{"id":"W6894028799","doi":"10.5281/zenodo.8100419","title":"Evaluating the meaning of answers to reading comprehension questions: A semantics-based approach","year":2012,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Meaning (existential); Reading comprehension; Comprehension; Reading (process); Association (psychology)","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.01002519,0.001250588,0.001249371,0.00903913,0.001301883,0.006328031,0.001845572,0.0026316,0.005397359],"category_scores_gemma":[0.07027462,0.0007465559,0.00156188,0.003211552,0.002767031,0.01043174,0.003912816,0.001675269,0.001041555],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001862353,"about_ca_system_score_gemma":0.001553629,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001726382,"about_ca_topic_score_gemma":0.001692506,"domain_scores_codex":[0.9870517,0.007044218,0.001296437,0.001388943,0.00287,0.0003486773],"domain_scores_gemma":[0.9563534,0.03105275,0.003106708,0.001946738,0.006909039,0.0006314146],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003505527,0.0009744909,0.03754339,0.004367195,0.0008528953,0.001606571,0.02768328,0.01635602,0.07225991,0.1589649,0.01044424,0.6654416],"study_design_scores_gemma":[0.0006797206,0.001608343,0.05945792,0.001117431,0.001506752,0.002127101,0.02132164,0.2268332,0.03664569,0.6207811,0.02755291,0.0003681506],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3567354,0.005155634,0.5944278,0.004111024,0.0003441572,0.001080186,0.002872996,0.002237011,0.03303578],"genre_scores_gemma":[0.850881,0.0006603278,0.1442053,0.0001750703,0.0001439226,0.0003271938,0.002136451,0.0002701975,0.001200526],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01002519,"threshold_uncertainty_score":0.05301887,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1167098047272723,"score_gpt":0.3276732036295565,"score_spread":0.2109633989022842,"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."}}