{"id":"W7134973199","doi":"10.1109/icdmw69685.2025.00120","title":"Smooth Transitions in Graph Self-Supervision: Mitigating Feature Twist Across Abstraction Levels","year":2025,"lang":"","type":"article","venue":"","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Feature (linguistics); Twist; Abstraction; Graph; Context (archaeology)","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005702417,0.0006483192,0.0005957783,0.0004333712,0.001057407,0.0007303464,0.001205237,0.0005769588,0.00008062777],"category_scores_gemma":[0.00004473918,0.0006753064,0.0004039683,0.005644016,0.0002521006,0.002341483,0.0003276791,0.001832411,0.00002950379],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002054255,"about_ca_system_score_gemma":0.000197821,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007903636,"about_ca_topic_score_gemma":0.00111399,"domain_scores_codex":[0.9953021,0.0002467092,0.0009902471,0.001581139,0.0005621149,0.001317668],"domain_scores_gemma":[0.9977977,0.0003371506,0.0002205937,0.001133722,0.0002615487,0.0002492794],"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":[0.0001147603,0.0016799,0.005762096,0.0006852014,0.0002572679,0.0005705979,0.01997517,0.07370444,0.008725419,0.07684813,0.005053161,0.8066239],"study_design_scores_gemma":[0.005139077,0.0003900961,0.244607,0.003014647,0.0001195137,0.0001583538,0.004577566,0.6588287,0.005830671,0.06345988,0.01114107,0.002733438],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.169616,0.00228632,0.7855532,0.02827008,0.004256797,0.00137164,0.00007959146,0.0008709413,0.007695429],"genre_scores_gemma":[0.9280788,0.0001987112,0.06811599,0.002218773,0.0001507746,0.00004641636,0.00001173768,0.00002873623,0.001150018],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8038904,"threshold_uncertainty_score":0.9995698,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01651576988460092,"score_gpt":0.2965794799860514,"score_spread":0.2800637101014505,"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."}}