Empagliflozin in heart failure with a preserved ejection fraction
Open accessAbstract
BACKGROUND: Sodium-glucose cotransporter 2 inhibitors reduce the risk of hospitalization for heart failure in patients with heart failure and a reduced ejection fraction, but their effects in patients with heart failure and a preserved ejection fraction are uncertain. METHODS: In this double-blind trial, we randomly assigned 5988 patients with class II-IV heart failure and an ejection fraction of more than 40% to receive empagliflozin (10 mg once daily) or placebo, in addition to usual therapy. The primary outcome was a composite of cardiovascular death or hospitalization for heart failure. RESULTS: Over a median of 26.2 months, a primary outcome event occurred in 415 of 2997 patients (13.8%) in the empagliflozin group and in 511 of 2991 patients (17.1%) in the placebo group (hazard ratio, 0.79; 95% confidence interval [CI], 0.69 to 0.90; P<0.001). This effect was mainly related to a lower risk of hospitalization for heart failure in the empagliflozin group. The effects of empagliflozin appeared consistent in patients with or without diabetes. The total number of hospitalizations for heart failure was lower in the empagliflozin group than in the placebo group (407 with empagliflozin and 541 with placebo; hazard ratio, 0.73; 95% CI, 0.61 to 0.88; P<0.001). Uncomplicated genital and urinary tract infections and hypotension were reported more frequently with empagliflozin. CONCLUSIONS: Empagliflozin reduced the combined risk of cardiovascular death or hospitalization for heart failure in patients with heart failure and a preserved ejection fraction, regardless of the presence or absence of diabetes. (Funded by Boehringer Ingelheim and Eli Lilly; EMPEROR-Preserved ClinicalTrials.gov number, NCT03057951).
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
SGLT2 inhibitors are safe and effective at eGFR levels of >20 mL/min/1.73m2.
“Subgroup analyses from DAPA-CKD (117) and analyses from the EMPEROR heart failure trials suggest that SGLT2 inhibitors are safe and effective at eGFR levels of >20 mL/min/1.73m 2 .”
From 11. Chronic Kidney Disease and Risk Management: Standards of Care in Diabetes—2025 (2025) · cites this paper as [118]
The Primary Outcome and Safety sections report that empagliflozin improved heart-failure outcomes and give overall adverse-event results. The trial analyzed kidney-function subgroups at an eGFR cutoff of 60 mL/min/1.73 m², but our copy does not establish efficacy or safety specifically down to >20 mL/min/1.73 m². (LLM, conf=0.84)
Experimental — accuracy not yet measuredThe EMPEROR-Reduced and EMPEROR-Preserved trials allowed enrollment of patients with an eGFR as low as 20 ml/min per 1.73 m2.
“The EMPEROR-Reduced 101 and EMPEROR-Preserved 102 trials, although not an exclusive CKD population, did allow enrollment of patients with an eGFR as low as 20 ml/min per 1.73 m 2.”
From KDIGO 2022 Clinical Practice Guideline for Diabetes Management in Chronic Kidney Disease (2022) · cites this paper as [102]
The Patients section identifies this as the EMPEROR-Preserved heart-failure trial, and Patient Characteristics and Randomization reports that about half of participants had an eGFR below 60 ml/min per 1.73 m². Our copy does not state that enrollment was allowed down to 20 ml/min per 1.73 m²; the Patients section refers readers to a supplementary appendix for the detailed eligibility criteria. The EMPEROR-Reduced trial is attached to a separate citation in the citing sentence. (LLM, conf=0.82)
Experimental — accuracy not yet measuredIn EMPEROR-Preserved and EMPEROR-Reduced, efficacy was seen at eGFR >20 mL/min/1.73m2 in people with heart failure.
“enrollment criteria included eGFR >60 mL/min/1.73m 2 , but efficacy was seen at eGFR >20 mL/min/1.73m 2 in people with heart failure.”
