{"id":"W2963185998","doi":"","title":"Plan, Attend, Generate: Planning for Sequence-to-Sequence Models","year":2017,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Topic Modeling","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke; Université de Montréal","funders":"","keywords":"Computer science; Sequence (biology); Plan (archaeology); Task (project management); Baseline (sea); Artificial intelligence; Character (mathematics); Mechanism (biology); Machine learning; Mathematics; Engineering","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004295874,0.0001850893,0.0002123338,0.0001426939,0.001078232,0.003395981,0.001465027,0.00009144203,3.892098e-7],"category_scores_gemma":[0.00009601073,0.0001669647,0.00004216559,0.0001016882,0.00003061372,0.01102571,0.0001868243,0.0001275781,0.00002666492],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008537388,"about_ca_system_score_gemma":0.0001391046,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009985315,"about_ca_topic_score_gemma":0.000001360427,"domain_scores_codex":[0.9983677,0.00002176576,0.0005746704,0.000275497,0.0003743563,0.0003860104],"domain_scores_gemma":[0.9982257,0.00002774889,0.0005521961,0.0007031691,0.0003558512,0.0001352839],"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":[0.0000178311,0.000007675356,0.0003411934,0.0006129072,0.000009470624,0.000005789819,0.006216611,0.8520806,0.001726111,0.02440028,0.0008910384,0.1136905],"study_design_scores_gemma":[0.0002489309,0.00003104343,0.00003881311,0.0001822984,0.000002854393,0.00005213922,0.0001200698,0.99573,0.0004125959,0.0005627722,0.002402504,0.0002160041],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02542496,0.00007626649,0.9702541,0.000892886,0.001124819,0.0005513773,0.00001755564,0.0002760892,0.001381996],"genre_scores_gemma":[0.9729123,0.000001177059,0.02581784,0.0006694534,0.0002141186,0.0001715087,0.0000191313,0.000009358797,0.0001851712],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9474873,"threshold_uncertainty_score":0.9976386,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1943342354376541,"score_gpt":0.3457445669782557,"score_spread":0.1514103315406015,"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."}}