{"id":"W4391117154","doi":"10.1609/aaaiss.v2i1.27713","title":"SurvivalEVAL: A Comprehensive Open-Source Python Package for Evaluating Individual Survival Distributions","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Symposium Series","topic":"Insurance, Mortality, Demography, Risk Management","field":"Social Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Alberta Machine Intelligence Institute; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Python (programming language); Open source; R package; Computer science; Software package; Open source software; Software engineering; Software; Data science; Programming language","routes":{"ca_aff":true,"ca_fund":true,"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":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.003089602,0.0002780387,0.0004111589,0.0001311401,0.001476986,0.001256105,0.001765212,0.0001254894,0.00003198611],"category_scores_gemma":[0.0004812709,0.0002305182,0.0003221883,0.001093321,0.0008541612,0.001209874,0.0009678625,0.0002380618,0.00001022079],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001216467,"about_ca_system_score_gemma":0.0001789952,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009028264,"about_ca_topic_score_gemma":0.0003488882,"domain_scores_codex":[0.9971331,0.0001194035,0.0005186751,0.0005451846,0.001076139,0.0006075259],"domain_scores_gemma":[0.998151,0.00035541,0.0003079886,0.000236592,0.000845568,0.0001034396],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002695817,0.000270811,0.05450869,0.001809355,0.0008685675,0.000001471057,0.04380511,0.00002785939,0.02562414,0.8492508,0.02043157,0.003132043],"study_design_scores_gemma":[0.002192883,0.001039355,0.1021245,0.001786726,0.002064106,0.00001376581,0.08809705,0.0004935248,0.02735028,0.0784694,0.6942441,0.002124363],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9343036,0.0007517572,0.0003351162,0.01436455,0.00334868,0.004374831,0.0007935611,0.0005819409,0.04114597],"genre_scores_gemma":[0.9944378,0.0002248539,0.00106947,0.00008873212,0.0003662703,0.0003491234,0.00003135195,0.00006077192,0.0033717],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7707814,"threshold_uncertainty_score":0.999823,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06270916326131269,"score_gpt":0.360950210917829,"score_spread":0.2982410476565163,"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."}}