{"id":"W4385572006","doi":"10.18653/v1/2023.bionlp-1.46","title":"GRASUM at BioLaySumm Task 1: Background Knowledge Grounding for Readable, Relevant, and Factual Biomedical Lay Summaries","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Automatic summarization; Readability; Computer science; Relevance (law); Task (project management); Ground; Information retrieval; Data science; Engineering","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":[],"consensus_categories":[],"category_scores_codex":[0.0007143234,0.000206149,0.0002534083,0.0002477949,0.0004124168,0.00028404,0.0005769623,0.0001392719,0.0000251414],"category_scores_gemma":[0.00012587,0.0001699041,0.00006935903,0.0004834149,0.0001397621,0.0004959667,0.0009135991,0.0001187004,0.0001957642],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009896392,"about_ca_system_score_gemma":0.00008079799,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008338076,"about_ca_topic_score_gemma":0.0002888105,"domain_scores_codex":[0.9980811,0.00005005647,0.0003354766,0.0006823337,0.0002504956,0.0006005596],"domain_scores_gemma":[0.9984114,0.0007711078,0.00006032634,0.0004799362,0.00006620561,0.0002110498],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00006967249,0.0001789702,0.005723222,0.0005332374,0.0001832876,0.00006323938,0.006253103,0.00003512784,0.01262202,0.575471,0.1705288,0.2283383],"study_design_scores_gemma":[0.001511332,0.0002672764,0.002960825,0.00009754166,0.00002901477,0.00005895368,0.0008216675,0.4846293,0.001714339,0.02060488,0.4864197,0.0008851799],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.165599,0.0003167665,0.8282967,0.001747339,0.0011844,0.0003181501,0.00002395089,0.0007307981,0.001782872],"genre_scores_gemma":[0.8707045,0.0002895312,0.09926645,0.0003815141,0.0006144214,0.0001054667,0.0001263543,0.00005838546,0.02845338],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7290303,"threshold_uncertainty_score":0.6928489,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06062182398145231,"score_gpt":0.3027965851717317,"score_spread":0.2421747611902794,"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."}}