{"id":"W2151552691","doi":"10.1162/089120102762671963","title":"Generating Indicative-Informative Summaries with SumUM","year":2002,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":140,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Université du Québec à Montréal","funders":"Université de Montréal; McGill University","keywords":"Automatic summarization; Computer science; Identification (biology); Information retrieval; Natural language processing; Process (computing); Artificial intelligence","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001135132,0.0001274499,0.0001239117,0.0000877924,0.000253478,0.0001886457,0.0004075291,0.00003602537,0.00001933667],"category_scores_gemma":[0.000654533,0.0001132733,0.00002388224,0.0002267813,0.0000725369,0.0001199132,0.0001336591,0.0001462152,0.00006835842],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004368013,"about_ca_system_score_gemma":0.00006430297,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005254433,"about_ca_topic_score_gemma":0.00000242781,"domain_scores_codex":[0.998931,0.00002962266,0.0002562515,0.00022612,0.0003588329,0.0001982077],"domain_scores_gemma":[0.998735,0.0002656161,0.0002041632,0.0002167083,0.0005020234,0.00007647874],"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":[0.000001746735,0.00003379204,0.00125175,0.00001529008,0.00002550096,0.00001622082,0.003304446,0.4440913,0.000001146957,0.5429035,0.000948429,0.007406801],"study_design_scores_gemma":[0.0001987581,0.00004074923,0.0004301332,0.0000193807,0.000004171493,0.000008989932,0.00003656173,0.9840606,0.00002149255,0.009939238,0.005083399,0.0001564733],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002850376,0.00009262795,0.9837396,0.000210948,0.0003023953,0.0000890099,0.000008083615,0.0001533783,0.01255365],"genre_scores_gemma":[0.5201121,0.000001819944,0.479193,0.0003360992,0.0002297053,0.000004783177,0.00001347604,0.000005446399,0.0001035348],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5399693,"threshold_uncertainty_score":0.4619151,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02829016747849478,"score_gpt":0.2487386652571547,"score_spread":0.2204484977786599,"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."}}