{"id":"W4411157553","doi":"10.1080/10645578.2025.2494485","title":"Implementing Culturally Responsive Evaluation Methods: Reflections on Challenges to Traditional Understandings of Power, Validity, and Rigor","year":2025,"lang":"en","type":"article","venue":"Visitor Studies","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Learning Partnership","funders":"National Aeronautics and Space Administration","keywords":"Power (physics); Rigour; Sociology; Psychology; Engineering ethics; Political science; Epistemology; Engineering","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":["metaresearch"],"category_scores_codex":[0.7113553,0.001757285,0.001803618,0.003327159,0.0147036,0.03016615,0.01034194,0.01385032,0.002608299],"category_scores_gemma":[0.7276533,0.00183137,0.002102304,0.002647169,0.06766578,0.03209163,0.01920419,0.04095713,0.0007622943],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.02608331,"about_ca_system_score_gemma":0.06121818,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01408598,"about_ca_topic_score_gemma":0.01182581,"domain_scores_codex":[0.1696985,0.740988,0.02276801,0.008686215,0.05104257,0.006816708],"domain_scores_gemma":[0.09649129,0.7965585,0.01061074,0.02150321,0.0696441,0.005192111],"domain_codex":"methods","domain_gemma":"methods","domain_candidate":"methods","domain_consensus":"methods","study_design_codex":"qualitative","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003122928,0.0007281284,0.006116816,0.003549929,0.0002708472,0.0008640712,0.5050537,0.00237988,0.001912298,0.2218634,0.05825133,0.1986973],"study_design_scores_gemma":[0.0002914596,0.00088991,0.003771767,0.013715,0.0001165591,0.0009634012,0.4083142,0.006717734,0.005239808,0.2445604,0.3148697,0.0005500294],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"methods","genre_scores_codex":[0.03320218,0.008308248,0.124421,0.8098192,0.003877308,0.001576494,0.00007344221,0.0003155537,0.01840661],"genre_scores_gemma":[0.6072224,0.006182099,0.2432124,0.1292192,0.00184332,0.006949179,0.00007254232,0.001014129,0.004284698],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.2886447,"threshold_uncertainty_score":0.3559503,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.728286921715105,"score_gpt":0.6583180992551956,"score_spread":0.06996882245990943,"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."}}