{"id":"W4387116260","doi":"10.1186/s40634-023-00662-4","title":"Accelerated evidence synthesis in orthopaedics—the roles of natural language processing, expert annotation and large language models","year":2023,"lang":"en","type":"article","venue":"Journal of Experimental Orthopaedics","topic":"Topic Modeling","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"Göteborgs Universitet","keywords":"Annotation; Natural language processing; Computer science; Natural language; Data science; Linguistics; Artificial intelligence; Philosophy","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":[],"consensus_categories":[],"category_scores_codex":[0.001101058,0.0001611784,0.0002859865,0.0003035589,0.00009227377,0.0001033091,0.0005851696,0.00006864529,0.000006763676],"category_scores_gemma":[0.0002506769,0.0001168896,0.000103997,0.0006659761,0.00006440129,0.001361345,0.0002458277,0.0002865601,0.000001262528],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006160312,"about_ca_system_score_gemma":0.0001318255,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002873543,"about_ca_topic_score_gemma":0.00003374832,"domain_scores_codex":[0.9980925,0.0001460016,0.0006387515,0.0002246727,0.0006249757,0.0002731314],"domain_scores_gemma":[0.9988635,0.0002321919,0.0004406291,0.0002470156,0.0001324055,0.00008425292],"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":[0.0003121082,0.0006082524,0.01542286,0.0002258495,0.0001216496,0.001263496,0.3365659,0.004036337,0.2642003,0.002258694,0.000665442,0.3743191],"study_design_scores_gemma":[0.0009687831,0.000168991,0.002056298,0.0008676876,0.0000181493,0.0001896394,0.03493085,0.9005048,0.05982817,0.00010177,0.00007959602,0.000285254],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9465921,0.03868207,0.01371589,0.0005432705,0.0002432423,0.0001315028,0.000002392148,0.00004279122,0.00004673459],"genre_scores_gemma":[0.9946406,0.000409851,0.004575025,0.0001946923,0.0001231105,0.00001096609,0.000001157112,0.00001415885,0.00003038432],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8964685,"threshold_uncertainty_score":0.4766619,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03212934952285237,"score_gpt":0.3233232041138951,"score_spread":0.2911938545910428,"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."}}