{"id":"W4386566692","doi":"10.18653/v1/2023.eacl-main.150","title":"TwiRGCN: Temporally Weighted Graph Convolution for Question Answering over Temporal Knowledge Graphs","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"Google (Canada)","funders":"Science and Engineering Research Board","keywords":"Computer science; Knowledge graph; Question answering; Convolution (computer science); Graph; Artificial intelligence; Theoretical computer science; Artificial neural network","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":[0.001773285,0.00104859,0.001380795,0.001965803,0.0009841331,0.001789409,0.002414401,0.001970569,0.008514973],"category_scores_gemma":[0.005092343,0.0005669047,0.001354963,0.002492832,0.0004921507,0.004724065,0.002565729,0.00189334,0.003632891],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001625068,"about_ca_system_score_gemma":0.001679655,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03446321,"about_ca_topic_score_gemma":0.05751409,"domain_scores_codex":[0.9990827,0.0002196838,0.00006019067,0.0003001711,0.0002530784,0.00008424125],"domain_scores_gemma":[0.9988177,0.0005697442,0.00005869752,0.0002761735,0.0001981523,0.00007942843],"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":[0.000848692,0.0005523956,0.001927272,0.0005459876,0.000267252,0.000319609,0.0004291252,0.0499823,0.009035904,0.0270618,0.1207508,0.788279],"study_design_scores_gemma":[0.00007707561,0.00008062686,0.0007617674,0.00004002987,0.00005823745,0.000122404,0.00012466,0.9335316,0.004231537,0.03964192,0.02130044,0.00002968465],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02229793,0.002818173,0.9086304,0.001012432,0.0004107536,0.0004276146,0.005926616,0.05321317,0.005262925],"genre_scores_gemma":[0.1940242,0.001126974,0.7680042,0.0007329818,0.0001911297,0.0005459212,0.02153017,0.001831323,0.01201301],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03446321,"threshold_uncertainty_score":0.06852525,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02940984131595029,"score_gpt":0.2913399630388992,"score_spread":0.2619301217229489,"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."}}