{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.4079899,0.002089039,0.001929485,0.01219066,0.004958752,0.03096385,0.007504384,0.007954605,0.001635112],"category_scores_gemma":[0.4189055,0.001898609,0.001645138,0.00652717,0.02357343,0.02166871,0.01603075,0.00690359,0.000780421],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01858315,"about_ca_system_score_gemma":0.02471322,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007532964,"about_ca_topic_score_gemma":0.006735831,"domain_scores_codex":[0.3329741,0.5994905,0.01685273,0.01123645,0.03664866,0.002797544],"domain_scores_gemma":[0.4399356,0.3941255,0.04026283,0.0587789,0.05999549,0.00690165],"domain_codex":"methods","domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004800111,0.002735677,0.03161696,0.003881568,0.0007464289,0.0003215094,0.2059144,0.01568489,0.003618023,0.2485241,0.006499796,0.4799767],"study_design_scores_gemma":[0.0006323857,0.003168848,0.02357739,0.02383483,0.0005380713,0.0007823397,0.1736655,0.09628722,0.01676082,0.5825242,0.07716442,0.001063975],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07956642,0.003311129,0.8521215,0.02702553,0.0005188168,0.004119191,0.0001393631,0.0007760344,0.03242201],"genre_scores_gemma":[0.4827639,0.0008720109,0.5101307,0.0008876313,0.00007300151,0.004018171,0.0001066492,0.00009792597,0.001049954],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4079899,"threshold_uncertainty_score":0.7300539,"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."}}