Anti-Inflammatory Effects of GLP-1-Based Therapies beyond Glucose Control
Open accessThe DOI matches its Crossref record; 116 of the 116 references it cites were found in a registry or an index; 35 of the 93 sources its claims cite were checked for support.
Abstract
Glucagon-like peptide-1 (GLP-1) is an incretin hormone mainly secreted from intestinal L cells in response to nutrient ingestion. GLP-1 has beneficial effects for glucose homeostasis by stimulating insulin secretion from pancreatic beta-cells, delaying gastric emptying, decreasing plasma glucagon, reducing food intake, and stimulating glucose disposal. Therefore, GLP-1-based therapies such as GLP-1 receptor agonists and inhibitors of dipeptidyl peptidase-4, which is a GLP-1 inactivating enzyme, have been developed for treatment of type 2 diabetes. In addition to glucose-lowering effects, emerging data suggests that GLP-1-based therapies also show anti-inflammatory effects in chronic inflammatory diseases including type 1 and 2 diabetes, atherosclerosis, neurodegenerative disorders, nonalcoholic steatohepatitis, diabetic nephropathy, asthma, and psoriasis. This review outlines the anti-inflammatory actions of GLP-1-based therapies on diseases associated with chronic inflammation in vivo and in vitro, and their molecular mechanisms of anti-inflammatory action.
Overview
CoChat Summary
## TL;DR
This review argues that GLP-1-based therapies have anti-inflammatory effects beyond glucose lowering, with evidence across diabetes, vascular disease, brain disorders, liver disease, nephropathy, and other inflammatory conditions. It summarizes in vitro, animal, and some human findings showing reductions in inflammatory cytokines, immune-cell infiltration, and related signaling pathways.
## Key findings
- In diabetes, GLP-1-based therapies reduced inflammatory mediators in islets and adipose tissue: liraglutide (100 nM) inhibited palmitate-induced TNF-α, IL-1β, and IL-6 in mouse islets; sitagliptin (100 mg/day) reduced plasma CRP, IL-6, IL-18, secreted phospholipase-A2, soluble ICAM-1, and E-selectin in type 2 diabetes patients, while the inflammatory score and HOMA index for insulin resistance were also significantly reduced.
- In vascular disease, liraglutide reduced adhesion molecules in endothelial cells and exendin-4 reduced atherosclerosis in mice; for example, exendin-4 (50 μg/kg/day) reduced atherosclerosis development and monocyte adhesion in APOE*3-Leiden.CETP mice, and sitagliptin reduced plaque macrophage infiltration and MMP-9 in ApoE−/− mice.
- In neurodegenerative disease models, liraglutide reduced activated microglia and inflammatory responses in Alzheimer’s disease models, and exendin-4 (10 μg/kg) decreased MPTP-induced microglial activation and TNF-α/IL-1β in Parkinson’s disease models.
- In other conditions, liraglutide improved asthma-related inflammation (including lower E-selectin, TNF-α, IL-4, IL-5, and IL-13) and exenatide improved sperm quality in diet-induced obese mice by suppressing testicular TNF-α, MCP-1, and F4/80.
## Methods
- Narrative review of published in vivo and in vitro studies on GLP-1, GLP-1 receptor agonists, and DPP-4 inhibitors across inflammatory diseases.
- Evidence base includes cell models, rodent and other animal models, and selected human studies (for example, patients with type 2 diabetes and nonalcoholic steatohepatitis).
- Main analysis was qualitative synthesis of anti-inflammatory effects and molecular mechanisms, organized by disease area and signaling pathways.
## Limitations
- The paper states that some reported benefits “need to be validated by clinical studies” for asthma, and that the safety of GLP-1-based therapy should be validated by “sufficient further studies” because rare cases of acute pancreatitis and neoplasms have been reported.
