{"id":"W4395475952","doi":"10.1016/j.slast.2024.100134","title":"ProtoCode: Leveraging large language models (LLMs) for automated generation of machine-readable PCR protocols from scientific publications","year":2024,"lang":"en","type":"article","venue":"SLAS TECHNOLOGY","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"BC Research (Canada)","funders":"Office of Naval Research Global","keywords":"Standardization; Protocol (science); Computer science; Process (computing); Data science; Software engineering; World Wide Web; Medicine; Programming language; Pathology","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":[0.02194371,0.003411568,0.001594352,0.00581534,0.001574618,0.008461914,0.004255761,0.002586604,0.01016218],"category_scores_gemma":[0.07225137,0.002533574,0.003733001,0.003022958,0.002128662,0.009424116,0.008006076,0.005069078,0.01548411],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002011665,"about_ca_system_score_gemma":0.008025615,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003019651,"about_ca_topic_score_gemma":0.004093562,"domain_scores_codex":[0.9874707,0.004159224,0.002036267,0.002486627,0.003464048,0.0003832064],"domain_scores_gemma":[0.9489395,0.02983225,0.004063567,0.01143232,0.004800443,0.0009318893],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001611021,0.0006396704,0.007152773,0.008099177,0.00120161,0.002135091,0.004269941,0.02232179,0.09024182,0.09894849,0.2553773,0.5080013],"study_design_scores_gemma":[0.0002652718,0.0003447317,0.001780023,0.001248993,0.0003346859,0.001174072,0.0005595572,0.2228736,0.1677992,0.1295487,0.4733963,0.0006749242],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001999808,0.0003249337,0.7735263,0.0008944545,0.000243167,0.0005960921,0.01076582,0.2100433,0.001606312],"genre_scores_gemma":[0.02253719,0.001005334,0.8864348,0.0009507856,0.0001348412,0.001949697,0.05035526,0.03330585,0.003326261],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02194371,"threshold_uncertainty_score":0.1160508,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1871900350361186,"score_gpt":0.4321698548553634,"score_spread":0.2449798198192448,"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."}}