{"id":"W3152688462","doi":"10.1145/3404835.3462961","title":"TIE: A Framework for Embedding-based Incremental Temporal Knowledge Graph Completion","year":2021,"lang":"en","type":"article","venue":"","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"Huawei Technologies (Canada); Université de Montréal; McGill University","funders":"","keywords":"Computer science; Forgetting; Embedding; Inference; Regularization (linguistics); Encoder; Artificial intelligence; Graph; Knowledge graph; Machine learning; Set (abstract data type); Theoretical computer science","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":[0.000142882,0.0001668033,0.0001900685,0.00009098146,0.0001946939,0.000129196,0.000455145,0.00009128654,0.00003890811],"category_scores_gemma":[0.00006056217,0.0001609888,0.0001587763,0.000760271,0.00004913897,0.0003148866,0.000181568,0.000174598,0.0000177916],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004280322,"about_ca_system_score_gemma":0.00005360008,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004489812,"about_ca_topic_score_gemma":0.00004658168,"domain_scores_codex":[0.998681,0.00006452055,0.0002327528,0.0004909024,0.0001842369,0.0003465774],"domain_scores_gemma":[0.9988272,0.0003361385,0.00007698681,0.0004906215,0.0001602709,0.0001087869],"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":[0.00005952016,0.000557317,0.004297099,0.00009243479,0.00005790163,0.00004721011,0.0002703547,0.004638298,0.002973529,0.9228877,0.02584068,0.03827795],"study_design_scores_gemma":[0.001338031,0.0002730293,0.0009081326,0.0001259818,0.00001389336,0.00002139053,0.00006009746,0.754228,0.01647283,0.188076,0.03786124,0.0006213313],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003584513,0.0002075284,0.993063,0.001375918,0.0006338277,0.0001788577,0.000005267012,0.0003263688,0.0006247074],"genre_scores_gemma":[0.4148648,0.000002563254,0.5833339,0.001491364,0.00009322341,0.00004460361,0.00003091738,0.00001218745,0.000126415],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7495897,"threshold_uncertainty_score":0.6564934,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03242645237418972,"score_gpt":0.3244876535897444,"score_spread":0.2920612012155547,"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."}}