{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0390881,0.0003208836,0.0005817426,0.004047436,0.0007133893,0.004515921,0.004587859,0.0002305735,0.0001940445],"category_scores_gemma":[0.009496863,0.0002632462,0.0001815894,0.004263098,0.0001222346,0.0003038483,0.01171216,0.0008372081,0.0006781674],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004673303,"about_ca_system_score_gemma":0.001550819,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002570898,"about_ca_topic_score_gemma":0.001530301,"domain_scores_codex":[0.989141,0.0004515942,0.001580005,0.002160264,0.005375248,0.00129187],"domain_scores_gemma":[0.9914802,0.002626064,0.0002070079,0.003591385,0.001757692,0.0003376878],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001124909,0.0004361638,0.0003328473,0.0005772919,0.00003464722,0.00002066572,0.03884143,0.04533011,0.00001369898,0.0008852576,0.4764342,0.4369812],"study_design_scores_gemma":[0.0005531065,0.00002423253,0.0005022965,0.001663792,0.00000552289,1.234699e-7,0.009712203,0.7116014,0.0001974072,0.03217713,0.2431807,0.0003820862],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.153134,0.000796097,0.8161732,0.002875481,0.005572539,0.008591688,0.005705075,0.0002274235,0.006924486],"genre_scores_gemma":[0.4262628,0.00001822073,0.4447694,0.0003492309,0.0007385804,0.002258838,0.005239738,0.00006541603,0.1202978],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6662713,"threshold_uncertainty_score":0.999982,"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."}}