{"id":"W4393108766","doi":"","title":"CASPER: A framework to assess the difficulty of exercises in terms of semiotic registers","year":2022,"lang":"en","type":"article","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Health, Education, and Physical Culture","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Semiotics; Computer science; Natural language processing; Artificial intelligence; Linguistics; Philosophy","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":[],"consensus_categories":[],"category_scores_codex":[0.002674183,0.0001093376,0.0002358121,0.00007878996,0.0002411673,0.00002383446,0.0007434593,0.00006948077,0.0004101416],"category_scores_gemma":[0.0006091981,0.00008923651,0.00008495842,0.0007828276,0.0001355598,0.00004219033,0.0001295123,0.0003833776,0.00001066028],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000667126,"about_ca_system_score_gemma":0.0001049499,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002519204,"about_ca_topic_score_gemma":0.001469179,"domain_scores_codex":[0.9942735,0.004560751,0.0003900604,0.000293729,0.0002671934,0.0002147979],"domain_scores_gemma":[0.9962264,0.001929757,0.0002525409,0.001196886,0.0003027751,0.00009164324],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00008149749,0.002789851,0.05030674,0.0001525982,0.00005102828,0.000002932472,0.3688592,0.0001641319,0.004145327,0.5481735,0.008687478,0.01658561],"study_design_scores_gemma":[0.001266321,0.000009693051,0.8346315,0.001306428,0.00008345518,0.00002675623,0.0228734,0.0004660916,0.01633625,0.0150207,0.1073061,0.0006732864],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9461923,0.0002241819,0.002537381,0.01419244,0.0002741251,0.0004683766,0.000052804,0.00002845134,0.03602991],"genre_scores_gemma":[0.9930248,0.00003449805,0.00186026,0.0002512003,0.00001476965,0.00008191166,0.00004312923,0.00001392913,0.004675463],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7843247,"threshold_uncertainty_score":0.4490763,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03172446985398993,"score_gpt":0.3075649848004368,"score_spread":0.2758405149464469,"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."}}