{"id":"W4385570097","doi":"10.18653/v1/2023.findings-acl.882","title":"Learning Query Adaptive Anchor Representation for Inductive Relation Prediction","year":2023,"lang":"en","type":"article","venue":"","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"Fundamental Research Funds for the Central Universities; Central China Normal University; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computer science; Relation (database); Representation (politics); Task (project management); Relationship extraction; Feature learning; Graph; Feature (linguistics); Artificial intelligence; Machine learning; Data mining; Theoretical computer science","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001725589,0.00007917899,0.00007892738,0.0001537601,0.0001887611,0.00004062697,0.0001448669,0.00006359385,0.000002181089],"category_scores_gemma":[0.0001270251,0.0000767993,0.00004850861,0.001023234,0.00001960892,0.001264568,0.00007521323,0.0001534996,0.00002544812],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004523029,"about_ca_system_score_gemma":0.00001502585,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009334215,"about_ca_topic_score_gemma":0.000004591255,"domain_scores_codex":[0.9990659,0.00006333635,0.0001582567,0.000367378,0.000157606,0.000187557],"domain_scores_gemma":[0.9993019,0.0002729263,0.00009500497,0.0001821153,0.000110282,0.0000377498],"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":[0.0001200986,0.00003582519,0.01369342,0.00001134187,0.00005838115,0.000007720073,0.003363379,0.4367054,0.006057462,0.212495,0.00927883,0.3181732],"study_design_scores_gemma":[0.0002625964,0.0002225469,0.04075183,0.00001123633,0.00000403679,0.000002054669,0.0002843382,0.9133359,0.001276763,0.04316025,0.0005870295,0.0001013707],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03332936,0.000007766865,0.9635212,0.0004095284,0.0004800167,0.0003851244,0.00000133547,0.0009082867,0.0009574246],"genre_scores_gemma":[0.9309075,0.00002094685,0.06659171,0.00007122155,0.0002082584,0.0001507588,0.00003702878,0.0000134878,0.001999077],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8975781,"threshold_uncertainty_score":0.3131785,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04635087952193891,"score_gpt":0.2962809972788805,"score_spread":0.2499301177569416,"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."}}