From 11. Chronic Kidney Disease and Risk Management: Standards of Care in Diabetes—2026 (2026) · cites this paper as [134]
The paper reports that empagliflozin reduced the combined risk of cardiovascular death or heart-failure hospitalization in EMPEROR-Preserved (Abstract, page unavailable), and its Discussion shows benefit in an eGFR subgroup below 60 mL/min/1.73 m². Our copy does not establish efficacy specifically down to an eGFR of 20 or report an eGFR-specific result for EMPEROR-Reduced. The Patient Characteristics section also says nearly half of EMPEROR-Preserved participants had eGFR below 60, rather than describing enrollment as limited to those above 60. (LLM, conf=0.86)
Experimental — accuracy not yet measuredIn EMPEROR-Preserved, the primary outcome of cardiovascular death or hospitalization for heart failure was reduced in adults with NYHA functional class I-IV and chronic HFpEF (LVEF >40%), irrespective of the presence of type 2 diabetes.
“In Empagliflozin Outcome Trial in Patients With Chronic Heart Failure With Preserved Ejection Fraction (EMPEROR-Preserved), the primary outcome of cardiovascular death or hospitalization for heart failure was reduced in adults with NYHA functional class I-IV and chronic HFpEF (LVEF >40%), extending the previously seen benefit in people with heart failure to those with preserved ejection fraction”
From 10. Cardiovascular Disease and Risk Management: Standards of Care in Diabetes—2025 (2025) · cites this paper as [250]
The Discussion reports a lower risk of cardiovascular death or heart-failure hospitalization with empagliflozin in patients with preserved ejection fraction, including those with or without diabetes. The Patients section specifies adults with LVEF >40% but lists NYHA class II–IV as the eligibility criterion, not I–IV. Table 1 records four class I participants; that does not establish the claimed class I–IV study population. (LLM, conf=0.87)
Experimental — accuracy not yet measuredThe SGLT2 inhibitors empagliflozin, canagliflozin, and dapagliflozin reduce the incidence of heart failure and improve heart failure-related outcomes, including hospitalization for heart failure and heart failure-related symptoms, in people with diabetes with preserved or reduced ejection fraction.
“The SGLT2 inhibitors empagliflozin, canagliflozin, and dapagliflozin reduce the incidence of heart failure and improve heart failure–related outcomes, including hospitalization for heart failure and heart failure–related symptoms, in people with diabetes with preserved or reduced ejection fraction (242,247,248,281,286–294).”
From 10. Cardiovascular Disease and Risk Management: Standards of Care in Diabetes—2026 (2026) · cites this paper as [242]
Split into 2 atoms — 0 confirmed, 2 partially supported, 0 disputed, 0 misattributed, 0 unverifiable. Expand the claim to see per-atom verdicts.
Experimental — accuracy not yet measured
In EMPEROR-Preserved, the primary outcome of cardiovascular death or hospitalization for heart failure was reduced in adults with NYHA functional class I-IV and chronic HFpEF (LVEF >40%), irrespective of the presence of type 2 diabetes.
“In Empagliflozin Outcome Trial in Patients With Chronic Heart Failure With Preserved Ejection Fraction (EMPEROR-Preserved), the primary outcome of cardiovascular death or hospitalization for heart failure was reduced in adults with NYHA functional class I–IV and chronic HFpEF (LVEF >40%), extending the previously seen benefit in people with heart failure to those with preserved ejection fraction”
From 10. Cardiovascular Disease and Risk Management: Standards of Care in Diabetes—2026 (2026) · cites this paper as [242]
The Discussion reports a lower risk of cardiovascular death or heart-failure hospitalization with empagliflozin, including in patients with or without diabetes. The Patients section specifies adults with LVEF greater than 40%, but its eligibility criterion was NYHA class II–IV, not I–IV. A table note mentions four class I patients; that does not make class I part of the stated eligibility criterion. (LLM, conf=0.90)
Experimental — accuracy not yet measuredThe EMPEROR trials provided clear evidence of efficacy and safety for empagliflozin among patients with eGFR ≥20 mL/min/1.73 m2 and heart failure.
“and the Empagliflozin Outcome Trial in Patients With Chronic Heart Failure (EMPEROR) trials (which provided clear evidence of efficacy and safety for empagliflozin among patients with eGFR ≥20 mL/min/1.73 m2 and HF) (54,57,58).”
