{"id":"W2097120204","doi":"","title":"Towards Robust Abstractive Multi-Document Summarization: A Caseframe Analysis of Centrality and Domain","year":2013,"lang":"en","type":"article","venue":"Meeting of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Automatic summarization; Centrality; Computer science; Redundancy (engineering); Sentence; Natural language processing; Information retrieval; Domain (mathematical analysis); Artificial intelligence; Abstraction; Multi-document summarization","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":[0.0007165367,0.00008428045,0.0002188145,0.00009425075,0.0001245886,0.00006578765,0.0002668058,0.00005765325,0.000002280509],"category_scores_gemma":[0.003441396,0.00007498434,0.0001235562,0.000380584,0.0000256593,0.00005576037,0.0001265226,0.00006738471,4.100677e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001600274,"about_ca_system_score_gemma":0.00008302229,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003277853,"about_ca_topic_score_gemma":0.00002395716,"domain_scores_codex":[0.9987148,0.00009074327,0.0004642716,0.0001922088,0.0004043157,0.0001336741],"domain_scores_gemma":[0.9967899,0.0007865981,0.0007991745,0.0001690555,0.001420578,0.00003464952],"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":[0.000002512956,0.00005545706,0.04691549,0.00003224802,0.000370927,9.230399e-8,0.0008279551,0.8622157,0.00002814869,0.08913369,0.00004967461,0.0003681038],"study_design_scores_gemma":[0.000257538,0.0000112459,0.1402108,0.00001840662,0.0001366933,1.302402e-7,0.00004619604,0.8291977,0.0001235714,0.02982892,0.00009658014,0.00007215013],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07560828,0.00002220825,0.9226575,0.0005519021,0.0003673323,0.0003216251,0.00005988277,0.00002334051,0.0003879216],"genre_scores_gemma":[0.6911564,8.515854e-7,0.3086889,0.00003868679,0.00004097073,0.000006866563,0.00001950623,0.000003270019,0.00004454197],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6155481,"threshold_uncertainty_score":0.4119921,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02083360009022558,"score_gpt":0.268047448719079,"score_spread":0.2472138486288535,"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."}}