{"id":"W4388708806","doi":"10.2139/ssrn.4633719","title":"Large Language Models:Expectations for Semantics-Driven Systems Engineering","year":2023,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Business Process Modeling and Analysis","field":"Business, Management and Accounting","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Semantics (computer science); Computer science; Programming language; Linguistics; Software engineering; Natural language processing; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001245294,0.0004133134,0.0005626036,0.0008635789,0.0004120325,0.0009573602,0.0006364492,0.0002619546,0.000004460469],"category_scores_gemma":[0.0001560413,0.0004020242,0.0004368147,0.0004809433,0.00001303002,0.0006233851,0.0003455827,0.002096618,0.00006777125],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003785628,"about_ca_system_score_gemma":0.0006535171,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004529386,"about_ca_topic_score_gemma":0.0006531925,"domain_scores_codex":[0.9962865,0.00001007015,0.0005884969,0.0004891547,0.0004088465,0.002217002],"domain_scores_gemma":[0.9984467,0.00004945609,0.0005782642,0.0003373121,0.0005646948,0.00002355505],"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":[0.00001432448,0.00005674889,0.00009251984,0.0009343596,0.0006617758,0.000006884893,0.0002585848,0.8325315,0.00003449849,0.1647482,0.0003189144,0.0003417191],"study_design_scores_gemma":[0.0004207666,0.000005695531,0.000005586468,0.0003159309,0.000519513,0.00001155132,0.005598794,0.8967391,0.000001070094,0.09545354,0.0005059952,0.0004224821],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0359696,0.006321323,0.9536813,0.001302601,0.001575329,0.0004268979,0.00003703932,0.0005519486,0.0001339821],"genre_scores_gemma":[0.9921774,0.000857869,0.000262851,0.00006064444,0.004656395,0.0001385311,0.00032066,0.0001755472,0.001350069],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9562078,"threshold_uncertainty_score":0.9998432,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0205918808441894,"score_gpt":0.2454878682986145,"score_spread":0.2248959874544251,"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."}}