{"id":"W2070292114","doi":"10.1002/ev.393","title":"Internal evaluation, historically speaking","year":2011,"lang":"en","type":"article","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"Centre for Advancing Health Outcomes; University of British Columbia","funders":"","keywords":"Context (archaeology); Conservatism; Speculation; Government (linguistics); Function (biology); Evaluation methods; Internal validity; Political science; Public administration; Sociology; Public relations; Law; Business; History","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01812725,0.0001636143,0.0002083475,0.0005522726,0.0004234069,0.0001627216,0.0004275002,0.00008961283,0.02066295],"category_scores_gemma":[0.007109472,0.0001378697,0.0001906123,0.0009179246,0.000037804,0.0008693263,0.00004272782,0.0001170788,0.000673414],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000803622,"about_ca_system_score_gemma":0.001248788,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003649111,"about_ca_topic_score_gemma":0.0009106458,"domain_scores_codex":[0.9941237,0.0005208685,0.0008935625,0.0005509414,0.003665056,0.000245871],"domain_scores_gemma":[0.9943635,0.0005012636,0.0004678326,0.0005714491,0.003943295,0.0001526457],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006994035,0.0001064948,0.004718515,0.000001770001,0.00003186737,8.036219e-8,0.002874009,0.0006423387,0.0001989345,0.002345803,0.03861834,0.9503919],"study_design_scores_gemma":[0.003079146,0.0003135103,0.1162775,0.00002492564,0.0003393954,0.00001053144,0.0007121035,0.3699005,0.001260747,0.1659406,0.3417998,0.0003412171],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.08032717,0.0007554456,0.3456487,0.002010304,0.01121147,0.004128161,0.00001711348,0.0002695734,0.5556321],"genre_scores_gemma":[0.9690315,0.00001807375,0.01840582,0.0002803786,0.0006846088,0.0005473531,0.00004555079,0.00002392617,0.01096284],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9500507,"threshold_uncertainty_score":0.9802323,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4596669989734262,"score_gpt":0.5336734648069541,"score_spread":0.07400646583352793,"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."}}