{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01015458,0.000882974,0.0005138044,0.001912785,0.002495541,0.008902935,0.001662237,0.001540923,0.007896948],"category_scores_gemma":[0.0270624,0.0006169225,0.0007703798,0.002075466,0.003637481,0.0136928,0.009701249,0.002280189,0.00165948],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008397992,"about_ca_system_score_gemma":0.001414253,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001848716,"about_ca_topic_score_gemma":0.004239213,"domain_scores_codex":[0.9939505,0.004695884,0.0002041325,0.0004004646,0.0005699604,0.0001791224],"domain_scores_gemma":[0.9846101,0.008264067,0.0006587542,0.004108157,0.001422819,0.000936199],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003523762,0.0001747778,0.01837282,0.001875094,0.0001322155,0.001184626,0.1530504,0.005889085,0.007236503,0.4520967,0.074112,0.2855234],"study_design_scores_gemma":[0.00004449145,0.00010032,0.00353582,0.00112859,0.00006745042,0.0009630204,0.0455059,0.009828047,0.002906219,0.2090809,0.7267227,0.0001165964],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0742745,0.002616168,0.8221446,0.03336659,0.001276474,0.00051531,0.002465679,0.004866307,0.05847433],"genre_scores_gemma":[0.3845828,0.00250672,0.5942298,0.003018153,0.0002979182,0.0009453858,0.001623764,0.002200881,0.01059467],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01015458,"threshold_uncertainty_score":0.05370325,"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."}}