{"id":"W2950905275","doi":"10.48550/arxiv.1706.06542","title":"Extract with Order for Coherent Multi-Document Summarization","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Lethbridge","funders":"","keywords":"Automatic summarization; Readability; Coherence (philosophical gambling strategy); Computer science; Rank (graph theory); Natural language processing; Key (lock); Selection (genetic algorithm); Sentence; Artificial intelligence; Information retrieval; Mathematics","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":[0.0002000453,0.0003436435,0.0003717846,0.0002330438,0.0002965116,0.0002672644,0.002158992,0.000217182,0.00001260066],"category_scores_gemma":[0.00005119156,0.0003418504,0.0001721116,0.0002538254,0.0001031126,0.0007451307,0.001221027,0.0003157875,0.00001308282],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002815101,"about_ca_system_score_gemma":0.0002084229,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001023032,"about_ca_topic_score_gemma":0.0002490196,"domain_scores_codex":[0.9981412,0.00005729459,0.0001879171,0.001180533,0.000111844,0.0003212602],"domain_scores_gemma":[0.9968162,0.00007332009,0.0005759395,0.001945511,0.0004696231,0.0001193906],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002428271,0.0008601596,0.01276969,0.0003944445,0.001068697,0.0004194786,0.0004600129,0.4411899,0.000327761,0.5008364,0.001095077,0.04033554],"study_design_scores_gemma":[0.001084275,0.0001475286,0.0009365063,0.0001848484,0.0002171534,0.000002489382,0.00002074025,0.9109704,0.001141869,0.08122306,0.003238246,0.0008328992],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005610654,0.00003497873,0.992394,0.00008657783,0.0001484681,0.0008116193,0.00001021369,0.000402624,0.0005008238],"genre_scores_gemma":[0.7719092,0.0001183214,0.2241416,0.000035214,0.00003592969,0.00001193686,0.00005212462,0.00002525454,0.003670412],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7682524,"threshold_uncertainty_score":0.9999034,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08428641476666028,"score_gpt":0.2399853855796845,"score_spread":0.1556989708130242,"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."}}