{"id":"W4200445293","doi":"10.2196/27386","title":"Benchmarking Effectiveness and Efficiency of Deep Learning Models for Semantic Textual Similarity in the Clinical Domain: Validation Study","year":2021,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Topic Modeling","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"U.S. National Library of Medicine; National Institutes of Health","keywords":"Benchmarking; Computer science; Natural language processing; Similarity (geometry); Artificial intelligence; Deep learning; Domain (mathematical analysis); Semantic similarity; Information retrieval","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00536955,0.00009816136,0.0002728133,0.00006159682,0.0001072762,0.00008021295,0.0004839646,0.0001155422,0.000002722335],"category_scores_gemma":[0.0006121328,0.00007171767,0.00005656359,0.000299258,0.00007224919,0.0003812024,0.0003096614,0.0003936959,4.858287e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001838638,"about_ca_system_score_gemma":0.0001184123,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005076547,"about_ca_topic_score_gemma":0.00001204438,"domain_scores_codex":[0.9976702,0.0004880307,0.0008094165,0.0001615983,0.0006701027,0.0002006438],"domain_scores_gemma":[0.9974257,0.001913219,0.0001759324,0.0003050093,0.0001093265,0.00007078945],"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":[0.00005678671,0.002258022,0.0783889,0.001724201,0.00009098276,0.00006015397,0.1614985,0.04185219,0.00001520627,0.05808993,0.00002026167,0.6559449],"study_design_scores_gemma":[0.001028678,0.0002229529,0.008304825,0.00009320012,0.00000810128,0.00001426865,0.005213098,0.9816245,0.00001921273,0.003368643,0.0000195289,0.00008301243],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4858282,0.00001521487,0.5135683,0.00006692334,0.00005994296,0.000341248,2.07375e-7,0.00001178673,0.0001081679],"genre_scores_gemma":[0.9795503,0.000009894467,0.02019457,0.0001455972,0.00004325932,0.00004949814,0.000003077696,0.000003123547,6.806732e-7],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9397723,"threshold_uncertainty_score":0.2924562,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04756599648023278,"score_gpt":0.3516154646810429,"score_spread":0.3040494682008101,"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."}}