{"id":"W3122897135","doi":"10.1186/s40172-015-0031-7","title":"Evaluating search and matching models using experimental data","year":2015,"lang":"en","type":"preprint","venue":"IZA Journal of Labor Economics","topic":"Auction Theory and Applications","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Matching (statistics); Randomized experiment; Earnings; Context (archaeology); Econometrics; Computer science; Experimental data; Duration (music); Measure (data warehouse); Propensity score matching; Economics; Statistics; Mathematics; Data mining; Finance","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01030154,0.0001550915,0.000447401,0.0003182658,0.0001647399,0.0006089153,0.001631421,0.0001259317,0.00008967413],"category_scores_gemma":[0.0003336044,0.0001348693,0.00006923672,0.0001257113,0.0001062578,0.001016046,0.002089605,0.0005381811,0.00001000886],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001592696,"about_ca_system_score_gemma":0.000791534,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000227402,"about_ca_topic_score_gemma":0.000003945592,"domain_scores_codex":[0.9975599,0.0002771063,0.001176579,0.0004314367,0.0004038221,0.0001511315],"domain_scores_gemma":[0.9967791,0.0004249601,0.001110475,0.0009357862,0.0005550589,0.0001946242],"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":[0.00005094927,0.00004071366,0.00008140682,0.000004692628,0.00005097968,0.000002177228,0.002046459,0.9830154,0.0004711707,0.007106634,0.0001514098,0.006978033],"study_design_scores_gemma":[0.00025773,0.00002869008,0.00001290931,0.000040259,0.0000286489,0.00012916,0.004572624,0.654618,0.0003894164,0.3394347,0.0003526622,0.0001351261],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9659395,0.001478915,0.03107229,0.0003248715,0.0006059798,0.00012076,0.000243865,0.000005273975,0.0002085067],"genre_scores_gemma":[0.9547552,0.0001336297,0.04436689,0.00009119407,0.0005346861,0.000001350658,0.0000078477,0.00002017299,0.00008899104],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3323281,"threshold_uncertainty_score":0.5871785,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7414195504464843,"score_gpt":0.5716567480852215,"score_spread":0.1697628023612628,"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."}}