{"id":"W4225786031","doi":"10.5964/jnc.6053","title":"When does the story matter? No evidence for the foregrounding hypothesis in math story problems","year":2021,"lang":"en","type":"article","venue":"Journal of Numerical Cognition","topic":"Cognitive and developmental aspects of mathematical skills","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Foregrounding; Replicate; Associative property; Comprehension; Psychology; Multiplication (music); Dissociation (chemistry); Cognitive psychology; Association (psychology); Computer science; Arithmetic; Linguistics; Mathematics; Statistics; Philosophy; Pure mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001641453,0.0001559643,0.0003230967,0.00006210958,0.0002290617,0.00009645867,0.0002352402,0.00005651163,0.0003201683],"category_scores_gemma":[0.006422229,0.00007363175,0.0002241652,0.0001548838,0.00008649933,0.0003295097,0.00007059586,0.0004231244,0.00006836131],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000149802,"about_ca_system_score_gemma":0.0001015843,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001613346,"about_ca_topic_score_gemma":0.000007571095,"domain_scores_codex":[0.9983715,0.0002573965,0.0005116237,0.0001529568,0.0004706784,0.0002358445],"domain_scores_gemma":[0.9851369,0.01373836,0.0004099756,0.000141954,0.0005084162,0.0000643653],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00416896,0.009137169,0.007686723,0.008853563,0.003579188,0.000833065,0.03476194,0.0000502133,0.03643485,0.04443906,0.2063328,0.6437224],"study_design_scores_gemma":[0.001474197,0.0003660117,0.01205993,0.003646005,0.0004710952,0.0004131794,0.004243311,0.0005145216,0.002347322,0.9687527,0.005311374,0.0004002949],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.485516,0.004215579,0.4263034,0.07297197,0.0020373,0.003238448,0.00004755476,0.00008403098,0.005585687],"genre_scores_gemma":[0.9659725,0.0001875793,0.0307364,0.001632719,0.0004280288,0.00009739354,0.000001600994,0.00003860196,0.0009052075],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9243137,"threshold_uncertainty_score":0.7688472,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09864487443674032,"score_gpt":0.3231829828884143,"score_spread":0.224538108451674,"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."}}