From Diabetes management in chronic kidney disease: a consensus report by the American Diabetes Association (ADA) and Kidney Disease: Improving Global Outcomes (KDIGO) (2022) · cites this paper as [57]
The Discussion reports that EMPEROR-Preserved reduced the risk of cardiovascular death or heart-failure hospitalization and notes a similar pattern of benefit in EMPEROR-Reduced. The Safety section reports adverse events, including more infections and hypotension with empagliflozin. Our copy does not establish the claimed eGFR ≥20 mL/min/1.73 m² threshold or efficacy and safety specifically down to that threshold; this paper directly studies preserved-ejection-fraction heart failure, not both trials. (LLM, conf=0.87)
Experimental — accuracy not yet measuredIn EMPEROR-Preserved, there was no significant interaction by eGFR status (≥60 vs <60 ml/min per 1.73 m2) for the primary cardiovascular outcome.
“there was no signi fi cant interaction by eGFR status ( $ 60 vs. < 60 ml/min per 1.73 m 2 ) for the primary cardiovascular outcome.”
From KDIGO 2022 Clinical Practice Guideline for Diabetes Management in Chronic Kidney Disease (2022) · cites this paper as [102]
In EMPEROR-Preserved, empagliflozin compared to placebo reduced the risk of the primary outcome of cardiovascular death or hospitalization for heart failure by 21% (HR 0.79; 95% CI 0.69-0.90).
“Empagli fl ozin, compared to placebo, reduced the risk of the primary outcome of cardiovascular death or hospitalization for heart failure by 21% (HR: 0.79; 95% CI: 0.69 -0.90).”
From KDIGO 2022 Clinical Practice Guideline for Diabetes Management in Chronic Kidney Disease (2022) · cites this paper as [102]
In EMPEROR-Preserved, the benefit was similar among patients with or without diabetes.
“This bene fi t was again similar among patients with or without diabetes.”
From KDIGO 2022 Clinical Practice Guideline for Diabetes Management in Chronic Kidney Disease (2022) · cites this paper as [102]
SGLT2 inhibitors reduce the incidence of heart failure and improve heart failure-related outcomes, including hospitalization for heart failure and heart failure-related symptoms, in people with diabetes with preserved or reduced ejection fraction.
“SGLT2 inhibitors reduce the incidence of heart failure and improve heart failurerelated outcomes, including hospitalization for heart failure and heart failure-related symptoms, in people with diabetes with preserved or reduced ejection fraction (250,(255)(256)(257)(298)(299)(300)(301)(302)(303)(304)(305)(306).”
From 10. Cardiovascular Disease and Risk Management: Standards of Care in Diabetes—2025 (2025) · cites this paper as [250]
The EMPEROR-Reduced and EMPEROR-Preserved trials allowed enrollment of participants with an eGFR as low as 20 ml/min per 1.73 m2.
“The EMPEROR-Reduced and EMPEROR-Preserved trials, although not exclusive CKD populations, did allow enrollment participants with an eGFR as low as 20 ml/min per 1.73 m 2 .”
From KDIGO 2022 Clinical Practice Guideline for Diabetes Management in Chronic Kidney Disease (2022) · cites this paper as [102]
The Patients section describes EMPEROR-Preserved as a heart-failure trial but refers readers to the Supplementary Appendix for its key eligibility criteria. Searches for an eGFR cutoff of 20 and for EMPEROR-Reduced enrollment criteria found no passage in our copy establishing that either trial allowed enrollment at that level. (LLM, conf=0.76)
Experimental — accuracy not yet measuredFinerenone reduces cardiovascular outcomes and the risk of CKD progression in people with type 2 diabetes and CKD.
“People with type 2 diabetes and CKD should be considered for treatment with finerenone to reduce cardiovascular outcomes and the risk of CKD progression (239–242).”
From 10. Cardiovascular Disease and Risk Management: Standards of Care in Diabetes—2026 (2026) · cites this paper as [242]
The Discussion reports cardiovascular benefits of empagliflozin in patients with heart failure and preserved ejection fraction. Searches for finerenone and CKD progression found no passage addressing finerenone’s effects in people with type 2 diabetes and CKD. (LLM, conf=0.77)
Experimental — accuracy not yet measuredMultiple SGLT2i trials included subsets of participants without diabetes, who appear to have derived similar benefits as those with T2D.
