{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001436016,0.000389252,0.0004371756,0.0004911291,0.000295445,0.00009283518,0.000734022,0.0005411058,0.00004781802],"category_scores_gemma":[0.0001521492,0.0004063012,0.0004531426,0.001049334,0.000116245,0.0005164781,0.00050044,0.0006927469,0.000003658031],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002039955,"about_ca_system_score_gemma":0.0008485608,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009000927,"about_ca_topic_score_gemma":0.0000811028,"domain_scores_codex":[0.9962789,0.0003674891,0.0008640839,0.001074464,0.001033688,0.0003813634],"domain_scores_gemma":[0.9948282,0.0008383632,0.0006027192,0.000977103,0.002628741,0.0001248948],"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":[0.00002358593,0.0001079022,0.0006617311,0.00004133796,0.0001166951,4.117027e-7,0.0001396733,0.6330059,0.00002920781,0.3569387,0.005602976,0.003331899],"study_design_scores_gemma":[0.0008205674,0.0001105879,0.02745549,0.0003777778,0.00009570386,0.000003781327,0.00001463527,0.7631075,0.0001315937,0.2072948,0.0002848497,0.0003026471],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005300982,0.0007415569,0.9859735,0.0005431798,0.003449893,0.002065137,0.0001119617,0.0002080471,0.001605746],"genre_scores_gemma":[0.6041404,0.0002297748,0.3896395,0.0002101304,0.0008576271,0.001692623,0.002852643,0.00004889296,0.000328414],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5988394,"threshold_uncertainty_score":0.9998389,"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."}}