{"id":"W7104182958","doi":"","title":"Relational Deep Dive: Error-Aware Queries Over Unstructured Data","year":2025,"lang":"","type":"article","venue":"ArXiv.org","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Schema (genetic algorithms); Unstructured data; Modular design; Completeness (order theory); Relational database; Information extraction; Population; Data extraction","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01399937,0.001536325,0.001555448,0.00320415,0.001362659,0.005980832,0.005093602,0.00219199,0.003143423],"category_scores_gemma":[0.06460311,0.001229926,0.001805748,0.004103404,0.002586131,0.01161963,0.01168052,0.003351022,0.002231973],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001444744,"about_ca_system_score_gemma":0.003564221,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003921408,"about_ca_topic_score_gemma":0.008989659,"domain_scores_codex":[0.9843351,0.004554681,0.001551091,0.003312625,0.005709708,0.0005367476],"domain_scores_gemma":[0.9560853,0.02214509,0.002273079,0.01541703,0.003524433,0.0005550653],"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":[0.0008140882,0.0003219745,0.02051955,0.001836081,0.0005518792,0.0007462269,0.003469116,0.07823316,0.02531661,0.08856756,0.09232275,0.6873009],"study_design_scores_gemma":[0.0001234312,0.0001707805,0.002421871,0.0001991962,0.0001142306,0.000960201,0.001131817,0.6771433,0.03810771,0.220039,0.05946616,0.0001222623],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01297469,0.001011184,0.9536378,0.001407422,0.0001007894,0.000242051,0.003884105,0.02496233,0.001779627],"genre_scores_gemma":[0.1455205,0.0005197639,0.8366554,0.001324693,0.0001110121,0.0002855045,0.01083302,0.002402336,0.002347859],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01399937,"threshold_uncertainty_score":0.07403666,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3177358625630345,"score_gpt":0.4352136701261027,"score_spread":0.1174778075630681,"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."}}