{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007655185,0.0007929338,0.001652952,0.01861976,0.002160413,0.005096553,0.001956567,0.002154109,0.001105002],"category_scores_gemma":[0.0347103,0.0008109922,0.001528591,0.01645643,0.0009282562,0.009267304,0.004744418,0.001350954,0.0006707039],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00109358,"about_ca_system_score_gemma":0.001875256,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003481897,"about_ca_topic_score_gemma":0.003706628,"domain_scores_codex":[0.9907555,0.0021227,0.001009156,0.001566084,0.004121761,0.000424872],"domain_scores_gemma":[0.9843909,0.008619614,0.002141306,0.001899274,0.002524655,0.0004243786],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005510496,0.0008418825,0.1096746,0.001081692,0.0006717798,0.001639534,0.003180855,0.07494428,0.01262318,0.03942991,0.005337125,0.7500242],"study_design_scores_gemma":[0.00009022862,0.0002982656,0.02103152,0.0002288184,0.0003282728,0.001249372,0.003720334,0.7906955,0.0281992,0.1407706,0.013263,0.000124915],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2894912,0.001773605,0.6986631,0.0007150124,0.00004350459,0.0007180125,0.002406189,0.003491685,0.00269773],"genre_scores_gemma":[0.4137931,0.0009483458,0.5801505,0.00009001524,0.00004129374,0.0002577081,0.003807585,0.0001825208,0.0007289153],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01861976,"threshold_uncertainty_score":0.04048496,"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."}}