{"id":"W4404781320","doi":"10.18653/v1/2024.tsar-1.5","title":"Cochrane-auto: An Aligned Dataset for the Simplification of Biomedical Abstracts","year":2024,"lang":"en","type":"article","venue":"","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Universiteit van Amsterdam; Canadian Institute of Steel Construction","keywords":"Computer science; Information retrieval; Data science","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":[0.002942526,0.001851899,0.0008651674,0.007829586,0.001181719,0.001504431,0.002022012,0.00235419,0.01241439],"category_scores_gemma":[0.02082842,0.0006732005,0.001201697,0.003913758,0.0006049561,0.002356327,0.002983813,0.001891242,0.01023089],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001093683,"about_ca_system_score_gemma":0.003376643,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00697143,"about_ca_topic_score_gemma":0.01772934,"domain_scores_codex":[0.9968851,0.0008835563,0.000643483,0.0007617879,0.0007222326,0.0001038526],"domain_scores_gemma":[0.9888045,0.005939676,0.0009502018,0.001820025,0.001862423,0.0006232381],"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":[0.0009018012,0.0005095323,0.005608863,0.009633359,0.0003327302,0.001351635,0.001118815,0.003215353,0.01767896,0.003258278,0.8530754,0.1033153],"study_design_scores_gemma":[0.0009939155,0.0003092832,0.01974124,0.0007894684,0.0002896691,0.00167299,0.0009280095,0.02410732,0.02247689,0.005117924,0.9233075,0.0002657985],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.02724431,0.002966778,0.02155839,0.00122925,0.0006567048,0.001172313,0.9156116,0.02232393,0.007236744],"genre_scores_gemma":[0.01273956,0.0003804594,0.03892019,0.0002243174,0.00008496657,0.001086419,0.9442421,0.0006779228,0.001644175],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.01241439,"threshold_uncertainty_score":0.04153031,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03063519998642854,"score_gpt":0.3629747871951487,"score_spread":0.3323395872087201,"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."}}