{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002061561,0.0005035768,0.0005051721,0.0002448865,0.0004069953,0.0001424033,0.002275293,0.0003707924,0.000007454995],"category_scores_gemma":[0.0001394747,0.0005472924,0.0004699535,0.0008134867,0.0001258561,0.0003088112,0.002088592,0.001365706,0.00009929163],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000140028,"about_ca_system_score_gemma":0.00009332145,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006699155,"about_ca_topic_score_gemma":0.00000691349,"domain_scores_codex":[0.9970106,0.0002213839,0.0002352192,0.001850926,0.00009140091,0.0005904682],"domain_scores_gemma":[0.9977782,0.0005014734,0.000375298,0.0009160885,0.0001710767,0.0002578322],"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":[0.00004630204,0.00004222241,0.0003526924,0.00005309208,0.0000451466,0.0001289348,0.0001037101,0.3079012,0.00001925994,0.6895258,0.0003142161,0.001467354],"study_design_scores_gemma":[0.0003661999,0.0002315745,0.0002899274,0.0001457914,0.00003599384,0.000002921106,0.00003024602,0.545593,0.00004977241,0.4512756,0.001483184,0.0004957818],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.037833,0.0004090309,0.954908,0.0002506,0.0009721085,0.0006430764,0.00001271675,0.001022068,0.003949385],"genre_scores_gemma":[0.9802961,0.0004464906,0.01796281,0.0002665768,0.0001503882,0.00000534903,0.00003872389,0.00003861608,0.0007949699],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9424631,"threshold_uncertainty_score":0.9996979,"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."}}