{"id":"W4327846044","doi":"10.5281/zenodo.7749795","title":"On Codex Prompt Engineering for OCL Generation: An Empirical Study","year":2023,"lang":"en","type":"paratext","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Model-Driven Software Engineering Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Software engineering; Programming language","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":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0009374259,0.0003828589,0.0003596071,0.0006040281,0.001148533,0.001643273,0.003028898,0.0002112491,0.001194328],"category_scores_gemma":[0.0001808958,0.0004202951,0.00009472415,0.0008176568,0.00003758463,0.0003893364,0.001650994,0.0005781366,0.01150062],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003094898,"about_ca_system_score_gemma":0.00001498837,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005536489,"about_ca_topic_score_gemma":2.417832e-7,"domain_scores_codex":[0.9970043,0.0002621421,0.000427512,0.001117475,0.0006509424,0.00053759],"domain_scores_gemma":[0.9975151,0.00005215087,0.0001392499,0.001381002,0.0006734069,0.0002390479],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001475542,0.0002778355,1.781831e-7,0.0001043965,0.00006504999,0.00001635989,0.001017637,0.01357618,0.0003011823,0.005625335,0.9451622,0.03383888],"study_design_scores_gemma":[0.0003000404,0.001149321,0.0000203715,0.00005266954,0.00001040555,0.00002008578,0.00000646634,0.1892278,0.0001868058,0.00003694369,0.8086098,0.0003793675],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0007346561,0.00002659062,0.9886227,0.0002324995,0.0007768159,0.001796646,0.0002911923,0.004573555,0.002945334],"genre_scores_gemma":[0.1584592,0.0004447526,0.5926176,0.001556952,0.01207221,0.0000434955,0.05966914,0.04638902,0.1287476],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3960051,"threshold_uncertainty_score":0.9998249,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08160528777467206,"score_gpt":0.3108684379442106,"score_spread":0.2292631501695385,"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."}}