{"id":"W4415130459","doi":"10.48550/arxiv.2506.02075","title":"Position: Stop Chasing the C-index when Evaluating Survival Analysis Models","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Alberta Machine Intelligence Institute; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Metric (unit); Censoring (clinical trials); Discriminative model; Probabilistic logic; Concordance; Set (abstract data type); Key (lock)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1123002,0.002001409,0.001775591,0.004664941,0.002771153,0.01104318,0.004845005,0.00657441,0.007247128],"category_scores_gemma":[0.4666736,0.0006822724,0.001744647,0.00472313,0.006373473,0.01214832,0.005804549,0.01312073,0.004807343],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004604648,"about_ca_system_score_gemma":0.007430497,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004224942,"about_ca_topic_score_gemma":0.00583731,"domain_scores_codex":[0.8892361,0.06814802,0.007384761,0.004471947,0.02999226,0.0007669023],"domain_scores_gemma":[0.5223224,0.3627986,0.02207266,0.03676154,0.05177789,0.004266859],"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":[0.0009318787,0.000358385,0.01607807,0.001828938,0.0007835443,0.0002386307,0.002479196,0.01661603,0.002441926,0.3578557,0.1704944,0.4298933],"study_design_scores_gemma":[0.0004226876,0.001873086,0.006305284,0.005011564,0.0003947385,0.0007769454,0.00157504,0.1353919,0.01342356,0.6449258,0.18934,0.0005595015],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"commentary","genre_scores_codex":[0.02264294,0.01334083,0.7958317,0.1244289,0.009834455,0.000538072,0.001204276,0.002668703,0.02951008],"genre_scores_gemma":[0.2952631,0.004828377,0.6536086,0.02801984,0.005784027,0.001239521,0.001075709,0.003078573,0.007102259],"genre_candidate":"commentary","genre_consensus":null,"teacher_disagreement_score":0.8876998,"threshold_uncertainty_score":0.5939074,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1276317103854846,"score_gpt":0.3810830518053872,"score_spread":0.2534513414199026,"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."}}