{"id":"W1980720057","doi":"10.1007/s00500-015-1632-6","title":"Feature-driven linguistic-based entity matching in linked data with application in pharmacy","year":2015,"lang":"en","type":"article","venue":"Soft Computing","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"SPARQL; Computer science; RDF; Process (computing); Linked data; Feature (linguistics); Information retrieval; Natural language; Hyperlink; Semantic Web; Natural language processing; World Wide Web; Web page; Linguistics; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005968488,0.0001116425,0.0002121327,0.0002430755,0.0000709676,0.0002685139,0.001427145,0.00002956409,0.000004480535],"category_scores_gemma":[0.002115319,0.00009297091,0.00001634142,0.0008113353,0.00004259407,0.0002885417,0.0007959922,0.0002453055,0.00008099962],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006997302,"about_ca_system_score_gemma":0.000127024,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001192748,"about_ca_topic_score_gemma":0.002572126,"domain_scores_codex":[0.9977182,0.000253184,0.0003946656,0.0006126977,0.0007827985,0.0002384121],"domain_scores_gemma":[0.9978746,0.0007168363,0.0002260134,0.0009701148,0.0001265428,0.00008586026],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002827064,0.0006285178,0.4454049,0.0000983462,0.00002783062,0.0001244602,0.006915906,0.1865946,0.0001309208,0.006574101,0.01188755,0.3413302],"study_design_scores_gemma":[0.001711367,0.00002005135,0.01532828,0.00009295221,0.000008677741,0.000001315205,0.0007857468,0.9057873,0.00001934479,0.006132036,0.06990552,0.0002073505],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2380484,0.00005086986,0.7575906,0.001989648,0.0002952596,0.0004424506,0.00003132058,0.0000875313,0.001463889],"genre_scores_gemma":[0.9715241,6.17526e-7,0.02763727,0.0005058394,0.000124727,0.00000360404,0.0001521639,0.000008078481,0.00004365537],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7334756,"threshold_uncertainty_score":0.3791244,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2202229176735751,"score_gpt":0.4482172416113033,"score_spread":0.2279943239377282,"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."}}