{"id":"W4411106689","doi":"10.3389/feduc.2025.1510007","title":"Recall or transfer? How assessment types drive text-marking behavior","year":2025,"lang":"en","type":"article","venue":"Frontiers in Education","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University; Kwantlen Polytechnic University","funders":"Social Sciences and Humanities Research Council of Canada; Kwantlen Polytechnic University","keywords":"Recall; Computer science; Transfer (computing); Artificial intelligence; Natural language processing; Information retrieval; Cognitive psychology; Psychology; Operating system","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":[0.0002654624,0.0001027011,0.0001388508,0.0002647469,0.00009641788,0.0001722159,0.0003562937,0.00006335964,0.000007877242],"category_scores_gemma":[0.00003367795,0.00009281602,0.00003888035,0.0004076554,0.00001479891,0.0002989655,0.00003304073,0.0001838358,0.000003391129],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000363216,"about_ca_system_score_gemma":0.0005051102,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005591778,"about_ca_topic_score_gemma":0.00001605946,"domain_scores_codex":[0.9991183,0.00009794518,0.0001657686,0.000295104,0.0001378893,0.0001850018],"domain_scores_gemma":[0.9995831,0.00003454523,0.00003793683,0.0002383418,0.00007500315,0.0000311107],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001085624,0.000301769,0.1104117,0.00006043651,0.00003082489,0.000005718946,0.002437666,0.0001655448,0.0004094286,0.1481711,0.01486887,0.7231261],"study_design_scores_gemma":[0.0004115944,0.0001378106,0.1633198,0.0008486161,0.0000413877,0.000006436608,0.004987694,0.01206097,0.00178478,0.001987482,0.8139092,0.0005042718],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01973161,0.0004427987,0.9647595,0.001225115,0.008970237,0.0003083881,4.272565e-7,0.00006417108,0.004497747],"genre_scores_gemma":[0.8334268,0.00006067304,0.1228521,0.0001880384,0.0001614275,0.0001740101,0.000004904832,0.000009463562,0.0431225],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8419074,"threshold_uncertainty_score":0.3784927,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01272013718666135,"score_gpt":0.2897447989584398,"score_spread":0.2770246617717784,"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."}}