- Evident from the text: this is a review, so many conclusions are based on preclinical or small clinical studies rather than a single controlled synthesis or meta-analysis.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures


Verification
Claims the paper makes
26 Valid · 0 Not valid · 23 Not checked · 23 Own results and interpretations
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Inflammation can be a mediator of insulin resistance and beta-cell damage by high glucose, fatty acids, or adipokines released from adipose tissues [37–39].”
§ Anti-Inflammatory Effects of GLP-1-Based Therapies beyond Glucose Control > 2. Diabetes
What the sources say
- Partly supportedcites [37] matched to “Diabetes and beta cell function: from mechanisms to evaluation and clinical implications” (2013) sourceExperimental — accuracy not yet measured
The “Autoimmunity and inflammation” section (page not provided) says high glucose and free fatty acids induce islet inflammation that contributes to beta-cell impairment and apoptosis. The “Adipokines” section says some adipose-derived factors promote inflammation and beta-cell failure. The paper does not establish that inflammation mediates insulin resistance, so that part of the attributed claim is unsupported. (LLM, conf=0.84)
- Partly supportedcites [38] matched to “β-Cell Failure in Type 2 Diabetes: Postulated Mechanisms and Prospects for Prevention and Treatment” (2014) sourceExperimental — accuracy not yet measured
The “Metabolic and Oxidative Stress” passage links glucotoxicity and lipotoxicity to β-cell damage. The “Inflammation” passage describes local islet inflammation in type 2 diabetes and says anti-inflammatory treatment can preserve some β-cell functional mass. Our copy does not establish that inflammation mediates insulin resistance or damage caused by adipose-derived adipokines, and it leaves the origin of islet inflammation unresolved. The indexed passages provide no page numbers. (LLM, conf=0.83)
- Not checked — no full text of the sourcecites [39] matched to “Mechanisms of Pancreatic β-Cell Death in Type 1 and Type 2 Diabetes” (2005) source
plainstates a possible cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“Therefore, suppression of CXCL10 production by exendin-4 could reduce islet inflammation by decreasing cytotoxic T lymphocyte recruitment into the islets in autoimmune type 1 diabetes [48].”
§ Anti-Inflammatory Effects of GLP-1-Based Therapies beyond Glucose Control > 2. Diabetes
What the sources say
- Supportedcites [48] matched to “Anti-inflammatory action of exendin-4 in human islets is enhanced by phosphodiesterase inhibitors: potential therapeutic benefits in diabetic patients” (2010) source
The paper's own Results ("Suppression of IFN-γ-induced CXCR3-binding chemokines by exendin-4 and cyclic AMP in human islets") show exendin-4 suppressing CXCL10 mRNA (~30% with rolipram, modest but significant with exendin-4 alone) and protein (38%), with reduced secretion into the medium, and the Introduction states that "CXCL10 plays an important role in trafficking effector T cells to islets during insulitis in type 1 diabetes" and that "suppression of CXCL10 production in islets could be an important therapeutic approach to reducing insulitis in type 1 diabetes." The citing sentence's hedged inference ("could reduce islet inflammation by decreasing ... T lymphocyte recruitment") reproduces that same reasoning, with "cytotoxic T lymphocyte" standing in for the source's CXCR3-bearing effector/activated T cells and NK cells. The source is in vitro human islets and MIN6 cells, so the type 1 diabetes benefit remains a stated possibility in both documents, not a demonstrated outcome. (LLM, conf=0.85)
hedgedstates a possible cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Expression of the GLP-1 receptor is widely detected in various cells and organs including the kidney, lung, heart, hypothalamus, endothelial cells, neurons, astrocytes, and microglia as well as pancreatic beta-cells [12–17]”
