{"id":"W7102416460","doi":"10.1016/j.ipm.2025.104460","title":"Text-free inductive knowledge graph embedding via meta graph-based prompt learning","year":2025,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"ca_institutions":"York University","funders":"Central China Normal University; China Postdoctoral Science Foundation; National Social Science Fund of China; Natural Science Foundation of Hubei Province; Ministry of Education of the People's Republic of China; National Outstanding Youth Science Fund Project of National Natural Science Foundation of China; National Natural Science Foundation of China","keywords":"Embedding; Graph; Knowledge graph; Node (physics); Inductive bias; Construct (python library); Bridge (graph theory); Entity linking","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":[0.0004744678,0.000304644,0.0002824781,0.001137758,0.0006271331,0.000635245,0.001366257,0.00008073502,0.000007005689],"category_scores_gemma":[0.00003712722,0.0002794549,0.0001572667,0.002969985,0.00008529184,0.004925395,0.0007211422,0.0003795154,0.00003067997],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009401307,"about_ca_system_score_gemma":0.00005113104,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003240475,"about_ca_topic_score_gemma":0.000001962391,"domain_scores_codex":[0.998098,0.00007808366,0.0005989728,0.0003799435,0.0004015774,0.00044348],"domain_scores_gemma":[0.9985432,0.00006226667,0.0004044024,0.000643502,0.000274451,0.00007215956],"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":[0.00001666329,0.00006504763,0.00006211209,0.0005009265,0.0002513272,0.000003625707,0.001128539,0.07999313,0.00001829189,0.04167547,0.001642125,0.8746427],"study_design_scores_gemma":[0.001786328,0.00009006985,0.001374674,0.0005301058,0.0003135045,0.000004176378,0.0004346938,0.7905546,0.001074373,0.1282654,0.07473745,0.0008345998],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0004273395,0.0005504582,0.980009,0.0007000549,0.0003409125,0.0005821279,6.621563e-7,0.0007033614,0.01668609],"genre_scores_gemma":[0.7791265,0.00004377469,0.2180574,0.001597855,0.00003451382,0.0004645259,0.00002476295,0.0000196466,0.0006310017],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8738081,"threshold_uncertainty_score":0.9999658,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01363896010083808,"score_gpt":0.2767357352978942,"score_spread":0.2630967751970561,"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."}}