{"id":"W6910489309","doi":"10.48448/zcn9-1s58","title":"Debiasing should be Good and Bad","year":2023,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Brock University","funders":"","keywords":"Debiasing; Consistency (knowledge bases); Interpretability; Generalizability theory; Domain (mathematical analysis); Protocol (science)","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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001356115,0.0004256647,0.000400037,0.001503437,0.0003325818,0.000346809,0.0008928663,0.0002853912,0.0006212878],"category_scores_gemma":[0.000546604,0.0003887393,0.00004804952,0.00233592,0.002295868,0.0002967015,0.0005179681,0.0004238315,0.002998419],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002621965,"about_ca_system_score_gemma":0.0005856663,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001127645,"about_ca_topic_score_gemma":0.008231497,"domain_scores_codex":[0.9963325,0.00004622366,0.0002896973,0.001135026,0.001335449,0.0008611194],"domain_scores_gemma":[0.9984535,0.0001346419,0.0002515268,0.0007403255,0.00009223463,0.0003277471],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001244619,0.0001673119,0.002035854,0.0001094922,0.00009328635,0.0001840519,0.0004802305,0.00003957247,0.007074846,0.01655479,0.9046991,0.06854902],"study_design_scores_gemma":[0.0006055927,0.0001014987,0.0007632524,0.0005662223,0.00009551541,0.00008826569,0.0003195104,0.009065983,0.0003406862,0.0009678451,0.9859536,0.001131985],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.0006091066,0.0009149482,0.0005142929,0.001298981,0.001640586,0.0007328754,0.0004319756,0.004927535,0.9889297],"genre_scores_gemma":[0.01924828,0.0002790787,0.0258063,0.00124269,0.001337955,0.00003486008,0.00007108425,0.006375243,0.9456045],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.08125455,"threshold_uncertainty_score":0.9998565,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07959819054041216,"score_gpt":0.3475135003449614,"score_spread":0.2679153098045493,"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."}}