{"id":"W4406028367","doi":"10.1109/tmc.2025.3525477","title":"Multi-Task Semantic Communication With Graph Attention-Based Feature Correlation Extraction","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Mobile Computing","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"Natural Science Foundation of Beijing Municipality; National Natural Science Foundation of China","keywords":"Computer science; Correlation; Feature extraction; Graph; Task (project management); Artificial intelligence; Feature (linguistics); Semantic feature; Natural language processing; Pattern recognition (psychology); Theoretical computer science","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":[0.0007855255,0.001592374,0.0009332285,0.001000384,0.0004268155,0.0007555611,0.001939477,0.0009955794,0.002241541],"category_scores_gemma":[0.002626235,0.0003574094,0.001174027,0.001387092,0.0005195319,0.002577639,0.001521293,0.001500212,0.0009712319],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001017029,"about_ca_system_score_gemma":0.001445374,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007359849,"about_ca_topic_score_gemma":0.009121968,"domain_scores_codex":[0.9993601,0.0001402674,0.00003050173,0.0002412288,0.0001354739,0.00009235766],"domain_scores_gemma":[0.9992942,0.0002724525,0.00007708877,0.0001666166,0.0001422276,0.00004749039],"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":[0.000552439,0.0005000788,0.003026921,0.0003407065,0.0002000584,0.000358797,0.0003209793,0.220733,0.0231242,0.0174016,0.01975418,0.7136869],"study_design_scores_gemma":[0.00002489583,0.0000813935,0.0006745455,0.00001109275,0.00004736208,0.00006264746,0.00003129245,0.9740859,0.006237363,0.01564608,0.003079233,0.00001815663],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04335494,0.001058816,0.9432698,0.0005473698,0.0001373744,0.0001427753,0.0006468978,0.006708249,0.004133705],"genre_scores_gemma":[0.7380581,0.0006204888,0.2477649,0.0004274149,0.000161073,0.0002806687,0.002898508,0.0004427776,0.009346144],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007359849,"threshold_uncertainty_score":0.01463407,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009291780807133998,"score_gpt":0.2653748857324918,"score_spread":0.2560831049253578,"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."}}