{"id":"W2069205250","doi":"10.1177/0963721413495236","title":"Validation in Reading Comprehension","year":2013,"lang":"en","type":"article","venue":"Current Directions in Psychological Science","topic":"Neurobiology of Language and Bilingualism","field":"Neuroscience","cited_by":113,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"","keywords":"Comprehension; Meaning (existential); Reading comprehension; Sentence; Consistency (knowledge bases); Psychology; Computer science; Representation (politics); Natural language processing; Task (project management); Reading (process); Linguistics; Cognitive psychology; Artificial intelligence","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":[],"consensus_categories":[],"category_scores_codex":[0.0003967435,0.00009723139,0.000112343,0.0003527175,0.0001780694,0.00006663832,0.0003781181,0.00004985286,0.0001949148],"category_scores_gemma":[0.001010999,0.00007360124,0.00002741514,0.001955636,0.0005654823,0.0003779253,0.00008586347,0.0003078806,0.0002205654],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000643571,"about_ca_system_score_gemma":0.00001188391,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003677256,"about_ca_topic_score_gemma":0.000004946644,"domain_scores_codex":[0.9983734,0.0001607993,0.0002464631,0.0006734392,0.0001870543,0.0003588572],"domain_scores_gemma":[0.999414,0.0002121007,0.00005258708,0.0002216924,0.00002952194,0.00007006557],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.000004743402,0.0003957067,0.009973365,0.000002212217,8.221787e-8,0.00002311,0.000181866,0.00002760896,0.8953897,0.0005591553,0.0001676534,0.09327477],"study_design_scores_gemma":[0.001448445,0.0003538019,0.6451118,0.0002324794,0.000004007137,0.0005399548,0.0002580612,0.002409305,0.3175985,0.02326352,0.00791242,0.000867645],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9922577,0.00005756122,0.00003458138,0.0003194559,0.001600585,0.0002638754,8.66043e-7,0.00008363952,0.005381769],"genre_scores_gemma":[0.9993173,0.0001288531,0.0001446075,0.0002823875,0.00003824233,0.00004584377,7.65344e-7,0.000002909574,0.0000390854],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6351385,"threshold_uncertainty_score":0.3001372,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09552312748834672,"score_gpt":0.4241243838134473,"score_spread":0.3286012563251006,"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."}}