{"id":"W2974904219","doi":"10.48550/arxiv.1909.08089","title":"Extractive Summarization of Long Documents by Combining Global and Local Context","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Automatic summarization; Context (archaeology); Computer science; Information retrieval; ROUGE; Data science; Artificial intelligence; Natural language processing; History; Archaeology","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":[0.001308722,0.001864975,0.001408677,0.002999003,0.0005147051,0.001757143,0.00154363,0.001181118,0.001680281],"category_scores_gemma":[0.004358792,0.0005242547,0.001070527,0.002642649,0.0004608488,0.003435039,0.001075508,0.001503752,0.001695677],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000711608,"about_ca_system_score_gemma":0.001012198,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0028867,"about_ca_topic_score_gemma":0.00740566,"domain_scores_codex":[0.9991485,0.0001831871,0.00008821061,0.0003251225,0.0002020064,0.00005294133],"domain_scores_gemma":[0.9979729,0.000905605,0.0003265664,0.0002451203,0.0004808596,0.00006898412],"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":[0.0004809397,0.0002048564,0.003391289,0.0008901851,0.0003835359,0.0003042862,0.0005357555,0.08430465,0.02835887,0.005292994,0.01150112,0.8643516],"study_design_scores_gemma":[0.00006397689,0.000428357,0.003523389,0.0001237489,0.0005160412,0.0002522981,0.0001984038,0.9377657,0.0193971,0.01921819,0.01843222,0.00008054908],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03616528,0.008626125,0.9469908,0.0008101133,0.000298911,0.0001745813,0.00120302,0.003564407,0.002166657],"genre_scores_gemma":[0.4671511,0.005700965,0.5025944,0.0006000956,0.001915507,0.0005803533,0.007312436,0.0006808797,0.01346423],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002999003,"threshold_uncertainty_score":0.006921291,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03937128616335209,"score_gpt":0.1951187590560857,"score_spread":0.1557474728927336,"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."}}