{"id":"W4416292984","doi":"10.1080/14647273.2025.2584673","title":"Ctrl + Alt + Conceive: fertility awareness in the age of Artificial Intelligence, how do large language models compare?","year":2025,"lang":"en","type":"article","venue":"Human Fertility","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Centre for Global Health Research","funders":"","keywords":"Fertility; Reproductive health; Reproductive technology; Quality (philosophy); Menstrual cycle; Information and Communications Technology; Total fertility rate; Perplexity","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":[0.001560404,0.0002108345,0.0005165768,0.0001895725,0.0002502255,0.00005488054,0.000357817,0.000148497,0.0001842886],"category_scores_gemma":[0.0003416109,0.0001636222,0.0001496629,0.0006469333,0.0003263104,0.0001446523,0.00006723254,0.0004684914,0.00001308045],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001620634,"about_ca_system_score_gemma":0.0003146351,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00274212,"about_ca_topic_score_gemma":0.004902537,"domain_scores_codex":[0.9975247,0.0003722013,0.0008332466,0.0004622334,0.0003639111,0.0004436997],"domain_scores_gemma":[0.9984124,0.0003029142,0.0001305789,0.000788024,0.0002871005,0.0000789644],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.003561493,0.008005264,0.6935499,0.002779339,0.0001536037,0.0001211988,0.1094212,0.0002904534,0.00928609,0.07941671,0.001845141,0.09156966],"study_design_scores_gemma":[0.0001206542,0.0001622908,0.8315368,0.0003859257,0.00008769443,0.00000207523,0.03898019,0.007436036,0.03059593,0.09000924,0.00043281,0.0002503611],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9881865,0.0005022001,0.005452433,0.001703271,0.0002388907,0.0008993816,0.00002806285,0.00005048764,0.002938797],"genre_scores_gemma":[0.9988362,0.00001136723,0.00006166119,0.0006459698,0.0000720609,0.00007829148,0.0001037244,0.0000104266,0.0001802941],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1379869,"threshold_uncertainty_score":0.6672319,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2092349228133938,"score_gpt":0.4560482009343415,"score_spread":0.2468132781209477,"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."}}