{"id":"W4417045320","doi":"10.31234/osf.io/rgf2u_v1","title":"Psychometric Measurement of Forecasters Using the Wisdom of Crowds","year":2025,"lang":"","type":"article","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":"Ground truth; Crowds; Event (particle physics); Aggregate (composite); Measure (data warehouse); Baseline (sea); Outcome (game theory)","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":[],"consensus_categories":[],"category_scores_codex":[0.005744163,0.000195092,0.000464371,0.001031565,0.0002440647,0.0000938589,0.001605624,0.0001138046,0.0004728288],"category_scores_gemma":[0.001518007,0.0001160071,0.0003290703,0.008868015,0.0007043838,0.0001128755,0.0003475807,0.000155028,0.00000538986],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008648877,"about_ca_system_score_gemma":0.0003374022,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003237944,"about_ca_topic_score_gemma":0.0000361491,"domain_scores_codex":[0.9957451,0.0001232795,0.001644842,0.000450236,0.001759938,0.0002765724],"domain_scores_gemma":[0.9954285,0.0006947933,0.0008143932,0.001412496,0.00159368,0.00005613436],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001868227,0.00109773,0.01631815,0.0002179671,0.000334321,2.437393e-7,0.0008759577,0.001809432,0.0475631,0.1262997,0.05128308,0.7540135],"study_design_scores_gemma":[0.002040571,0.0009631266,0.01554744,0.002059787,0.0007506842,0.00001315492,0.007295122,0.2996095,0.3775748,0.2124515,0.08079988,0.0008945016],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1268198,0.001387562,0.8222342,0.002036133,0.0005105805,0.001002845,0.00002558296,0.00002820665,0.04595504],"genre_scores_gemma":[0.9713426,0.00006372253,0.02741199,0.0001132584,0.00001704767,0.0000160552,2.444422e-7,0.000008022098,0.001027034],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8445228,"threshold_uncertainty_score":0.5177143,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2997204130172303,"score_gpt":0.4336905674516686,"score_spread":0.1339701544344383,"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."}}