{"id":"W4384613985","doi":"10.48550/arxiv.2307.07107","title":"Graph Positional and Structural Encoder","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Fonds de recherche du Québec – Nature et technologies; Institut de Valorisation des Données; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research; National Science Foundation","keywords":"Computer science; Encoder; Graph; Identifiability; Artificial intelligence; Theoretical computer science; Machine learning; Pattern recognition (psychology)","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":[0.0005046411,0.001038447,0.0005101762,0.001262517,0.0005079684,0.001064964,0.001742957,0.001160563,0.01150729],"category_scores_gemma":[0.005960334,0.0005197701,0.0007984765,0.001376916,0.0007884962,0.003295755,0.001432345,0.002434939,0.004553357],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001248933,"about_ca_system_score_gemma":0.001853646,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007171101,"about_ca_topic_score_gemma":0.02357497,"domain_scores_codex":[0.9995229,0.00009474723,0.00002137402,0.000189622,0.0001248964,0.00004651707],"domain_scores_gemma":[0.9987592,0.0004374423,0.00006058305,0.0004374523,0.0002530384,0.00005240501],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001956976,0.0001293629,0.003770571,0.000572353,0.00008039521,0.0002440201,0.0002670518,0.239753,0.009309147,0.2585423,0.0748797,0.4122564],"study_design_scores_gemma":[0.0000225013,0.00004594875,0.0007383937,0.0001001307,0.00003846404,0.0001737505,0.00007908099,0.7215215,0.005734242,0.2359965,0.03551986,0.00002961841],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01655661,0.0005762427,0.9468672,0.0009288652,0.0002713674,0.0001853264,0.01260329,0.008286863,0.01372426],"genre_scores_gemma":[0.352398,0.00138104,0.586129,0.0009979972,0.0001590842,0.0006425611,0.0343984,0.002393532,0.02150039],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01150729,"threshold_uncertainty_score":0.03849566,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06640210577149619,"score_gpt":0.1932313591957524,"score_spread":0.1268292534242562,"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."}}