{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02985991,0.0004939224,0.000675099,0.003626012,0.0009594936,0.006997258,0.0009493034,0.001277539,0.007954586],"category_scores_gemma":[0.1898726,0.0003350204,0.0008525759,0.002383522,0.002501508,0.0130359,0.00401156,0.001947561,0.002078402],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00306116,"about_ca_system_score_gemma":0.001887368,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004885255,"about_ca_topic_score_gemma":0.003415612,"domain_scores_codex":[0.9774672,0.01790143,0.00085093,0.001242305,0.002058637,0.000479492],"domain_scores_gemma":[0.8093506,0.1636569,0.009490707,0.005470141,0.009970848,0.002060749],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001940195,0.0003249295,0.2486199,0.003238815,0.0004973477,0.000705497,0.1182358,0.00267216,0.002323449,0.02645134,0.02822444,0.5667661],"study_design_scores_gemma":[0.0002847768,0.002179589,0.5072122,0.00873661,0.0009507443,0.00337648,0.1393071,0.04057805,0.005949302,0.1159813,0.174513,0.0009310287],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7974348,0.02496954,0.06835624,0.03904709,0.001874074,0.001120186,0.005071572,0.001943176,0.06018345],"genre_scores_gemma":[0.9676774,0.003236523,0.01781154,0.004170643,0.0003738433,0.0007203205,0.001756147,0.0004035612,0.003849962],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02985991,"threshold_uncertainty_score":0.1579162,"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."}}