{"id":"W4366548874","doi":"10.1145/3544548.3581086","title":"We are the Data: Challenges and Opportunities for Creating Demographically Diverse Anthropographics","year":2023,"lang":"en","type":"article","venue":"","topic":"Innovative Human-Technology Interaction","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Diversity (politics); Variety (cybernetics); ENCODE; Data science; Set (abstract data type); Computer science; Homogeneous; Visualization; Human–computer interaction; Artificial intelligence; Sociology; Biology","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":[],"consensus_categories":[],"category_scores_codex":[0.0007622189,0.0001112542,0.0001153505,0.0003251887,0.0005104676,0.0001098696,0.0009667043,0.00008117225,0.000003966656],"category_scores_gemma":[0.0001667663,0.00007661039,0.00002774746,0.0004143555,0.0003948118,0.0007099082,0.0009409303,0.0001716379,0.000004038818],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005594847,"about_ca_system_score_gemma":0.00001655416,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005901652,"about_ca_topic_score_gemma":0.0001271349,"domain_scores_codex":[0.9990562,0.00005914767,0.0001589501,0.0003700678,0.0001397482,0.000215868],"domain_scores_gemma":[0.9984118,0.0005758844,0.0001119926,0.000714945,0.0001623812,0.00002296537],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","study_design_scores_codex":[0.000005091979,0.00001847087,0.0003423433,0.00003025639,0.0000559503,0.00001610177,0.001052533,6.661355e-7,0.00006249703,0.8871711,0.004101939,0.107143],"study_design_scores_gemma":[0.00152053,0.0009007304,0.04327017,0.0004029033,0.0001060999,0.0001779669,0.2715885,0.1968928,0.001009565,0.244782,0.2380169,0.001331776],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.1227457,0.00335871,0.3428649,0.5126652,0.001926254,0.001413245,0.0001013185,0.004185496,0.01073918],"genre_scores_gemma":[0.9627805,0.0214373,0.01342726,0.001341308,0.0001403614,0.0001039731,0.00003277952,0.0000215881,0.0007149135],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8400348,"threshold_uncertainty_score":0.3926155,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2950052236385427,"score_gpt":0.3537212160289532,"score_spread":0.05871599239041053,"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."}}