{"id":"W4287601596","doi":"10.5281/zenodo.4482922","title":"MeDAL: Medical Abbreviation Disambiguation Dataset for Natural Language Understanding Pretraining","year":2020,"lang":"en","type":"paratext","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Natural language processing; Medal; Artificial intelligence; Natural language; Natural (archaeology); Information retrieval; History","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0006995789,0.0002216984,0.0002380495,0.0001052638,0.0008967887,0.0003241365,0.0008397262,0.0003951829,0.005046264],"category_scores_gemma":[0.003515255,0.0002182113,0.00008880872,0.0002003001,0.0002189586,0.00001158519,0.0007706473,0.000412778,0.001726189],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001045145,"about_ca_system_score_gemma":0.00002264472,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006727304,"about_ca_topic_score_gemma":0.000001230271,"domain_scores_codex":[0.9979763,0.00026628,0.0003133878,0.0006177036,0.0004746245,0.0003517033],"domain_scores_gemma":[0.9990762,0.00005038037,0.0001908843,0.000319876,0.0001562211,0.0002064236],"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":[0.0001210966,0.00003102064,1.793449e-7,0.00021008,0.0000974966,0.000003984024,0.0003985408,0.000004310693,0.003506239,0.00009032438,0.8901412,0.1053955],"study_design_scores_gemma":[0.0006897341,0.0003785693,0.000007382868,0.0001285632,0.00003524545,0.00003622141,0.000790042,0.0009898203,0.0005643778,0.00001726061,0.9961061,0.0002566703],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"dataset","genre_scores_codex":[0.003650789,0.01455142,0.8031784,0.01356332,0.00475317,0.004305664,0.05604233,0.001162845,0.09879202],"genre_scores_gemma":[0.2703372,0.0009456546,0.001076992,0.001141081,0.002390013,6.882763e-7,0.7171349,0.001721178,0.005252282],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8021014,"threshold_uncertainty_score":0.9990511,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07407423310831963,"score_gpt":0.3220944828030508,"score_spread":0.2480202496947312,"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."}}