{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002042824,0.0006282922,0.000474878,0.001972474,0.0003323326,0.001162113,0.0005772702,0.001005181,0.005911649],"category_scores_gemma":[0.01812121,0.0001564834,0.0005768124,0.001050078,0.0005164962,0.001703532,0.0008269917,0.000936696,0.002450727],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003490116,"about_ca_system_score_gemma":0.0005361448,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002649822,"about_ca_topic_score_gemma":0.002558284,"domain_scores_codex":[0.998887,0.0002297682,0.0001313095,0.0001827903,0.0004150371,0.000154085],"domain_scores_gemma":[0.9907225,0.003750985,0.002306262,0.0008132806,0.001470491,0.0009365347],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0005150245,0.001273144,0.8091281,0.0001197945,0.0002172404,0.0002550186,0.00118321,0.003103967,0.00226195,0.002597912,0.02593894,0.1534058],"study_design_scores_gemma":[0.00005924454,0.0009358734,0.9732423,0.00005960281,0.00005204513,0.0004172405,0.0004606489,0.007731083,0.002437161,0.004418547,0.01012301,0.00006322061],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.956403,0.0003147015,0.01038342,0.001007683,0.0001485014,0.0004361904,0.006505356,0.0004656876,0.02433539],"genre_scores_gemma":[0.9809466,0.0003009404,0.007158568,0.0002590797,0.00007342816,0.0005458571,0.006030519,0.00006800989,0.004616936],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005911649,"threshold_uncertainty_score":0.0197764,"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."}}