{"id":"W4411544081","doi":"10.31234/osf.io/a7kdx_v4","title":"The Forecasting Proficiency Test: A General Use Assessment of Forecasting Ability","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Forecasting Techniques and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Test (biology); Econometrics; Computer science; Economics; Geology","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":[0.008766451,0.0003848992,0.0006397482,0.0002664819,0.0007821697,0.0008805986,0.002803289,0.0002845424,0.00006897112],"category_scores_gemma":[0.0200364,0.0002244042,0.000465663,0.001178665,0.0004279196,0.0001670174,0.003883797,0.0008410502,0.000002813613],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001678034,"about_ca_system_score_gemma":0.000923756,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004889867,"about_ca_topic_score_gemma":0.0001970619,"domain_scores_codex":[0.9941511,0.0002571159,0.002227569,0.001219601,0.001616925,0.0005277151],"domain_scores_gemma":[0.9807018,0.01308149,0.001615707,0.002752176,0.001737272,0.0001115475],"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":[0.00002487748,0.0007705748,0.3407102,0.0002939984,0.00009031132,0.000005668916,0.0004858581,0.0148094,0.0007352158,0.1987778,0.02643618,0.41686],"study_design_scores_gemma":[0.00008264951,0.00007240594,0.01263442,0.0001839296,0.00003051622,0.000006568725,0.0001146295,0.8255953,0.000543825,0.1561394,0.004335614,0.0002607803],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4525958,0.0000977368,0.4505666,0.001989601,0.0008576839,0.003991047,0.0005587262,0.0004726684,0.08887015],"genre_scores_gemma":[0.7710965,0.0000120981,0.22037,0.00006215448,0.00009728115,0.000483267,0.00001570234,0.00001608581,0.007846882],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8107859,"threshold_uncertainty_score":0.9882182,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3495453691955047,"score_gpt":0.4677185149289907,"score_spread":0.118173145733486,"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."}}