{"id":"W3134539481","doi":"10.1038/s41598-021-84869-4","title":"Pattern discovery and disentanglement on relational datasets","year":2021,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Data science; Data mining; Information retrieval; Computational biology; Biology","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":[0.000557976,0.00009015396,0.00008520868,0.00008351624,0.0002240092,0.0008284487,0.0002127167,0.00002674879,0.00003214491],"category_scores_gemma":[0.0001039141,0.0000827214,0.00002665097,0.0003205814,0.00009640803,0.0009963324,0.0003838569,0.00007306613,0.0000216516],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004590994,"about_ca_system_score_gemma":0.0001138241,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000314755,"about_ca_topic_score_gemma":0.000006244409,"domain_scores_codex":[0.9980953,0.00004457349,0.000293453,0.0008722937,0.000528124,0.0001662218],"domain_scores_gemma":[0.9980348,0.00003961162,0.0001594346,0.001622864,0.00007040825,0.00007290879],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000004168076,0.0005484378,0.04269585,0.00005109669,0.0000390744,0.003132244,0.0004186312,0.00002718544,0.03895089,0.1576285,0.6382697,0.1182342],"study_design_scores_gemma":[0.0002456198,0.00004834715,0.06899071,0.0001281023,0.00001297311,0.0009238013,0.00005242212,0.003688397,0.2120219,0.07343358,0.639873,0.0005811076],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03429577,0.0001485235,0.9525517,0.004078781,0.00588024,0.0003087702,0.0002012583,0.0003279595,0.002206951],"genre_scores_gemma":[0.9704247,0.00001155868,0.02354518,0.0005093616,0.00005386676,0.00003648325,0.002615257,0.000009412017,0.00279418],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9361289,"threshold_uncertainty_score":0.798875,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02321418973549529,"score_gpt":0.2676938593327197,"score_spread":0.2444796695972244,"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."}}