{"id":"W4415513509","doi":"10.1016/j.engappai.2025.112910","title":"CGMAE: Self-supervised Masked Auto-Encoder with Cross-Graph node alignment for node classification","year":2025,"lang":"en","type":"article","venue":"Engineering Applications of Artificial Intelligence","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"Fundamental Research Funds for the Central Universities; National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Node (physics); Pattern recognition (psychology); 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008676399,0.001611237,0.001500311,0.001359791,0.0007529879,0.0008776472,0.003622019,0.001817661,0.006452448],"category_scores_gemma":[0.002648199,0.0008327219,0.001009636,0.001276329,0.0005106182,0.002200643,0.001851663,0.002618874,0.006390464],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006561417,"about_ca_system_score_gemma":0.001614618,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008002502,"about_ca_topic_score_gemma":0.02976801,"domain_scores_codex":[0.999241,0.0001425332,0.00003145054,0.0003608191,0.0001442028,0.00008003171],"domain_scores_gemma":[0.9987545,0.0003472722,0.00005915031,0.0004684477,0.0002930115,0.00007761738],"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":[0.0004982526,0.00043941,0.001420324,0.0002850822,0.0002607866,0.0001988072,0.0001474177,0.04036183,0.03783795,0.006354401,0.06163327,0.8505624],"study_design_scores_gemma":[0.00005282516,0.0001059068,0.000563271,0.00002440647,0.00004740535,0.0001360328,0.00004174572,0.9618065,0.02016973,0.009433234,0.007586676,0.00003227521],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01504445,0.0008278732,0.9365824,0.0001773098,0.0003479953,0.0001815067,0.001946065,0.04319474,0.001697677],"genre_scores_gemma":[0.144574,0.0003059367,0.8304229,0.0005302092,0.0001162271,0.0003578103,0.01057316,0.002408048,0.01071178],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008002502,"threshold_uncertainty_score":0.02158558,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0233850047276575,"score_gpt":0.2881942941159746,"score_spread":0.2648092893883171,"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."}}