{"id":"W3208642674","doi":"10.1145/3460210.3493557","title":"User Scored Evaluation of Non-Unique Explanations for Relational Graph Convolutional Network Link Prediction on Knowledge Graphs","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Thales (Canada)","funders":"","keywords":"Computer science; Ground truth; Benchmark (surveying); Link (geometry); Graph; Relevance (law); Machine learning; Task (project management); Artificial intelligence; Data mining; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005855246,0.001947631,0.0006937558,0.0026991,0.0004793358,0.001403904,0.00148067,0.002527995,0.005434593],"category_scores_gemma":[0.04267836,0.0002829115,0.0009594493,0.001371514,0.0006671129,0.002375047,0.001560369,0.001313468,0.0012532],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001124206,"about_ca_system_score_gemma":0.0008159967,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008370553,"about_ca_topic_score_gemma":0.02305884,"domain_scores_codex":[0.9940799,0.002922465,0.0004659498,0.001241083,0.001039706,0.000250805],"domain_scores_gemma":[0.9617391,0.03034013,0.001397967,0.003297503,0.002507033,0.000718225],"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":[0.006995422,0.001916835,0.09136222,0.003763558,0.001538911,0.001291207,0.001646133,0.1620046,0.01286939,0.005223757,0.0851607,0.6262272],"study_design_scores_gemma":[0.0004959578,0.001228902,0.04017562,0.0003421771,0.0002855111,0.0006972262,0.0006102581,0.9190893,0.01428386,0.006357523,0.01629121,0.0001423953],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8573769,0.004758126,0.08507058,0.0009850758,0.0003905065,0.0005815326,0.019501,0.01929966,0.0120366],"genre_scores_gemma":[0.8645658,0.0005373078,0.09506149,0.0002934998,0.00005839447,0.000278491,0.03501841,0.0004516877,0.003734795],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008370553,"threshold_uncertainty_score":0.03096586,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05815114462211044,"score_gpt":0.3178067646145841,"score_spread":0.2596556199924736,"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."}}