{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008629402,0.003478996,0.002255099,0.007613175,0.002227291,0.004706799,0.002983724,0.003748261,0.03102829],"category_scores_gemma":[0.04471263,0.0007336396,0.002644793,0.003471192,0.001003005,0.005210612,0.006916066,0.003095211,0.02232661],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002100396,"about_ca_system_score_gemma":0.00533217,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006396195,"about_ca_topic_score_gemma":0.008791321,"domain_scores_codex":[0.9937961,0.002156916,0.0007157979,0.001745701,0.001266036,0.0003193495],"domain_scores_gemma":[0.9813048,0.009384742,0.001337006,0.002871492,0.003781654,0.001320288],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001035849,0.0003269742,0.003450457,0.01007835,0.0004019996,0.0003955753,0.0007609803,0.006153745,0.01008127,0.004219985,0.7096988,0.253396],"study_design_scores_gemma":[0.001053789,0.0008604215,0.01076396,0.002754537,0.0006182893,0.0008502335,0.00125654,0.06685411,0.02241718,0.02458939,0.8676859,0.0002956518],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.03321924,0.01890436,0.1664529,0.01091602,0.003159528,0.005544866,0.6346564,0.1046226,0.02252416],"genre_scores_gemma":[0.0347729,0.002129994,0.2079082,0.001122808,0.0006193417,0.003198279,0.7401225,0.002727493,0.007398486],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03102829,"threshold_uncertainty_score":0.1038,"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."}}