{"id":"W1973373172","doi":"10.3138/cjpe.29.1.118","title":"Evaluating Humanitarian Action in Real Time: Recent Practices, Challenges, and Innovations","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Formative assessment; Accountability; Bridge (graph theory); Action (physics); Process management; Business; Computer science; Risk analysis (engineering); Political science; Sociology; Law","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04204954,0.0001205832,0.0002351297,0.001107907,0.0002282272,0.0003401719,0.0002636681,0.00009913663,0.001077243],"category_scores_gemma":[0.01611207,0.0001042188,0.00003814824,0.0008264993,0.00006474197,0.001163117,0.00001458885,0.000296012,0.00005647781],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004972377,"about_ca_system_score_gemma":0.003150871,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000791261,"about_ca_topic_score_gemma":0.07126598,"domain_scores_codex":[0.9950356,0.001461404,0.001102618,0.0002609558,0.001884755,0.0002546425],"domain_scores_gemma":[0.9937544,0.0005804398,0.001788753,0.0002671565,0.003341789,0.0002675016],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00001463539,0.0000374278,0.003068872,0.000004500249,0.00001049187,0.000001048992,0.001382811,0.0006287749,0.0001458345,0.001940993,0.0003254822,0.9924392],"study_design_scores_gemma":[0.002348595,0.001636916,0.5116633,0.000122003,0.0001110918,0.00007758188,0.003337605,0.2933215,0.00004045687,0.04011771,0.1469361,0.0002872218],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9657997,0.00143252,0.0001918193,0.01206282,0.0008573667,0.001352585,0.000002465137,0.00001584007,0.01828492],"genre_scores_gemma":[0.991486,0.0006485289,0.007200422,0.0001366399,0.0003108226,0.00006907357,0.00001980294,0.00001274673,0.0001159539],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9921519,"threshold_uncertainty_score":0.9998359,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7423398199910727,"score_gpt":0.610782611392342,"score_spread":0.1315572085987307,"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."}}