{"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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.003902843,0.0001520318,0.000258575,0.001636845,0.0003814111,0.001248269,0.001414122,0.0001341532,0.0001935754],"category_scores_gemma":[0.001131255,0.0001204605,0.00009542909,0.002958088,0.0001888293,0.0005793369,0.0005613648,0.0001465317,0.0001654817],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005422817,"about_ca_system_score_gemma":0.0001782824,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006230674,"about_ca_topic_score_gemma":0.0001491987,"domain_scores_codex":[0.9969106,0.00006924909,0.0007268749,0.001171112,0.0007428079,0.0003793908],"domain_scores_gemma":[0.9972936,0.000265761,0.0002068097,0.001771381,0.0004135918,0.00004887566],"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":[0.00002368451,0.0004094123,0.0007363798,0.0001178893,0.0001010412,0.000007950218,0.001859154,0.005045302,0.05889493,0.3209423,0.471781,0.140081],"study_design_scores_gemma":[0.0002331165,0.00003084455,0.00002367117,0.00004404781,0.000009981853,0.000001751254,0.0002774176,0.7762331,0.01112222,0.06183061,0.1500864,0.0001068023],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06756634,0.0003173882,0.8851048,0.004414296,0.00120755,0.03468487,0.001457657,0.003529585,0.001717555],"genre_scores_gemma":[0.9045075,5.901543e-7,0.04925124,0.00005221175,0.0001073385,0.03500566,0.0006139157,0.00003428841,0.01042722],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8369412,"threshold_uncertainty_score":0.9997885,"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."}}