{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001101018,0.001748449,0.0007639407,0.0009456236,0.0004288482,0.0007704143,0.002345818,0.001430834,0.0061653],"category_scores_gemma":[0.003722894,0.0005963032,0.001030138,0.0008340362,0.0003914202,0.002106411,0.00124432,0.002341787,0.004936877],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008100032,"about_ca_system_score_gemma":0.001209827,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003968798,"about_ca_topic_score_gemma":0.010276,"domain_scores_codex":[0.9994468,0.0001567051,0.00003471054,0.0002250802,0.00008156864,0.00005512782],"domain_scores_gemma":[0.9989042,0.0005255585,0.00007991727,0.0001913105,0.0002291065,0.00006987767],"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":[0.0004305512,0.000351758,0.001273198,0.0007757626,0.0002410373,0.000248095,0.0004020681,0.09732729,0.03882291,0.00417415,0.06405322,0.7919],"study_design_scores_gemma":[0.00007045023,0.000314362,0.0007284284,0.00004250299,0.00008450794,0.0001281472,0.0001006721,0.9504794,0.02649226,0.007001063,0.01452406,0.00003424562],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01735701,0.001788307,0.9325159,0.000400831,0.0003259431,0.0003942047,0.002687107,0.04179562,0.002735134],"genre_scores_gemma":[0.2172752,0.0008364309,0.7400224,0.0008832861,0.0002645359,0.001164952,0.02198355,0.002236513,0.01533309],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0061653,"threshold_uncertainty_score":0.020625,"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."}}