{"id":"W4393783423","doi":"10.5281/zenodo.4031691","title":"Supplemental Material for Paper 'Taxonomy Extraction Using Knowledge Graph Embeddings and Hierarchical Clustering'","year":2020,"lang":"en","type":"dataset","venue":"PolyPublie (École Polytechnique de Montréal)","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; Taxonomy (biology); Hierarchical clustering; Computer science; Graph; Information retrieval; Data mining; Artificial intelligence; Biology; Theoretical computer science; 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":[0.001373909,0.002814242,0.001312036,0.005064704,0.001305041,0.002748175,0.00315595,0.002518206,0.2057871],"category_scores_gemma":[0.008172134,0.000784235,0.001249843,0.00595494,0.0005522805,0.002051401,0.002706075,0.002181373,0.1867045],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002540272,"about_ca_system_score_gemma":0.002620016,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03210676,"about_ca_topic_score_gemma":0.1204138,"domain_scores_codex":[0.998591,0.0002059743,0.0001701618,0.00036836,0.0004373607,0.0002271264],"domain_scores_gemma":[0.9955744,0.001342419,0.000277423,0.001117765,0.001284815,0.0004031433],"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":[0.00002543789,0.00003610347,0.0002999494,0.0003126902,0.00001153237,0.00001217596,0.00001116409,0.0001046925,0.00007762245,0.0003199763,0.9965221,0.002266502],"study_design_scores_gemma":[0.0001856328,0.00002184193,0.003950597,0.0002599339,0.00002143318,0.0001134959,0.0001317688,0.000910455,0.0006453065,0.00276284,0.9909658,0.0000310129],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0001552288,0.00003781718,0.0002285623,0.0000567209,0.00004801942,0.00003373392,0.9972551,0.0007050738,0.001479684],"genre_scores_gemma":[0.0002693369,0.00001987942,0.0008351994,0.00004317765,0.000004780709,0.00009211995,0.9978961,0.00007575442,0.0007636794],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.2057871,"threshold_uncertainty_score":0.6884266,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02580619798811,"score_gpt":0.2758470520028876,"score_spread":0.2500408540147776,"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."}}