{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2251661,0.001060282,0.001536805,0.005650084,0.002506547,0.01768103,0.005872633,0.004226577,0.003533327],"category_scores_gemma":[0.2125889,0.0007630534,0.0007971344,0.007258732,0.01771899,0.01453199,0.006398514,0.005650577,0.0006254647],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.02068757,"about_ca_system_score_gemma":0.03001024,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03860623,"about_ca_topic_score_gemma":0.04092391,"domain_scores_codex":[0.8655325,0.0955029,0.008168658,0.007871283,0.02087286,0.002051767],"domain_scores_gemma":[0.5772405,0.3009056,0.0111696,0.0161023,0.08910789,0.005474159],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.0002112283,0.000364814,0.00996774,0.007281967,0.0001341716,0.00008576645,0.01586027,0.003504056,0.0009033624,0.06478885,0.009562334,0.8873355],"study_design_scores_gemma":[0.00022354,0.001802184,0.04463538,0.06398495,0.0003717479,0.0009040869,0.1058045,0.01489907,0.008651769,0.1683504,0.5894899,0.00088245],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.07921702,0.4096492,0.1089951,0.3101878,0.003260111,0.00105706,0.0006399364,0.0006322147,0.08636147],"genre_scores_gemma":[0.6845369,0.1777605,0.1201162,0.01082582,0.001789388,0.001031542,0.0003530931,0.0003094653,0.003277169],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9793124,"threshold_uncertainty_score":0.9555081,"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."}}