{"id":"W3013316335","doi":"10.29007/h71z","title":"On relationships between imbalance and overlapping of datasets","year":2020,"lang":"en","type":"article","venue":"EPiC series in computing","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; King Abdulaziz City for Science and Technology","keywords":"Support vector machine; Computer science; Precision and recall; Decision tree; Artificial intelligence; Data mining; Machine learning; Recall; k-nearest neighbors algorithm; Pattern recognition (psychology)","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":[],"consensus_categories":[],"category_scores_codex":[0.0003710813,0.00008551565,0.000170224,0.00006399094,0.00007198937,0.00004150329,0.0004863881,0.00004371577,0.000002048324],"category_scores_gemma":[0.0005699901,0.00009273428,0.00001218426,0.0003919026,0.00005982873,0.0003938381,0.0003576612,0.0002227324,0.000003621593],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002016388,"about_ca_system_score_gemma":0.00002004231,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005001274,"about_ca_topic_score_gemma":7.811503e-7,"domain_scores_codex":[0.999016,0.0001032185,0.0003036807,0.0003042515,0.0001373605,0.0001354874],"domain_scores_gemma":[0.998937,0.000468248,0.0001556896,0.0003730421,0.00001942924,0.00004664698],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00002373008,0.00004584538,0.3322404,0.0002274183,0.00002443935,0.00001781096,0.008971783,0.0005884892,0.002584977,0.5994527,0.003712385,0.05210996],"study_design_scores_gemma":[0.0006065897,0.0002573239,0.8435528,0.0003829318,0.000004793557,0.00001080463,0.0003532725,0.1123043,0.009860438,0.02829894,0.003895226,0.000472637],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1627579,0.00007728185,0.8313447,0.00432817,0.00008851292,0.0001944495,0.00005423726,0.0002848907,0.0008698624],"genre_scores_gemma":[0.9019071,0.000006996118,0.09784053,0.0001673127,0.00003649841,0.000001624007,0.00003369065,0.000004452423,0.00000179771],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7391492,"threshold_uncertainty_score":0.3781594,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05639342327698976,"score_gpt":0.2835915093782327,"score_spread":0.2271980861012429,"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."}}