{"id":"W4387641015","doi":"10.31234/osf.io/my24e","title":"When expert predictions fail","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Philosophy and History of Science","field":"Arts and Humanities","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"The Scarborough Hospital; University of Waterloo; Defence Research and Development Canada","funders":"Social Sciences and Humanities Research Council of Canada; John Templeton Foundation; National Science Foundation","keywords":"Humility; Context (archaeology); Epistemology; Data science; Sociology; Psychology; Computer science; Management science; Political science; Engineering; History; Law","routes":{"ca_aff":true,"ca_fund":true,"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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.05548954,0.0008687315,0.001412771,0.004520065,0.00282024,0.009196817,0.002719037,0.007215463,0.01213685],"category_scores_gemma":[0.3269341,0.0006603087,0.0006882173,0.002617808,0.004611091,0.01290308,0.005059569,0.004894046,0.005083561],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002695042,"about_ca_system_score_gemma":0.003451435,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007182045,"about_ca_topic_score_gemma":0.007437758,"domain_scores_codex":[0.9616528,0.01720415,0.002558082,0.006601292,0.008882593,0.003101091],"domain_scores_gemma":[0.7177693,0.2086388,0.02038843,0.01784561,0.02953426,0.005823547],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001372567,0.0004814736,0.1683755,0.0007796306,0.000668282,0.004168299,0.01466599,0.02346283,0.00116033,0.1477396,0.173683,0.4634424],"study_design_scores_gemma":[0.0001215914,0.0002220544,0.02917682,0.001322126,0.0001414003,0.001454796,0.009690546,0.06361067,0.001951762,0.8363252,0.0557069,0.0002762304],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.3214099,0.01024744,0.1735268,0.249845,0.006202666,0.0003671605,0.002817675,0.001934099,0.2336492],"genre_scores_gemma":[0.9623558,0.001413035,0.01398083,0.01474278,0.001433487,0.00009899135,0.0009043111,0.0002316252,0.004839144],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9445105,"threshold_uncertainty_score":0.2934602,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1802571539235935,"score_gpt":0.2654187513234654,"score_spread":0.08516159739987189,"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."}}