{"id":"W4391987539","doi":"10.48550/arxiv.2402.11742","title":"Balanced Data, Imbalanced Spectra: Unveiling Class Disparities with Spectral Imbalance","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Institute for Advanced Research; McKnight Foundation; Instituto de Ciencias del Mar y Limnología, Universidad Nacional Autónoma de México; Alfred P. Sloan Foundation; National Science Foundation","keywords":"Class (philosophy); Spectral line; Mathematics; Artificial intelligence; Computer science; Physics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006618674,0.001123244,0.001087012,0.001527124,0.0009096244,0.002129262,0.001611132,0.001509478,0.001577457],"category_scores_gemma":[0.02349095,0.0003811932,0.0006812921,0.00127933,0.00197427,0.005016028,0.003599866,0.003362981,0.0007268722],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001128233,"about_ca_system_score_gemma":0.001226926,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001448543,"about_ca_topic_score_gemma":0.001904146,"domain_scores_codex":[0.9973807,0.00086327,0.0001298544,0.000699008,0.0007328797,0.0001943062],"domain_scores_gemma":[0.9912992,0.004071516,0.0008429264,0.002486458,0.001012626,0.0002872769],"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":[0.001288254,0.0006073618,0.03802296,0.0003726581,0.0002884211,0.000301454,0.001270945,0.1762922,0.02566108,0.06238061,0.01173489,0.6817793],"study_design_scores_gemma":[0.00005476108,0.0001997112,0.006655838,0.0001068357,0.00007570141,0.0002226748,0.0003486532,0.8329787,0.01726678,0.1365846,0.005457756,0.00004798553],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2004311,0.001334438,0.7904937,0.001690174,0.0002791816,0.0000942972,0.0005877052,0.001293758,0.003795551],"genre_scores_gemma":[0.8475518,0.0003876089,0.1478728,0.0006844057,0.0002140084,0.0001202868,0.0009967022,0.0002424306,0.001929845],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006618674,"threshold_uncertainty_score":0.03500336,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0663146756179159,"score_gpt":0.2113965726880288,"score_spread":0.1450818970701129,"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."}}