{"id":"W4295005888","doi":"","title":"Semantics Altering Modifications for Evaluating Comprehension in Machine Reading","year":2020,"lang":"en","type":"preprint","venue":"Research Explorer (The University of Manchester)","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Open Text (Canada)","funders":"","keywords":"Computer science; Semantics (computer science); Natural language processing; Artificial intelligence; Process (computing); Sentence; Comprehension; Domain (mathematical analysis); Reading (process); Machine learning; Programming language; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00590866,0.001994865,0.0008273886,0.002112812,0.0004546595,0.002319775,0.001788805,0.002778114,0.003705951],"category_scores_gemma":[0.03319176,0.0004812122,0.0008153023,0.001361695,0.001129764,0.005175901,0.001848349,0.003083216,0.001411609],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001153667,"about_ca_system_score_gemma":0.0008636902,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002438271,"about_ca_topic_score_gemma":0.003971764,"domain_scores_codex":[0.9967557,0.001654605,0.0002707179,0.0006813459,0.0005105839,0.0001271167],"domain_scores_gemma":[0.9820647,0.01301909,0.001157331,0.002128095,0.001272071,0.0003586868],"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":[0.001574417,0.0008211143,0.03298639,0.002236271,0.0008491631,0.000383603,0.001777432,0.2371497,0.06585747,0.004985202,0.009691427,0.6416878],"study_design_scores_gemma":[0.00009259694,0.001235774,0.01752893,0.000127204,0.0002048523,0.0002588336,0.0005481676,0.9033601,0.0591217,0.01309495,0.004321781,0.0001050754],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6065909,0.004935468,0.3548376,0.001356418,0.0003190849,0.0007951361,0.002819995,0.01476446,0.01358091],"genre_scores_gemma":[0.9081848,0.0004794625,0.0857188,0.0001633725,0.00006630925,0.0002630316,0.003081573,0.000337144,0.001705643],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00590866,"threshold_uncertainty_score":0.03124833,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3797729647456968,"score_gpt":0.3952079562685746,"score_spread":0.01543499152287786,"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."}}