{"id":"W2268779592","doi":"10.1080/02697459.2015.1081335","title":"Plan Evaluation: Challenges and Directions for Future Research","year":2015,"lang":"en","type":"article","venue":"Planning Practice and Research","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":58,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Plan (archaeology); Outcome (game theory); Management science; Government (linguistics); Subject (documents); Process management; Evaluation methods; Site plan; Political science; Business; Computer science; Engineering; Regional planning; Urban planning; Economics; Geography; Civil engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"}],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1942762,0.001624526,0.004039907,0.00588586,0.005538098,0.02286883,0.008907299,0.008207167,0.02050749],"category_scores_gemma":[0.1902874,0.000942501,0.002226924,0.009491239,0.01426294,0.03615897,0.01030411,0.01109445,0.002684474],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01427851,"about_ca_system_score_gemma":0.0709635,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0189452,"about_ca_topic_score_gemma":0.02984339,"domain_scores_codex":[0.9177865,0.06385884,0.003600545,0.002607059,0.007940116,0.004206988],"domain_scores_gemma":[0.6078269,0.2930885,0.007683589,0.01264977,0.05988356,0.01886768],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003603123,0.0008226399,0.006991296,0.009629723,0.0001881972,0.0002252821,0.00463309,0.003264487,0.0001499218,0.235236,0.09327324,0.6452258],"study_design_scores_gemma":[0.0002341881,0.0005699656,0.006539204,0.04435234,0.0001876225,0.0005139069,0.09950709,0.01111954,0.0003802924,0.6047027,0.2316263,0.0002669293],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.005805357,0.2098056,0.02497081,0.7280864,0.004109131,0.0006904702,0.0002829237,0.000299356,0.02595007],"genre_scores_gemma":[0.2626961,0.4976921,0.1664744,0.05235716,0.007321685,0.004485073,0.001039079,0.0003036922,0.00763072],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.1942762,"threshold_uncertainty_score":0.9936009,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9129376068496025,"score_gpt":0.7272479990415307,"score_spread":0.1856896078080718,"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."}}