{"id":"W4399453597","doi":"10.48550/arxiv.2406.04220","title":"BEADs: Bias Evaluation Across Domains","year":2024,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Government of Canada; Canadian Institute for Advanced Research","keywords":"Environmental science","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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001736575,0.0002970063,0.0002823127,0.0001079626,0.0001304587,0.000439291,0.001596941,0.0003033601,0.00003272493],"category_scores_gemma":[0.0001918898,0.0002854597,0.0001888573,0.000255083,0.00004406517,0.0001720904,0.004777399,0.0008598526,0.0009884565],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003817026,"about_ca_system_score_gemma":0.0003891761,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002668509,"about_ca_topic_score_gemma":0.0001086919,"domain_scores_codex":[0.9970554,0.0001572804,0.0004439533,0.001171183,0.0007383491,0.000433797],"domain_scores_gemma":[0.9975831,0.00009094609,0.0001665319,0.001849121,0.0002064047,0.000103897],"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":[0.0000185644,0.000356741,0.2280463,0.001447652,0.000774115,0.0003666298,0.03907006,0.06243933,0.002743779,0.06981073,0.00737847,0.5875477],"study_design_scores_gemma":[0.0003921521,0.00003512471,0.03016302,0.0005597884,0.00008958243,0.00001854395,0.0001350094,0.897636,0.001579767,0.06456534,0.004011728,0.0008139748],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8683678,0.001113222,0.1212128,0.001894272,0.00426224,0.0004320394,0.00001050474,0.0004625927,0.002244592],"genre_scores_gemma":[0.988215,0.00003557318,0.009920176,0.0003552482,0.0006424243,0.0001250443,0.00002033745,0.00002922767,0.0006570268],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8351966,"threshold_uncertainty_score":0.9999598,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1884305838164817,"score_gpt":0.3731990703844707,"score_spread":0.184768486567989,"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."}}