{"id":"W4400904993","doi":"10.1109/tkde.2024.3432767","title":"One Subgraph for All: Efficient Reasoning on Opening Subgraphs for Inductive Knowledge Graph Completion","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Rough Sets and Fuzzy Logic","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"China Postdoctoral Science Foundation; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computer science; Knowledge graph; Subgraph isomorphism problem; Induced subgraph isomorphism problem; Graph; Inductive reasoning; Theoretical computer science; Artificial intelligence; Line graph; Voltage graph","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005058674,0.0002745847,0.0002783565,0.0005651994,0.0003088888,0.0003212008,0.0006417242,0.000106852,0.000002422272],"category_scores_gemma":[0.00001509448,0.0002702978,0.0001336106,0.000671495,0.00003468405,0.0004495036,0.00002016698,0.0002776865,0.00001349411],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004470121,"about_ca_system_score_gemma":0.00004574105,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001191704,"about_ca_topic_score_gemma":0.00003355752,"domain_scores_codex":[0.998283,0.00002673133,0.000276487,0.0008748905,0.0001276702,0.0004111911],"domain_scores_gemma":[0.9985071,0.0005499453,0.00003173067,0.0006907959,0.00008279839,0.0001376229],"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":[0.000301043,0.002010957,0.00001059556,0.00226221,0.001236513,0.00001633599,0.009250427,0.1079125,0.008873831,0.1996597,0.003771586,0.6646942],"study_design_scores_gemma":[0.0005863272,0.0003800694,0.00009111935,0.0004535303,0.00008611788,0.000009103027,0.00003262247,0.9812853,0.002138373,0.000398446,0.01414385,0.0003951334],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003415609,0.001452659,0.9914849,0.0001145561,0.001792735,0.0007031471,0.0003552978,0.0004097283,0.0002713732],"genre_scores_gemma":[0.9459093,0.0001579993,0.05329009,0.0000294886,0.0001655546,0.0002635503,0.0001022266,0.00004736015,0.00003447154],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9424937,"threshold_uncertainty_score":0.9999749,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0577649098250396,"score_gpt":0.3025058440658079,"score_spread":0.2447409342407683,"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."}}