{"id":"W3132397809","doi":"10.1007/s12652-020-02821-2","title":"Entity alignment via knowledge embedding and type matching constraints for knowledge graph inference","year":2021,"lang":"en","type":"article","venue":"Journal of Ambient Intelligence and Humanized Computing","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"National Development and Reform Commission; Department of Science and Technology of Sichuan Province","keywords":"Computer science; Embedding; Knowledge graph; Inference; Matching (statistics); Domain knowledge; Vector space; Artificial intelligence; Graph; Similarity (geometry); Representation (politics); Graph embedding; Pattern recognition (psychology); Data mining; Theoretical computer science; Natural language processing; Mathematics; Image (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":[],"consensus_categories":[],"category_scores_codex":[0.0007080947,0.0002183503,0.000408117,0.0001964433,0.0004182425,0.0003221743,0.0004377553,0.00006745026,0.000008392516],"category_scores_gemma":[0.0001432777,0.0002051868,0.0001248841,0.0003960891,0.0001542632,0.0004964169,0.0004880107,0.0003349984,0.000002449655],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004874237,"about_ca_system_score_gemma":0.0001020723,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001907746,"about_ca_topic_score_gemma":0.000009339452,"domain_scores_codex":[0.9982387,0.000104014,0.0007106048,0.0003828754,0.0001970008,0.0003668006],"domain_scores_gemma":[0.9976675,0.0007736777,0.0004702169,0.0002070378,0.0007011052,0.0001804906],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000072574,0.0004662844,0.001352801,0.0003267543,0.0002500392,0.0001447533,0.01743233,0.00769071,0.01289149,0.1921797,0.0001768249,0.7670157],"study_design_scores_gemma":[0.001812308,0.001483833,0.001507453,0.002540665,0.0001631754,0.001946924,0.00312406,0.6005381,0.0369657,0.3462754,0.002314698,0.001327687],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1661287,0.003034478,0.8295913,0.00005409152,0.000936501,0.0001216406,6.372079e-7,0.000027796,0.0001048671],"genre_scores_gemma":[0.9029876,0.0004712732,0.09623389,0.00009940571,0.0001668932,0.000001004025,8.685731e-7,0.00001122557,0.00002783934],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7656881,"threshold_uncertainty_score":0.8367275,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04664498597235815,"score_gpt":0.3376758821140567,"score_spread":0.2910308961416985,"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."}}