{"id":"W3112518056","doi":"10.1163/15718069-bja10031","title":"Best Practices in the Measurement and Evaluation of Track Two Dialogues: Towards a “Reflective Practice Model”","year":2020,"lang":"en","type":"article","venue":"International Negotiation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Snapshot (computer storage); Computer science; Measure (data warehouse); Best practice; Field (mathematics); Negotiation; Political science; Data mining; Law; Mathematics","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01488533,0.00009243181,0.0001271663,0.0001567709,0.00005869044,0.0001919361,0.0003925566,0.00003657876,0.0001518176],"category_scores_gemma":[0.02117956,0.00006378171,0.00004033437,0.0004350581,0.00003686535,0.001677931,0.00004599543,0.0001440461,0.00004216399],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001686724,"about_ca_system_score_gemma":0.0004585136,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001901602,"about_ca_topic_score_gemma":0.0005098746,"domain_scores_codex":[0.9923989,0.0008167215,0.0006290571,0.0003155157,0.005749764,0.00009007915],"domain_scores_gemma":[0.994592,0.0008765567,0.001057899,0.0001618898,0.003274734,0.00003688427],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009938993,0.0009840453,0.01348274,0.00001969136,0.0001849372,0.000002562472,0.111114,0.4451908,0.00473414,0.02380865,0.002239211,0.3972453],"study_design_scores_gemma":[0.001106874,0.0001252045,0.01763541,0.00001652777,0.00006574772,0.000003235504,0.007112138,0.956804,0.0004239415,0.01425838,0.002372079,0.00007645807],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7316676,0.0003089042,0.01765908,0.119378,0.0006135904,0.001367506,0.00002998826,0.00002093343,0.1289544],"genre_scores_gemma":[0.9960598,0.00005535167,0.00155523,0.002101542,0.0001354558,0.00005935565,0.00001390964,0.00000433403,0.00001499013],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5116132,"threshold_uncertainty_score":0.9870654,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7031697532543458,"score_gpt":0.5923994374193863,"score_spread":0.1107703158349596,"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."}}