{"id":"W4394048558","doi":"10.5281/zenodo.4031692","title":"Supplemental Material for Paper 'Taxonomy Extraction Using Knowledge Graph Embeddings and Hierarchical Clustering'","year":2020,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Cluster analysis; Computer science; Hierarchical clustering; Taxonomy (biology); Knowledge graph; Data mining; Information retrieval; Graph; Knowledge extraction; Artificial intelligence; Theoretical computer science; Biology; Ecology","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":[0.001331588,0.002790426,0.001313642,0.004823835,0.001207082,0.002734609,0.003000064,0.002469186,0.2124185],"category_scores_gemma":[0.007482617,0.0007718458,0.001204438,0.005569468,0.0005293266,0.00199266,0.002534182,0.002140807,0.1894044],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002307154,"about_ca_system_score_gemma":0.002348254,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02402967,"about_ca_topic_score_gemma":0.09024147,"domain_scores_codex":[0.9987134,0.0001860343,0.0001570483,0.0003423228,0.0003946591,0.0002066093],"domain_scores_gemma":[0.9960426,0.001259135,0.0002475304,0.001023258,0.001079528,0.000347864],"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":[0.00002926401,0.00004011773,0.0002876214,0.0003500475,0.00001321026,0.00001338011,0.00001169383,0.0001240396,0.00009560843,0.0003560436,0.9962054,0.002473518],"study_design_scores_gemma":[0.0001997692,0.00002300991,0.003782689,0.0002656782,0.0000232382,0.0001221004,0.0001273437,0.001022732,0.0007280505,0.003167093,0.9905059,0.00003242348],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0001643469,0.00004046427,0.000251884,0.00005459971,0.00004966693,0.00003285136,0.9971738,0.0008036656,0.001428624],"genre_scores_gemma":[0.0002895223,0.00002098301,0.0009032822,0.00004193352,0.000004860684,0.00009283345,0.9978163,0.00008235363,0.0007478356],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.2124185,"threshold_uncertainty_score":0.7106107,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06037724805516045,"score_gpt":0.2877602265953038,"score_spread":0.2273829785401434,"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."}}