{"id":"W2151101070","doi":"10.2139/ssrn.789464","title":"Evaluating Search and Matching Models Using Experimental Data","year":2005,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University","funders":"","keywords":"Matching (statistics); Computer science; Data mining; Econometrics; Mathematics; Statistics","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":[0.01977555,0.0001630748,0.0002415993,0.0003260515,0.0007402796,0.0005673616,0.001595731,0.00005883931,0.0001116223],"category_scores_gemma":[0.0005339304,0.0001265527,0.00005047947,0.0004112826,0.000116129,0.002795195,0.0009705554,0.001975771,0.00003818366],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001023866,"about_ca_system_score_gemma":0.002049481,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007992423,"about_ca_topic_score_gemma":0.0001878059,"domain_scores_codex":[0.9933005,0.0004252487,0.0005742045,0.000613686,0.002696196,0.002390191],"domain_scores_gemma":[0.9983032,0.0004423606,0.0001379983,0.0006918486,0.0002380688,0.0001865267],"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":[0.0001071912,0.00009705544,0.0001261587,0.000001711519,0.00007273788,0.000009872461,0.001445564,0.3785321,0.01200838,0.005768253,0.00003473637,0.6017962],"study_design_scores_gemma":[0.0005444018,0.0001280551,0.00001291377,0.0000100963,0.000005570926,0.0008776825,0.007603406,0.7982106,0.0005902865,0.1918094,0.00007721471,0.0001303398],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5981959,0.005807769,0.3953824,0.0003429531,0.00006132484,0.0001101475,0.000004855858,0.00001347573,0.00008119431],"genre_scores_gemma":[0.9723325,0.0004642173,0.02591193,0.00003969995,0.0005553702,0.000001422735,0.000002035994,0.00002645597,0.0006663375],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6016659,"threshold_uncertainty_score":0.8583851,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.46222288934752,"score_gpt":0.568678542894699,"score_spread":0.106455653547179,"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."}}