{"id":"W4392114473","doi":"10.1162/opmi_a_00121","title":"Quantifying Bias in Hierarchical Category Systems","year":2024,"lang":"en","type":"article","venue":"Open Mind","topic":"Categorization, perception, and language","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Categorization; Dewey Decimal Classification; Abstraction; Set (abstract data type); Computer science; Library classification; Focus (optics); Data science; Information retrieval; Library of Congress Classification; Cognitive psychology; Natural language processing; Psychology; Artificial intelligence; Epistemology; World Wide Web","routes":{"ca_aff":true,"ca_fund":true,"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":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0005631678,0.0001036603,0.0001575147,0.0001819917,0.00005178338,0.0003604183,0.0002518996,0.000112904,0.01623826],"category_scores_gemma":[0.00002012918,0.00009256938,0.00003673002,0.0003353079,0.0000395708,0.0001599454,0.00005575682,0.0001958101,0.005343168],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004756458,"about_ca_system_score_gemma":0.00007317378,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002939413,"about_ca_topic_score_gemma":0.001598307,"domain_scores_codex":[0.9988738,0.0001662167,0.000265522,0.0003735949,0.0001051293,0.0002157325],"domain_scores_gemma":[0.999549,0.0001023903,0.00002465186,0.0002507961,0.00001590273,0.00005722219],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002708601,0.0007219355,0.07028543,0.0002770498,0.0002558882,0.002122809,0.2788449,0.0003008146,0.006826577,0.1154769,0.02872029,0.4958965],"study_design_scores_gemma":[0.001353228,0.0001442458,0.1023233,0.000308119,0.00006221972,0.0003260114,0.02641468,0.003532112,0.0001302927,0.0003905045,0.8642741,0.0007411927],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8688697,0.001645465,0.0004270283,0.0001640097,0.00187844,0.0003782396,0.00001790712,0.00001065159,0.1266085],"genre_scores_gemma":[0.974247,0.00001579596,0.00008915111,0.00002498413,0.0002580025,0.00003837344,0.00008599183,0.0000217722,0.02521895],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8355538,"threshold_uncertainty_score":0.9954313,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1777832188856202,"score_gpt":0.4196129243194952,"score_spread":0.241829705433875,"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."}}