{"id":"W6891583109","doi":"10.48448/fchk-0m80","title":"Medical Knowledge-enriched Textual Entailment Framework","year":2020,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Textual entailment; Context (archaeology); Benchmark (surveying); Logical consequence; Knowledge representation and reasoning; Representation (politics); Unified Medical Language System; Language understanding","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":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001803597,0.0007742913,0.0008195492,0.001225048,0.0003069443,0.0002616788,0.003813977,0.0009350855,0.03900807],"category_scores_gemma":[0.003227174,0.0006749835,0.0001554375,0.003980513,0.004086211,0.0001697542,0.001481769,0.001757628,0.06809357],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007067584,"about_ca_system_score_gemma":0.004412772,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000163895,"about_ca_topic_score_gemma":0.0005380647,"domain_scores_codex":[0.9916776,0.0001784355,0.0006824635,0.00185748,0.004283552,0.001320427],"domain_scores_gemma":[0.9962365,0.0002890662,0.0004577341,0.001215583,0.0001606773,0.001640444],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001344744,0.0004445785,0.0001173125,0.00006110193,0.00007054626,0.00009046866,0.0004512624,0.000003063979,0.0004838916,0.04081837,0.9409556,0.0164904],"study_design_scores_gemma":[0.0005913756,0.0001761506,0.00005672854,0.0005345758,0.00007451892,0.00002918628,0.000452582,0.006874076,0.00008476272,0.001533618,0.9886609,0.0009315205],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.00002530449,0.001984308,0.01278071,0.002228633,0.002248107,0.0008605628,0.0001728932,0.001982844,0.9777166],"genre_scores_gemma":[0.08745094,0.0005267666,0.09933207,0.00694924,0.01408693,0.0002213799,0.0005888051,0.00562688,0.785217],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.1924997,"threshold_uncertainty_score":0.9995701,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02550419955291692,"score_gpt":0.3404935713699894,"score_spread":0.3149893718170725,"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."}}