{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001229813,0.0001926405,0.0003778739,0.0002465763,0.0001392918,0.0004714535,0.000633311,0.0001298864,0.0002740728],"category_scores_gemma":[0.0003004625,0.0001518052,0.000453168,0.001195124,0.00004197504,0.0002995112,0.0004533308,0.0001444352,0.00009545577],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007238249,"about_ca_system_score_gemma":0.0001501099,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003115291,"about_ca_topic_score_gemma":0.001148074,"domain_scores_codex":[0.9974097,0.00007694319,0.0008182637,0.001025147,0.0003094854,0.0003604308],"domain_scores_gemma":[0.9979218,0.0004985809,0.00009145832,0.001218399,0.0001249336,0.0001448519],"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":[0.00008531573,0.0003740471,0.049841,0.0005109386,0.009820612,0.004990556,0.007558059,0.01448117,0.009009851,0.1443736,0.380776,0.3781789],"study_design_scores_gemma":[0.0001298599,0.00003207901,0.0003017602,0.00001568694,0.0003083805,0.00003556331,0.00003193677,0.9460248,0.001347521,0.00080638,0.05071905,0.0002470316],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05583555,0.001028458,0.934684,0.002079858,0.001772002,0.0002386141,0.00001529596,0.0005575771,0.00378868],"genre_scores_gemma":[0.6160018,0.00005313726,0.1663829,0.001098637,0.0006135478,0.00007270114,0.0001480659,0.00003521595,0.215594],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9315436,"threshold_uncertainty_score":0.6190435,"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."}}