{"id":"W4416092706","doi":"10.1186/s43058-025-00808-8","title":"Streamlining surgical instrument counting: a matrixed multiple case study on the fidelity of weighing systems in the operating room","year":2025,"lang":"en","type":"article","venue":"Implementation Science Communications","topic":"Patient Safety and Medication Errors","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Phoenix Foundation","keywords":"Workflow; Fidelity; High fidelity; Surgical instrument; Troubleshooting","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.01005081,0.0000977927,0.0001585653,0.0002297673,0.003561619,0.00001895382,0.001262748,0.00003349417,0.00002824563],"category_scores_gemma":[0.001229235,0.00006147023,0.00002999774,0.001575932,0.0002660489,0.0002566923,0.0004148071,0.0004876291,0.000006878033],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002294553,"about_ca_system_score_gemma":0.0007481095,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00541511,"about_ca_topic_score_gemma":0.003417944,"domain_scores_codex":[0.9956371,0.002136074,0.001159524,0.0002198409,0.0005622452,0.0002852156],"domain_scores_gemma":[0.9923842,0.005310645,0.0005653481,0.001368667,0.0003313676,0.00003977126],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"qualitative","study_design_scores_codex":[0.00001224707,0.0004764816,0.8663269,0.00003128339,0.00001848686,0.000005368006,0.09559721,0.0006083665,0.0002133848,0.03428545,0.0001970843,0.002227755],"study_design_scores_gemma":[0.001226158,0.00005877079,0.1386731,0.0001610835,0.0000187974,0.000005651508,0.8460628,0.01105811,0.00002494673,0.00006116975,0.002583758,0.00006558489],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9860306,0.00004145958,0.0006743517,0.00846798,0.0002579051,0.00265588,0.00002719325,0.00002312099,0.001821533],"genre_scores_gemma":[0.9982433,0.00001739379,0.0002631831,0.0004807976,0.00001436763,0.0009373749,0.00002356346,0.00000382191,0.00001625304],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7504656,"threshold_uncertainty_score":0.9977356,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3108365821597748,"score_gpt":0.5780091092360714,"score_spread":0.2671725270762966,"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."}}