{"id":"W4409168760","doi":"10.1145/3728373","title":"Recall, Robustness, and Lexicographic Evaluation","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Recommender Systems","topic":"Topic Modeling","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Microsoft (Canada)","funders":"","keywords":"Lexicographical order; Robustness (evolution); Recall; Computer science; Artificial intelligence; Cognitive psychology; Mathematics; Psychology; Chemistry; Combinatorics","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":[0.0007612761,0.0001408424,0.0001692025,0.0003320963,0.0002546413,0.0002103505,0.0005531373,0.0001034773,0.00001098537],"category_scores_gemma":[0.0000243766,0.0001367333,0.00005584601,0.0005191104,0.00002060472,0.0003479113,0.00001947096,0.0002008993,0.000005278347],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007919181,"about_ca_system_score_gemma":0.0000728432,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009074969,"about_ca_topic_score_gemma":0.0000291439,"domain_scores_codex":[0.9985675,0.0002384555,0.0002930857,0.00044949,0.0002540259,0.000197485],"domain_scores_gemma":[0.9986079,0.0001890791,0.00005736526,0.0009819386,0.0001061275,0.00005761541],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001021137,0.0001528634,0.000246541,0.0001181716,0.0001578036,0.000001363949,0.000363656,0.07333764,0.0000783565,0.01298767,0.001339019,0.9112067],"study_design_scores_gemma":[0.0006893229,0.00004358389,0.0003239692,0.0001411368,0.00004612688,0.00001396509,0.0002133787,0.9875956,0.000174241,0.003614408,0.006936765,0.0002075645],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002848154,0.0005435486,0.9857339,0.006949252,0.002031258,0.0004293341,0.000001906909,0.0001966684,0.001265961],"genre_scores_gemma":[0.9818031,0.000116289,0.01702511,0.0003653767,0.00002756793,0.0002077994,0.000001982822,0.00000802161,0.000444794],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9789549,"threshold_uncertainty_score":0.5575824,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05255388057789485,"score_gpt":0.2979719475362509,"score_spread":0.2454180669583561,"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."}}