{"id":"W4417452315","doi":"10.48550/arxiv.2512.12783","title":"Credit Risk Estimation with Non-Financial Features: Evidence from a Synthetic Istanbul Dataset","year":2025,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Microfinance and Financial Inclusion","field":"Economics, Econometrics and Finance","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Payment; Quarter (Canadian coin); Earnings; Estimation; Credit card; Credit risk; Census; Blueprint; Point (geometry); Spurious relationship","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":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010324,0.001179553,0.001860188,0.0008782129,0.001210095,0.0003232566,0.002350496,0.00140927,0.0005960098],"category_scores_gemma":[0.0008467125,0.001520438,0.0005218153,0.001733469,0.0005587203,0.001261947,0.002342673,0.002146849,0.001068345],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001214145,"about_ca_system_score_gemma":0.0009433157,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01551047,"about_ca_topic_score_gemma":0.002016124,"domain_scores_codex":[0.9935452,0.0001571711,0.001282885,0.00387781,0.0001102027,0.001026694],"domain_scores_gemma":[0.9931548,0.000566686,0.002588158,0.00310667,0.000263892,0.0003197988],"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":[0.01151473,0.002967148,0.1159781,0.003001265,0.001846221,0.002664335,0.008853166,0.6017228,0.0001255925,0.1529556,0.08053928,0.01783179],"study_design_scores_gemma":[0.007128899,0.001457845,0.1127586,0.0143113,0.002638242,0.0000171216,0.0006812171,0.627399,0.0008741166,0.1419733,0.08332289,0.007437441],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4334227,0.003773572,0.503933,0.0002085854,0.002820498,0.001526885,0.05231594,0.00009233436,0.001906488],"genre_scores_gemma":[0.9653124,0.02430155,0.002982082,0.0002124592,0.000460955,0.00001213703,0.002755489,0.00006715076,0.003895767],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5318897,"threshold_uncertainty_score":0.9998871,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04746289017654391,"score_gpt":0.1865717825722737,"score_spread":0.1391088923957298,"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."}}