{"id":"W4416026889","doi":"10.48550/arxiv.2511.04557","title":"Integrating Temporal and Structural Context in Graph Transformers for Relational Deep Learning","year":2025,"lang":"","type":"preprint","venue":"ArXiv.org","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Institute for Advanced Research; National Science Foundation","keywords":"Statistical relational learning; Deep learning; Relational database; Bottleneck; Feature learning; Relational model; Scalability; Graph","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008927739,0.001142296,0.0007468213,0.0008244731,0.0004439787,0.00106191,0.002171947,0.00113329,0.003642353],"category_scores_gemma":[0.003622329,0.0005993022,0.001070528,0.001084119,0.0009405616,0.004659606,0.002471204,0.00270837,0.001014279],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001597218,"about_ca_system_score_gemma":0.001105526,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007477732,"about_ca_topic_score_gemma":0.01897273,"domain_scores_codex":[0.9996106,0.00009797182,0.00001742985,0.000158267,0.00007310572,0.00004270568],"domain_scores_gemma":[0.9991147,0.0003703411,0.00007437034,0.0002530841,0.0001053983,0.00008212795],"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":[0.0003497092,0.0003207495,0.003765701,0.0002457947,0.0001418127,0.0002322681,0.0003112092,0.5364168,0.01512821,0.09051542,0.009717333,0.3428549],"study_design_scores_gemma":[0.000009600312,0.00003127173,0.0001265313,0.000008316179,0.0000138639,0.00002808047,0.00001676365,0.9578664,0.001643665,0.03946944,0.0007792171,0.000006873071],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03356332,0.0004309945,0.9609427,0.000421268,0.0000378208,0.00004828891,0.000407971,0.00273036,0.001417373],"genre_scores_gemma":[0.7514228,0.0006765482,0.2403837,0.0005351395,0.00006047797,0.0001195817,0.002218825,0.0005199072,0.004062924],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007477732,"threshold_uncertainty_score":0.01486844,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0344528090153732,"score_gpt":0.2839593920499296,"score_spread":0.2495065830345564,"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."}}