{"id":"W3158874880","doi":"10.1016/j.artmed.2021.102077","title":"Fenchel duality of Cox partial likelihood with an application in survival kernel learning","year":2021,"lang":"en","type":"article","venue":"Artificial Intelligence in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"National Institute of Dental and Craniofacial Research; National Cancer Institute; National Institutes of Health; American Cancer Society","keywords":"Computer science; Kernel (algebra); Duality (order theory); Proportional hazards model; Convex optimization; Mathematical optimization; Likelihood function; Regularization (linguistics); Artificial intelligence; Machine learning; Regular polygon; Algorithm; Mathematics; Statistics; Estimation 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":[0.00207319,0.0001341974,0.0004400134,0.00008118615,0.00003272776,0.000009439315,0.0001396948,0.00008304515,0.0002317846],"category_scores_gemma":[0.00514352,0.000108357,0.00001959815,0.0006241936,0.0002618505,0.00006380938,0.00003495429,0.0003450018,0.000007388699],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003607258,"about_ca_system_score_gemma":0.0000965131,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001306223,"about_ca_topic_score_gemma":0.003025208,"domain_scores_codex":[0.9977724,0.0004690895,0.0007989556,0.0003369612,0.0003597511,0.0002628461],"domain_scores_gemma":[0.9976225,0.001633802,0.0001720147,0.0002872375,0.000191826,0.00009258069],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002375071,0.0006801297,0.02451196,0.0001394911,0.00001227004,0.00005869674,0.005155127,0.0002134934,0.01137622,0.6895505,0.00000561711,0.268059],"study_design_scores_gemma":[0.0001611016,0.0006088589,0.00808018,0.0003393083,0.00002783171,0.000006654554,0.01077517,0.05395043,0.04541427,0.8803889,0.00003713491,0.0002102094],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4179941,0.00002987487,0.580674,0.0003530747,0.00007787428,0.000138618,0.00000234005,0.00001714514,0.0007129811],"genre_scores_gemma":[0.9568632,0.00002508773,0.0428965,0.00004724804,0.0001072523,0.00002630222,0.000009629624,0.00001260703,0.00001221499],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5388691,"threshold_uncertainty_score":0.6157645,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1623907024273834,"score_gpt":0.4396824087499342,"score_spread":0.2772917063225508,"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."}}