{"id":"W326774523","doi":"10.3138/cjpe.025.003","title":"Constructing and Verifying Program Theory Using Source Documentation","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Documentation; Computer science; A priori and a posteriori; Logic model; Management science; Program Design Language; Software engineering; Programming language; Epistemology; Engineering; Sociology","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01669077,0.0001078192,0.0001760961,0.0005308311,0.0003426129,0.0009502098,0.000227392,0.00008258521,0.001518245],"category_scores_gemma":[0.002989497,0.00008727966,0.0000665346,0.0004790506,0.0001950417,0.001048758,0.00001343003,0.0003289716,0.00001189746],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001778422,"about_ca_system_score_gemma":0.002415619,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002764753,"about_ca_topic_score_gemma":0.008280247,"domain_scores_codex":[0.9970371,0.0004643968,0.0007370986,0.0001825588,0.001339893,0.000238947],"domain_scores_gemma":[0.9966684,0.0003041454,0.0007537316,0.000178902,0.001714774,0.0003800221],"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":[0.000008375517,0.00001254337,0.05127354,0.000003009616,0.00001351708,0.000001501893,0.000916287,0.0002736346,0.000397643,0.001381626,0.00004268438,0.9456757],"study_design_scores_gemma":[0.004126844,0.001255221,0.1052882,0.0001841819,0.0004905388,0.001215112,0.03528475,0.7035756,0.001581367,0.08118825,0.0651,0.0007099605],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9918916,0.0001448177,0.004049783,0.0004024886,0.001076337,0.0008827765,0.000001776981,0.0000134486,0.001536927],"genre_scores_gemma":[0.958858,0.000002523945,0.04077703,0.00007224337,0.0002023786,0.00002619312,0.000004974463,0.000009293197,0.00004739067],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9449657,"threshold_uncertainty_score":0.9993945,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3169777432876522,"score_gpt":0.5515263442620003,"score_spread":0.2345486009743482,"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."}}