{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003299735,0.000393319,0.001980369,0.0002288003,0.0002242795,0.0005996376,0.004554179,0.0002120033,0.00000196303],"category_scores_gemma":[0.00124728,0.0002921111,0.0001571181,0.002059792,0.00004110158,0.002567668,0.006105326,0.0005932401,0.000004047779],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005809448,"about_ca_system_score_gemma":0.0002946302,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009084343,"about_ca_topic_score_gemma":0.000004780665,"domain_scores_codex":[0.9961599,0.0005076881,0.00127226,0.001195529,0.0005930258,0.0002715643],"domain_scores_gemma":[0.992757,0.0009147269,0.00107816,0.005003216,0.0001689914,0.0000778973],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[0.000001275739,0.00002139806,0.000002229404,0.9198074,0.0001682038,0.000005076527,0.00007238961,2.789953e-7,3.976955e-8,0.0005716657,0.004032899,0.07531711],"study_design_scores_gemma":[0.00006864961,0.00006827762,7.571545e-7,0.5953211,0.0006609531,0.00005149339,0.000006753192,0.03287487,2.145158e-7,0.00002762266,0.3706773,0.0002420855],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[8.576813e-7,0.9844811,0.01099719,0.00003032799,0.000858314,0.001942309,0.0015613,0.00008482282,0.00004379014],"genre_scores_gemma":[0.000003712923,0.989315,0.002335046,0.00003626027,0.0002338485,0.0001357479,0.00780946,0.00003161105,0.00009929415],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.3666444,"threshold_uncertainty_score":0.9999531,"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."}}