{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0361639,0.0003175406,0.0002910807,0.002143659,0.002962874,0.005680424,0.001366942,0.00169548,0.004646744],"category_scores_gemma":[0.2470178,0.0004176973,0.000394347,0.003606738,0.003514373,0.01061849,0.002776457,0.003036059,0.0005296473],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003413175,"about_ca_system_score_gemma":0.009685759,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0050341,"about_ca_topic_score_gemma":0.006596909,"domain_scores_codex":[0.9760413,0.01446864,0.001737019,0.001287208,0.005031499,0.001434445],"domain_scores_gemma":[0.4637133,0.4698483,0.02807391,0.009203776,0.02363741,0.005523345],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0008665827,0.003742449,0.7638959,0.0008825165,0.0001169205,0.001322871,0.06639844,0.004268198,0.001416641,0.05990098,0.004404634,0.0927838],"study_design_scores_gemma":[0.0002702055,0.002323076,0.5507079,0.001445091,0.0001857365,0.001309124,0.3117439,0.03712622,0.00371557,0.05235759,0.03866573,0.0001498949],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9811552,0.000285505,0.003408932,0.003029998,0.00002837841,0.0001595804,0.00009892294,0.00001389734,0.01181951],"genre_scores_gemma":[0.9976771,0.0001032635,0.001423316,0.0001532418,0.00001165624,0.00007128185,0.00006397493,0.000007366725,0.0004888496],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9638361,"threshold_uncertainty_score":0.1912553,"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."}}