§ Anti-Inflammatory Effects of GLP-1-Based Therapies beyond Glucose Control > 1. Introduction
What the sources say
- Partly supportedcites [12] matched to “Inhibition of Monocyte Adhesion to Endothelial Cells and Attenuation of Atherosclerotic Lesion by a Glucagon-like Peptide-1 Receptor Agonist, Exendin-4” (2010) sourceExperimental — accuracy not yet measured
The Results section (page unavailable) reports GLP-1 receptor expression in lung, pancreatic β-cells, and endothelial cells; the introductory text also refers broadly to neural cells. The paper does not establish receptor expression in the kidney, heart, hypothalamus, astrocytes, or microglia, nor does it identify neurons specifically. Its discussion of GLP-1 effects on the heart is not evidence of receptor expression there. (LLM, conf=0.88)
- Not checked — no full text of the sourcecites [13] matched to “Expression cloning of the pancreatic beta cell receptor for the gluco-incretin hormone glucagon-like peptide 1.” (1992) source
- Not checked — no full text of the sourcecites [14] matched to “The protective roles of GLP-1R signaling in diabetic nephropathy: possible mechanism and therapeutic potential” (2014) source
- Not checked — no full text of the sourcecites [15] matched to “Pulmonary GLP-1 Receptor Increases at Birth and Exogenous GLP-1 Receptor Agonists Augmented Surfactant-Protein Levels in Litters From Normal and Nitrofen-Treated Pregnant Rats” (2013) source
- Not checked — no full text of the sourcecites [16] matched to “Distribution of GLP‐1 Binding Sites in the Rat Brain: Evidence that Exendin‐4 is a Ligand of Brain GLP‐1 Binding Sites” (1995) source
- Not checked — no full text of the sourcecites [17] matched to “Glucagon-like peptide-1 inhibits LPS-induced IL-1β production in cultured rat astrocytes” (2006) source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Thus, GLP-1 therapy may be beneficial for the treatment of chronic inflammatory diseases including nonalcoholic steatohepatitis, atherosclerosis, neurodegenerative disorders, diabetic nephropathy, asthma, and psoriasis [14, 26–32].”
§ Anti-Inflammatory Effects of GLP-1-Based Therapies beyond Glucose Control > 1. Introduction
What the sources say
- Not checked — no full text of the sourcecites [14] matched to “The protective roles of GLP-1R signaling in diabetic nephropathy: possible mechanism and therapeutic potential” (2014) source
- Partly supportedcites [26] matched to “Sitagliptin reduces plaque macrophage content and stabilises arteriosclerotic lesions in Apoe −/− mice” (2012) sourceExperimental — accuracy not yet measured
Vittone et al. (2012) supports only the atherosclerosis element of the list: the Discussion (p. 6) states that sitagliptin 'decreases plaque macrophage content and stabilises arteriosclerotic lesions in Apoe -/- mice, while GLP-1 directly inhibits monocyte migration and macrophage MMP-9 production in vitro', and the same passage notes broadly that 'there is evidence of anti-inflammatory effects of GLP-1 in different tissues'. Our copy makes no claim that GLP-1 therapy is beneficial in nonalcoholic steatohepatitis, diabetic nephropathy or asthma (searched: those terms plus 'chronic inflammatory diseases'); neurodegenerative and psoriatic disease appear only as titles of cited works (refs 25 and 26, References p. 9), not as conditions this paper shows GLP-1 treats. The remaining diseases in the citing list must rest on the other citations in the cluster [14, 26–31]. (LLM, conf=0.78)
- Not checked — no full text of the sourcecites [27] matched to “The role of glial cells in Parkinsonʼs disease” (2001) source
- Not checked — no full text of the sourcecites [28] matched to “Glucagon‐like peptide‐1 preserves non‐alcoholic fatty liver disease through inhibition of the endoplasmic reticulum stress‐associated pathway” (2016) source
- Not checked — no full text of the sourcecites [29] matched to “Mechanisms mediating the diuretic and natriuretic actions of the incretin hormone glucagon-like peptide-1” (2011) source
