{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002003751,0.0009029206,0.0006440688,0.002733675,0.0005303998,0.001301071,0.002137698,0.001153357,0.006145231],"category_scores_gemma":[0.007172032,0.0003282311,0.001750769,0.001264291,0.0008482711,0.002715161,0.002196816,0.001495544,0.002456017],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001549683,"about_ca_system_score_gemma":0.002603781,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005794442,"about_ca_topic_score_gemma":0.008045615,"domain_scores_codex":[0.9982505,0.0005856421,0.0001824179,0.0004755131,0.000406375,0.00009940305],"domain_scores_gemma":[0.9982492,0.0006572751,0.0002253772,0.0003414648,0.0004468763,0.00007986053],"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":[0.0007038814,0.0004479949,0.004094181,0.00176965,0.0003598738,0.001715307,0.0006828521,0.114693,0.03004141,0.1162708,0.03864552,0.6905757],"study_design_scores_gemma":[0.00009564694,0.0002282484,0.001432655,0.0001904939,0.0002853446,0.001559161,0.0002412088,0.7317572,0.03090143,0.1803642,0.05285076,0.00009369335],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01738173,0.00159848,0.9586502,0.002664668,0.0001290868,0.0003432766,0.006024635,0.006872017,0.006336036],"genre_scores_gemma":[0.3442543,0.001010192,0.6269826,0.0009921005,0.0002921741,0.000271518,0.01771818,0.0004109823,0.0080679],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006145231,"threshold_uncertainty_score":0.02055788,"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."}}