{"id":"W2888136048","doi":"10.1145/3233547.3233717","title":"Choosing Non-redundant Representative Subsets Of Protein Sequence Data Sets Using Submodular Optimization","year":2018,"lang":"en","type":"article","venue":"","topic":"Complexity and Algorithms in Graphs","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Submodular set function; Computer science; Optimization problem; Disjoint sets; Selection (genetic algorithm); Data mining; Sequence (biology); Redundancy (engineering); Preprocessor; Set (abstract data type); Mathematics; Algorithm; Mathematical optimization; Artificial intelligence; Biology; 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":[0.0004773749,0.0001411219,0.0001851542,0.000134947,0.0002229791,0.0001400732,0.001699445,0.00004694048,0.0000487237],"category_scores_gemma":[0.00008878702,0.0001335148,0.00003612604,0.0007726391,0.0003111621,0.001456804,0.001173294,0.00009669942,0.000005485273],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003420186,"about_ca_system_score_gemma":0.0001281933,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005369202,"about_ca_topic_score_gemma":0.00002166845,"domain_scores_codex":[0.9983254,0.0000961285,0.0003192037,0.0006316182,0.0003612788,0.0002663342],"domain_scores_gemma":[0.9978323,0.00004003434,0.000190888,0.001597323,0.000265566,0.00007391793],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001806077,0.001506042,0.00463945,0.0005041739,0.0005916019,0.0002498959,0.01882728,0.1178104,0.5864547,0.1055236,0.002339088,0.1613732],"study_design_scores_gemma":[0.0001774891,0.00005337647,0.0002209003,0.00008025768,0.000005694223,0.00001958425,0.00004388727,0.9370633,0.06006317,0.002071413,0.00004228015,0.0001586039],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06046285,0.00002856643,0.9382657,0.0001516188,0.0001993701,0.0003186339,0.00002050785,0.00007835177,0.0004743965],"genre_scores_gemma":[0.3877023,0.000003237525,0.6121582,0.00003862607,0.000046484,0.000002555126,0.00001693841,0.000006390549,0.00002526425],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.819253,"threshold_uncertainty_score":0.5444576,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1608780064708306,"score_gpt":0.368667685748764,"score_spread":0.2077896792779334,"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."}}