- Not checked — no full text of the sourcecites [30] matched to “Glucagon like peptide-1 attenuates bleomycin-induced pulmonary fibrosis, involving the inactivation of NF-κB in mice” (2014) source
- Partly supportedcites [31] matched to “Glucagon-like peptide-1 (GLP-1) and the regulation of human invariant natural killer T cells: lessons from obesity, diabetes and psoriasis” (2011) sourceExperimental — accuracy not yet measured
The Conclusions/interpretation and Discussion (pages not provided) suggest therapeutic potential for GLP-1 in inflammatory conditions such as psoriasis, based on improvement observed in patients. The Discussion also mentions cardiovascular and neuroprotective effects, but the paper does not support the full list of proposed treatments, particularly nonalcoholic steatohepatitis, diabetic nephropathy, and asthma. (LLM, conf=0.87)
- Not checked — no full text of the sourcecites [32] matched to “Exendin-4 and GLP-1 decreases induced expression of ICAM-1, VCAM-1 and RAGE in human retinal pigment epithelial cells” (2013) source
hedgedstates a possible cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“emerging data suggest that GLP-1-based therapies also showed anti-inflammatory effects on the liver, vascular system including aorta and vein endothelial cells, brain, kidney, lung, testis, and skin by reducing the production of inflammatory cytokines and infiltration of immune cells in the tissues [17, 21–25].”
§ Anti-Inflammatory Effects of GLP-1-Based Therapies beyond Glucose Control > 1. Introduction
What the sources say
- Not checked — no full text of the sourcecites [17] matched to “Glucagon-like peptide-1 inhibits LPS-induced IL-1β production in cultured rat astrocytes” (2006) source
- Partly supportedcites [21] matched to “Effects of glucagon-like peptide-1 receptor agonists on non-alcoholic fatty liver disease and inflammation” (2014) sourceExperimental — accuracy not yet measured
The GLP-1RAs AND INFLAMMATION section reports anti-inflammatory effects in endothelial cells and reduced inflammatory-cytokine release; the IL-6 and chemokines sections report reductions in the liver, brain, and kidney. The monocytes/macrophages section reports reduced macrophage infiltration in adipose tissue, not across the listed organs. The cited passages do not establish anti-inflammatory effects in the aorta, lung, testis, or skin. Page numbers were not available in our copy. (LLM, conf=0.88)
- Could not verifycites [22] matched to “Anti-proliferative effect of pro-inflammatory cytokines in cultured β cells is associated with extracellular signal-regulated kinase 1/2 pathway inhibition: protective role of glucagon-like peptide -1” (2008) sourceExperimental — accuracy not yet measured
Our copy of Blandino-Rosano et al. (2008) is confined to rat pancreatic islet/β-cell culture: the Abstract and the results section 'GLP-1 has a protective role against anti-proliferative effects of cytokines' show GLP-1 reversing IL-1β/IFN-γ/TNF-α-induced ERK1/2 inactivation and restoring β-cell proliferation, and the Discussion frames this as possible use in early-stage DM1. No passage addresses anti-inflammatory actions of GLP-1-based therapies in liver, aorta/vein endothelium, brain, kidney, lung, testis or skin, nor reduced cytokine production or immune-cell infiltration in those tissues (searched: extrapancreatic tissues/endothelial/kidney/anti-inflammatory in vivo; inflammatory cytokine production and immune infiltration). Since our copy neither states nor contradicts the tissue-level claim, it cannot be verified from this source. (LLM, conf=0.70)
- Partly supportedcites [23] matched to “A long-acting glucagon-like peptide-1 analogue attenuates induction of plasminogen activator inhibitor type-1 and vascular adhesion molecules” (2009) sourceExperimental — accuracy not yet measured
Split into 2 atoms — 0 confirmed, 2 partially supported, 0 disputed, 0 misattributed, 0 unverifiable. Expand the claim to see per-atom verdicts.
