{"id":"W4404471047","doi":"10.31234/osf.io/a7kdx","title":"The Forecasting Proficiency Test: A General Use Assessment of Forecasting Ability","year":2024,"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); Probabilistic forecasting; Computer science; Econometrics; Artificial intelligence; Economics","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":[0.003787143,0.0006930207,0.0007634403,0.002871912,0.0003650871,0.001500987,0.0008373572,0.001458137,0.006328466],"category_scores_gemma":[0.02798668,0.0001878855,0.0006244485,0.001683584,0.0006062947,0.002084744,0.001097219,0.001099178,0.003059366],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003923353,"about_ca_system_score_gemma":0.0006844015,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002367805,"about_ca_topic_score_gemma":0.002251508,"domain_scores_codex":[0.9980165,0.0005368111,0.0002003085,0.0002873576,0.0008196429,0.0001393908],"domain_scores_gemma":[0.988279,0.005429409,0.002325079,0.001101753,0.002104516,0.0007603771],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0006994943,0.000812781,0.5273328,0.0003781281,0.000291459,0.0001786451,0.001190084,0.00346361,0.003482606,0.00464527,0.0379066,0.4196186],"study_design_scores_gemma":[0.0001042249,0.001353774,0.9359773,0.000276469,0.0001242312,0.0007031189,0.0007202625,0.01296444,0.003670849,0.01618137,0.02778519,0.0001388341],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8226815,0.002052559,0.08640563,0.004309135,0.0005226706,0.001515083,0.02218828,0.0023697,0.05795545],"genre_scores_gemma":[0.931343,0.001520201,0.04115438,0.000825699,0.0002588502,0.001673011,0.0151008,0.0002239869,0.007900203],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006328466,"threshold_uncertainty_score":0.02117079,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3578384490180099,"score_gpt":0.4638868639794628,"score_spread":0.1060484149614528,"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."}}