{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003548246,0.0002401142,0.0003764763,0.0009414565,0.00009531031,0.000220991,0.001526504,0.0003179952,0.0001498783],"category_scores_gemma":[0.0001867998,0.0002225652,0.0002869239,0.003461549,0.0001140055,0.0002489057,0.004424846,0.001154924,0.000231802],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001264811,"about_ca_system_score_gemma":0.00004871834,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006859117,"about_ca_topic_score_gemma":0.00006174812,"domain_scores_codex":[0.9976795,0.0002099742,0.0002462581,0.001406532,0.0001162225,0.0003415172],"domain_scores_gemma":[0.9987997,0.0001792958,0.0001292534,0.0007078681,0.00006289654,0.000120945],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001895017,0.0001272804,0.02204736,0.00004928083,0.0001135942,0.001948302,0.0003105766,0.2597256,0.00001895935,0.7091652,0.0004417015,0.006033171],"study_design_scores_gemma":[0.0002483716,0.00008351134,0.006995115,0.0000601549,0.00008216784,0.000007344313,0.0002614246,0.4237635,0.00004466753,0.5668756,0.00108479,0.0004934247],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7233979,0.0002802444,0.2655646,0.0007425052,0.000521186,0.0001768694,0.00000958402,0.0004489579,0.008858219],"genre_scores_gemma":[0.994834,0.0003734917,0.0009144294,0.00008288645,0.00004824368,0.000001281173,0.00002827888,0.000006443188,0.003710934],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2714361,"threshold_uncertainty_score":0.9075946,"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."}}