{"id":"W4401403374","doi":"10.52041/serj.v23i1.673","title":"CAUSAL LANGUAGE AND STATISTICS INSTRUCTION: EVIDENCE FROM A RANDOMIZED EXPERIMENT","year":2024,"lang":"en","type":"article","venue":"Statistics Education Research Journal","topic":"Statistics Education and Methodologies","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Institute of Education Sciences; York University","keywords":"Mathematics education; Psychology; Statistics; Computer science; Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.005642417,0.0002093652,0.0004297387,0.0005220544,0.0004354776,0.0009938789,0.0002352389,0.00009134144,0.002201976],"category_scores_gemma":[0.03239553,0.0001741343,0.00004925703,0.0003446983,0.000621521,0.0002204534,0.00009625962,0.0009475392,0.0000837949],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003138235,"about_ca_system_score_gemma":0.00255647,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002867138,"about_ca_topic_score_gemma":0.00003278858,"domain_scores_codex":[0.9953731,0.002139098,0.0007044798,0.0003784713,0.0009836179,0.0004212418],"domain_scores_gemma":[0.9731283,0.02510281,0.000160011,0.0002909735,0.0009587566,0.0003591155],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0008583024,0.000107627,0.0000386332,0.0002110364,0.000142258,0.00005555959,0.01600188,7.679459e-7,0.0004989718,0.5223241,0.3617363,0.09802459],"study_design_scores_gemma":[0.004196106,0.00009569957,0.0001776842,0.0006392257,0.0001260766,0.000276536,0.01946862,0.001784461,0.0006661389,0.96504,0.007277454,0.0002520448],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02385119,0.01136139,0.9547355,0.001441092,0.006231925,0.0006628794,0.001029692,0.00009199296,0.0005943439],"genre_scores_gemma":[0.02738922,0.004219959,0.9614155,0.00005929546,0.001256745,0.0001656049,0.00009494504,0.00005010308,0.005348652],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4427159,"threshold_uncertainty_score":0.9987102,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.294198042816408,"score_gpt":0.5727169526890182,"score_spread":0.2785189098726102,"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."}}