{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004851703,0.0001522941,0.0002473257,0.0002024376,0.0003459839,0.0001708243,0.001882442,0.0001015533,0.0002871383],"category_scores_gemma":[0.0000340427,0.0001376082,0.000288851,0.001458011,0.0004827712,0.0007604176,0.0008307542,0.0002054902,0.0001644452],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009145585,"about_ca_system_score_gemma":0.0002533451,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000205172,"about_ca_topic_score_gemma":0.0002233101,"domain_scores_codex":[0.9983041,0.0001316951,0.000228276,0.0005819757,0.0004961372,0.0002578521],"domain_scores_gemma":[0.9981105,0.000175599,0.0001448765,0.001300013,0.0001812138,0.00008778958],"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":[0.00004066182,0.000373614,0.00205513,0.002090618,0.0002102524,0.00004135976,0.02381148,0.000213809,0.02347592,0.2695541,0.06844164,0.6096914],"study_design_scores_gemma":[0.0006514558,0.0002265588,0.0916285,0.0008540963,0.000149716,0.00004312808,0.002875221,0.03365857,0.002671603,0.0240803,0.8424618,0.0006990287],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7878574,0.003893471,0.1659767,0.02219485,0.004664655,0.001300725,0.0004643472,0.0005343265,0.01311362],"genre_scores_gemma":[0.9936858,0.00003584354,0.001335666,0.00009417487,0.00002463691,3.632867e-7,0.000008585906,0.000008242289,0.004806684],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7740202,"threshold_uncertainty_score":0.5611501,"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."}}