{"id":"W4401042103","doi":"10.18653/v1/2024.semeval-1.79","title":"TLDR at SemEval-2024 Task 2: T5-generated clinical-Language summaries for DeBERTa Report Analysis","year":2024,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"SemEval; Computer science; Natural language processing; Task (project management); Artificial intelligence; Information retrieval; Engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01104716,0.001848846,0.0008511425,0.001710912,0.0007078288,0.002566109,0.002521741,0.002563212,0.02306193],"category_scores_gemma":[0.069311,0.0006773253,0.001720332,0.0008045688,0.000712316,0.003169114,0.004236081,0.003349223,0.01061905],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001286386,"about_ca_system_score_gemma":0.003360769,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001995236,"about_ca_topic_score_gemma":0.00273442,"domain_scores_codex":[0.9906221,0.005267123,0.0008553514,0.001695409,0.001362357,0.0001976849],"domain_scores_gemma":[0.9448137,0.04313586,0.002145672,0.005351138,0.003761332,0.0007922102],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.004060687,0.0007968007,0.006398741,0.005572938,0.0006498357,0.002480768,0.004334827,0.04353935,0.05751991,0.03088733,0.2413598,0.6023991],"study_design_scores_gemma":[0.001613199,0.001255602,0.004322561,0.0006802721,0.0004502833,0.002611156,0.001603815,0.5391364,0.1332771,0.07230239,0.242389,0.0003582178],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05452581,0.001288919,0.7782688,0.003835593,0.001007188,0.001863104,0.03681052,0.1106582,0.01174185],"genre_scores_gemma":[0.2397445,0.0003871158,0.7084259,0.000942428,0.000317619,0.001241644,0.03969288,0.005075141,0.0041728],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02306193,"threshold_uncertainty_score":0.07714987,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0438955340263462,"score_gpt":0.3581720558475281,"score_spread":0.3142765218211819,"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."}}