567675,0.005867776],"genre_scores_gemma":[0.4652737,0.000002281134,0.5321924,0.0006605792,0.00001373033,0.0001884869,0.0000018733,0.000009977452,0.001656979],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8366005,"threshold_uncertainty_score":0.5610356,"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."}}