{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01894336,0.001289721,0.002564449,0.001731486,0.001621672,0.00891922,0.004170692,0.004341683,0.006701581],"category_scores_gemma":[0.130569,0.001744208,0.002867606,0.001562497,0.006602373,0.02183202,0.003879541,0.008843342,0.002215913],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003258825,"about_ca_system_score_gemma":0.003614765,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00556786,"about_ca_topic_score_gemma":0.003728977,"domain_scores_codex":[0.9870992,0.006804572,0.000608757,0.001220573,0.003749648,0.0005173316],"domain_scores_gemma":[0.8480256,0.1249527,0.002710833,0.01415292,0.007896013,0.002261924],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001845646,0.0001438684,0.001058778,0.000248001,0.00008135109,0.00009123514,0.0005823856,0.04666027,0.0009719988,0.9287452,0.003612047,0.01762045],"study_design_scores_gemma":[0.00004010219,0.00002616799,0.0001013522,0.00004179982,0.00002456507,0.00003235555,0.00008649874,0.1291498,0.0005593258,0.866829,0.00309016,0.00001891589],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01325398,0.0006160766,0.9700307,0.006932809,0.0001812905,0.0001639596,0.0004240163,0.00100513,0.007392094],"genre_scores_gemma":[0.430294,0.001512548,0.5560251,0.002638484,0.0009551647,0.001291962,0.001971545,0.001365237,0.003945981],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01894336,"threshold_uncertainty_score":0.1001833,"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."}}