{"id":"W2156229087","doi":"10.1109/icdm.2009.107","title":"Multi-document Summarization by Information Distance","year":2009,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Automatic summarization; Computer science; Multi-document summarization; Information retrieval; Set (abstract data type); The Internet; Document clustering; Cluster (spacecraft); Data mining; Artificial intelligence; Cluster analysis; World Wide Web","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":[0.001714619,0.001535751,0.001908586,0.008087994,0.000793807,0.002366136,0.001321505,0.0009455484,0.002211913],"category_scores_gemma":[0.006219898,0.0005079149,0.001046539,0.006387465,0.0004904353,0.003673636,0.001310532,0.00115268,0.001998288],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009325427,"about_ca_system_score_gemma":0.000809622,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001886708,"about_ca_topic_score_gemma":0.002511596,"domain_scores_codex":[0.9976639,0.0005813959,0.0002567086,0.0006291154,0.000774277,0.00009473981],"domain_scores_gemma":[0.996711,0.001198735,0.0004897419,0.0005598311,0.0009461238,0.00009453711],"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":[0.0001829003,0.0000807253,0.0008749093,0.0004821721,0.0002109295,0.00009096233,0.0002452444,0.03770864,0.01195282,0.006379159,0.008608325,0.9331833],"study_design_scores_gemma":[0.0001373619,0.0008164187,0.004496397,0.0001249763,0.0004903198,0.0006134675,0.0004296986,0.8424919,0.04503593,0.05630921,0.04884161,0.0002127872],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01298298,0.003846173,0.9768667,0.0002319882,0.0001555237,0.0001922914,0.0006151547,0.003583904,0.001525396],"genre_scores_gemma":[0.1701876,0.002307148,0.8154751,0.0001122871,0.000496531,0.0003293295,0.004665599,0.0005903854,0.005835996],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008087994,"threshold_uncertainty_score":0.009067893,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00811618052685527,"score_gpt":0.2271488213773083,"score_spread":0.219032640850453,"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."}}