{"id":"W4387031631","doi":"10.48550/arxiv.2309.12886","title":"Implementing Automated Data Validation for Canadian Political Datasets","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Consistency (knowledge bases); Politics; Workflow; Government (linguistics); Work (physics); Sample (material); Computer science; Data science; Data mining; Political science; Database; Engineering; Artificial intelligence","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.07333781,0.001761675,0.00123668,0.00712888,0.005488741,0.005270131,0.006005579,0.001620949,0.00301994],"category_scores_gemma":[0.2030966,0.001349506,0.00214397,0.00888634,0.002381998,0.003967556,0.006147075,0.004050173,0.002295943],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01139775,"about_ca_system_score_gemma":0.02790179,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.5391106,"about_ca_topic_score_gemma":0.5654663,"domain_scores_codex":[0.9474557,0.02234498,0.004569988,0.00761595,0.01526634,0.002747017],"domain_scores_gemma":[0.8079012,0.07924219,0.005757154,0.04874579,0.05482221,0.003531415],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001329322,0.001144668,0.2049575,0.001359152,0.001283733,0.0005760717,0.007570298,0.07353732,0.01675288,0.03072514,0.3148054,0.3459585],"study_design_scores_gemma":[0.0008174518,0.0002097695,0.09863637,0.0006814789,0.0002470965,0.0003090371,0.004122533,0.5148684,0.04864268,0.03401706,0.296983,0.0004651672],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.239483,0.002089591,0.4710432,0.01002736,0.001240777,0.004826493,0.1584646,0.08994463,0.02288037],"genre_scores_gemma":[0.277788,0.0003328888,0.4778284,0.001688657,0.0001288528,0.002803303,0.2317502,0.004071768,0.003608008],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9266622,"threshold_uncertainty_score":0.9272074,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2610642722276903,"score_gpt":0.2717482466922979,"score_spread":0.01068397446460756,"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."}}