{"id":"W4404024979","doi":"10.1073/pnas.2409770121","title":"Measuring diversity in Hollywood through the large-scale computational analysis of film","year":2024,"lang":"en","type":"article","venue":"Proceedings of the National Academy of Sciences","topic":"Cinema and Media Studies","field":"Economics, Econometrics and Finance","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Andrew W. Mellon Foundation","keywords":"Hollywood; Representation (politics); Diversity (politics); Affordance; Film industry; Ethnic group; Computer science; Scale (ratio); Pipeline (software); Data science; Visual arts; Political science; Human–computer interaction; Movie theater; Law; Art; Politics; Geography","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":[0.001148271,0.0002941646,0.0003529753,0.002367509,0.0008023607,0.002472213,0.0007993855,0.0004470224,0.002514595],"category_scores_gemma":[0.009126284,0.0002120762,0.0004428616,0.002025659,0.001072584,0.003149504,0.001522167,0.001028775,0.0002654527],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001057661,"about_ca_system_score_gemma":0.0003851363,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009874996,"about_ca_topic_score_gemma":0.01670618,"domain_scores_codex":[0.999408,0.0002617698,0.00002499995,0.000149853,0.0000955547,0.00005981856],"domain_scores_gemma":[0.9953099,0.003209709,0.0006406887,0.0004453532,0.0002366108,0.0001577745],"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":[0.0004392959,0.0005130811,0.3825972,0.0004672376,0.000329501,0.0005845733,0.007682449,0.1636951,0.007520691,0.1712443,0.01266288,0.2522637],"study_design_scores_gemma":[0.00002198293,0.0000716756,0.2024036,0.0001446994,0.00005906764,0.0002062247,0.006344032,0.6008676,0.004238769,0.1701405,0.01543409,0.00006765992],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.858765,0.0007061047,0.1210323,0.001823341,0.00004108791,0.00009796241,0.002477655,0.0002240693,0.01483246],"genre_scores_gemma":[0.9649742,0.0002094484,0.03210676,0.00008858604,0.00003106648,0.00004946989,0.001581746,0.00003899301,0.0009197889],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009874996,"threshold_uncertainty_score":0.01963502,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1042844054733135,"score_gpt":0.2849207730285917,"score_spread":0.1806363675552782,"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."}}