{"id":"W4361281614","doi":"10.31219/osf.io/wuzy9","title":"Towards Automated Assessment of Scientific Explanations in Turkish using Language Transfer","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Azrieli Foundation","keywords":"Turkish; Computer science; Natural language processing; Formative assessment; Annotation; Artificial intelligence; Hebrew; Transformer; Language model; Transfer of learning; Linguistics; Mathematics education; Engineering; Psychology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005118855,0.001281649,0.0004106594,0.003277695,0.000563138,0.002656369,0.001165218,0.0009952669,0.003086732],"category_scores_gemma":[0.02359469,0.0002965485,0.001030997,0.001217827,0.0006372341,0.003751671,0.002386448,0.001878518,0.002253921],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001468399,"about_ca_system_score_gemma":0.001815493,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003289737,"about_ca_topic_score_gemma":0.004120568,"domain_scores_codex":[0.9947118,0.003498713,0.00023053,0.0008350831,0.0005731527,0.0001507387],"domain_scores_gemma":[0.9821215,0.01154192,0.001320311,0.001531646,0.00316314,0.0003215075],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005097986,0.0004500236,0.01595256,0.0008050044,0.0001617021,0.000462948,0.007947007,0.02804749,0.03355984,0.008695789,0.008011692,0.895396],"study_design_scores_gemma":[0.00009185879,0.0005469999,0.0184321,0.0002355145,0.0002033245,0.000622252,0.007315665,0.8462713,0.070371,0.02884964,0.02686993,0.0001904658],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1653334,0.0005038179,0.8114477,0.0009233906,0.0000849366,0.0006132285,0.001449802,0.01419377,0.005449942],"genre_scores_gemma":[0.6591251,0.0002183448,0.334123,0.0001113061,0.00004028201,0.0003305628,0.00322194,0.0003530433,0.002476385],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005118855,"threshold_uncertainty_score":0.02707148,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09673746239018131,"score_gpt":0.3736425509112112,"score_spread":0.2769050885210299,"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."}}