{"id":"W2071988634","doi":"10.1145/1102256.1102262","title":"Generalized benchmark generation for dynamic combinatorial problems","year":2005,"lang":"en","type":"article","venue":"","topic":"Evolutionary Algorithms and Applications","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Benchmark (surveying); Computer science; Sequence (biology); Test case; Mathematical optimization; Optimization problem; Theoretical computer science; Algorithm; Machine learning; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.0001371472,0.0000765329,0.00007278973,0.0000365948,0.000210048,0.00007930097,0.0003157797,0.00004140178,0.00003015719],"category_scores_gemma":[0.000006074676,0.00006972573,0.00004923009,0.0001524124,0.00001410529,0.0003591188,0.00005120239,0.00003491163,0.00003169898],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005386155,"about_ca_system_score_gemma":0.00004378661,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001054789,"about_ca_topic_score_gemma":0.00002269703,"domain_scores_codex":[0.9992836,0.00001396339,0.0001677537,0.0002612595,0.0001153214,0.0001580766],"domain_scores_gemma":[0.9995145,0.0000241116,0.00004228075,0.0002804158,0.00008833977,0.00005039423],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[7.331641e-7,0.00008741065,0.000006216732,0.000002234025,0.000005329148,4.380134e-8,0.00004362098,0.002003965,0.007629391,0.964391,0.01069936,0.01513071],"study_design_scores_gemma":[0.0005148979,0.00003406109,0.000104639,0.000001032307,0.000002404307,0.000002452143,0.000001171787,0.8957133,0.0006480454,0.0257102,0.07716738,0.0001004128],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00723614,0.00008977128,0.9853492,0.005193172,0.0004155047,0.0004311767,0.000004525133,0.000144307,0.001136189],"genre_scores_gemma":[0.3211531,0.0000178674,0.675639,0.0003474489,0.0005674278,0.0003712981,0.00007236705,0.000006624181,0.00182482],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9386808,"threshold_uncertainty_score":0.2843333,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01602578299514038,"score_gpt":0.2577925186605712,"score_spread":0.2417667356654308,"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."}}