{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00167297,0.0000894544,0.0001171867,0.0001727038,0.0002998729,0.0000822198,0.0005464433,0.00004255845,0.0001787721],"category_scores_gemma":[0.0004702914,0.00006028764,0.00005885184,0.0003653798,0.0001080314,0.001759724,0.0002569915,0.00004755269,0.0002285778],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008893909,"about_ca_system_score_gemma":0.00004744871,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001035516,"about_ca_topic_score_gemma":0.0006803505,"domain_scores_codex":[0.998786,0.00009168407,0.0001847287,0.0004928687,0.000243343,0.000201414],"domain_scores_gemma":[0.9982907,0.0008133673,0.0001614732,0.0005152698,0.0001500513,0.00006917211],"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":[0.0001697764,0.00002845719,0.004787704,0.000006476972,0.00002747139,0.00001869023,0.00009530201,0.006027126,0.0001467879,0.9839524,0.002786128,0.001953701],"study_design_scores_gemma":[0.002917323,0.0002189475,0.03410638,0.0001097261,0.0001099017,0.00001014846,0.002830274,0.01906126,0.000273583,0.8102261,0.1295607,0.0005756076],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2023917,0.000003322314,0.7942882,0.0002357988,0.00009476918,0.0001393396,0.0001083982,0.0000376788,0.002700878],"genre_scores_gemma":[0.9859838,0.000009222201,0.002302221,0.00007798555,0.00003181167,6.864911e-7,0.0000262602,0.000004848855,0.01156312],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7919859,"threshold_uncertainty_score":0.2937981,"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."}}