{"id":"W2113415503","doi":"10.14778/1687627.1687695","title":"Modeling and querying possible repairs in duplicate detection","year":2009,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":57,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Scalability; Data mining; Parameterized complexity; Cluster analysis; Identification (biology); Set (abstract data type); Database; Algorithm; Machine learning","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":[],"consensus_categories":[],"category_scores_codex":[0.002739317,0.00009031103,0.0001644315,0.0001356132,0.0001070442,0.0001505834,0.000482875,0.00003103909,0.000006136772],"category_scores_gemma":[0.0005686248,0.00005852234,0.0000553686,0.0005058983,0.00003290044,0.0004335258,0.0002648217,0.00009461305,0.00000547431],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004813184,"about_ca_system_score_gemma":0.000006082922,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001858219,"about_ca_topic_score_gemma":0.00004561871,"domain_scores_codex":[0.9983742,0.00001306557,0.0004855796,0.0003369924,0.0006125953,0.0001776123],"domain_scores_gemma":[0.9994571,0.00004543715,0.0001737364,0.0001786475,0.0001044465,0.00004060034],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003350113,0.0005314434,0.01065423,0.000138553,0.0000498459,0.000001895424,0.006801615,0.007408602,0.1449892,0.07114186,0.002017694,0.7559301],"study_design_scores_gemma":[0.001723764,0.0003684465,0.03003691,0.0003286577,0.00005442585,0.00002011553,0.009990656,0.2712159,0.1467687,0.5345029,0.004465778,0.0005237359],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.989849,0.00009880213,0.0009361174,0.003192071,0.00008745865,0.000351172,0.000001911943,0.00003136423,0.005452071],"genre_scores_gemma":[0.9987292,0.00005106165,0.0006796776,0.0002749681,0.00001767917,0.00001280809,1.6896e-7,0.000003302485,0.0002311365],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7554063,"threshold_uncertainty_score":0.2386471,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08693929288766766,"score_gpt":0.3472986307308046,"score_spread":0.260359337843137,"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."}}