{"id":"W4415045096","doi":"10.21203/rs.3.rs-7642675/v1","title":"From Prompt to Pipeline: Large Language Models for Scientific Workflow Development in Bioinformatics","year":2025,"lang":"en","type":"preprint","venue":"Research Square","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Workflow; Subject-matter expert; Domain (mathematical analysis); Pipeline (software); Workflow technology; Workflow engine","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":[],"consensus_categories":[],"category_scores_codex":[0.006475081,0.002167693,0.001090949,0.001207383,0.001200527,0.004342435,0.00346495,0.00214113,0.009497867],"category_scores_gemma":[0.02640985,0.001781928,0.003106644,0.001561485,0.001151189,0.007903129,0.004176901,0.005849201,0.004725655],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001392477,"about_ca_system_score_gemma":0.005365362,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009387627,"about_ca_topic_score_gemma":0.01364395,"domain_scores_codex":[0.9967048,0.00162556,0.0002600105,0.0005073775,0.0007099414,0.0001924255],"domain_scores_gemma":[0.9885775,0.007137186,0.0003244234,0.002471629,0.001039502,0.0004497546],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.002758927,0.0007309558,0.004460428,0.001077387,0.0003796481,0.0005606313,0.001046788,0.2403429,0.007502827,0.1763673,0.1959463,0.368826],"study_design_scores_gemma":[0.000136116,0.00006880867,0.0001381418,0.00004719387,0.00004929427,0.00005310493,0.00006686206,0.8581479,0.005430014,0.1142944,0.02152485,0.00004338479],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003626352,0.0001467909,0.9510889,0.0009138549,0.0001465535,0.0001229841,0.002900126,0.04023828,0.0008161993],"genre_scores_gemma":[0.09107892,0.0005216086,0.8827719,0.000727365,0.0001392652,0.0006681548,0.01004158,0.009698459,0.004352726],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009497867,"threshold_uncertainty_score":0.03424388,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2472947329855588,"score_gpt":0.490562235191545,"score_spread":0.2432675022059861,"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."}}