CoChat
Sign Up
Cited by 14Sleep and related disordersObstructive Sleep Apnea ResearchAnxiety, Depression, Psychometrics, Treatment, Cognitive Processes

Benefits of Cognitive Behavioral Therapy for Insomnia for Women Veterans with and without Probable Post-Traumatic Stress Disorder

Open access
Carlson, Gwendolyn C., Kelly, Monica R., Mitchell, Michael, Josephson, Karen R., McGowan, Sarah Kate, Culver, Najwa C., Kay, Morgan, Alessi, Cathy A. +5 more·2022·Women's Health Issues
DOI 10.1016/j.whi.2021.10.007PMC PMC9124441
Open this paper in CoChat — free account

Abstract

Objective: This study compared the benefits of cognitive–behavioral therapy for insomnia for sleep, mental health symptoms, and quality of life (QoL) in a sample of women veterans with and without probable post-traumatic stress disorder (PTSD) comorbid with insomnia disorder. Methods: Seventy-three women veterans (30 with probable PTSD) received a manual-based 5-week cognitive–behavioral therapy for insomnia treatment as part of a behavioral sleep intervention study. Measures were completed at baseline, post-treatment, and 3-month follow-up. Sleep measures included the Insomnia Severity Index, Pittsburgh Sleep Quality Index, sleep efficiency measured by actigraphy, and sleep efficiency and total sleep time measured by sleep diary. Mental health measures included the PTSD Checklist-5, nightmares per week, Patient Health Questionnaire-9, and Generalized Anxiety Disorder-7 scale. QoL was measured with the Short Form-12. Linear mixed models compared changes over time across groups. Independent t tests examined PTSD symptom changes in women veterans with probable PTSD. Results: Both groups demonstrated improvements across sleep (ps < .001–.040), mental health symptoms (ps < .001), and QoL measures (ps < .001). The probable PTSD group reported greater improvements in diary sleep efficiency (p = .046) and nightmares per week (p = .001) at post-treatment and in total sleep time (p = .029) and nightmares per week (p = .006) at follow-up. Most participants with probable PTSD experienced clinically significant reductions in PTSD symptoms at post-treatment (66.7%) and follow-up (60.0%). Significant reductions in intrusive and arousal/reactivity symptoms were maintained at follow-up. Conclusions: Cognitive–behavioral therapy for insomnia improves insomnia, mental health symptoms, and QoL among women veterans, with greater improvement in those with probable PTSD. © 2021

Integrity signals

Registry

Crossref · 10.1016/j.whi.2021.10.007

Cites

49 of 49 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Claims the paper makes

14 of 35 cited sources checked · 4 supported · 0 flagged · accuracy not yet measured

  • Premisecitation

    Prior studies support CBT-I efficacy for improving sleep and mental health symptoms in veterans with PTSD.

    “Studies have examined the impact of CBT-I in veterans with posttraumatic stress disorder (PTSD), and the results support the efficacy of CBT-I for improving sleep and mental health symptoms (DeViva et al., 2018; Gellis & Gehrman, 2011; Talbot et al., 2014).”
    Quote in the paperSubstantial claim1 of 3 sources checked
    • cites DeViva et al., 2018 source
    • cites Gellis & Gehrman, 2011 source
    • cites Talbot et al., 2014 source

      The Results report improved sleep and work and interpersonal functioning with CBT-I, but the participant table shows that only 9 of 45 participants were veterans, so this was not a trial specifically of veterans. The Nonsleep PTSD Symptoms and Depression Symptoms sections report no significant treatment-by-time advantage over the waitlist group; the claim therefore overstates the evidence for improvement in mental health symptoms. (LLM, conf=0.90)

      Experimental — accuracy not yet measured
  • Premisecitation

    Except for Talbot et al. (2014), prior CBT-I studies in veterans with PTSD included predominantly male patients.

    “However, with the exception of Talbot et al. (2014), these studies included predominantly male patients.”
    Quote in the paperSubstantial claim1 of 1 sources checked
    • cites Talbot et al. (2014) source
  • Premisecitation

    Nightmares are more frequent when patients are sleep deprived.

