{"id":"W3164193251","doi":"10.48550/arxiv.2105.11698","title":"Guiding the Growth: Difficulty-Controllable Question Generation through Step-by-Step Rewriting","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Rewriting; Interpretability; Controllability; Computer science; Task (project management); Inference; Artificial intelligence; Question answering; Rule of inference; Programming language; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00551337,0.001308424,0.000917821,0.001193303,0.0006066129,0.001628857,0.002462724,0.001472993,0.004047704],"category_scores_gemma":[0.03773435,0.0005907177,0.001766079,0.0007486091,0.001268296,0.00337514,0.002909097,0.002232078,0.001618479],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008371901,"about_ca_system_score_gemma":0.001064918,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001878234,"about_ca_topic_score_gemma":0.003326013,"domain_scores_codex":[0.993859,0.0033683,0.0002965064,0.001431076,0.0008212749,0.0002237663],"domain_scores_gemma":[0.9720514,0.02232155,0.0007397928,0.002982804,0.001542,0.0003624748],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0007759152,0.0008934,0.01486622,0.001794962,0.0003384132,0.001640443,0.006795608,0.13283,0.0800491,0.0791662,0.02368477,0.6571651],"study_design_scores_gemma":[0.0001320952,0.0001851238,0.001425795,0.00008877266,0.0001616072,0.0004332564,0.000514279,0.8442634,0.02940097,0.1037574,0.01957468,0.00006257145],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03744123,0.0005094103,0.9534749,0.0006510047,0.00006425688,0.0004567165,0.000555252,0.004507604,0.002339719],"genre_scores_gemma":[0.2940667,0.0002206568,0.6987284,0.0003814959,0.00007660143,0.0003905114,0.002417224,0.0009522013,0.0027663],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00551337,"threshold_uncertainty_score":0.02915782,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09930973333867954,"score_gpt":0.2001857070874032,"score_spread":0.1008759737487236,"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."}}