{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009834756,0.0006882902,0.0006358302,0.0006957219,0.0003092769,0.001075376,0.00239917,0.0009747804,0.003342116],"category_scores_gemma":[0.003386584,0.000595293,0.0009108346,0.001064088,0.0006903418,0.002862055,0.001349806,0.002556181,0.001158913],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001074673,"about_ca_system_score_gemma":0.0009706707,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008409096,"about_ca_topic_score_gemma":0.01378286,"domain_scores_codex":[0.9994645,0.0001319252,0.00003315789,0.0001749046,0.0001479355,0.00004764298],"domain_scores_gemma":[0.9993094,0.0002907167,0.00009141937,0.0001390414,0.0001289998,0.00004038445],"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":[0.0002017846,0.000146411,0.002664119,0.0002943745,0.0002563874,0.0002193399,0.0001803612,0.5169458,0.004522688,0.1471147,0.01900754,0.3084464],"study_design_scores_gemma":[0.000008398222,0.00001771452,0.0001960197,0.00002150521,0.00001569672,0.00004165933,0.000008974431,0.938182,0.0007837375,0.05685193,0.003863057,0.000009300161],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008535235,0.000842747,0.9839393,0.000591437,0.00007093606,0.00003602353,0.001046033,0.001885959,0.003052316],"genre_scores_gemma":[0.4539249,0.00222609,0.5237441,0.0008675331,0.000140927,0.0002664477,0.005868411,0.0004270306,0.01253451],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008409096,"threshold_uncertainty_score":0.01672029,"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."}}