{"id":"W4415139805","doi":"10.1007/s10115-025-02601-4","title":"Learning to rank under uncertainty: a robust neural approach","year":2025,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"ENCODE; Probabilistic logic; Relevance (law); Generalizability theory; Ambiguity; Divergence-from-randomness model; Rank (graph theory); Space (punctuation); Learning to rank","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":[0.0004585147,0.0001146318,0.0001615441,0.0002774864,0.000248581,0.0005174648,0.0002724781,0.00005510328,0.000001480811],"category_scores_gemma":[0.00005515571,0.00009538212,0.00003124026,0.0005851767,0.00001335804,0.001213412,0.0001725917,0.0001862264,0.000107689],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003429233,"about_ca_system_score_gemma":0.00005025634,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006461511,"about_ca_topic_score_gemma":0.000001213704,"domain_scores_codex":[0.9991453,0.0001067101,0.0002926317,0.0001482145,0.0001224601,0.0001846626],"domain_scores_gemma":[0.9994598,0.00005903081,0.00007134265,0.0001942298,0.0001351933,0.00008042708],"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":[0.000008585504,0.00002576371,0.0005756544,0.000321085,0.00003004533,3.389751e-7,0.01205259,0.6478217,0.000008797171,0.1246482,0.006168293,0.208339],"study_design_scores_gemma":[0.0002629971,0.00003522455,0.0004950449,0.00004325998,0.000002601545,0.000008094999,0.0008387148,0.8323424,0.000002514734,0.00001817603,0.1658543,0.00009665219],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004776258,0.0003698661,0.8907028,0.0004531138,0.0007478398,0.0002508413,7.231359e-7,0.0002442273,0.1024543],"genre_scores_gemma":[0.9926482,0.00000939176,0.00192415,0.0003913725,0.0000888849,0.0000322135,0.00001294661,0.00000337034,0.004889478],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9878719,"threshold_uncertainty_score":0.4989925,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0118893420822846,"score_gpt":0.2471812885091502,"score_spread":0.2352919464268656,"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."}}