{"id":"W4417428429","doi":"10.1177/00169862251392934","title":"Making a List Requires Checking it Twice: A Call for Empirical Evidence in Characteristics Lists","year":2025,"lang":"en","type":"article","venue":"Gifted Child Quarterly","topic":"Education, Achievement, and Giftedness","field":"Psychology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"American Psychological Foundation","keywords":"Distrust; Empirical evidence; Privilege (computing); Empirical research; Grounded theory","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006738398,0.0003102157,0.0004302463,0.000391489,0.0002393701,0.000150322,0.0004811275,0.0002556505,0.0002300995],"category_scores_gemma":[0.0003021296,0.0003269164,0.0001405235,0.0006539614,0.0001206067,0.0002225002,0.00002854807,0.0004058409,0.00003974946],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001573436,"about_ca_system_score_gemma":0.0001583666,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002523018,"about_ca_topic_score_gemma":0.0008188638,"domain_scores_codex":[0.9973779,0.0002239515,0.0008204191,0.0007226802,0.0002010838,0.0006539986],"domain_scores_gemma":[0.9982296,0.000582349,0.0002689613,0.0006762516,0.0001535818,0.0000892132],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001288504,0.001801174,0.7558635,0.0007825529,0.0003035996,0.00006638914,0.09402891,0.000001382073,0.0004298679,0.01446229,0.08112316,0.04984861],"study_design_scores_gemma":[0.001615134,0.0006268902,0.9512154,0.002300966,0.0001091769,0.00001552989,0.004870627,0.000189089,0.00002442745,0.001625758,0.0368651,0.0005418712],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9620051,0.0009677365,0.003821521,0.01845142,0.003240054,0.001212399,0.00006928423,0.0001810425,0.01005142],"genre_scores_gemma":[0.9904061,0.00001632743,0.0003818072,0.005663292,0.0005670525,0.0003813926,0.00008111876,0.00003688909,0.002466019],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1953519,"threshold_uncertainty_score":0.9999183,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.149879191649207,"score_gpt":0.4557469802000595,"score_spread":0.3058677885508525,"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."}}