{"id":"W1981334977","doi":"10.1007/s10472-010-9191-0","title":"Tradeoffs in the empirical evaluation of competing algorithm designs","year":2010,"lang":"en","type":"article","venue":"Annals of Mathematics and Artificial Intelligence","topic":"Constraint Satisfaction and Optimization","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Algorithm; Parameterized complexity; Set (abstract data type); Algorithm design; Integer programming","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":[0.002573309,0.00005734067,0.0001078827,0.00007336949,0.00004093775,0.00003984014,0.0002226936,0.0000360671,0.0000214657],"category_scores_gemma":[0.0003997238,0.00004289885,0.00003071865,0.0002367402,0.00009943855,0.0001248317,0.00002797323,0.0000992904,0.000001666807],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000001574549,"about_ca_system_score_gemma":0.00004015356,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001147818,"about_ca_topic_score_gemma":0.00002769324,"domain_scores_codex":[0.9990137,0.00007835488,0.0003833088,0.000106471,0.0003318177,0.00008631959],"domain_scores_gemma":[0.9989802,0.0004240109,0.0001473073,0.0001765241,0.0002509347,0.00002106011],"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":[0.000001011817,0.0001800203,0.00007261263,0.00001371283,0.000004412172,4.83001e-7,0.009374819,0.0006752589,0.001492221,0.2137315,0.00001175486,0.7744422],"study_design_scores_gemma":[0.00001477578,0.00003448152,0.0003147231,0.00002276758,0.000005373632,0.000007675992,0.002060658,0.8733056,0.02308032,0.1010829,0.0000208145,0.00004989564],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1115069,0.00003302207,0.8855836,0.002073878,0.00007070565,0.0001591599,0.000001371899,0.000007408319,0.0005639396],"genre_scores_gemma":[0.8431685,0.00002416379,0.1566767,0.0001112228,0.00001275688,0.000003906127,4.873261e-7,0.00000177812,4.954032e-7],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8726304,"threshold_uncertainty_score":0.1749364,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4438438458895254,"score_gpt":0.4265607545525879,"score_spread":0.01728309133693751,"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."}}