    “as previous studies demonstrate that nightmares are more frequent when patients are sleep deprived (Creamer, Brock, Matsangas, Motamedi, & Mysliwiec, 2018; Tamanna, Parker, Lyons, & Ullah, 2014).”
    Quote in the paperSubstantial claim2 of 2 sources checked
    • cites Creamer, Brock, Matsangas, Motamedi, & Mysliwiec, 2018 source

      The Abstract reports that insomnia was associated with nightmares, and the Discussion reports shorter self-reported sleep in the trauma-related nightmare group than in the nightmare-disorder-only group. These findings support a relationship between nightmares and poor sleep, but the paper does not demonstrate that being sleep deprived makes nightmares more frequent; the Discussion instead raises the possibility that nightmares contribute to sleep deprivation. Page numbers were not available in our copy. (LLM, conf=0.86)

      Experimental — accuracy not yet measured
    • cites Tamanna, Parker, Lyons, & Ullah, 2014 source

      The Discussion (page not provided) reports that interrupted sleep at night predicted nightmares in patients with obstructive sleep apnea. The Results (page not provided) also show fewer nightmares after CPAP treatment in veterans with PTSD and sleep apnea. Neither passage establishes that nightmares are more frequent when patients are sleep deprived specifically; that extends the finding beyond the conditions studied. (LLM, conf=0.82)

      Experimental — accuracy not yet measured
  • Premisecitation

    When veterans are shown descriptions of evidence-based PTSD and insomnia treatments, those who screen positive for insomnia and PTSD report greater willingness to seek insomnia treatment than PTSD treatment.

    “Previous research has demonstrated that when veterans are presented with descriptions of evidence-based treatments for PTSD and insomnia, veterans who screen positive for insomnia and PTSD report greater willingness to seek insomnia versus PTSD treatment (Gutner, Pedersen, & Drummond, 2018).”
    Quote in the paperNot a substantial claim1 of 1 sources checked
    • cites Gutner, Pedersen, & Drummond, 2018 source

      The Results (§3.2.1) report that veterans screening positive for both insomnia and PTSD were more willing to seek sleep treatment than PTSD treatment. But the Methods (§2.2.4) describe ratings of willingness to consider counseling for specified symptoms, not responses to descriptions of evidence-based PTSD and insomnia treatments. (LLM, conf=0.88)

      Experimental — accuracy not yet measured
  • Interpretationcitation

    Reduced nightmares per week may be related to increased total sleep time.

    “Reduced nightmares per week may be related to increased total sleep time, as previous studies demonstrate that nightmares are more frequent when patients are sleep deprived (Creamer, Brock, Matsangas, Motamedi, & Mysliwiec, 2018; Tamanna, Parker, Lyons, & Ullah, 2014).”
    Quote in the paperNot a substantial claim2 of 2 sources checked
    • cites Creamer, Brock, Matsangas, Motamedi, & Mysliwiec, 2018 source

      The Discussion reports that shorter self-reported sleep time and more frequent nightmares occurred together in findings from Vietnam veterans, which supports a possible relationship. But it does not establish that sleep deprivation makes nightmares more frequent; the paper also proposes the reverse direction, with nightmares contributing to sleep deprivation. (LLM, conf=0.81)

      Experimental — accuracy not yet measured
    • cites Tamanna, Parker, Lyons, & Ullah, 2014 source

      The Results report fewer nightmares per week after CPAP treatment, and the introduction notes that people with PTSD have shorter total sleep time than those without PTSD. Neither passage links the reduction in nightmares to increased total sleep time or demonstrates that sleep deprivation makes nightmares more frequent. (LLM, conf=0.84)

      Experimental — accuracy not yet measured
  • Classified as probably not a substantial claim. 19
  • May combine two claims. 12

  • Classified as probably not a substantial claim.

    Premisecitation

    CBT-I is the recommended first-line treatment for insomnia disorder, including in people with comorbid psychiatric conditions.

    “Cognitive Behavioral Therapy for Insomnia (CBT-I) is the recommended first-line treatment for insomnia disorder, including among individuals with comorbid psychiatric conditions”
    • Also stated in: § Introduction · plain
      “Cognitive Behavioral Therapy for Insomnia (CBT-I) is the recommended first-line treatment for insomnia disorder, including among individuals with comorbid psychiatric conditions (Edinger et al., 2020; Mysliwiec et al., 2020; Qaseem, Kansagara, Forciea, Cooke, & Denberg, 2016; Wu, Appleman, Salazar, & Ong, 2015).”
    Quote in the paperSubstantial claim1 of 3 sources checked
    • cites Edinger et al., 2020 source
    • cites Mysliwiec et al., 2020 source
    • cites Qaseem, Kansagara, Forciea, Cooke, & Denberg, 2016 source

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Study design and conductcitation

    Randomization procedures followed CONSORT criteria for randomized trials.

