{"id":"W3131239930","doi":"10.48550/arxiv.2102.09557","title":"Knowledge Hypergraph Embedding Meets Relational Algebra","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Hypergraph; Embedding; Relational algebra; Theoretical computer science; Computer science; Relational database; Set (abstract data type); Mathematical proof; Relational model; Relation (database); Relational calculus; Projection (relational algebra); Relation algebra; Knowledge representation and reasoning; Graph; Representation (politics); Algebra over a field; Mathematics; Discrete mathematics; Artificial intelligence; Algorithm; Algebra representation; Data mining; Two-element Boolean algebra; Programming language; Pure mathematics","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":[0.0001761386,0.0004261638,0.0004073203,0.0003887317,0.000278917,0.0001645065,0.001884319,0.0004125918,0.00004492034],"category_scores_gemma":[0.00004513384,0.00052768,0.000411789,0.001467661,0.0001345338,0.000861512,0.003430944,0.001039546,0.00006735243],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001842642,"about_ca_system_score_gemma":0.0002377339,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001328608,"about_ca_topic_score_gemma":0.00003571358,"domain_scores_codex":[0.9972153,0.000211695,0.000268493,0.001675193,0.0001345288,0.0004948008],"domain_scores_gemma":[0.9974743,0.0002640316,0.0002715978,0.001469224,0.0002774467,0.000243368],"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":[0.000008343024,0.00008077644,0.001413916,0.00003850174,0.0001007667,0.0005311495,0.0001949741,0.4991968,0.00004861245,0.4969288,0.0003964359,0.001060923],"study_design_scores_gemma":[0.0004157994,0.00002735459,0.002045692,0.0002266095,0.00005954684,0.00002415226,0.00004676778,0.905597,0.0001121378,0.08870047,0.001963748,0.000780754],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1547716,0.0008351488,0.8373756,0.0001629098,0.001594007,0.0002151261,0.000006110231,0.000469601,0.004569927],"genre_scores_gemma":[0.9780111,0.0003461511,0.01996082,0.0001091688,0.0001428483,0.000001444658,0.00003753432,0.00002920398,0.00136177],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8232395,"threshold_uncertainty_score":0.9997175,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07236993584907335,"score_gpt":0.2092159988634295,"score_spread":0.1368460630143561,"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."}}