{"id":"W3091984691","doi":"10.48550/arxiv.2010.04029","title":"RNNLogic: Learning Logic Rules for Reasoning on Knowledge Graphs","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"HEC Montréal; Université de Montréal","funders":"","keywords":"Probabilistic logic network; Computer science; Artificial intelligence; Rule of inference; Probabilistic logic; Inference; Machine learning; Set (abstract data type); Logic programming; Autoepistemic logic; Multimodal logic; Description logic; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00157218,0.001263028,0.0008351014,0.001733604,0.0005478217,0.001419859,0.003285932,0.001532639,0.004356035],"category_scores_gemma":[0.008748869,0.0007126969,0.001386608,0.001146138,0.001042561,0.002724919,0.001592338,0.002917503,0.001169114],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001805949,"about_ca_system_score_gemma":0.002093855,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00949279,"about_ca_topic_score_gemma":0.0218366,"domain_scores_codex":[0.9989952,0.0002715535,0.00005574469,0.0003667335,0.0002412028,0.00006954052],"domain_scores_gemma":[0.9972574,0.001748729,0.0002047555,0.0004089417,0.0002722173,0.0001079601],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001423002,0.0003253328,0.003675865,0.0004611524,0.0001880962,0.0001743508,0.0001213043,0.6072448,0.001991199,0.02995132,0.01402201,0.3417022],"study_design_scores_gemma":[0.00001864611,0.00002404001,0.0002121045,0.00002600837,0.00001982226,0.00004282971,0.00001160823,0.9644199,0.0008850169,0.03215117,0.002181023,0.000007938189],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01525023,0.0007627832,0.9730061,0.0008310371,0.000104891,0.0002543652,0.001267195,0.005451559,0.003071758],"genre_scores_gemma":[0.332327,0.0009697307,0.6539628,0.001228395,0.0001205214,0.0005194041,0.005939994,0.0005621255,0.004370037],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00949279,"threshold_uncertainty_score":0.01887506,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.106210173396454,"score_gpt":0.2240957223252701,"score_spread":0.1178855489288161,"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."}}