{"id":"W2923483049","doi":"","title":"Toward a Dialogue: Following Professional Standards on Education Achievement Testing","year":2018,"lang":"en","type":"article","venue":"Journal of research practice","topic":"Educational Assessment and Improvement","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Interpretation (philosophy); Test (biology); Context (archaeology); Action (physics); Sociocultural evolution; Process (computing); Psychology; Pedagogy; Engineering ethics; Computer science; Sociology; 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":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05154277,0.0001078147,0.0002033283,0.0007707735,0.0005715383,0.0005801202,0.0008248885,0.00005337799,0.0003226517],"category_scores_gemma":[0.1395109,0.00006985606,0.0001164399,0.001408749,0.0001247242,0.001856711,0.0002046881,0.0008645934,0.0001640916],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006172226,"about_ca_system_score_gemma":0.007781855,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003182686,"about_ca_topic_score_gemma":0.000005335248,"domain_scores_codex":[0.9870124,0.001595697,0.0008816947,0.0002746255,0.009871206,0.0003643796],"domain_scores_gemma":[0.9694817,0.01474168,0.0009292601,0.0003423805,0.01422632,0.0002786281],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001450064,0.004465778,0.01686555,0.00002382689,0.0001896033,0.00005516066,0.00427585,0.00001108928,0.008162051,0.01101416,0.6430988,0.3103881],"study_design_scores_gemma":[0.0008058033,0.004966346,0.02371505,0.0004328242,0.00003055253,0.00006568763,0.02872119,0.0000855824,0.001729142,0.03378502,0.9055026,0.000160263],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7657031,0.0003140539,0.001639853,0.1418477,0.009359733,0.0007140664,0.000010955,0.00001479599,0.08039582],"genre_scores_gemma":[0.9756799,0.00001724302,0.01550499,0.001313238,0.002725481,0.00002010259,0.000001375158,0.00001157151,0.004726097],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3102278,"threshold_uncertainty_score":0.9978431,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4493990704713637,"score_gpt":0.6295861663902028,"score_spread":0.1801870959188391,"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."}}