{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007805278,0.0001544273,0.0002710105,0.000627274,0.00005138818,0.0002710643,0.001036351,0.0001444325,0.00002820151],"category_scores_gemma":[0.00002315023,0.0001527229,0.00008822577,0.0006276835,0.00003583497,0.0001702353,0.0007464603,0.0002913878,0.000004046386],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001635635,"about_ca_system_score_gemma":0.0006759756,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001778287,"about_ca_topic_score_gemma":0.0005637123,"domain_scores_codex":[0.9980779,0.00008125002,0.0004697037,0.0006422797,0.0004941947,0.0002347301],"domain_scores_gemma":[0.9988613,0.00004036464,0.0000583721,0.0008890175,0.0001031077,0.00004780925],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001302115,0.0002643014,0.002626237,0.0006014045,0.00009420999,0.0001223779,0.01256953,0.8861039,0.01474159,0.066272,0.0002751192,0.01632801],"study_design_scores_gemma":[0.0001216066,0.000003869749,0.004924508,0.0001369992,0.000005874276,0.000001468627,0.00009744469,0.9919442,0.001265977,0.001339369,0.000009161667,0.0001495451],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3183309,0.00001949663,0.6788122,0.000178838,0.0009949661,0.0002067214,0.00001642909,0.0005633284,0.0008771316],"genre_scores_gemma":[0.7999279,0.000002400689,0.1998449,0.00001685069,0.00001943429,0.00001794418,0.00002649505,0.00001056713,0.0001334195],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4815971,"threshold_uncertainty_score":0.6227859,"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."}}