{"id":"W4386727921","doi":"10.20944/preprints202309.0962.v1","title":"Directional Graph Attention Networks","year":2023,"lang":"en","type":"preprint","venue":"Preprints.org","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Graph; Attention network; Data mining; Margin (machine learning); Theoretical computer science; Artificial intelligence; Machine learning; Pattern recognition (psychology)","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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007371012,0.0005450416,0.0004998597,0.0004032055,0.0002780201,0.000111794,0.002576449,0.0005441002,0.00007356139],"category_scores_gemma":[0.000118876,0.000597972,0.000542197,0.001003847,0.0001306502,0.0004244169,0.007267219,0.001896566,0.00137569],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000138515,"about_ca_system_score_gemma":0.00007911569,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006973506,"about_ca_topic_score_gemma":0.00003007374,"domain_scores_codex":[0.9955202,0.0002377388,0.0006848345,0.002151207,0.0006704348,0.0007355316],"domain_scores_gemma":[0.996267,0.0002170008,0.000491635,0.002565305,0.0002211396,0.0002379316],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0000307829,0.000172866,0.5224707,0.0001021262,0.0003046184,0.0001136797,0.0001532339,0.4535107,0.0009284975,0.01454464,0.001496204,0.006171978],"study_design_scores_gemma":[0.0002907251,0.00001888218,0.7947738,0.0002677185,0.0000380832,0.00002698516,0.000006649063,0.09899427,0.0005885614,0.1015913,0.002470789,0.000932221],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1191469,0.0002853722,0.861344,0.001414711,0.0111662,0.0008764455,0.00001071673,0.003457567,0.002298045],"genre_scores_gemma":[0.986603,0.0007123013,0.006716831,0.0002873885,0.000902302,0.0004228367,0.0001017806,0.00009717261,0.004156377],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8674561,"threshold_uncertainty_score":0.9996471,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1264386529009888,"score_gpt":0.3404159394477672,"score_spread":0.2139772865467784,"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."}}