{"id":"W2622935668","doi":"10.3138/jvme.0616-113r","title":"Adaptive Comparative Judgment: A Tool to Support Students' Assessment Literacy","year":2017,"lang":"en","type":"article","venue":"Journal of Veterinary Medical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Ranking (information retrieval); Cohort; Task (project management); Psychology; Process (computing); Work (physics); Mathematics education; Medical education; Computer science; Applied psychology; Information retrieval; Statistics; Medicine; Mathematics; Engineering","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002073419,0.0001187288,0.0002841866,0.0001267097,0.0006874967,0.0004552479,0.001143751,0.0001101493,0.001621277],"category_scores_gemma":[0.0005510042,0.0001026009,0.0001126631,0.00009160454,0.000169404,0.0009496092,0.000189208,0.0003965313,0.00005318632],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003473662,"about_ca_system_score_gemma":0.002560222,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001171198,"about_ca_topic_score_gemma":0.00002739468,"domain_scores_codex":[0.9968902,0.0002254466,0.0005074413,0.0001522757,0.001983294,0.0002412662],"domain_scores_gemma":[0.9980909,0.0001070109,0.0006336347,0.0002189289,0.0004724109,0.0004771796],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001218766,0.008354378,0.2409282,0.00005025263,0.0005597769,0.0003644071,0.2122355,0.000003786251,0.0005339279,0.00941043,0.1220737,0.4042668],"study_design_scores_gemma":[0.001160371,0.003360413,0.7201391,0.0003616105,0.00006428964,0.00005018678,0.01775181,0.00001992498,0.000009417327,0.0004497734,0.2563988,0.0002342502],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9704638,0.00004143359,0.0004384033,0.008374297,0.003484263,0.0003023587,0.000001604939,0.000008648417,0.01688523],"genre_scores_gemma":[0.9924123,0.0001047443,0.003524367,0.0009039642,0.001501675,0.00002174217,0.000002442869,0.000006573477,0.001522208],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4792109,"threshold_uncertainty_score":0.9992914,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.156100825334503,"score_gpt":0.5426009298816273,"score_spread":0.3865001045471244,"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."}}