{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006248263,0.0006824099,0.000987153,0.001339277,0.0008792253,0.00339536,0.001966266,0.002219163,0.01021709],"category_scores_gemma":[0.1018806,0.0009560442,0.0006770971,0.0009086953,0.003412377,0.007743554,0.004326368,0.002436606,0.0007244056],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007381728,"about_ca_system_score_gemma":0.0008410961,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001161335,"about_ca_topic_score_gemma":0.001153395,"domain_scores_codex":[0.9928147,0.001879017,0.0009599604,0.001689011,0.002270186,0.0003870934],"domain_scores_gemma":[0.8237033,0.12414,0.03370699,0.01037057,0.003495267,0.004583795],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.01380579,0.004346527,0.6780681,0.003908006,0.0009115592,0.002316767,0.07295576,0.001792274,0.04584684,0.02228716,0.001680784,0.1520805],"study_design_scores_gemma":[0.0006534447,0.001503715,0.9482032,0.0006684168,0.000475786,0.001939433,0.008869433,0.003904077,0.006809969,0.02181488,0.005031961,0.0001255573],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9909648,0.0006041154,0.001695833,0.0006244972,0.00003506391,0.00003837767,0.0001181889,0.00002458742,0.005894509],"genre_scores_gemma":[0.9971226,0.0003493894,0.00136331,0.0002431495,0.00005156286,0.00005817711,0.0002460658,0.00004626449,0.000519501],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01021709,"threshold_uncertainty_score":0.03417963,"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."}}