{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006952525,0.0000426266,0.00003520424,0.00002309207,0.00003904185,0.0001291124,0.0002233242,0.00001808177,0.000008342565],"category_scores_gemma":[0.00001051445,0.00003802322,0.00001065757,0.00009369944,0.000002762906,0.001570835,0.00002595004,0.00002718618,0.00004211676],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002971658,"about_ca_system_score_gemma":0.000009673486,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001297617,"about_ca_topic_score_gemma":0.000002357181,"domain_scores_codex":[0.9995672,0.000007596759,0.0001277741,0.00008392047,0.0001234041,0.00009011842],"domain_scores_gemma":[0.9997056,0.000005188133,0.0000333299,0.0001984098,0.00002926221,0.00002822128],"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":[0.000001776517,0.00003968521,0.0003955843,0.000005394158,0.000002529336,4.255741e-7,0.0009016158,0.002363434,0.001064827,0.4254541,0.007270654,0.5624999],"study_design_scores_gemma":[0.0002085108,0.00001827031,0.0009942289,0.000004181619,5.701456e-7,5.711854e-7,0.000009692998,0.9698075,0.001517995,0.002336595,0.02501211,0.00008978517],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0007130124,0.00001748933,0.9944648,0.001411259,0.00008508343,0.00006651989,3.693573e-7,0.0001298819,0.003111586],"genre_scores_gemma":[0.7161078,0.000006688759,0.2815818,0.001483847,0.000009375725,0.000002222831,0.00000945056,7.806369e-7,0.0007979926],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9674441,"threshold_uncertainty_score":0.1550542,"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."}}