{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02068424,0.0004648438,0.0007121151,0.006792868,0.001067588,0.003248701,0.001019205,0.001023462,0.001847883],"category_scores_gemma":[0.1549843,0.0003458463,0.0008385609,0.006384886,0.002950673,0.004305209,0.00382755,0.001304841,0.0003523109],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001685944,"about_ca_system_score_gemma":0.0009760137,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005229169,"about_ca_topic_score_gemma":0.005320269,"domain_scores_codex":[0.9819036,0.008104348,0.001521531,0.003032847,0.004715,0.0007226395],"domain_scores_gemma":[0.860426,0.08830937,0.02015577,0.0194949,0.01044848,0.001165493],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003608266,0.0001011822,0.8100939,0.0003947674,0.0007384754,0.00006647965,0.006319359,0.01156337,0.004488413,0.03752429,0.001863067,0.1264858],"study_design_scores_gemma":[0.00006610812,0.0001983477,0.6267701,0.000210828,0.0002288935,0.0003269683,0.003504548,0.08810538,0.007248689,0.2641683,0.008987091,0.0001847628],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8164505,0.001040499,0.172412,0.0005332443,0.0000637198,0.0002002698,0.001544219,0.0003317825,0.007423865],"genre_scores_gemma":[0.9654505,0.00009614937,0.03309767,0.00008174003,0.00003280422,0.0001360229,0.0008189869,0.00003791315,0.0002482308],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02068424,"threshold_uncertainty_score":0.10939,"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."}}