{"id":"W3206557162","doi":"","title":"PRIMER: Pyramid-based Masked Sentence Pre-training for Multi-document Summarization.","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Automatic summarization; Computer science; Sentence; Pyramid (geometry); Artificial intelligence; Salient; Natural language processing; Code (set theory); Multi-document summarization; Focus (optics); Information retrieval; Set (abstract data type)","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003375096,0.000361589,0.0003909628,0.0002222574,0.0002152047,0.0002942715,0.001806271,0.0002759593,0.0000178469],"category_scores_gemma":[0.000109632,0.0004542463,0.000288158,0.0004238051,0.00007766435,0.0004391581,0.00153979,0.0003958541,0.000007049372],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000316459,"about_ca_system_score_gemma":0.0007781879,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001874092,"about_ca_topic_score_gemma":0.0000619507,"domain_scores_codex":[0.9972876,0.0001271815,0.0003188647,0.001626828,0.0001524001,0.0004871667],"domain_scores_gemma":[0.9974695,0.0001480144,0.0003162358,0.001538008,0.0003432207,0.0001850155],"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":[0.00002266201,0.0001131473,0.002292717,0.0002098704,0.0001002819,0.0001169592,0.0009171486,0.9459861,0.000194984,0.04722131,0.00002596851,0.002798838],"study_design_scores_gemma":[0.0008592775,0.00002776077,0.0006497546,0.0001987972,0.00005823963,0.000001490064,0.0001633124,0.9935384,0.0007025595,0.003119549,0.0002139361,0.0004669255],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08817776,0.00005538999,0.9096387,0.0001647748,0.000831611,0.0006924594,0.00001153235,0.0003192851,0.0001084771],"genre_scores_gemma":[0.8071569,0.0000277836,0.1912875,0.0001950797,0.00006192893,0.000007187743,0.00006358248,0.00002291795,0.001177151],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7189791,"threshold_uncertainty_score":0.9997909,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1383790392116263,"score_gpt":0.2316414733761355,"score_spread":0.09326243416450919,"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."}}