{"id":"W3211455799","doi":"10.1145/3486622.3493921","title":"Linked Data Ground Truth for Quantitative and Qualitative Evaluation of Explanations for Relational Graph Convolutional Network Link Prediction on Knowledge Graphs","year":2021,"lang":"en","type":"article","venue":"IEEE/WIC/ACM International Conference on Web Intelligence","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Thales (Canada)","funders":"Agence Nationale de la Recherche","keywords":"Computer science; Ground truth; Leverage (statistics); Convolutional neural network; Benchmark (surveying); Graph; Data mining; Machine learning; Metric (unit); Theoretical computer science; Artificial intelligence","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":[0.006723693,0.001317687,0.0005601716,0.00630821,0.0006927843,0.002016085,0.001832231,0.002689799,0.004429419],"category_scores_gemma":[0.06325375,0.00028122,0.0009844229,0.003534757,0.001403967,0.005024939,0.002378059,0.001644648,0.000818681],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002326786,"about_ca_system_score_gemma":0.001482413,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006600156,"about_ca_topic_score_gemma":0.01474494,"domain_scores_codex":[0.9932054,0.00278376,0.0005091269,0.001318476,0.001934012,0.0002491568],"domain_scores_gemma":[0.9609613,0.02532986,0.00339781,0.005769152,0.004019582,0.0005222533],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001437961,0.0006971766,0.08016998,0.002456874,0.0009554361,0.0005352375,0.0009876328,0.4389846,0.005162794,0.05596121,0.03167125,0.3809799],"study_design_scores_gemma":[0.00008876294,0.0001961034,0.01047691,0.0003168353,0.0001199694,0.0001494772,0.0004057052,0.9207714,0.007973621,0.05196071,0.007489234,0.00005119236],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3662661,0.004324444,0.5603115,0.002241056,0.0003461307,0.0006434063,0.04158832,0.01290038,0.01137863],"genre_scores_gemma":[0.7625194,0.0004512177,0.1921599,0.0003000073,0.00006552241,0.0003354509,0.04261075,0.0003385991,0.001219114],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006723693,"threshold_uncertainty_score":0.0355587,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4002114937819156,"score_gpt":0.459318220150168,"score_spread":0.05910672636825243,"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."}}