{"id":"W3172226794","doi":"10.1016/j.regsciurbeco.2021.103711","title":"Urban economics in a historical perspective: Recovering data with machine learning","year":2021,"lang":"en","type":"article","venue":"Regional Science and Urban Economics","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Economic and Social Research Council; Social Sciences and Humanities Research Council of Canada; Agence Nationale de la Recherche; Centre for Economic Policy Research","keywords":"Exploit; Perspective (graphical); Data science; Flexibility (engineering); Computer science; Quality (philosophy); Artificial intelligence; Epistemology; Economics; Computer security","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001606421,0.00009359754,0.0001921033,0.0001502771,0.0005567117,0.0001868134,0.0003875106,0.00003960965,0.00003213859],"category_scores_gemma":[0.0003466159,0.00009379884,0.00002964001,0.0005276982,0.0004153497,0.0007661353,0.0001956095,0.0001587767,0.0000036231],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001448946,"about_ca_system_score_gemma":0.001376105,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002979011,"about_ca_topic_score_gemma":0.01012693,"domain_scores_codex":[0.9987244,0.00009034433,0.0001842701,0.0005842483,0.0001469667,0.0002697528],"domain_scores_gemma":[0.9991671,0.0002332258,0.00009961747,0.0001949678,0.000149084,0.0001560371],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00008121235,0.000179027,0.3420673,0.000009598779,0.00006518467,0.00003214345,0.01105466,0.007301076,0.00004714242,0.6028724,0.002137701,0.03415263],"study_design_scores_gemma":[0.0005023311,0.00005622158,0.02533598,0.00002313575,0.00002649367,0.00003099316,0.005463453,0.1071679,0.00001056414,0.01097736,0.8499655,0.000440079],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9623722,0.00201564,0.0007004315,0.01410075,0.0002349263,0.0001153591,0.000009864024,0.00003547908,0.02041533],"genre_scores_gemma":[0.985575,0.002474653,0.006876637,0.0004828169,0.0004491803,0.000004647427,0.00002406051,0.00001299782,0.004100053],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8478278,"threshold_uncertainty_score":0.5651065,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06850432648639783,"score_gpt":0.3202648587124314,"score_spread":0.2517605322260336,"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."}}