- Not checked — no full text of the sourcecites [24] matched to “The type 2 diabetes drug liraglutide reduces chronic inflammation induced by irradiation in the mouse brain” (2013) source
- Partly supportedcites [25] matched to “Sitagliptin Prevents Inflammation and Apoptotic Cell Death in the Kidney of Type 2 Diabetic Animals” (2014) sourceExperimental — accuracy not yet measured
Split into 2 atoms — 0 confirmed, 2 partially supported, 0 disputed, 0 misattributed, 0 unverifiable. Expand the claim to see per-atom verdicts.
hedgedstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
47 more claims · 13 with their cited sources checked
Create a free account to see all 72 claims and to verify the 6 references still open.
- It may state two separate claims as one. 20
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?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“GLP-1RAs have effects on systemic inflammation such as reduction in high-sensitivity C-reactive protein (hs-CRP) that are not mediated by weight loss or glycemic control [15, 27, 28].”
From evoke and evoke+: design of two large-scale, double-blind, placebo-controlled, phase 3 studies evaluating efficacy, safety, and tolerability of semaglutide in early-stage symptomatic Alzheimer’s disease (2025) · cites this paper as [27]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“There is increasing evidence that GLP-1RAs act as modulators of atherosclerosis, 76 and their anti-inflammatory and antioxidant properties may contribute to this, as supported by laboratory studies. 77,78”
The cited source says what the claim attributes to it.
In the citing paper
“Experimental and translational data support anti‐inflammatory and antioxidant actions of GLP‐1RAs beyond glycemic control [5].”
The cited source says what the claim attributes to it.
In the citing paper
“These benefits suggest important non‐glycemic effects, including modulation of inflammatory and vascular pathways [5].”
The cited source says what the claim attributes to it.
In the citing paper
“GLP‐1 receptor signalling may inhibit pro‐inflammatory transcriptional pathways, attenuate oxidative stress, improve endothelial function and modulate immune cell activation [5, 10].”
5 more claims about this paper
Create a free account to see every claim other papers make about this one.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Self-check results appear here once an independent check has confirmed them.
Cited works that were retracted
Works this paper cites that were later retracted, from the retraction notices publishers deposit. Major when the notice came out before this paper was published.
Rated major: it would touch a result — a value a result rests on, reported and recomputed p-values on opposite sides of the significance level, two passages that conflict with no sign which is right, or a cited work retracted before this paper was published.
In the paper
“Nonalcoholic steatohepatitis [61, 93, 96]”
Cited work 10.1007/s00125-010-1831-8 · retracted 2011-12-15 · notice 10.1007/s00125-011-2394-z · this paper published 2016
Citations
Cites
1 retracted
Hattori, Y., Jojima, T., Tomizawa, A., Satoh, H., Hattori, S., Kasai, K., & Hayashi, T. (2010) · Diabetologia · doi:10.1007/s00125-010-1831-8 · Cited by 183 · cited 3×
“Nonalcoholic steatohepatitis [61, 93, 96]”
BackgroundRetractedRole of Insulin Resistance in Human Disease
Reaven, G. M. (1988) · Diabetes · doi:10.2337/diab.37.12.1595 · Cited by 12,154
Kanda, H. (2006) · Journal of Clinical Investigation · doi:10.1172/jci26498 · Cited by 2,682
The biology of incretin hormones
Drucker, D. J. (2006) · Cell Metabolism · doi:10.1016/j.cmet.2006.01.004 · Cited by 2,210 · cited 1×
