{"id":"W4412825323","doi":"10.1007/s10664-025-10705-2","title":"An Empirical Investigation on the Challenges in Scientific Workflow Systems Development","year":2025,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Workflow; Computer science; Systems engineering; Data science; Empirical research; Software engineering; Engineering; Database; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.007899741,0.0001947483,0.0002393546,0.0007561775,0.0003370757,0.001176048,0.001256522,0.0000825198,0.00002508472],"category_scores_gemma":[0.006572052,0.0001263233,0.0000535801,0.00256689,0.00008416171,0.0002214632,0.0003086753,0.0002743975,0.0001869768],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001853939,"about_ca_system_score_gemma":0.0001334809,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005845271,"about_ca_topic_score_gemma":0.00002210856,"domain_scores_codex":[0.9963683,0.0002405241,0.0006848644,0.001013352,0.001293072,0.0003998771],"domain_scores_gemma":[0.9956666,0.002744775,0.00007703342,0.001249808,0.0001221004,0.0001396366],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.00002465191,0.0003207742,0.3253767,0.00007378576,0.00004215171,0.00002938867,0.005487001,0.40649,0.00005564906,0.005476751,0.0892111,0.167412],"study_design_scores_gemma":[0.0002441707,0.00003807347,0.5101786,0.0003663612,0.000005810102,0.000001642977,0.0007306241,0.1709346,0.0001832184,0.002566309,0.3143924,0.0003581026],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8979834,0.0006898112,0.09137697,0.004891791,0.003963945,0.0003937016,0.000003437514,0.0003400252,0.0003568915],"genre_scores_gemma":[0.9950467,0.000002554971,0.003824239,0.000316873,0.00007803885,0.00005333478,0.000009495845,0.00001105751,0.0006577556],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2355554,"threshold_uncertainty_score":0.9998608,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.242921593947304,"score_gpt":0.3787638175672227,"score_spread":0.1358422236199187,"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."}}