{"id":"W2010270738","doi":"10.4102/aej.v2i1.98","title":"Reshaping development evaluation: Meeting the challenges of a changing context","year":2014,"lang":"en","type":"article","venue":"African Evaluation Journal","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mastercard Foundation","funders":"","keywords":"Context (archaeology); Development (topology); Computer science; Process management; Engineering ethics; Engineering; Geography; Mathematics","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"],"category_scores_codex":[0.1273614,0.0001546578,0.0002818622,0.0005673926,0.0008583434,0.0002441061,0.0006980159,0.00005052641,0.00253994],"category_scores_gemma":[0.009675578,0.00009471839,0.0001183685,0.0008323494,0.0001142522,0.0004504641,0.0001023782,0.0002443535,0.0001284142],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002380254,"about_ca_system_score_gemma":0.001207941,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002475564,"about_ca_topic_score_gemma":0.00006157227,"domain_scores_codex":[0.9868705,0.003225755,0.001421739,0.0003124728,0.007837792,0.0003317425],"domain_scores_gemma":[0.9917744,0.001737281,0.001443558,0.000460056,0.004466183,0.0001185125],"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":[0.00001701408,0.00002148705,0.0007152566,0.000003315747,0.00003638869,1.247264e-7,0.02052929,0.005529352,0.00013336,0.006741958,0.0005655167,0.9657069],"study_design_scores_gemma":[0.002514303,0.0002365535,0.03606356,0.0002816611,0.0001708651,0.00007038741,0.1132699,0.7195128,0.001740284,0.04260766,0.08317025,0.0003617979],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6776399,0.01035835,0.02951542,0.0736087,0.002900529,0.002117508,0.000002651113,0.00005654807,0.2038004],"genre_scores_gemma":[0.9974607,0.00004341554,0.001355925,0.0004727395,0.0004603975,0.00006763692,0.000001686578,0.00001071847,0.0001267617],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9653451,"threshold_uncertainty_score":0.9986663,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3887763805361222,"score_gpt":0.4856660053502125,"score_spread":0.09688962481409025,"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."}}