{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002118781,0.001162817,0.0008399124,0.001781626,0.0004274595,0.0008625055,0.001870083,0.0007666894,0.004436763],"category_scores_gemma":[0.008833425,0.0003369893,0.00088738,0.002081143,0.0007297658,0.000865894,0.001229877,0.001117279,0.0005368118],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008399832,"about_ca_system_score_gemma":0.0009949333,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001159712,"about_ca_topic_score_gemma":0.001467554,"domain_scores_codex":[0.9983114,0.000757504,0.00009504282,0.000201759,0.0004742783,0.0001599688],"domain_scores_gemma":[0.9963846,0.001924821,0.0002526727,0.0008445877,0.0004864924,0.0001068337],"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":[0.0002518581,0.0002995776,0.001579068,0.0006926541,0.00006937263,0.0004209941,0.0001302476,0.5886266,0.01247491,0.0704454,0.01062272,0.3143866],"study_design_scores_gemma":[0.0001356254,0.0003113126,0.0009141924,0.00008174746,0.00004429105,0.0002678122,0.0000490478,0.9020327,0.01206776,0.06509436,0.01895794,0.0000432079],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05880452,0.0008892259,0.9218168,0.0002815134,0.0001268491,0.0007943839,0.0006680276,0.003469601,0.01314919],"genre_scores_gemma":[0.3181761,0.0007094207,0.6721599,0.0001960445,0.00005280614,0.001205156,0.003084135,0.0007680872,0.00364833],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004436763,"threshold_uncertainty_score":0.01484245,"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."}}