{"id":"W4287982101","doi":"10.1093/bib/bbac279","title":"Implications of Topological Imbalance for Representation Learning on Biomedical Knowledge Graphs","year":2021,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; Canadian Institute for Advanced Research; HEC Montréal","funders":"","keywords":"Computer science; Inference; Embedding; Machine learning; Representation (politics); Theoretical computer science; Graph; Knowledge graph; Artificial intelligence; Data science; Data mining","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006926406,0.00005976955,0.00008410384,0.00002635697,0.00007126379,0.000004861079,0.0001015533,0.0001022929,0.00001562685],"category_scores_gemma":[0.00005275053,0.00006241994,0.00008779945,0.0001624882,0.00008363524,0.000002770314,0.00006064519,0.0000598626,0.000004053547],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000917154,"about_ca_system_score_gemma":0.0000421618,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000174847,"about_ca_topic_score_gemma":0.000006897592,"domain_scores_codex":[0.9995348,0.00002987803,0.0001016124,0.0002053323,0.00001543579,0.0001129494],"domain_scores_gemma":[0.9995612,0.00003583232,0.0000651029,0.0001930216,0.00009588457,0.00004894122],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003021858,0.0005426221,0.03192203,0.00007831058,0.000208235,0.000009841465,0.000167601,0.01455632,0.146197,0.7945228,0.005582693,0.00591035],"study_design_scores_gemma":[0.0119925,0.005336418,0.1482337,0.0001871812,0.0004542464,0.00008517396,0.003845234,0.1529593,0.2265707,0.2728483,0.1752853,0.002201875],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.91415,0.0001254788,0.08182231,0.0001221159,0.00008545717,0.0001065429,0.00001796557,0.00001004782,0.00356011],"genre_scores_gemma":[0.9981426,0.0001844625,0.0003669932,0.00005754425,0.00004553586,0.000001066391,0.0001606996,0.000004494076,0.001036604],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5216745,"threshold_uncertainty_score":0.2545411,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04786946096316707,"score_gpt":0.2291345781142058,"score_spread":0.1812651171510387,"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."}}