    “Randomization procedures followed the CONSORT criteria for randomized trials (Schulz, Altman, & Moher, 2010).”
    Quote in the paperNot a substantial claim1 of 1 sources checked
    • cites Schulz, Altman, & Moher, 2010 source

      The checklist (Implications and limitations, p. 6) includes items for reporting how the random allocation sequence was generated and concealed. But the paper describes CONSORT as guidance for reporting trials (Intent of CONSORT 2010, p. 1), not as criteria for conducting randomization procedures; it cannot establish that the citing trial followed them. (LLM, conf=0.84)

      Experimental — accuracy not yet measured

  • May combine two claims.

    Premisecitation

    Insomnia is a risk factor for PTSD development and severity.

    “Research suggests that insomnia is a risk factor for PTSD development and severity (Miller, Brownlow, & Gehrman, 2020).”
    Quote in the paperSubstantial claim1 of 1 sources checked
    • cites Miller, Brownlow, & Gehrman, 2020 source

      The Abstract says trauma-related sleep problems contribute to the development and maintenance of PTSD, and the References describe a study in which pre-deployment insomnia predicted post-deployment PTSD. The copy does not establish insomnia as a risk factor for PTSD severity specifically; maintenance and improvement in symptoms after insomnia treatment do not directly make that claim. (LLM, conf=0.83)

      Experimental — accuracy not yet measured

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Premisecitation

    A quarter of women veterans receiving VA healthcare meet diagnostic criteria for both insomnia disorder and PTSD.

    “A quarter of women veterans receiving Veterans Affairs (VA) healthcare meet diagnostic criteria for both insomnia disorder and PTSD (Hughes, Jouldjian, Washington, Alessi, & Martin, 2013; Martin et al., 2017), with poor sleep being one of the most commonly reported symptoms associated with PTSD.”
    Quote in the paperNot a substantial claim1 of 2 sources checked
    • cites Hughes, Jouldjian, Washington, Alessi, & Martin, 2013 source
    • cites Martin et al., 2017 source

      The Results report that 52.6% of surveyed women veterans receiving VA care met the study’s operational definition of insomnia disorder. The paper also notes that women veterans with insomnia have higher rates of PTSD, but it does not report that a quarter met criteria for both disorders. (LLM, conf=0.86)

      Experimental — accuracy not yet measured

  • Probably not a substantial claim: may not pass S2 (checkable), S3 (load-bearing).

    Premisecitation

    A growing body of literature highlights the importance of trauma-informed care.

    “There is also a growing body of literature highlighting the importance of trauma-informed care (Machtinger, Cuca, Khanna, Rose, & Kimberg, 2015).”
    Quote in the paperNot a substantial claim1 of 1 sources checked
    • cites Machtinger, Cuca, Khanna, Rose, & Kimberg, 2015 source

  • Probably not a substantial claim: may not pass S2 (checkable), S3 (load-bearing).

    Premisecitation

    Presenting evidence-based treatment options for both PTSD and insomnia and supporting patient preferences is consistent with a shared decision-making approach.

    “Presenting evidence-based treatment options for both PTSD and insomnia and supporting patient preferences is consistent with a shared decision-making approach (Elwyn et al., 2012).”
    Quote in the paperNot a substantial claim1 of 1 sources checked
    • cites Elwyn et al., 2012 source

  • May combine two claims.

    Findingown data

    In the year after the study, 10 participants with probable PTSD had fewer mental health encounters and 7 had more.

    “Medical record review revealed that 17 participants with probable PTSD had mental health encounters in the year prior to the study. The following year, 10 participants had fewer and 7 had more mental health encounters, suggesting findings are not simply the result of concurrent treatment and/or motivation to engage in treatment.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

    Study design and conductnone given

    The study used an established 5-session CBT-I treatment protocol and a comprehensive battery of well-established measures and methods.

    “This study included an established 5-session CBT-I treatment protocol and a comprehensive assessment battery of well-established measures and methods.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

    Premisecitation

    The ISI correlates well with the PSQI and with sleep diary measures.

    “The ISI correlates well with scores on the Pittsburg Sleep Quality Index (r=0.67) and with sleep diary measures (r’s=0.32-0.91) (Bastien et al., 2001).”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites Bastien et al., 2001 source

  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

    Premisecitation

    The GAD-7 has strong internal consistency and construct validity.

    “The GAD-7 has strong internal consistency (α=0.89) and construct validity (Löwe et al., 2008).”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites Löwe et al., 2008

      Couldn’t be matched to a paper in Crossref, so it can’t be checked.

