{"id":"W2067449005","doi":"10.1002/ev.326","title":"Real‐time evaluation in humanitarian emergencies","year":2010,"lang":"en","type":"article","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Social Sciences and Humanities Research Council","funders":"","keywords":"Formative assessment; Credibility; Evaluation methods; Program evaluation; Field (mathematics); Emergency management; Process management; Computer science; Monitoring and evaluation; Risk analysis (engineering); Political science; Business; Psychology; Engineering; Public administration","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":["insufficient_payload"],"category_scores_codex":[0.02473062,0.000166799,0.0002240592,0.0008356414,0.0004360841,0.000225463,0.0003461498,0.0001440369,0.02111136],"category_scores_gemma":[0.007601687,0.0001493982,0.0001354214,0.001349853,0.00004347226,0.000930701,0.00003354747,0.0002025159,0.0009041436],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002848825,"about_ca_system_score_gemma":0.001409882,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005338709,"about_ca_topic_score_gemma":0.01547348,"domain_scores_codex":[0.9945185,0.0004904731,0.0009112529,0.0005576141,0.003247,0.00027519],"domain_scores_gemma":[0.9958813,0.0007165552,0.0003233731,0.0006398227,0.002326706,0.000112252],"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":[0.00006143743,0.0002419479,0.00970449,0.000003804331,0.00002548199,1.009647e-7,0.002576572,0.006711751,0.03248901,0.006500219,0.03778033,0.9039049],"study_design_scores_gemma":[0.002290877,0.0001454365,0.2089537,0.00001012086,0.0001158524,0.00000263069,0.0006367078,0.6159611,0.001640717,0.09887509,0.071104,0.0002637062],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9112027,0.00005001839,0.001530063,0.002535789,0.003859328,0.002819557,0.00001626215,0.0001038417,0.07788242],"genre_scores_gemma":[0.9831802,0.0000303897,0.004547333,0.00008297061,0.0006410053,0.0009268737,0.0001874923,0.0000236074,0.01038009],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9036412,"threshold_uncertainty_score":0.9998738,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2369325683844146,"score_gpt":0.526100458986193,"score_spread":0.2891678906017783,"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."}}