{"id":"W3094859785","doi":"10.1016/j.patcog.2022.108973","title":"GripNet: Graph information propagation on supergraph for heterogeneous graphs","year":2022,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"Perimeter Institute; University of Waterloo; Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada; Queen's University; University of Sheffield; Compute Canada","keywords":"Epigraph; Computer science; Graph; Combinatorics; Mathematics; Theoretical computer science; Mathematical optimization","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.0002236771,0.0001828005,0.0001327949,0.0004301555,0.0004977841,0.0001134142,0.0004110709,0.00004858227,0.00003384508],"category_scores_gemma":[0.000019002,0.0001933332,0.0001596714,0.0006385892,0.00002295179,0.001095257,0.0001135168,0.0002213082,0.00003111644],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005770429,"about_ca_system_score_gemma":0.00001372234,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009127089,"about_ca_topic_score_gemma":0.000007891964,"domain_scores_codex":[0.9984983,0.000114357,0.0003317434,0.0003443402,0.000390152,0.0003210896],"domain_scores_gemma":[0.9991849,0.0001000547,0.000201085,0.0003222084,0.000122116,0.00006961368],"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":[0.00007220401,0.0001124744,0.0004575947,0.00003885837,0.00002586832,0.000005494204,0.0003515782,0.005535013,0.0004343022,0.0009225839,0.001138526,0.9909055],"study_design_scores_gemma":[0.008076444,0.008667555,0.007344611,0.0002011706,0.0001151929,0.0005464725,0.0003260658,0.3280576,0.03601716,0.575506,0.03160996,0.003531714],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1634303,0.00003075002,0.8327174,0.0005313579,0.001482535,0.001136576,0.0001418981,0.0003636068,0.0001656492],"genre_scores_gemma":[0.9920961,0.0000222484,0.003133636,0.00272125,0.00008751143,0.001210495,0.000703908,0.00001736756,0.000007449263],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9873738,"threshold_uncertainty_score":0.7883898,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01986458204256742,"score_gpt":0.2278329279900972,"score_spread":0.2079683459475298,"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."}}