{"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004115581,0.0001197483,0.0001432087,0.00007068313,0.0006078614,0.00004483397,0.000118894,0.00003728325,0.01099573],"category_scores_gemma":[0.00006835304,0.0001188937,0.00008668203,0.0001753964,0.00008728988,0.0001026917,0.00006771633,0.00017665,0.000305385],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007292214,"about_ca_system_score_gemma":0.00004719695,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001755231,"about_ca_topic_score_gemma":0.00000887753,"domain_scores_codex":[0.9987434,0.0003409502,0.0002051417,0.0002738065,0.0002240977,0.0002126192],"domain_scores_gemma":[0.9992726,0.0003242671,0.0001126288,0.0002038397,0.00005231309,0.00003430957],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.003057154,0.003471362,0.07669713,0.0008341152,0.001800774,0.000724639,0.03682458,0.001119616,0.03634249,0.4192581,0.2790113,0.1408587],"study_design_scores_gemma":[0.005022003,0.003321439,0.6633814,0.0001229326,0.0007142917,0.00144037,0.1274704,0.00005864894,0.00623535,0.04028982,0.1500608,0.001882519],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7625421,0.0003886822,0.00002467732,0.0008202066,0.001732232,0.000241619,0.00003552693,0.0001149977,0.2341],"genre_scores_gemma":[0.9930144,0.000004401974,0.0000421631,0.0003915607,0.0002533834,0.0004791205,0.0002603648,0.00001465201,0.005539948],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5866842,"threshold_uncertainty_score":0.9899083,"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."}}