{"id":"W1773568500","doi":"10.3138/cjpe.0028.007","title":"Evaluator Competencies: The Aotearoa New Zealand Experience","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Aotearoa; Credentialing; Underpinning; Pedagogy; Set (abstract data type); Engineering ethics; Cultural competence; Sociology; Psychology; Medical education; Engineering; Computer science; Medicine; Gender studies","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":[0.0226114,0.000133405,0.0002330857,0.0003611126,0.0003406441,0.0006817573,0.0009588725,0.00006542286,0.004291863],"category_scores_gemma":[0.006640275,0.00007774596,0.0001405074,0.0007826823,0.0001711871,0.0005893757,0.0000174055,0.0002382811,0.000228595],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002442671,"about_ca_system_score_gemma":0.006229897,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001614443,"about_ca_topic_score_gemma":0.01546313,"domain_scores_codex":[0.9941275,0.001017901,0.0009415319,0.0002119555,0.003374862,0.0003263197],"domain_scores_gemma":[0.9950349,0.0005683614,0.0007325042,0.0004923657,0.002497347,0.0006744677],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001113632,0.00001579081,0.02331101,9.8664e-7,0.00001510276,9.828595e-7,0.007438072,0.002745355,0.00004155123,0.000459453,0.046282,0.9196786],"study_design_scores_gemma":[0.0009977571,0.0005403476,0.09661956,0.00003333235,0.00006556979,0.00005616623,0.002278227,0.1226297,0.00007385333,0.02898066,0.7475715,0.0001533025],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9601,0.0005074422,0.003262424,0.02432773,0.002919035,0.00172429,0.000003872834,0.00002055922,0.007134626],"genre_scores_gemma":[0.992255,0.000006528527,0.003138152,0.000783054,0.0005510037,0.00004212911,0.000003542727,0.000009693078,0.003210928],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9195253,"threshold_uncertainty_score":0.9994038,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2732667343657929,"score_gpt":0.4978504535242318,"score_spread":0.2245837191584389,"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."}}