{"id":"W3196754906","doi":"10.1109/tnnls.2021.3106156","title":"Full-Scale Information Diffusion Prediction With Reinforced Recurrent Networks","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks and Learning Systems","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":55,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; Canadian Institute for Advanced Research","funders":"Fundamental Research Funds for the Central Universities; National Research Foundation Singapore; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China; Canadian Institute for Advanced Research","keywords":"Computer science; Diffusion; Diffusion process; Context (archaeology); Recurrent neural network; Artificial intelligence; Process (computing); Machine learning; Task (project management); Scale (ratio); Reinforcement learning; Artificial neural network; Data mining; Innovation diffusion; Physics","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":[0.0001954065,0.0002523225,0.000322531,0.0001032205,0.0006362441,0.000301409,0.00007771466,0.00009542503,0.00007413563],"category_scores_gemma":[9.724179e-7,0.0002171297,0.0001227474,0.0004496855,0.00004250518,0.0004216743,0.000004135153,0.0008473403,0.000003235818],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000354647,"about_ca_system_score_gemma":0.00001679984,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001419367,"about_ca_topic_score_gemma":0.00002616289,"domain_scores_codex":[0.9984896,0.0002351672,0.0004380757,0.0002865195,0.00023439,0.0003163054],"domain_scores_gemma":[0.9991551,0.000110773,0.0002197298,0.0002413995,0.0001475584,0.000125436],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001154135,0.00002752928,0.0007602958,0.00001326939,0.00006945719,0.000001275341,0.0001090435,0.9535679,0.00004027714,0.00008356139,0.0001962296,0.04501577],"study_design_scores_gemma":[0.0004553797,0.0003619524,0.0003537807,0.0001739501,0.0001002906,0.00002173136,0.0004174162,0.9953364,0.00003456912,0.000002825307,0.002520508,0.0002212473],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1060199,0.0001426399,0.8923796,0.00004402227,0.0005096304,0.0002660871,0.000006597634,0.0002089056,0.0004225876],"genre_scores_gemma":[0.9984853,0.00007852931,0.0001080753,0.00003041639,0.00039333,0.0000909782,0.0001216182,0.00002303742,0.0006687624],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8924653,"threshold_uncertainty_score":0.885429,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005795683263584928,"score_gpt":0.2043894768798737,"score_spread":0.1985937936162888,"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."}}