{"id":"W1541033774","doi":"10.1007/978-3-642-13059-5_22","title":"Overlap versus Imbalance","year":2010,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":134,"is_retracted":false,"has_abstract":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Classifier (UML); Interdependence; Training set; Isolation (microbiology); Artificial intelligence; Machine learning; Pattern recognition (psychology)","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":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0008133386,0.0005901762,0.0005237971,0.0007929769,0.0002724124,0.0006825423,0.006708858,0.0005854804,0.00003842799],"category_scores_gemma":[0.0002082877,0.0005737853,0.0001293304,0.0006729316,0.001027458,0.001055323,0.001844122,0.001650321,0.000183831],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003585737,"about_ca_system_score_gemma":0.0006720114,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001280514,"about_ca_topic_score_gemma":0.0000577765,"domain_scores_codex":[0.9955101,0.00002534443,0.0005599478,0.001956109,0.00119109,0.0007574345],"domain_scores_gemma":[0.9951813,0.0005110152,0.0004168516,0.003375823,0.0003123017,0.0002027569],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00002036248,0.0000434146,0.0000693534,0.00003448911,0.00001318234,0.00008283603,0.0002555963,0.0003718208,0.004258779,0.214584,0.0001486802,0.7801175],"study_design_scores_gemma":[0.001514722,0.0006212053,0.0008835513,0.000607508,0.0000201543,0.0001594172,1.865293e-7,0.2312115,0.06869977,0.6021608,0.0908526,0.003268608],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00001843576,0.0001592007,0.9824937,0.0009625262,0.004121608,0.0003757837,0.00001678271,0.0006451822,0.0112068],"genre_scores_gemma":[0.04117057,0.00008994727,0.9560795,0.001295606,0.0006460221,0.00002530397,0.00002102235,0.0000527158,0.000619303],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7768489,"threshold_uncertainty_score":0.9996713,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02038288687829102,"score_gpt":0.2655751414727915,"score_spread":0.2451922545945005,"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."}}