{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002123497,0.0003415588,0.0003600274,0.0003888734,0.0003457051,0.0001434701,0.001506972,0.0001900788,0.00005101651],"category_scores_gemma":[0.002666999,0.000356534,0.0001600658,0.0007317518,0.0003308789,0.001090245,0.0002721478,0.0003505098,0.00001075726],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001608155,"about_ca_system_score_gemma":0.000725741,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006614999,"about_ca_topic_score_gemma":0.00008642108,"domain_scores_codex":[0.9959444,0.0004909588,0.0009071587,0.001216916,0.001076947,0.0003636547],"domain_scores_gemma":[0.9875063,0.006299524,0.000592318,0.0009295635,0.004543105,0.0001291356],"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":[0.000222339,0.0001772567,0.00006699048,0.00002373381,0.0001903085,8.596528e-7,0.001094919,0.02051309,0.000303445,0.9659581,0.001011616,0.0104373],"study_design_scores_gemma":[0.0005574172,0.0003572282,0.0007484178,0.000204474,0.00004405274,0.000006017902,0.0005243917,0.5421897,0.0003652494,0.4543337,0.0004583567,0.0002110188],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00670877,0.0005556521,0.9823413,0.002603869,0.003530563,0.001156518,0.001806192,0.00009398667,0.001203076],"genre_scores_gemma":[0.876104,0.0004439074,0.1205614,0.0001848206,0.0003479496,0.0004370612,0.001758484,0.00002491827,0.0001374423],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8693953,"threshold_uncertainty_score":0.9998887,"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."}}