{"id":"W4362677817","doi":"10.1007/s44248-023-00003-x","title":"A systematic literature review of cyber-security data repositories and performance assessment metrics for semi-supervised learning","year":2023,"lang":"en","type":"review","venue":"Discover Data","topic":"Network Security and Intrusion Detection","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Vector Institute","keywords":"Computer science; Scarcity; Machine learning; Data science; Limiting; Artificial intelligence; Computer security; Engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.01304673,0.001666076,0.003127611,0.01750391,0.000724861,0.002853329,0.002810076,0.001694712,0.00378808],"category_scores_gemma":[0.06099378,0.0009590143,0.003242373,0.01935118,0.001209336,0.004142616,0.001610626,0.001531354,0.001525592],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001933404,"about_ca_system_score_gemma":0.01081652,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005162123,"about_ca_topic_score_gemma":0.01022822,"domain_scores_codex":[0.9935408,0.002037935,0.001575631,0.0008411336,0.001876915,0.0001276549],"domain_scores_gemma":[0.9124775,0.07282084,0.003863237,0.002326645,0.008119318,0.0003924456],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"systematic_review","study_design_scores_codex":[0.0001643939,0.0001209419,0.002650826,0.2339805,0.001158011,0.0000987386,0.0003511278,0.001919445,0.0007241939,0.005569041,0.02920981,0.7240528],"study_design_scores_gemma":[0.00009817779,0.0005196658,0.01226527,0.3436985,0.007111753,0.001052331,0.0008105797,0.003621935,0.003126001,0.0120245,0.6153985,0.0002727605],"study_design_candidate":"systematic_review","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.001495803,0.9853501,0.006773467,0.001188925,0.0003115761,0.0002562046,0.00236542,0.0002073653,0.002051107],"genre_scores_gemma":[0.008955919,0.9712867,0.01330435,0.0008104261,0.0002390364,0.0005955309,0.004274845,0.00009366979,0.0004396418],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.01750391,"threshold_uncertainty_score":0.06899852,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07736740096400081,"score_gpt":0.3581277139363865,"score_spread":0.2807603129723857,"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."}}