“Multiple SGLT2i trials included subsets of participants without diabetes, who appear to have derived similar benefits as those with T2D, 8,14,18”
In the DELIVER trial, dapagliflozin reduced the primary outcome of worsening heart failure or cardiovascular death by 18%, mainly driven by a reduction in heart failure hospitalization, and this effect was independent of diabetes status.
“Compared with placebo, dapagliflozin reduced the primary outcome, a composite of worsening HF or CV death, by 18%, which was mainly driven by a reduction in hospitalization for HF.This effect was independent of diabetes status.532”
From 2023 ESC guidelines for the management of cardiovascular disease in patients with diabetes. (2023) · cites this paper as [532]
Large placebo-controlled trials have shown that SGLT2 inhibitors reduce the risk of cardiovascular disease, and particularly hospitalisation for heart failure, in patients with type 2 diabetes at high risk of atherosclerotic cardiovascular disease, heart failure, or chronic kidney disease.
“Large placebo-controlled trials have shown that sodium glucose co-transporter-2 (SGLT2) inhibitors reduce the risk of cardiovascular disease, and particularly hospitalisation for heart failure, in patients with type 2 diabetes at high risk of atherosclerotic cardiovascular disease, heart failure, or chronic kidney disease.”
There is good evidence to support the use of SGLT2 inhibitors as a foundational therapy to prevent cardiovascular death or hospitalisation for heart failure in patients with heart failure, irrespective of ejection fraction or history of previous diabetes.
“There is good evidence to support the use of SGLT2 inhibitors as a foundational therapy to prevent cardiovascular death or hospitalisation for heart failure in patients with heart failure, irrespective of ejection fraction or history of previous diabetes.1, 2, 3, 4, 5”
In EMPEROR-Preserved, empagliflozin reduced the primary composite outcome by 21% compared with placebo (HR 0.79).
“Over a median of 26.2 months, there was a 21% reduction (HR 0.79 [95% CI 0.69 -0.90]; P < 0.001) of the primary outcome.”
From 10. Cardiovascular Disease and Risk Management: <i>Standards of Care in Diabetes—2023</i> (2023) · cites this paper as [189]
EMPEROR-Preserved was a randomized double-blinded placebo-controlled trial of 5,988 adults with NYHA class I-IV chronic HFpEF and left ventricular ejection fraction >40%, evaluating empagliflozin 10 mg daily versus placebo on top of standard care.
“EMPEROR-Preserved, a randomized double-blinded placebo-controlled trial of 5,988 adults with NYHA functional class I -IV chronic HFpEF (left ventricular ejection fraction > 40%), evaluated the ef fi cacy of empagli fl ozin 10 mg daily versus placebo on top of standard of care on the primary outcome of composite cardiovascular death or hospitalization for heart failure (189).”
From 10. Cardiovascular Disease and Risk Management: <i>Standards of Care in Diabetes—2023</i> (2023) · cites this paper as [189]
In EMPEROR-Preserved, the effects of empagliflozin were consistent in people with or without diabetes.
“The effects of empagli fl ozin were consistent in people with or without diabetes (189).”
From 10. Cardiovascular Disease and Risk Management: <i>Standards of Care in Diabetes—2023</i> (2023) · cites this paper as [189]
Over the past decade, medications effective in heart failure with reduced ejection fraction have been evaluated in large-scale trials in patients with heart failure with mildly reduced ejection fraction and patients with heart failure with preserved ejection fraction.
“Over the past decade, the use of medications that have been demonstrated to be effective in patients with HF with reduced ejection fraction (angiotensin receptor neprilysin inhibitors, mineralocorticoid receptor antagonists, and sodium-glucose cotransporter 2 [SGLT2] inhibitors) has been evaluated in large-scale trials in patients with HF and mildly reduced ejection fraction and patients with HFpE”
From Effects of Tirzepatide on the Clinical Trajectory of Patients With Heart Failure, Preserved Ejection Fraction, and Obesity (2025) · cites this paper as [4]
The median NT-proBNP in SUMMIT was significantly lower than in the STEP-HFpEF program (median ≈470 pg/mL) and substantially lower than in other large-scale outcome trials in HFpEF (median 900-1400 pg/mL).