  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

    Premisecitation

    The PHQ-9 has strong internal consistency and good convergent and discriminant validity.

    “The PHQ-9 has strong internal consistency (α=0.87) and good convergent and discriminant validity (Beard, Hsu, Rifkin, Busch, & Björgvinsson, 2016).”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites Beard, Hsu, Rifkin, Busch, & Björgvinsson, 2016 source

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Study design and conductown data

    Fidelity ratings based on 10% of CBT-I session recordings showed high adherence to the treatment protocol (97.5%).

    “Fidelity ratings based on 10% of the CBT-I session recordings showed high adherence to the treatment protocol (97.5%).”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Premisecitation

    A PSQI score greater than 5 has 89.6% sensitivity and 86.5% specificity for distinguishing normal from abnormal sleepers.

    “PSQI score greater than 5 has a sensitivity for distinguishing between normal and abnormal sleepers of 89.6% and a specificity of 86.5% (kappa=0.75, P<.001) (Buysse et al., 1989).”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites Buysse et al., 1989 source

  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

    Premisecitation

    The SF-12 has test-retest reliability of 0.80 for the physical component and 0.76 for the mental component.

    “Test-retest reliability is 0.80 for the physical health component score and 0.76 for the mental health component score (Ware Jr, Kosinski, & Keller, 1996).”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites Ware Jr, Kosinski, & Keller, 1996 source

  • May combine two claims.

    Premisecitation

    Women veterans whose insomnia symptoms are linked to a traumatic event have more severe insomnia and mental health symptoms and go longer without insomnia treatment than women veterans whose insomnia is not trauma-linked.

    “Women veterans with insomnia symptoms linked to a traumatic event demonstrate more severe insomnia and mental health symptoms and go without insomnia treatment longer than women veterans who experience insomnia that is not linked to trauma (Carlson et al., 2020).”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites Carlson et al., 2020

      Couldn’t be matched to a paper in Crossref, so it can’t be checked.

  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

    Premisecitation

    The PCL-5 has strong internal reliability, test-retest reliability, and convergent validity.

    “The PCL-5 has demonstrated strong internal reliability (α=0.94), test-retest reliability (r=0.82), and convergent validity (r’s=0.74 to 0.85) (Blevins, Weathers, Davis, Witte, & Domino, 2015).”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites Blevins, Weathers, Davis, Witte, & Domino, 2015 source

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Study design and conductnone given

    Insomnia disorder diagnosis was confirmed by both a psychologist specializing in behavioral sleep medicine and a board-certified sleep medicine physician.

    “Diagnosis was confirmed by both a psychologist specializing in behavioral sleep medicine and board-certified sleep medicine physician.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Premisenone given

    The current CBT-I protocol did not specifically target nightmares, and CBT-I has no strategies that specifically target other PTSD avoidance symptoms.

    “however, the current CBT-I protocol did not specifically target nightmares and there are no strategies in CBT-I that specifically target other PTSD avoidance symptoms.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Premisecitation

    A discrepancy between subjective and objective sleep efficiency measures has been repeatedly observed across various populations.

    “The discrepancy between subjective and objective sleep efficiency measures has been repeatedly observed across a variety of populations (Campanini et al., 2017; Short, Gradisar, Lack, Wright, & Carskadon, 2012).”
    Quote in the paperNot a substantial claim0 of 2 sources checked
    • cites Campanini et al., 2017 source
    • cites Short, Gradisar, Lack, Wright, & Carskadon, 2012 source

  • Classified as probably not a substantial claim. May combine two claims.

    Premisenone given

    CBT-I targets sleep-related problematic thoughts rather than trauma-related thoughts, and it does not include techniques such as exposure or behavioral activation to reduce avoidance.

    “That being said, it is important to note that CBT-I targets problematic thoughts related to sleep, not problematic thoughts related to trauma, nor does CBT-I include techniques to reduce avoidance such as exposure or behavioral activation.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

    Study design and conductreasoning

    The study was exploratory and did not include alpha adjustments for multiple comparisons.

    “The current study was exploratory in nature and, as such, analyses did not include alpha adjustments for multiple comparisons; therefore, it is possible that chance might explain one particular finding, but chance alone is unlikely to explain the overall pattern of results showing significant benefits across a range of outcomes.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Premisecitation

    Patients with PTSD may delay falling asleep at night to avoid nightmares.

