{"id":"W4367285108","doi":"10.51744/cip2","title":"Designing evaluations to provide evidence to inform action in new settings","year":2018,"lang":"en","type":"report","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"Impact","funders":"","keywords":"Psychological intervention; Context (archaeology); Action (physics); Public relations; Promotion (chess); Psychology; Political science; Geography","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":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.02900062,0.0003151256,0.0005195116,0.001802908,0.0002495155,0.0007702681,0.0009789879,0.0002517171,0.01033227],"category_scores_gemma":[0.03988921,0.0002396563,0.0001288554,0.003292827,0.00002490907,0.001509001,0.0003249747,0.0003470544,0.009035832],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001420007,"about_ca_system_score_gemma":0.01700462,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001243948,"about_ca_topic_score_gemma":0.01005933,"domain_scores_codex":[0.9878724,0.0002300791,0.001889963,0.0009155308,0.008634313,0.0004577244],"domain_scores_gemma":[0.9923433,0.001675051,0.0006875433,0.001037813,0.003809697,0.0004465887],"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":[0.00002399622,0.00001257469,0.003059482,0.00001691942,0.000007302132,7.457867e-7,0.001487228,0.001015428,0.000212898,0.00002411951,0.5998243,0.394315],"study_design_scores_gemma":[0.000170073,0.0003485222,0.02385677,0.0008802551,0.00002836443,0.00001074284,0.001220163,0.002006495,0.001258671,0.0009906417,0.9688165,0.0004128654],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.02583496,0.0003085517,0.3090954,0.06549532,0.007846535,0.009536045,0.00002102553,0.0003487373,0.5815133],"genre_scores_gemma":[0.07339884,0.000350621,0.1439956,0.01189848,0.002620106,0.0007213519,0.00005363061,0.00008575644,0.7668756],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.3939021,"threshold_uncertainty_score":0.9998482,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7086949615913435,"score_gpt":0.6482410702142726,"score_spread":0.06045389137707091,"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."}}