{"id":"W2922481072","doi":"10.48550/arxiv.1903.08351","title":"Distributed Maximization of Submodular plus Diversity Functions for Multi-label Feature Selection on Huge Datasets","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Submodular set function; Feature selection; Redundancy (engineering); Computer science; Automatic summarization; Feature (linguistics); Greedy algorithm; Maximization; Function (biology); Data mining; Mathematical optimization; Optimization problem; Minimum redundancy feature selection; Selection (genetic algorithm); Artificial intelligence; Machine learning; Algorithm; Mathematics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001409591,0.000249672,0.0002856743,0.0003415034,0.0003333625,0.00006926294,0.0013746,0.0004198687,0.000007964362],"category_scores_gemma":[0.00008063397,0.0002848215,0.0001380293,0.0007037977,0.00008114068,0.0004510275,0.001920345,0.0003590418,0.00002573106],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003857367,"about_ca_system_score_gemma":0.0001357913,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007192809,"about_ca_topic_score_gemma":0.00003402022,"domain_scores_codex":[0.9985225,0.00006096226,0.0001580907,0.000912353,0.0001138083,0.0002323193],"domain_scores_gemma":[0.998113,0.00007369726,0.0004074003,0.001087421,0.0002592904,0.00005920232],"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":[0.0003902668,0.000993292,0.01461783,0.0004319184,0.0004053492,0.00001523954,0.0002071824,0.55822,0.0004129325,0.3915676,0.02949017,0.003248145],"study_design_scores_gemma":[0.001504988,0.0001474277,0.005860685,0.00004880598,0.0001026464,7.706772e-7,0.00007178067,0.9850509,0.0008203713,0.004634337,0.001410047,0.0003472697],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03094477,0.00002029443,0.9656709,0.0002485662,0.0004930661,0.0007209199,0.001423922,0.0004328135,0.00004478003],"genre_scores_gemma":[0.9871445,0.00006899652,0.008914089,0.00002701565,0.0000180779,0.000003734191,0.002314613,0.00001112434,0.001497872],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9567568,"threshold_uncertainty_score":0.9999604,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1241586205553751,"score_gpt":0.225360866407087,"score_spread":0.1012022458517119,"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."}}