{"id":"W2963109792","doi":"10.48550/arxiv.1712.02831","title":"RelNN: A Deep Neural Model for Relational Learning","year":2017,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Statistical relational learning; Computer science; Artificial intelligence; Deep learning; Scalability; Machine learning; Object (grammar); Artificial neural network; Focus (optics); Modular design; Deep belief network; Architecture; Relational database; 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":[0.0001525714,0.00009703445,0.00009426421,0.00005223812,0.0007662656,0.0001382026,0.0009058725,0.0000686829,0.000004184652],"category_scores_gemma":[0.00008145503,0.0001099169,0.00008027341,0.00007172763,0.00006229323,0.000853523,0.000226613,0.0001660773,0.00002699312],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003453469,"about_ca_system_score_gemma":0.00004889653,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001612487,"about_ca_topic_score_gemma":0.00001319198,"domain_scores_codex":[0.9992283,0.0000242318,0.00008078405,0.0004031582,0.00004837989,0.0002151196],"domain_scores_gemma":[0.9991017,0.00005886302,0.0001159391,0.0005253084,0.0001068149,0.00009136849],"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":[0.000009013556,0.000009290441,0.001133466,0.000002581799,0.000005313681,0.000008220919,0.00008358656,0.5402547,0.00002287867,0.456954,0.00003243352,0.001484475],"study_design_scores_gemma":[0.0002959204,0.00003241992,0.0007849752,0.000006290463,0.000008187779,0.000002351542,0.000008245482,0.9332099,0.00001279083,0.06542882,0.00007800877,0.0001321133],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05677164,0.000008938128,0.9405466,0.0002481702,0.00009858766,0.00006574435,0.000001006478,0.0001129884,0.002146298],"genre_scores_gemma":[0.9817703,0.000007088965,0.01479682,0.00007118657,0.00003103888,5.712151e-7,0.000001835396,0.000006475045,0.003314701],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9257498,"threshold_uncertainty_score":0.5893573,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1608143345827374,"score_gpt":0.2127503735265826,"score_spread":0.05193603894384527,"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."}}