{"id":"W2550374641","doi":"10.48550/arxiv.1611.06951","title":"Enforcing Relational Matching Dependencies with Datalog for Entity Resolution","year":2016,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Datalog; Computer science; Relational database; Matching (statistics); Conjunctive query; Programming language; Semantics (computer science); Task (project management); Resolution (logic); Dependency theory (database theory); Theoretical computer science; Database; Process (computing); Data mining; Functional dependency; Mathematics","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":[0.00743305,0.0005470474,0.0006618098,0.001277247,0.0007204809,0.002304348,0.0023542,0.001000077,0.00234108],"category_scores_gemma":[0.02282763,0.0008364963,0.001598055,0.001617647,0.002241242,0.005547709,0.00327582,0.003190359,0.0005353418],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002229752,"about_ca_system_score_gemma":0.003859202,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0058661,"about_ca_topic_score_gemma":0.007975497,"domain_scores_codex":[0.994505,0.001969533,0.0004891125,0.0007026548,0.00197971,0.0003538768],"domain_scores_gemma":[0.9836198,0.01123671,0.001024951,0.002721091,0.001138424,0.0002589259],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003091215,0.0004901265,0.004692948,0.0005480468,0.0001185337,0.0005318405,0.0009314787,0.3145943,0.007041179,0.5040529,0.009349315,0.1573403],"study_design_scores_gemma":[0.00004290482,0.00006095056,0.0003263698,0.0000690657,0.0000524093,0.0001341998,0.00008650578,0.7128665,0.009689029,0.2603713,0.01626955,0.00003124397],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009195866,0.0001437914,0.9859959,0.0007096861,0.00003167431,0.0001676205,0.0004330755,0.001849974,0.00147243],"genre_scores_gemma":[0.269905,0.0004395322,0.7240047,0.0008017421,0.0001303434,0.0004065946,0.001572612,0.000496237,0.002243242],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00743305,"threshold_uncertainty_score":0.03931022,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.307296180899797,"score_gpt":0.2671823725150406,"score_spread":0.04011380838475642,"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."}}