{"id":"W2144719390","doi":"10.1162/coli_a_00077","title":"Information Status Distinctions and Referring Expressions: An Empirical Study of References to People in News Summaries","year":2011,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Atomic Energy of Canada Limited","keywords":"Automatic summarization; Computer science; Salience (neuroscience); Affect (linguistics); Context (archaeology); Information retrieval; Natural language processing; Artificial intelligence; Linguistics; History","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014131,0.00008126213,0.0001292637,0.0001895111,0.00009654233,0.00006229727,0.0002154262,0.00002968264,0.000003585195],"category_scores_gemma":[0.001084485,0.00007873586,0.000008958368,0.0002536046,0.0000177103,0.0002163698,0.000213714,0.00008921577,0.000002246755],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002583892,"about_ca_system_score_gemma":0.00009072454,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000795785,"about_ca_topic_score_gemma":0.0009320165,"domain_scores_codex":[0.9990447,0.00005901064,0.0003854111,0.000157945,0.0002206366,0.0001322738],"domain_scores_gemma":[0.9991326,0.0001649712,0.00009478484,0.0001946436,0.0003138784,0.00009915228],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00003725066,0.0005678919,0.700582,0.00003536461,0.00001174606,0.000003154374,0.1206624,0.08985949,0.000002712751,0.07577664,0.00007601114,0.01238534],"study_design_scores_gemma":[0.0003294692,0.0002889006,0.693621,0.00003158781,0.000005397898,0.000001165612,0.004269131,0.2816797,0.000004352401,0.01897703,0.0006556744,0.0001365029],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6164947,0.000009350111,0.382322,0.00001620665,0.0002101331,0.0001369818,0.000006802722,0.00003527289,0.0007686004],"genre_scores_gemma":[0.840021,0.000001422821,0.1598575,0.00005540031,0.00003578394,0.00001092892,0.00001317182,0.000002421583,0.000002368032],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2235264,"threshold_uncertainty_score":0.3210755,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09209636236490953,"score_gpt":0.3350728771866981,"score_spread":0.2429765148217886,"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."}}