{"id":"W3208939115","doi":"10.1177/1098214020936769","title":"The Use of Evaluability Assessments in Improving Future Evaluations: A Scoping Review of 10 Years of Literature (2008–2018)","year":2021,"lang":"en","type":"review","venue":"American Journal of Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; University of Guelph","funders":"","keywords":"Ambiguity; Psychology; Engineering ethics; Equity (law); Relevance (law); Management science; Political science; Engineering; Computer science","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"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06344813,0.0003283481,0.003111648,0.0008705746,0.00007778259,0.0001451385,0.0008925869,0.000150824,0.000862468],"category_scores_gemma":[0.02940827,0.000210491,0.0009969742,0.004559773,0.0003184494,0.0008796083,0.0001514113,0.000626304,0.000005179373],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004433475,"about_ca_system_score_gemma":0.01066186,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001759566,"about_ca_topic_score_gemma":0.00003016786,"domain_scores_codex":[0.9744276,0.01011017,0.006840216,0.000479472,0.007875055,0.000267486],"domain_scores_gemma":[0.9659846,0.006484188,0.0153905,0.001249932,0.01079496,0.00009581108],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"systematic_review","study_design_scores_codex":[0.00002495414,0.0001067715,0.00009509738,0.008238254,0.0001095714,0.000001106611,0.0002323378,0.0002331895,0.000004452129,0.00001877128,0.0003988632,0.9905366],"study_design_scores_gemma":[0.00121767,0.001650457,0.002898832,0.8531283,0.003162652,0.00008665565,0.001316484,0.004767446,0.00001077354,0.0004746058,0.1307919,0.0004943014],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0009881364,0.99584,0.0002422294,0.0001898818,0.0006852604,0.00195228,0.00004335276,0.000001978404,0.00005688611],"genre_scores_gemma":[0.0003083153,0.9953063,0.003974634,0.00006226773,0.0001516031,0.00006913425,0.00005179028,0.00002152715,0.00005439825],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9900423,"threshold_uncertainty_score":0.9949468,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3614297121157451,"score_gpt":0.6078438813411042,"score_spread":0.2464141692253591,"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."}}