{"id":"W4288049091","doi":"10.2196/38414","title":"Leveraging Representation Learning for the Construction and Application of a Knowledge Graph for Traditional Chinese Medicine: Framework Development Study","year":2022,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Traditional Chinese Medicine Studies","field":"Medicine","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Guangzhou University; National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence; Machine learning; Inference; Embedding; Knowledge extraction; Natural language processing; Data mining","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":[0.001044094,0.0001490172,0.0003614277,0.0001902935,0.0006569558,0.000005699994,0.0001142134,0.00004801696,0.0000534489],"category_scores_gemma":[0.001360677,0.00009561137,0.00006486294,0.0004207172,0.0003257943,0.00007790422,0.00006975057,0.0004152104,4.844788e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007261839,"about_ca_system_score_gemma":0.0001830621,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005875176,"about_ca_topic_score_gemma":0.000002818282,"domain_scores_codex":[0.9980409,0.00004671725,0.0007669142,0.0001354942,0.0008597563,0.0001502207],"domain_scores_gemma":[0.9967379,0.00250263,0.000293862,0.0001419206,0.0002153805,0.0001083177],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"observational","study_design_scores_codex":[0.00169775,0.002095211,0.2942335,0.003586116,0.001569926,0.000004003015,0.3541696,0.0008337569,0.0001161406,0.02191921,0.007986238,0.3117886],"study_design_scores_gemma":[0.0152556,0.003712288,0.6317149,0.0005047459,0.0005853809,0.0004928409,0.2004008,0.102843,0.00003515877,0.01833197,0.02569783,0.0004254083],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6763436,0.000331983,0.3152218,0.003363601,0.0004257185,0.003920205,0.00001482869,0.00007118455,0.0003070557],"genre_scores_gemma":[0.9857178,0.00002246209,0.00970714,0.0003167276,0.0004585411,0.003493509,0.0002459453,0.00001440789,0.00002348186],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3374814,"threshold_uncertainty_score":0.505284,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04760253371613882,"score_gpt":0.3517121390385153,"score_spread":0.3041096053223765,"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."}}