{"id":"W4324355422","doi":"10.3390/data8030061","title":"TKGQA Dataset: Using Question Answering to Guide and Validate the Evolution of Temporal Knowledge Graph","year":2023,"lang":"en","type":"article","venue":"Data","topic":"Topic Modeling","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Royal Bank of Canada","funders":"","keywords":"Knowledge graph; Computer science; Question answering; Graph; Parsing; Information retrieval; Process (computing); Artificial intelligence; Natural language processing; 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":[0.0008572303,0.00005738093,0.00006901362,0.0000956306,0.00008646787,0.00005979786,0.001049734,0.00001911347,0.000001238253],"category_scores_gemma":[0.00008094545,0.00004630857,0.000006998868,0.0004388403,0.00002093985,0.0005189946,0.002216542,0.00004514055,0.00001351038],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000256076,"about_ca_system_score_gemma":0.0000459689,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001575531,"about_ca_topic_score_gemma":0.0001949659,"domain_scores_codex":[0.9992457,0.00005659766,0.0001607594,0.0002986656,0.0001130328,0.000125228],"domain_scores_gemma":[0.9984881,0.0000367995,0.00004307896,0.00137133,0.00002528173,0.0000354118],"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":[0.00003784995,0.0001915563,0.05658204,0.0005711958,0.0001690514,0.00006412371,0.009637585,0.03407161,0.07778551,0.1630806,0.2404873,0.4173216],"study_design_scores_gemma":[0.00007742698,0.0000105159,0.003044302,0.00004709772,0.000007563895,0.000006795929,0.00007006378,0.9771222,0.0002453531,0.00140565,0.01787672,0.00008627885],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08492439,0.0001147152,0.9134264,0.0003729327,0.0002467632,0.0001155735,0.0006710847,0.00007466873,0.00005346602],"genre_scores_gemma":[0.8841936,0.00002515914,0.113633,0.0000760062,0.0001354867,0.000004288825,0.001876717,0.00001116625,0.00004460639],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9430506,"threshold_uncertainty_score":0.2762761,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1071454944889778,"score_gpt":0.3625074726673969,"score_spread":0.2553619781784191,"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."}}