{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0006913121,0.0008569342,0.0009558782,0.0006173514,0.0007381864,0.0002002156,0.0008471065,0.0006443564,0.00001907909],"category_scores_gemma":[0.0003736743,0.0008766256,0.0004419417,0.001075716,0.0004477021,0.00109379,0.0006389451,0.003178171,0.000002744275],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001842389,"about_ca_system_score_gemma":0.0002393247,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000183968,"about_ca_topic_score_gemma":0.001025524,"domain_scores_codex":[0.9949532,0.0003150008,0.001426152,0.001895645,0.0003962618,0.001013807],"domain_scores_gemma":[0.9970643,0.001341407,0.0006527625,0.0004122643,0.0002851367,0.0002441431],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001515731,0.0000197134,0.7209939,0.0002087938,0.0000925951,0.00001268382,0.003026481,0.03014929,0.00006811994,0.01172867,0.000006853646,0.2335413],"study_design_scores_gemma":[0.00202075,0.0002785134,0.243736,0.0011089,0.00005810474,0.00002357154,0.00119008,0.7287035,0.0001117329,0.02103562,0.0006820714,0.001051158],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4973122,0.001986286,0.497431,0.0005844344,0.001220648,0.001155618,0.00001634721,0.00009180858,0.0002016674],"genre_scores_gemma":[0.9686283,0.0003685599,0.02985525,0.0003243501,0.0001602221,0.0001795654,0.00009981302,0.00003676767,0.0003472017],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6985542,"threshold_uncertainty_score":0.9993684,"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."}}