{"id":"W2970263339","doi":"10.18653/v1/d19-1298","title":"Extractive Summarization of Long Documents by Combining Global and Local Context","year":2019,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":159,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Huawei Technologies","keywords":"Automatic summarization; Computer science; Context (archaeology); Information retrieval; Multi-document summarization; Geography; 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":[0.0000842028,0.000052221,0.0000872156,0.00001277022,0.00001726263,0.00003993718,0.0001650461,0.00003091545,0.00002210826],"category_scores_gemma":[0.00000610404,0.00004850887,0.00001138356,0.00007171511,0.00001928328,0.0004406233,0.0001267307,0.00003416409,0.00001090049],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002780724,"about_ca_system_score_gemma":0.00001783215,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002904611,"about_ca_topic_score_gemma":0.00001966629,"domain_scores_codex":[0.9994488,0.00002023752,0.0001225638,0.000181616,0.0001333198,0.00009348884],"domain_scores_gemma":[0.9996845,0.00003256276,0.00005376541,0.0001585193,0.00003770662,0.00003293857],"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":[0.00001323765,0.00007110076,0.2380863,0.0000279073,0.00003194458,0.00000299541,0.0005884609,0.0005819089,0.001128502,0.2390932,0.0004123191,0.5199622],"study_design_scores_gemma":[0.001588929,0.0001529269,0.02149315,0.0000622595,0.00000699191,0.00001282765,0.0003933258,0.9630653,0.007130616,0.005402426,0.0004407538,0.0002505287],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2480398,0.0000563525,0.7466421,0.00007072555,0.00009994591,0.00006981858,7.306592e-7,0.00002063927,0.00499996],"genre_scores_gemma":[0.9945297,0.000003233657,0.004981558,0.000117505,0.000003290809,8.559369e-7,0.000001565416,0.000001616319,0.0003606696],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9624833,"threshold_uncertainty_score":0.1978134,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008216913181033503,"score_gpt":0.2435327832202689,"score_spread":0.2353158700392354,"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."}}