{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0004850561,0.0008140522,0.0008117735,0.0004500172,0.0002322207,0.0007426463,0.007796996,0.0004510256,0.0000244996],"category_scores_gemma":[0.00005390567,0.0008320677,0.0001808599,0.001325435,0.0004155948,0.001180804,0.007211448,0.001917014,0.0002082334],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005952523,"about_ca_system_score_gemma":0.0006980488,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002030161,"about_ca_topic_score_gemma":0.0001864353,"domain_scores_codex":[0.9945903,0.0001679633,0.0004920688,0.003467571,0.0003312476,0.0009508887],"domain_scores_gemma":[0.9923684,0.0001633692,0.0004779695,0.006493337,0.0002207502,0.0002761752],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001310422,0.0002149575,0.0068295,0.0006683402,0.0003979201,0.001388625,0.0001830876,0.01298198,0.0007514934,0.9648449,0.01095158,0.0006565396],"study_design_scores_gemma":[0.0007980674,0.0001478494,0.005374326,0.0007763985,0.0001843968,0.0000583883,0.00008037007,0.8231796,0.003274126,0.1609306,0.003365079,0.00183074],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03745685,0.0004659801,0.9448631,0.001174865,0.001067167,0.0009293305,0.0006629191,0.00371585,0.009663913],"genre_scores_gemma":[0.9671031,0.0006691242,0.02888239,0.000222154,0.0002773191,0.000009501743,0.0005744772,0.0000795159,0.002182405],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9296463,"threshold_uncertainty_score":0.999413,"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."}}