{"id":"W4399765342","doi":"10.1101/2024.06.17.599219","title":"Path-based reasoning for biomedical knowledge graphs with BioPathNet","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research; HEC Montréal; Université de Montréal; Mila - Quebec Artificial Intelligence Institute; Cegep Edouard Montpetit","funders":"Bundesministerium für Bildung und Forschung; National Institutes of Health; Joachim Herz Stiftung","keywords":"Path (computing); Knowledge graph; Computer science; Artificial intelligence; Data science; Programming language","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007628675,0.0009824933,0.0008601916,0.0007763663,0.0002781306,0.000652753,0.002228392,0.0007195375,0.000004442047],"category_scores_gemma":[0.000148895,0.0008776074,0.0003638771,0.002309204,0.0003487849,0.0002431427,0.00150356,0.001498632,0.00005126253],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002364693,"about_ca_system_score_gemma":0.001273976,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008440064,"about_ca_topic_score_gemma":0.000002549525,"domain_scores_codex":[0.9949348,0.000146637,0.0007088271,0.00243235,0.0006095914,0.001167822],"domain_scores_gemma":[0.9956426,0.0002732143,0.0004462833,0.002439395,0.0005935546,0.0006049499],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005898733,0.002524541,0.003755123,0.01383227,0.0017858,0.00294223,0.0001791359,0.003775718,0.3302424,0.6220024,0.01786818,0.0005023637],"study_design_scores_gemma":[0.004898991,0.002021099,0.007273036,0.01505328,0.0007725324,5.713663e-7,0.000005135199,0.7770537,0.1332905,0.002202929,0.04913783,0.008290462],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0774421,0.01160357,0.8968872,0.001034114,0.005988901,0.002586012,0.000430917,0.004009839,0.00001728237],"genre_scores_gemma":[0.7711248,0.00008064747,0.2270193,0.0002509412,0.0005094795,0.0008036578,0.000001014868,0.0002051388,0.000005001146],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7732779,"threshold_uncertainty_score":0.9993675,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01147742921684764,"score_gpt":0.2321011121363298,"score_spread":0.2206236829194822,"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."}}