“GLP-1 has many beneficial effects on the control of blood glucose levels including stimulation of insulin secretion and inhibition of glucagon secretion, expansion of the beta-cell mass by stimulating beta-cell proliferation and differentiation and inhibiting beta-cell apoptosis, delay of gastric emptying, and reducti…”
BackgroundMicroglia and inflammation-mediated neurodegeneration: Multiple triggers with a common mechanism
Block, M. L., & Hong, J.-S. (2005) · Progress in Neurobiology · doi:10.1016/j.pneurobio.2005.06.004 · Cited by 1,557
CCR2 modulates inflammatory and metabolic effects of high-fat feeding
Weisberg, S. P., Hunter, D., Huber, R., Lemieux, J., Slaymaker, S., Vaddi, K., Charo, I., Leibel, R. L., & Jr., A. W. F. (2006) · Journal of Clinical Investigation · doi:10.1172/jci24335 · Cited by 1,497
Mechanisms of Pancreatic β-Cell Death in Type 1 and Type 2 Diabetes
Cnop, M., Welsh, N., Jonas, J.-C., Jörns, A., Lenzen, S., & Eizirik, D. L. (2005) · Diabetes · doi:10.2337/diabetes.54.suppl_2.s97 · Cited by 1,491
CCR2 modulates inflammatory and metabolic effects of high-fat feeding
Weisberg, S. P. (2006) · Journal of Clinical Investigation · doi:10.1172/jci24335c1 · Cited by 1,425
Normalization of obesity-associated insulin resistance through immunotherapy
Winer, S., Chan, Y., Paltser, G., Truong, D., Tsui, H., Bahrami, J., Dorfman, R., Wang, Y., Zielenski, J., Mastronardi, F., et al. (2009) · Nature Medicine · doi:10.1038/nm.2001 · Cited by 1,370
MENTLEIN, R., GALLWITZ, B., & SCHMIDT, W. E. (1993) · European Journal of Biochemistry · doi:10.1111/j.1432-1033.1993.tb17986.x · Cited by 1,161
Cited by
Items 501–501 of 501
Bigda, P., Rafałowska, Z., Rutz, S., Wojtala, A., Kret, J., Wyrostkiewicz, A., Sadkowski, A., Gdula, J., Zielińska, L., Szpunar, M., et al. (2026) · International Journal of Innovative Technologies in Social Science · doi:10.31435/ijitss.3(51).2026.6153
Metadata
- Authors
- Lee, Y.-S., & Jun, H.-S.
- Affiliations
- Gachon University (KR)
- Corresponding author
- Jun, Hee-Sook
- Venue
- Mediators of Inflammation
- Publisher
- Wiley
- Published
- 2016
- Volume
- 2016
- Pages
- 1-11
- ISSN
- 0962-9351 (ISSN-L)
- 1466-1861
- PMC
- PMC4823510
- OpenAlex
- W2306319461
- Cited by
- 530
- References
- 116
- Citations by year
- 2026: 68 · 2025: 83 · 2024: 56 · 2023: 52 · 2022: 60 · 2021: 72 · 2020: 53 · 2019: 47 · 2018: 21 · 2017: 15 · 2016: 3
- FWCI
- 3.59
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Locations
- Mediators of Inflammation (publishedVersion, cc-by)
- Europe PMC (PubMed Central) (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- National Research Foundation of Korea (2015R1D1A1A01060232)
- Topics
- Health Sciences › Medicine › Endocrinology, Diabetes and Metabolism › Diabetes Treatment and Management
- Health Sciences › Medicine › Endocrinology, Diabetes and Metabolism › Adipokines, Inflammation, and Metabolic Diseases
- Life Sciences › Neuroscience › Cellular and Molecular Neuroscience › Neuropeptides and Animal Physiology
- Keywords
- glucagon-like peptide-1, GLP-1 receptor agonists, DPP-4 inhibitors, anti-inflammatory activity, chronic inflammation, type 2 diabetes, type 1 diabetes, atherosclerosis, neurodegenerative diseases, nonalcoholic steatohepatitis, diabetic nephropathy, asthma, psoriasis, glucose homeostasis, molecular mechanisms of inflammation
- MeSH terms
- Animals, Anti-Inflammatory Agents, Blood Glucose, Diabetes Mellitus, Type 2, Humans, Inflammation, Glucagon-Like Peptide 1
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.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol and qwen3.8-omni-flash).
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.