{"id":"W2086886584","doi":"10.1145/1538902.1538906","title":"Empirical hardness models","year":2009,"lang":"en","type":"article","venue":"Journal of the ACM","topic":"Auction Theory and Applications","field":"Decision Sciences","cited_by":110,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Division of Information and Intelligent Systems; Defense Advanced Research Projects Agency","keywords":"Computer science; Benchmark (surveying); Suite; Machine learning; Artificial intelligence; Algorithm","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":[0.001732031,0.00004049045,0.000113931,0.00005815766,0.0001434459,0.00007237842,0.00262845,0.00002781703,0.0001461683],"category_scores_gemma":[0.003185012,0.00001872595,0.0001700391,0.0003628061,0.00004284795,0.0002809915,0.00013151,0.0001573383,0.0000823895],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001491158,"about_ca_system_score_gemma":0.0000450197,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":1.410004e-7,"about_ca_topic_score_gemma":1.493378e-7,"domain_scores_codex":[0.9987323,0.000124515,0.0003887288,0.00006996024,0.0006145517,0.00006988814],"domain_scores_gemma":[0.9981325,0.0002793295,0.0003708779,0.0009244867,0.0002333636,0.00005938628],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001103585,0.0002361439,0.001820894,4.605019e-7,0.00002150501,0.000005407746,0.00120723,0.01199587,0.00227633,0.04650131,0.8667916,0.06903291],"study_design_scores_gemma":[0.00009082379,0.00002431859,0.009039691,0.000003784684,0.00000646538,0.00009063736,0.0001538604,0.0003371691,0.0006749321,0.9453319,0.04422068,0.00002576515],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7212672,0.0001421085,0.05701592,0.2112637,0.00115569,0.00008151428,0.000002715269,0.00001143254,0.009059698],"genre_scores_gemma":[0.9928832,0.000004318189,0.001620461,0.001953656,0.0002203798,2.599125e-7,1.833965e-8,0.00000161119,0.003316069],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8988306,"threshold_uncertainty_score":0.4884358,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3077122164162031,"score_gpt":0.4750898193824556,"score_spread":0.1673776029662526,"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."}}