{"id":"W3038039974","doi":"10.1016/j.patter.2020.100053","title":"Harvesting Patterns from Textual Web Sources with Tolerance Rough Sets","year":2020,"lang":"en","type":"article","venue":"Patterns","topic":"Rough Sets and Fuzzy Logic","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Winnipeg","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Categorical variable; Rough set; Set (abstract data type); Scalability; Artificial intelligence; Natural language processing; Benchmark (surveying); Data mining; Machine learning; Information retrieval; Database; Programming language","routes":{"ca_aff":true,"ca_fund":true,"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":[0.00007228243,0.0002507652,0.0002616371,0.00002897076,0.0001442054,0.0004149071,0.001071684,0.00005951953,0.00009919187],"category_scores_gemma":[0.00001935524,0.0001940809,0.0000614546,0.0001795489,0.00002969984,0.0005322667,0.0003275771,0.0002366093,0.0001680002],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001717133,"about_ca_system_score_gemma":0.00004111356,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007290904,"about_ca_topic_score_gemma":0.0001910962,"domain_scores_codex":[0.9981932,0.00006872966,0.0002501925,0.0006900055,0.0003738679,0.0004239843],"domain_scores_gemma":[0.9990348,0.0001012002,0.0001320906,0.0004737049,0.00003789395,0.0002203342],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00002540005,0.00009433769,0.9009362,0.00006685044,0.00006490226,0.0004194599,0.009355539,0.001831972,0.0004086295,0.0005565492,0.001084225,0.08515592],"study_design_scores_gemma":[0.002368168,0.0008057764,0.5264602,0.0004098765,0.00004324271,0.00005612935,0.0006962551,0.4500276,0.001715,0.0005035222,0.01529136,0.001622784],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7448688,0.00007900604,0.2495708,0.0034929,0.0001323176,0.0001276511,0.0001127914,0.0003026513,0.001313152],"genre_scores_gemma":[0.9823936,0.00001320702,0.01169621,0.00543024,0.0003732765,0.00001527753,0.00002489243,0.00002135516,0.00003192232],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4481957,"threshold_uncertainty_score":0.7914389,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02918136637718301,"score_gpt":0.2239053876632163,"score_spread":0.1947240212860332,"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."}}