{"id":"W7105890051","doi":"10.7910/dvn/3g6yxy","title":"Replication Data for: Machines Do See Color: Using LLMs to Classify Overt and Covert Racism in Text","year":2025,"lang":"","type":"dataset","venue":"Harvard Dataverse","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Covert; Racism; Replication (statistics); Code (set theory); Order (exchange)","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001027358,0.002984755,0.001057726,0.00212502,0.001111654,0.00201801,0.002491925,0.001775103,0.09436475],"category_scores_gemma":[0.006173171,0.0005900855,0.001316827,0.002261579,0.0006100298,0.001958908,0.002214465,0.002083613,0.1836811],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001013218,"about_ca_system_score_gemma":0.001201868,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03065609,"about_ca_topic_score_gemma":0.07079805,"domain_scores_codex":[0.9992319,0.0001313042,0.00006475571,0.0002404102,0.0001757127,0.000155817],"domain_scores_gemma":[0.9973869,0.0004249115,0.000129498,0.0009751742,0.0008065396,0.0002771087],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005924139,0.00003965254,0.0009149555,0.0001512769,0.00001334322,0.00001548439,0.00002872159,0.0001734021,0.0001360949,0.0001350529,0.9942122,0.004120582],"study_design_scores_gemma":[0.0003767504,0.00006867616,0.01319228,0.0003139638,0.00003620553,0.0001116027,0.0003668157,0.003630928,0.002152714,0.002245703,0.9774265,0.0000777857],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.001333351,0.00009473893,0.0002930424,0.0002798281,0.0002289537,0.00005227577,0.9908711,0.004252978,0.002593654],"genre_scores_gemma":[0.00215953,0.00003827495,0.0007899684,0.00007361608,0.00003204818,0.0001026728,0.9937866,0.0003429055,0.002674395],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.9989727,"threshold_uncertainty_score":0.3156816,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05194991065910323,"score_gpt":0.3452946737553614,"score_spread":0.2933447630962581,"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."}}