{"id":"W2973697852","doi":"10.1371/journal.pone.0247936","title":"Learning temporal attention in dynamic graphs with bilinear interactions","year":2021,"lang":"en","type":"preprint","venue":"PLoS ONE","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research; University of Saskatchewan; University of Guelph; Vector Institute","funders":"National Institute of Environmental Health Sciences; Defense Advanced Research Projects Agency; Canada Foundation for Innovation; Canada Research Chairs; University of Guelph; University of Saskatchewan; Government of Canada; Defense Sciences Office, DARPA; Vector Institute; Canadian Institute for Advanced Research; U.S. Department of Defense","keywords":"Computer science; Concatenation (mathematics); Node (physics); Term (time); Bilinear interpolation; Task (project management); Artificial intelligence; Feature (linguistics); Flexibility (engineering); Graph; Key (lock); Theoretical computer science; Machine learning; Mathematics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001300322,0.0002593727,0.0003855228,0.0003660363,0.00008956772,0.0002137753,0.0005929585,0.0001309826,0.00001084307],"category_scores_gemma":[0.0000428137,0.0002567459,0.0001046676,0.0008130591,0.00005022662,0.0004867537,0.0008782272,0.001872075,0.0000101143],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000107537,"about_ca_system_score_gemma":0.00007860137,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005915315,"about_ca_topic_score_gemma":0.0007824295,"domain_scores_codex":[0.9979641,0.0001641783,0.0003379824,0.0008328417,0.0003938279,0.0003070886],"domain_scores_gemma":[0.9987037,0.00008957681,0.0002608919,0.0007161074,0.0001547063,0.00007500649],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002131334,0.01017205,0.5100506,0.001880741,0.00188393,0.001664249,0.003766016,0.3975953,0.03432014,0.002657296,0.00005317381,0.03574331],"study_design_scores_gemma":[0.0004784394,0.0002077817,0.02308358,0.00314818,0.00006833783,0.00002008947,0.00013998,0.9681538,0.0005346488,0.003475941,0.00001969811,0.0006694846],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8773687,0.0001856251,0.1208953,0.0005714864,0.0002106978,0.0003552527,0.000001790445,0.0002923787,0.0001187773],"genre_scores_gemma":[0.8733895,0.0001379755,0.1258607,0.00004560022,0.00003155856,0.00008306013,0.00009785485,0.00002687885,0.0003269204],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5705585,"threshold_uncertainty_score":0.9999885,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02905274807875053,"score_gpt":0.2513163439872472,"score_spread":0.2222635959084967,"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."}}