{"id":"W7135995046","doi":"","title":"Overview of the CLEF 2024 SimpleText Task 3: Simplify Scientific Text","year":2024,"lang":"en","type":"article","venue":"UvA-DARE (University of Amsterdam)","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Universiteit van Amsterdam; Agence Nationale de la Recherche; Canadian Institute of Steel Construction","keywords":"Clef; Task (project management); Complement (music); Distortion (music); Text simplification; Information source (mathematics)","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":[0.01301113,0.003691872,0.002125779,0.004847649,0.002511406,0.003352596,0.003178597,0.002961112,0.0380458],"category_scores_gemma":[0.04283768,0.0009309656,0.002182613,0.003043261,0.001438648,0.002767348,0.004601833,0.00379965,0.02495329],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002396837,"about_ca_system_score_gemma":0.005636617,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006636776,"about_ca_topic_score_gemma":0.009046989,"domain_scores_codex":[0.9837785,0.007411724,0.001577244,0.002200748,0.004334687,0.0006970274],"domain_scores_gemma":[0.9737629,0.01228788,0.001345178,0.003298029,0.00751363,0.001792437],"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":[0.0008347352,0.000522346,0.001944079,0.005835502,0.0003251995,0.0006393726,0.0007723684,0.00699219,0.02946579,0.002699018,0.7013612,0.2486082],"study_design_scores_gemma":[0.001757851,0.001199472,0.01508391,0.001035246,0.0002818689,0.002719111,0.0008913658,0.04793879,0.04048832,0.01169177,0.8763745,0.0005377557],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09399302,0.02561155,0.4191505,0.01618274,0.005760137,0.02125177,0.2095516,0.1027802,0.1057185],"genre_scores_gemma":[0.09636247,0.002577821,0.4055702,0.004187268,0.001648163,0.01425655,0.4384714,0.009387948,0.02753812],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0380458,"threshold_uncertainty_score":0.1272759,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03074876376059146,"score_gpt":0.2420102287770144,"score_spread":0.211261465016423,"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."}}