{"id":"W4416716417","doi":"10.48550/arxiv.2410.01778","title":"TopER: Topological Embeddings in Graph Representation Learning","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topological and Geometric Data Analysis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Department of Mechanical Engineering, University of Texas at Austin; University of Texas at Austin; National Science Foundation","keywords":"Interpretability; Topological data analysis; Graph; Graph embedding; Embedding; Topological graph theory; Cluster analysis; Feature learning; Representation (politics)","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":[0.002105837,0.001705325,0.001226673,0.002624253,0.0007283961,0.003109564,0.002903847,0.002010994,0.00500002],"category_scores_gemma":[0.01633668,0.0007360051,0.001534891,0.002876051,0.001483566,0.008074042,0.003927878,0.004218884,0.002658068],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001052146,"about_ca_system_score_gemma":0.000987043,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001900553,"about_ca_topic_score_gemma":0.002741377,"domain_scores_codex":[0.9983974,0.0006233226,0.00008091137,0.0003865109,0.0004250391,0.00008677875],"domain_scores_gemma":[0.9944946,0.002885911,0.0004568701,0.001355036,0.0005702968,0.0002372984],"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":[0.0002936069,0.0002545484,0.003134872,0.0006388943,0.000229825,0.0002185981,0.0004391144,0.3245112,0.004988121,0.2158669,0.03739227,0.4120319],"study_design_scores_gemma":[0.00001678578,0.00005444183,0.00019049,0.00003520494,0.00001693266,0.0000809287,0.00004034477,0.8502118,0.001396262,0.1420811,0.005851385,0.00002433431],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006818384,0.000548444,0.9857581,0.000517694,0.0001041796,0.00005935802,0.0006806174,0.004168516,0.001344742],"genre_scores_gemma":[0.26094,0.001746971,0.7212716,0.0006229652,0.0003358947,0.0005535702,0.006616383,0.002173948,0.005738622],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00500002,"threshold_uncertainty_score":0.01672673,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08002898316307643,"score_gpt":0.221564961347544,"score_spread":0.1415359781844676,"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."}}