{"id":"W4299149419","doi":"10.1007/978-3-031-01880-0_2","title":"Background: Corpora and Evaluation Methods","year":2011,"lang":"en","type":"book-chapter","venue":"Synthesis lectures on data management","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Automatic summarization; Computer science; Natural language processing; Terminology; Information retrieval; Artificial intelligence; Linguistics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002379318,0.0004737203,0.0004004409,0.0004445633,0.0001369017,0.0004089124,0.003656385,0.0002538744,0.0002888431],"category_scores_gemma":[0.000124236,0.0003956724,0.00005974806,0.0000701397,0.00008786342,0.0005162511,0.003120162,0.0003628314,0.00006113495],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001295256,"about_ca_system_score_gemma":0.00004221613,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001985548,"about_ca_topic_score_gemma":0.00001126103,"domain_scores_codex":[0.9970412,0.0001902231,0.0003368136,0.001425868,0.0007445393,0.0002613688],"domain_scores_gemma":[0.9953991,0.0003090487,0.0003785498,0.003744803,0.00008890377,0.00007960673],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000007361532,0.000009599183,8.083924e-8,0.0000823459,0.0001088959,0.00001902092,0.00002249603,3.373166e-7,0.000007438671,0.3647397,0.007685068,0.6273176],"study_design_scores_gemma":[0.0001003522,0.00006291485,0.00001193836,0.0005138887,0.0004128889,0.00001459751,0.000003601379,0.001778925,0.001089091,0.7600325,0.2352983,0.0006809262],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[6.6852e-7,0.008427779,0.6615658,0.0004655554,0.0003067895,0.0009064041,0.00005276491,0.0005327794,0.3277414],"genre_scores_gemma":[0.000695997,0.0008862881,0.9720316,0.0007532703,0.00009711871,0.00008153114,0.0001520777,0.00006532732,0.02523678],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6266367,"threshold_uncertainty_score":0.9998495,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.129098398023798,"score_gpt":0.3666662195041515,"score_spread":0.2375678214803534,"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."}}