{"id":"W4392503529","doi":"10.2214/ajr.24.31060","title":"Reply to “Zero-, Single-, and Few-Shot Learning in Large Language Models to Identify Incidental Findings From Radiology Reports”","year":2024,"lang":"en","type":"letter","venue":"American Journal of Roentgenology","topic":"Radiology practices and education","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto; University Health Network","funders":"","keywords":"Medicine; Zero (linguistics); Radiology; Medical physics; Shot (pellet); Linguistics","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":[0.005168758,0.0008586056,0.00144451,0.0009320764,0.003995446,0.003160282,0.001919544,0.0526881,0.004853904],"category_scores_gemma":[0.04157753,0.001072706,0.001069125,0.0007841027,0.002421565,0.002553188,0.001329536,0.0445644,0.005852798],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003083567,"about_ca_system_score_gemma":0.004218191,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01120018,"about_ca_topic_score_gemma":0.02171885,"domain_scores_codex":[0.9973807,0.0007487455,0.0004607607,0.0004396584,0.000543868,0.00042632],"domain_scores_gemma":[0.9853977,0.009653246,0.0007123235,0.0003863971,0.002580501,0.001269813],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001137255,0.00002853997,0.001362621,0.00003569317,0.00003118601,0.001408433,0.0002113076,0.00006629044,0.0002338585,0.001366443,0.9890473,0.006094493],"study_design_scores_gemma":[0.0005095921,0.0001999697,0.007754636,0.0007131866,0.0001850104,0.006046402,0.002046118,0.00327635,0.001410346,0.02591091,0.9516501,0.0002973709],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"commentary","genre_scores_codex":[0.0005154512,0.0003314305,0.0002234297,0.9920555,0.006015797,0.00001363343,0.0001215547,0.00004421468,0.000679004],"genre_scores_gemma":[0.003438801,0.0002500882,0.0004707198,0.9832286,0.01020796,0.00004813583,0.00004195611,0.0000265389,0.002287326],"genre_candidate":"commentary","genre_consensus":"commentary","teacher_disagreement_score":0.0526881,"threshold_uncertainty_score":0.02733529,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02833361801041726,"score_gpt":0.3311129402821396,"score_spread":0.3027793222717223,"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."}}