“This level was significantly lower than that in the STEP-HFpEF program (median, ≈470 pg/mL)36 and substantially lower than in other large-scale outcome trials in HFpEF (median 900–1400 pg/mL).3–6”
From Effects of Tirzepatide on the Clinical Trajectory of Patients With Heart Failure, Preserved Ejection Fraction, and Obesity (2025) · cites this paper as [4]
In EMPEROR-Preserved and DELIVER, SGLT2 inhibition reduced the risk of cardiovascular death and worsening HF events by 18% to 21% and improved KCCQ-CSS by 1.5 to 2.3 points, with odds ratios for threshold improvements in KCCQ-CSS of 1.1 to 1.2.
“In the EMPEROR-Preserved trial (Empagliflozin Outcome Trial in Patients With Chronic Heart Failure With Preserved Ejection Fraction) and DELIVER trial (Dapagliflozin Evaluation to Improve the Lives of Patients With Preserved Ejection Fraction Heart Failure), SGLT2 inhibition reduced the risk of cardiovascular death and worsening HF events by 18% to 21%4,5 and improved KCCQ-CSS by 1.5 to 2.3 points”
From Effects of Tirzepatide on the Clinical Trajectory of Patients With Heart Failure, Preserved Ejection Fraction, and Obesity (2025) · cites this paper as [4]
EMPEROR-Preserved was the first study to show a significant reduction on a combined hard end point of HF hospitalizations and cardiovascular mortality in patients with HFpEF.
“EMPEROR-Preserved (Empagliflozin Outcome Trial in Patients With Chronic Heart Failure With Preserved Ejection Fraction), evaluating the effects of the sodium glucose co-transporter 2 inhibitor empagliflozin, was the first study to show a significant reduction on a combined “hard” end point of HF hospitalizations and cardiovascular mortality in patients with HFpEF.10”
From The cardioprotective effects of semaglutide exceed those of dietary weight loss in mice with HFpEF (2023) · cites this paper as [10]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
The citation lists haven’t been fetched yet
References 16 · Cited by 4,874
Research works printed but not linked: 1
- [15]15. Butler J, Anker SD, Packer M. Rede- fining heart failure with a reduced ejec- tion fraction. JAMA 2019; 322: 1761-2.
- Authors
- Anker, S. D., Butler, J., Filippatos, G., Ferreira, J. P., Bocchi, E., Böhm, M., Brunner–La Rocca, H.-P., Choi, D.-J., Chopra, V., Chuquiure-Valenzuela, E., Giannetti, N., Gomez-Mesa, J. E., Janssens, S., Januzzi, J. L., Gonzalez-Juanatey, J. R., Merkely, B., Nicholls, S. J., Perrone, S. V., Piña, I. L., Ponikowski, P., Senni, M., Sim, D., Spinar, J., Squire, I., Taddei, S., Tsutsui, H., Verma, S., Vinereanu, D., Zhang, J., Carson, P., Lam, C. S. P., Marx, N., Zeller, C., Sattar, N., Jamal, W., Schnaidt, S., Schnee, J. M., Brueckmann, M., Pocock, S. J., Zannad, F., & Packer, M.
- Affiliations
- Inserm (FR)
- From the Department of Cardiology (CVK) and the Berlin Institute of Health Center for Regenerative Therapies (BCRT), German Center for Cardiovascular Research (DZHK) partner site Berlin, Charité Universitätsmedizin Berlin, Berlin (S.D.A.), Universitätsklinikum des Saarlandes, Homberg (M. Böhm), RWTH Aachen University, Aachen (N.M.), Boehringer Ingelheim Pharma, Biberach (C.Z., S.S.), Boehringer Ingelheim International, Ingelheim (W.J., M. Brueckmann), and the Faculty of Medicine Mannheim, University of Heidelberg, Mannheim (M. Brueckmann) — all in Germany; the University of Mississippi Medical Center, Jackson (J.B.); National and Kapodistrian University of Athens School of Medicine, Athens (G.F.); Université de Lorraine, INSERM, Centre d’Investigations Cliniques Plurithématique 1433, and INSERM Unité 1116, CHRU, F-CRIN INI-CRCT (Cardiovascular and Renal Clinical Trialists) (J.P.F.), and Université de Lorraine, INSERM INI-CRCT, CHRU (F.Z.) — both in Nancy, France; the Cardiovascular Research and Development...
