{"id":"W4414857280","doi":"10.48550/arxiv.2505.24434","title":"Graph Flow Matching: Enhancing Image Generation with Neighbor-Aware Flow Fields","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Pointwise; Flow (mathematics); Vector field; Matching (statistics); Graph; Flow velocity; Scalability; Artificial neural network; 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":[0.001082271,0.001065284,0.0006616974,0.00121951,0.0003641616,0.0009611126,0.001995529,0.001384923,0.003355799],"category_scores_gemma":[0.003592162,0.0004192283,0.0007848612,0.0008511372,0.0006336706,0.001812565,0.001495099,0.001566663,0.001200442],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001041505,"about_ca_system_score_gemma":0.00101211,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008486885,"about_ca_topic_score_gemma":0.01055767,"domain_scores_codex":[0.9995454,0.00007386001,0.0000186271,0.0001669359,0.0001420926,0.00005299738],"domain_scores_gemma":[0.9993317,0.0002529344,0.00006339241,0.0001539623,0.0001443819,0.00005361604],"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":[0.0002962906,0.0002608518,0.002120794,0.0001498363,0.00007906878,0.0001306261,0.0001238731,0.3488829,0.02647612,0.01272722,0.01191653,0.5968358],"study_design_scores_gemma":[0.00001958766,0.00003422872,0.0002069128,0.000007436961,0.000008886069,0.00003170271,0.000009645405,0.9861161,0.006738124,0.005541387,0.001278423,0.000007663771],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03356373,0.0004899258,0.955111,0.0003757914,0.0001863746,0.0001212817,0.0003072557,0.006808744,0.003035882],"genre_scores_gemma":[0.4625063,0.000327089,0.5280272,0.0005666403,0.0001151399,0.0001478349,0.00147124,0.0009505535,0.005888035],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008486885,"threshold_uncertainty_score":0.01687497,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02261056781284036,"score_gpt":0.2773195554684678,"score_spread":0.2547089876556274,"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."}}