{"id":"W2950622432","doi":"","title":"Guided Data Repair","year":2011,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Rank (graph theory); Process (computing); Quality (philosophy); Set (abstract data type); Data quality; Data mining; Data set; Machine learning; Information retrieval; Artificial intelligence; Engineering","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","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.005111197,0.0003160635,0.0005073203,0.0004507277,0.0001776829,0.0002341367,0.009684685,0.0002778605,0.001856244],"category_scores_gemma":[0.001594755,0.0003052939,0.0002882546,0.0007625874,0.0002419659,0.0008596128,0.02268237,0.0004795241,0.003347345],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009173417,"about_ca_system_score_gemma":0.0001884439,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0010283,"about_ca_topic_score_gemma":0.0004560393,"domain_scores_codex":[0.995446,0.0005428247,0.0006092171,0.002607727,0.0004219072,0.0003722964],"domain_scores_gemma":[0.9883074,0.0003905889,0.0005734244,0.01021827,0.0002858908,0.0002244425],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00006555197,0.0001972709,0.002627214,0.00005179183,0.0002384667,0.0005296469,0.0002192047,0.00521205,0.000001673473,0.3501902,0.6384848,0.002182163],"study_design_scores_gemma":[0.0004087119,0.0000321672,0.002472156,0.00005476881,0.0002297201,0.000002621542,0.0007132172,0.05134922,0.00001135308,0.5236506,0.4204486,0.000626815],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.1663002,0.0002398522,0.3839119,0.0008395549,0.005834663,0.001644935,0.002731471,0.001505599,0.4369918],"genre_scores_gemma":[0.942827,0.0002414758,0.001639652,0.0005624679,0.0001462863,6.259426e-7,0.0005176333,0.00002305277,0.05404178],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7765268,"threshold_uncertainty_score":0.9999399,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7109900226280569,"score_gpt":0.3369640349040057,"score_spread":0.3740259877240512,"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."}}