{"id":"W3028930880","doi":"10.48550/arxiv.2003.04642","title":"A Framework for Evaluation of Machine Reading Comprehension Gold\\n Standards","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"Open Text (Canada)","funders":"","keywords":"Computer science; Correctness; Paragraph; Reading comprehension; Artificial intelligence; Natural language processing; Schema (genetic algorithms); Comprehension; Ambiguity; Popularity; Set (abstract data type); Reading (process); Machine learning; Linguistics; Psychology; World Wide Web; Programming language","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.07408886,0.002290312,0.002095939,0.01932776,0.00223936,0.01329821,0.005093295,0.003778133,0.003883698],"category_scores_gemma":[0.1944182,0.001064617,0.002082494,0.009527605,0.0072778,0.01038736,0.007627495,0.003938878,0.001395277],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.006672929,"about_ca_system_score_gemma":0.003954091,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007417099,"about_ca_topic_score_gemma":0.005318985,"domain_scores_codex":[0.90839,0.0607448,0.006208775,0.008753773,0.01460541,0.001297174],"domain_scores_gemma":[0.8530696,0.09687054,0.01121522,0.01864397,0.0188013,0.001399403],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004276119,0.0005609824,0.0212176,0.001118343,0.0004112029,0.0002659762,0.006820904,0.03986228,0.009000366,0.6602158,0.0107966,0.2493024],"study_design_scores_gemma":[0.0001084358,0.0005697377,0.01676359,0.000710515,0.0001449806,0.0003294048,0.003035677,0.344208,0.008801797,0.5978571,0.02720817,0.0002626629],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01808632,0.0007577867,0.968177,0.001281465,0.00007830909,0.0006797568,0.001264375,0.001315295,0.008359605],"genre_scores_gemma":[0.2272702,0.000235243,0.7657512,0.0002441912,0.00009996987,0.002412823,0.00251487,0.0003156,0.001155914],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9259111,"threshold_uncertainty_score":0.391824,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1712827149806367,"score_gpt":0.2700363482322421,"score_spread":0.09875363325160538,"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."}}