{"id":"W4400931347","doi":"10.32388/028gr5","title":"Review of: \"How Effective are Tabletop Role-Playing (Serious) Games in Understanding and Validating the Predictive Capabilities of Disaster Response Agent-based Models?\"","year":2024,"lang":"en","type":"peer-review","venue":"","topic":"Complex Systems and Decision Making","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Human–computer interaction","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","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.02124026,0.0006311183,0.002755676,0.0008661384,0.0001922724,0.000410383,0.001076639,0.0002285214,0.0003311095],"category_scores_gemma":[0.0153011,0.00035272,0.0006271666,0.001814711,0.0004124085,0.0003839373,0.0007885993,0.0006828378,0.000007464958],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003977557,"about_ca_system_score_gemma":0.0003859256,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003295226,"about_ca_topic_score_gemma":0.0004764974,"domain_scores_codex":[0.9891105,0.003626223,0.002614124,0.001322747,0.002876167,0.0004502701],"domain_scores_gemma":[0.9693578,0.02613961,0.002051744,0.001543245,0.0007925149,0.00011504],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"systematic_review","study_design_scores_codex":[0.0007336859,0.00008349923,0.0004823281,0.09483355,0.0002776643,0.00004320137,0.004990865,0.001619082,0.00006218611,0.005731849,0.8772712,0.01387083],"study_design_scores_gemma":[0.0007660181,0.0003836329,0.0003335412,0.6440517,0.000562019,0.00004845385,0.03411451,0.06778235,0.00002988972,0.07564311,0.1753065,0.0009783399],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.002211924,0.9262113,0.03760548,0.01857184,0.001957432,0.005442913,0.001258778,0.00006678764,0.006673575],"genre_scores_gemma":[0.9127136,0.01826224,0.001271575,0.005193125,0.0003564808,0.001119274,0.00005786514,0.0002310855,0.06079471],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.9105017,"threshold_uncertainty_score":0.9998925,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1812455907523141,"score_gpt":0.3957855732809609,"score_spread":0.2145399825286468,"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."}}