{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001410709,0.0001897606,0.0002775646,0.00006968111,0.00005321685,0.0000675867,0.0007462888,0.0002066821,0.000007339168],"category_scores_gemma":[0.00001447954,0.0002345825,0.00006537964,0.0001926414,0.00009390338,0.0004709271,0.001444336,0.0002534151,0.000009466196],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002040442,"about_ca_system_score_gemma":0.0001177035,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006610184,"about_ca_topic_score_gemma":0.00004405777,"domain_scores_codex":[0.998686,0.00009142246,0.0001833559,0.0007463184,0.0000985642,0.0001943783],"domain_scores_gemma":[0.9988441,0.00006863887,0.0002876781,0.0005907078,0.000122494,0.00008640606],"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":[0.00008996638,0.0002141432,0.1913713,0.0002913619,0.0003035819,0.0001562183,0.0007989114,0.406352,0.00007548775,0.3623618,0.0003258581,0.03765937],"study_design_scores_gemma":[0.0007843444,0.00004799657,0.003509341,0.0001600415,0.00004395649,0.000003653591,0.0001646697,0.9799104,0.0002064056,0.01479954,0.00006864705,0.0003010129],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3066413,0.00009221609,0.6916148,0.00002003161,0.0002708379,0.0001581228,0.00001217781,0.00003935403,0.001151168],"genre_scores_gemma":[0.9987515,0.00006881247,0.0007172493,0.00004143428,0.00001007351,2.515301e-7,0.00001611749,0.000006299016,0.0003882509],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6921102,"threshold_uncertainty_score":0.9565995,"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."}}