{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.003416417,0.0004777454,0.0006268437,0.0004462406,0.001024865,0.0006515649,0.00463765,0.0003056356,0.009088774],"category_scores_gemma":[0.004735877,0.000420054,0.0001812023,0.001901048,0.0008537373,0.003223153,0.007392281,0.0005400135,0.001952803],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001291114,"about_ca_system_score_gemma":0.0004712878,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003382146,"about_ca_topic_score_gemma":0.001172657,"domain_scores_codex":[0.9931723,0.0006101258,0.001605227,0.002009264,0.001912155,0.0006909114],"domain_scores_gemma":[0.9924405,0.001551965,0.0005471827,0.004892395,0.0003441168,0.0002237937],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001970785,0.0002029462,0.6155971,0.0001033576,0.0004129557,0.00004289694,0.001036057,0.0002180119,0.00003162046,0.1147493,0.223101,0.04430776],"study_design_scores_gemma":[0.0006059838,0.00002840546,0.5126013,0.00008202857,0.0001310455,0.000001504208,0.00219325,0.003301079,0.00003489998,0.01459516,0.4661044,0.0003208965],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.71696,0.004693974,0.1839905,0.03653916,0.01713323,0.001939127,0.006343872,0.0003225025,0.0320776],"genre_scores_gemma":[0.9641014,0.0002941473,0.001294203,0.004863496,0.0002700921,0.00001606048,0.001405593,0.00002202687,0.02773301],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2471413,"threshold_uncertainty_score":0.9998251,"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."}}