{"id":"W2528898284","doi":"","title":"Record linkage for web data","year":2012,"lang":"en","type":"dissertation","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Record linkage; Linkage (software); Linked data; Relational database; Task (project management); Information retrieval; Process (computing); Set (abstract data type); Matching (statistics); Data mining; Database; World Wide Web; Semantic Web; Data science; Engineering; Programming language","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":[0.01137694,0.001330962,0.001667415,0.007144199,0.002777522,0.009575372,0.003932636,0.004140791,0.01798157],"category_scores_gemma":[0.03783989,0.001274975,0.003004082,0.01421077,0.002257798,0.01329742,0.007305606,0.00510793,0.01499845],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002730499,"about_ca_system_score_gemma":0.004420296,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00310262,"about_ca_topic_score_gemma":0.002276993,"domain_scores_codex":[0.9820093,0.006191895,0.001892989,0.002159771,0.007246777,0.0004993805],"domain_scores_gemma":[0.9813142,0.007355397,0.001835375,0.006446088,0.00269045,0.0003584391],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006005819,0.00009052065,0.0009580159,0.001670112,0.0002088951,0.0006317664,0.0005973739,0.007794272,0.001269536,0.5980369,0.08819236,0.3004901],"study_design_scores_gemma":[0.0000308348,0.00003704861,0.0003786104,0.0005350862,0.00006017415,0.001108886,0.0002404977,0.03275068,0.002696224,0.4237889,0.5382893,0.00008371382],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001030421,0.005372739,0.9651229,0.00367492,0.0008071061,0.0005213086,0.00320214,0.005589664,0.01467883],"genre_scores_gemma":[0.01995417,0.008147926,0.9447985,0.001687017,0.0007371723,0.00113072,0.008069779,0.001484514,0.01399017],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01798157,"threshold_uncertainty_score":0.06016779,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5393046271116645,"score_gpt":0.5347174130476245,"score_spread":0.004587214064039946,"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."}}