{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004690329,0.0007590182,0.0009783449,0.004407273,0.0007458478,0.002145149,0.00198684,0.001054896,0.0009227216],"category_scores_gemma":[0.02346967,0.0006606266,0.001363998,0.003452882,0.0007536099,0.004540686,0.003007354,0.001931534,0.001014689],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006860838,"about_ca_system_score_gemma":0.001445692,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001632228,"about_ca_topic_score_gemma":0.003070241,"domain_scores_codex":[0.9968555,0.0008841294,0.0003052569,0.0005947516,0.001246923,0.0001134322],"domain_scores_gemma":[0.9890952,0.005848282,0.0007950091,0.002566629,0.001519938,0.0001749309],"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":[0.0003008029,0.0004499355,0.01382581,0.0005080037,0.0002987123,0.0005080042,0.001136544,0.1476903,0.009677039,0.0157022,0.007754218,0.8021485],"study_design_scores_gemma":[0.00003345575,0.0001373505,0.002675212,0.00006407641,0.00005976476,0.0002830713,0.000367571,0.9265063,0.01674311,0.04643848,0.0066363,0.00005533835],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05684935,0.000259756,0.9378386,0.0003301279,0.0000376397,0.0002291427,0.0008322456,0.0024701,0.001153013],"genre_scores_gemma":[0.271698,0.0002649282,0.7215387,0.0001489377,0.0000421921,0.000366118,0.004161644,0.0001618326,0.001617675],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004690329,"threshold_uncertainty_score":0.02480513,"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."}}