{"id":"W2542835211","doi":"10.48550/arxiv.1610.09038","title":"Professor Forcing: A New Algorithm for Training Recurrent Networks","year":2016,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":330,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Forcing (mathematics); Computer science; Treebank; Sampling (signal processing); MNIST database; Algorithm; Handwriting; Sample (material); Artificial intelligence; Sequence (biology); Machine learning; Speech recognition; Artificial neural network; Mathematics; Parsing","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":[],"consensus_categories":[],"category_scores_codex":[0.0002045212,0.0001344435,0.0001514474,0.00008589034,0.0001330264,0.00003726096,0.0007505962,0.00007882609,0.000009893302],"category_scores_gemma":[0.00002917558,0.0001146384,0.0001038141,0.000279654,0.00002620801,0.0005195815,0.0001952171,0.00008357201,0.00001359876],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009523849,"about_ca_system_score_gemma":0.0001265269,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001164657,"about_ca_topic_score_gemma":0.00001385722,"domain_scores_codex":[0.9988117,0.00003607125,0.0001313206,0.0005695627,0.00004739705,0.0004039653],"domain_scores_gemma":[0.9990375,0.0001560323,0.00009105329,0.0004758211,0.00006602769,0.0001735649],"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":[0.00001325949,0.00002227664,0.0001419298,0.000005408408,0.0000243106,0.00002143208,0.0003998982,0.005026475,0.00002941948,0.2432811,0.0007529424,0.7502816],"study_design_scores_gemma":[0.0009864754,0.00007842392,0.00004047159,0.00006087304,0.00001259577,0.000003120723,0.00005348622,0.9693931,0.00005422105,0.02594836,0.003173888,0.0001949536],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005434868,0.00003473697,0.9926689,0.0004857356,0.0006143529,0.0002608025,0.000001751292,0.0001830363,0.0003158662],"genre_scores_gemma":[0.9197095,0.00002235835,0.07347507,0.0001177452,0.0002551641,0.000001607739,9.088887e-7,0.00001253818,0.006405078],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9643667,"threshold_uncertainty_score":0.4674817,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1343603456892092,"score_gpt":0.2081793152473785,"score_spread":0.07381896955816938,"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."}}