{"id":"W4285601870","doi":"10.24963/ijcai.2022/731","title":"Improving Inductive Link Prediction Using Hyper-Relational Facts (Extended Abstract)","year":2022,"lang":"en","type":"article","venue":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Bundesministerium für Bildung und Forschung","keywords":"Computer science; Statistical relational learning; Inference; Inductive logic programming; Link (geometry); Metric (unit); Inductive bias; Task (project management); Set (abstract data type); Inductive reasoning; Artificial intelligence; Relational database; Machine learning; Graph; Code (set theory); Training set; Theoretical computer science; Multi-task learning; Information retrieval; 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":[0.0005759285,0.0003001736,0.000260651,0.0003484717,0.0007863108,0.0002162019,0.002084774,0.00009707257,0.000178859],"category_scores_gemma":[0.0003888612,0.0002649591,0.000206973,0.0007350626,0.0002326921,0.001188568,0.001260291,0.001018372,0.00001820142],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003937126,"about_ca_system_score_gemma":0.0001578547,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008153079,"about_ca_topic_score_gemma":0.000008727624,"domain_scores_codex":[0.9966159,0.00002706471,0.0008637292,0.0007332737,0.001382017,0.0003779528],"domain_scores_gemma":[0.9975398,0.0001395778,0.0009974879,0.0002857828,0.0009353003,0.0001020932],"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":[0.0001305367,0.0002410283,0.0004864713,0.00001825518,0.00005621496,0.000002283871,0.001124815,0.03121226,0.05788626,0.8580759,0.00006265003,0.0507034],"study_design_scores_gemma":[0.00008895725,0.0002307764,0.003089989,0.0001477691,0.00001769322,0.00005381423,0.0007006322,0.6711453,0.08130223,0.2425056,0.0003530707,0.0003641867],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6145471,0.00005134047,0.3445906,0.01915834,0.009397382,0.001699709,0.0001514682,0.0005246701,0.009879447],"genre_scores_gemma":[0.9889435,0.0000118242,0.01030918,0.0002675675,0.0002774105,0.00005705743,0.000005111072,0.00002151678,0.0001068696],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.639933,"threshold_uncertainty_score":0.9999803,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09351631533544383,"score_gpt":0.2831491543966582,"score_spread":0.1896328390612143,"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."}}