- ORCID
- Anker, Stefan D.
- Butler, Javed
- Filippatos, Gerasimos
- Ferreira, João P.
- Bocchi, Edimar
- Böhm, Michael
- Choi, Dong-Ju
- Chopra, Vijay
- Giannetti, Nadia
- Janssens, Stefan
- Januzzi, James L.
- Nicholls, Stephen J.
- Perrone, Sergio V.
- Piña, Ileana L.
- Ponikowski, Piotr
- Senni, Michele
- Sim, David
- Squire, Iain
- Taddei, Stefano
- Tsutsui, Hiroyuki
- Verma, Subodh
- Zhang, Jian
- Lam, Carolyn Su Ping
- Marx, Nikolaus
- Zeller, Cordula
- Sattar, Naveed
- Jamal, Waheed
- Schnee, Janet M.
- Brueckmann, Martina
- Pocock, Stuart J.
- Zannad, Faiez
- Packer, Milton
- Venue
- New England Journal of Medicine
- Publisher
- Massachusetts Medical Society
- Published
- 2021-10-14
- Volume
- 385
- Issue
- 16
- Pages
- 1451-1461
- ISSN
- 0028-4793 (ISSN-L)
- 1533-4406
- OpenAlex
- W3193297191
- Semantic Scholar
- 08338a7b32a574650a88a27013e04be9acbd9cf7
- Cited by
- 4,874
- References
- 16
- Citations by year
- 2026: 793 · 2025: 968 · 2024: 952 · 2023: 1008 · 2022: 989 · 2021: 156 · 2019: 1 · 2012: 1
- FWCI
- 522.09
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- New England Journal of Medicine (publishedVersion)
- PubMed (publishedVersion)
- LSHTM Research Online (London School of Hygiene and Tropical Medicine) (acceptedVersion)
- Repositorio Institucional UCA (Pontificia Universidad Católica Argentina) (submittedVersion, cc-by-nc-sa)
- HAL (submittedVersion, other-oa)
- CINECA IRIS Institutial research information system (University of Pisa) (submittedVersion)
- BOA (University of Milano-Bicocca) (submittedVersion)
- Research Publications (Maastricht University) (submittedVersion, other-oa)
- Figshare (submittedVersion, cc-by-nd)
- Lirias (KU Leuven) (submittedVersion)
- Site cant be reached (submittedVersion, cc-by)
- RWTH Publications (RWTH Aachen) (submittedVersion)
- PuSH - Publication Server of Helmholtz Zentrum München (submittedVersion, cc-by)
- Radboud Repository (Radboud University) (submittedVersion)
- Research Publications (Maastricht University) (submittedVersion)
- Funders
- Boehringer Ingelheim
- Eli Lilly and Company
- Topics
- Health Sciences › Medicine › Cardiology and Cardiovascular Medicine › Heart Failure Treatment and Management
- Health Sciences › Medicine › Endocrinology, Diabetes and Metabolism › Diabetes Treatment and Management
- Health Sciences › Medicine › Cardiology and Cardiovascular Medicine › Cardiovascular Function and Risk Factors
- Keywords
- empagliflozin, heart failure with preserved ejection fraction, SGLT2 inhibitors, heart failure hospitalization, cardiovascular mortality, diabetes mellitus, hypotension
- MeSH terms
- Sodium-Glucose Transporter 2 Inhibitors, Adult, Benzhydryl Compounds, Cardiovascular Diseases, Chronic Disease, Double-Blind Method, Female, Glucosides, Heart Failure, Hospitalization, Humans, Male, Stroke Volume
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
