{"id":"W4410519181","doi":"10.1002/tea.70009","title":"A Multimodal Interactive Framework for Science Assessment in the Era of Generative Artificial Intelligence","year":2025,"lang":"en","type":"article","venue":"Journal of Research in Science Teaching","topic":"Educational Games and Gamification","field":"Psychology","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Institute of Education Sciences; University of Georgia; U.S. Department of Education","keywords":"Generative grammar; Science education; Mathematics education; Computer science; Cognitive science; Artificial intelligence; Psychology","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03654504,0.00006101463,0.0001413169,0.001352845,0.0003549893,0.0001742506,0.001366686,0.00003747473,0.00001482502],"category_scores_gemma":[0.005712621,0.00004158431,0.00004509243,0.002682014,0.001492796,0.0005218996,0.00008953475,0.001983912,0.000001109241],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004973467,"about_ca_system_score_gemma":0.002065744,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001924917,"about_ca_topic_score_gemma":0.00003158239,"domain_scores_codex":[0.9971089,0.0006093035,0.0005584479,0.0002535388,0.001097709,0.0003721445],"domain_scores_gemma":[0.9949626,0.003602474,0.0002514144,0.0002423337,0.000890128,0.00005103014],"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":[0.0001018831,0.0005552769,0.005432772,0.00000911161,0.000005272635,0.000003027158,0.04924031,0.0005600459,0.009335008,0.804113,0.00003589493,0.1306084],"study_design_scores_gemma":[0.0001962336,0.0005755742,0.2527513,0.000821078,0.000004563088,0.00001625409,0.2272017,0.01802112,0.004783697,0.495333,0.0001958012,0.0000996152],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.82065,0.00008800645,0.1586308,0.01726305,0.0007519069,0.0003959211,0.000001646011,0.000001437453,0.002217146],"genre_scores_gemma":[0.9462634,0.000007540038,0.05346092,0.0001053377,0.0001065036,0.00003559012,1.630368e-7,0.000002135528,0.00001838323],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.30878,"threshold_uncertainty_score":0.9920796,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1873675951264364,"score_gpt":0.595336900515216,"score_spread":0.4079693053887796,"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."}}