{"id":"W7154600941","doi":"10.48448/w1m3-4w83","title":"Maybe She’ll Say Yes: How Young Learners Acquire and Apply Knowledge about Inconsistent Causal Relationships from Different Domains","year":2025,"lang":"","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Cognition; Causal reasoning; Probabilistic logic; Causality (physics); Causal model; Causal inference; Knowledge level; Cognitive development","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":["metaepi_narrow","sts","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","sts","research_integrity","insufficient_payload"],"category_scores_codex":[0.004487205,0.002977762,0.002701345,0.004861853,0.004787743,0.003424361,0.003843043,0.001868669,0.002038124],"category_scores_gemma":[0.00271477,0.002791242,0.000527419,0.005269559,0.01628147,0.001556205,0.003454867,0.003740271,0.003944512],"about_ca_system_candidate":true,"about_ca_system_consensus":true,"about_ca_system_score_codex":0.004674914,"about_ca_system_score_gemma":0.009115809,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001989836,"about_ca_topic_score_gemma":0.01995146,"domain_scores_codex":[0.9830697,0.001858574,0.002196943,0.006027361,0.003522528,0.003324892],"domain_scores_gemma":[0.9890935,0.002075193,0.002081016,0.003558274,0.001128483,0.002063463],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001430285,0.01104687,0.3520373,0.003147882,0.006233236,0.0007160212,0.0767822,0.001480436,0.03973321,0.2812645,0.1426583,0.08346978],"study_design_scores_gemma":[0.02164979,0.001935884,0.3500844,0.0198262,0.008676243,0.0003446324,0.113186,0.1257508,0.001738897,0.02337674,0.3136357,0.01979473],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.2246579,0.03542257,0.02565338,0.00757924,0.01741235,0.0137594,0.01036459,0.002585081,0.6625655],"genre_scores_gemma":[0.7909462,0.001468268,0.004819841,0.0002100481,0.001154795,0.0001979886,0.0007443406,0.0008576182,0.1996008],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5662884,"threshold_uncertainty_score":0.9994271,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03009769712222841,"score_gpt":0.2834472329476278,"score_spread":0.2533495358253994,"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."}}