{"id":"W1981578383","doi":"10.14778/2536336.2536345","title":"Discovering linkage points over web data","year":2013,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":41,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Schema matching; Schema (genetic algorithms); Data integration; Information retrieval; Data mining; Linked data; Linkage (software); Star schema; Database schema; Semi-structured model; Semantic Web; Database design","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0028414,0.0001493088,0.0002410156,0.000111895,0.0001296427,0.0005334381,0.004363943,0.00003589757,0.001071971],"category_scores_gemma":[0.001698829,0.000083659,0.0000911408,0.000453439,0.000113735,0.001815323,0.005402943,0.0001304826,0.0004606688],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003873338,"about_ca_system_score_gemma":0.0000215134,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002499803,"about_ca_topic_score_gemma":0.00001809055,"domain_scores_codex":[0.9969058,0.00001883626,0.0006434542,0.000578454,0.001570425,0.0002830384],"domain_scores_gemma":[0.9980738,0.0001745578,0.0004360118,0.001058929,0.0001717631,0.00008495867],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002763786,0.0003479121,0.01746137,0.0001262831,0.0001264102,6.487209e-7,0.001208549,0.00001393529,0.02869423,0.07321998,0.849081,0.02969203],"study_design_scores_gemma":[0.001791781,0.0001334438,0.08077819,0.0003077345,0.0001130785,0.000007088147,0.006213301,0.006896957,0.0335144,0.214115,0.6554526,0.0006764249],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9129798,0.0001141534,0.0002280286,0.01653756,0.0009450997,0.001337805,0.0002417573,0.00006987094,0.06754591],"genre_scores_gemma":[0.9934257,0.00004439742,0.00125006,0.0008516749,0.00009147658,0.00003378485,0.000006921232,0.00001099996,0.004285006],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1936284,"threshold_uncertainty_score":0.9998412,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1633565029719125,"score_gpt":0.3784563459656941,"score_spread":0.2150998429937816,"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."}}