{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002740361,0.0004288032,0.0006584563,0.0004433541,0.0007075784,0.000419231,0.003041202,0.0003294693,0.00005616504],"category_scores_gemma":[0.0002990935,0.0003587688,0.0004616571,0.001158585,0.00006630733,0.0002784102,0.003606829,0.001957438,0.00002969171],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002912334,"about_ca_system_score_gemma":0.0006536899,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003008019,"about_ca_topic_score_gemma":0.0002367944,"domain_scores_codex":[0.9949711,0.001443129,0.0007018522,0.001325222,0.001002023,0.000556679],"domain_scores_gemma":[0.9953438,0.0006866156,0.0005410055,0.002803221,0.0004968614,0.0001284686],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000008888229,0.0000314051,0.3233395,0.0001889838,0.000581177,0.00001359733,0.004828328,0.6506912,0.000008734854,0.00650106,0.00007073209,0.01373636],"study_design_scores_gemma":[0.0001157382,0.00002549247,0.1080538,0.0001714302,0.0002580409,0.000002998767,0.00007866677,0.8807223,0.000009796119,0.01018353,0.0000743134,0.0003038933],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.256435,0.0006098715,0.7216886,0.01538885,0.001579971,0.0005137562,0.00001595779,0.0004034219,0.003364501],"genre_scores_gemma":[0.9823165,0.0000248854,0.01488393,0.001141747,0.0004097336,0.00008943244,0.00005297013,0.00002130701,0.001059483],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7258815,"threshold_uncertainty_score":0.9998865,"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."}}