{"id":"W4292365330","doi":"10.3758/s13421-022-01351-w","title":"Text validation: Overlooking consistency effect discrepancies","year":2022,"lang":"en","type":"article","venue":"Memory & Cognition","topic":"Educational Strategies and Epistemologies","field":"Psychology","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Consistency (knowledge bases); Psychology; Sentence; Reading (process); Comprehension; Cognitive psychology; Reading comprehension; Linguistics; Interpretation (philosophy); Social psychology; Natural language processing; Computer science; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1136171,0.001177183,0.001348069,0.004554792,0.002109388,0.005137081,0.003848641,0.00340523,0.009636356],"category_scores_gemma":[0.6570151,0.001052191,0.001381408,0.003141521,0.004149153,0.01007261,0.005762334,0.004005366,0.001607706],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001628828,"about_ca_system_score_gemma":0.002643323,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001824183,"about_ca_topic_score_gemma":0.002138629,"domain_scores_codex":[0.8827084,0.06603134,0.01250756,0.01496288,0.02261663,0.001173118],"domain_scores_gemma":[0.2307162,0.6283451,0.03012006,0.07894643,0.03049128,0.001380989],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.006000283,0.0008862728,0.1806305,0.005342562,0.003159772,0.002795546,0.05204005,0.004405992,0.02664892,0.1503819,0.0455105,0.5221977],"study_design_scores_gemma":[0.001842417,0.0008173962,0.2149939,0.004214244,0.002877143,0.004254523,0.01453095,0.06663195,0.08019248,0.4968038,0.1122956,0.0005456037],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4972346,0.004212871,0.3722574,0.01862111,0.003781951,0.003222371,0.003238728,0.003535645,0.09389535],"genre_scores_gemma":[0.9230116,0.000252492,0.06646112,0.002878382,0.0005627593,0.0006935266,0.0008773648,0.00141658,0.003846033],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1136171,"threshold_uncertainty_score":0.6008717,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03331642632621365,"score_gpt":0.3172685916776198,"score_spread":0.2839521653514062,"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."}}