{"id":"W2188891439","doi":"","title":"Summarizing through sense concentration and Contextual Exploration rules: the CHORAL system at TAC 2009","year":2009,"lang":"en","type":"article","venue":"Theory and applications of categories","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Automatic summarization; Computer science; Task (project management); Set (abstract data type); Feature (linguistics); Natural language processing; Word (group theory); Choir; Artificial intelligence; Sense (electronics); Information retrieval; Linguistics; Engineering; Psychology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004273728,0.001163407,0.001140622,0.002095391,0.001520141,0.002378677,0.001910901,0.001362044,0.005758325],"category_scores_gemma":[0.01312624,0.0005657605,0.0005188358,0.00128016,0.0006871045,0.003842641,0.002331714,0.001329651,0.003854992],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008637683,"about_ca_system_score_gemma":0.001392143,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006027609,"about_ca_topic_score_gemma":0.01445706,"domain_scores_codex":[0.9966161,0.001379803,0.0003204888,0.0008584564,0.0006779844,0.0001470987],"domain_scores_gemma":[0.9922111,0.003484407,0.0004194042,0.001582769,0.001761907,0.0005403934],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.003882176,0.0009931518,0.004412954,0.001759686,0.0004373143,0.0009298983,0.006586139,0.01479998,0.0521424,0.003746825,0.1891903,0.7211192],"study_design_scores_gemma":[0.00241594,0.002652097,0.01487878,0.0002083495,0.0006037072,0.0007206329,0.006082025,0.5274605,0.1284984,0.01428715,0.3015819,0.0006105029],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.3458371,0.001737881,0.3221632,0.00305282,0.0009349007,0.001791664,0.01997512,0.2815014,0.02300584],"genre_scores_gemma":[0.4714729,0.0003223809,0.452732,0.0004991012,0.0003618693,0.001093231,0.05147269,0.006576331,0.01546949],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006027609,"threshold_uncertainty_score":0.0226019,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01235884093442323,"score_gpt":0.2606624554211631,"score_spread":0.2483036144867398,"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."}}