    “Patients with PTSD may delay falling asleep at night in an effort to avoid nightmares (Aurora et al., 2010).”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites Aurora et al., 2010 source

  • Probably not a substantial claim: may not pass S2 (checkable), S3 (load-bearing).

    Premisecitation

    Trauma-informed care involves tailoring existing interventions to meet the unique needs of patients who have experienced trauma.

    “While trauma-focused treatments specifically target PTSD symptoms, trauma-informed care involves tailoring existing interventions to meet the unique needs of patients who have experienced trauma (Kelly, Boyd, Valente, & Czekanski, 2014).”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites Kelly, Boyd, Valente, & Czekanski, 2014 source
23 of 23

  • The paper relies on this without support.

    No prior study had examined CBT-I's impact on sleep and mental health symptoms in an exclusively women-veteran sample.

    “No studies have examined the impact of CBT-I on sleep and mental health symptoms in a sample of exclusively women veterans.”
    “To our knowledge, this was the first study to examine the impact of CBT-I in a sample of exclusively women veterans.”
1 of 1

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?

  • Worry journals represent a simple and evidence-based approach to manage sleep onset anxiety.

    “Worry journals represent a simple and evidence-based approach to manage sleep onset anxiety [87].”

    From Pre-Sleep Anxiety: Mechanisms and Therapeutic Approaches in Clinical Practice. (2026) · cites this paper as [87]

    The Discussion reports improved insomnia and anxiety after CBT-I and says scheduled worry time may help reduce intrusive thoughts and hyperarousal. It does not identify worry journals as an intervention or test whether they manage sleep-onset anxiety; the evidence concerns a broader, multicomponent treatment. (LLM, conf=0.82)

    Experimental — accuracy not yet measured

  • By externalizing anxiety through writing, clients can reduce internal tension that interferes with sleep.

    “By externalizing anxiety through writing, clients can reduce internal tension that interferes with sleep [87].”

    From Pre-Sleep Anxiety: Mechanisms and Therapeutic Approaches in Clinical Practice. (2026) · cites this paper as [87]

    The Discussion reports improvements in sleep and anxiety among women veterans receiving CBT-I and suggests that scheduled worry time may help reduce intrusive thoughts and hyperarousal. It does not say that writing externalizes anxiety or establish that writing reduces sleep-disrupting internal tension; the claimed mechanism is unsupported. (LLM, conf=0.84)

    Experimental — accuracy not yet measured

  • Journaling helps identify recurring patterns of worry, such as those related to work or family, that often precede heightened nighttime anxiety.

    “Journaling also helps identify recurring pa erns of worry, such as those related to work or family, that often precede heightened nigh ime anxiety [87].”

    From Pre-Sleep Anxiety: Mechanisms and Therapeutic Approaches in Clinical Practice. (2026) · cites this paper as [87]

    The Methods (Measures; page unavailable) describe a sleep diary used to calculate sleep duration and efficiency, not journaling about worries. The Discussion (page unavailable) mentions scheduled worry time, but does not say that journaling identifies recurring work or family worries that precede nighttime anxiety. Searches for journaling and worry patterns found no passage addressing that claim. (LLM, conf=0.76)

    Experimental — accuracy not yet measured

Cites

Flagged first, then by citations

2 of the 51 references couldn’t be matched to a known paper.

Cited by

Sorted by citations

Related

Authors
Carlson, G. C., Kelly, M. R., Mitchell, M., Josephson, K. R., McGowan, S. K., Culver, N. C., Kay, M., Alessi, C. A., Fung, C. H., Washington, D. L., Hamilton, A., Yano, E. M., & Martin, J. L.
Affiliations
  • University of California, Los Angeles (US)
  • VA Greater Los Angeles Healthcare System (US)
ORCID
Venue
Women's Health Issues
Publisher
Elsevier BV
Published
2022-03
Volume
32
Issue
2
Pages
194-202
ISSN
1049-3867 (ISSN-L)
DOI
10.1016/j.whi.2021.10.007
PMC
PMC9124441
OpenAlex
W3215612297
Cited by
14
References
51
Citations by year
2026: 4 · 2025: 3 · 2024: 3 · 2023: 2 · 2022: 2
FWCI
1.69
Type
journal article
Language
en
Open access
Licence
Locations
  • Women s Health Issues (publishedVersion)
  • PubMed (publishedVersion)
  • PubMed Central (acceptedVersion)
  • eScholarship (California Digital Library) (submittedVersion)
Funders
  • U.S. Department of Veterans Affairs (I01 HX002300, IK6 HX003160, I01 HX001287)
  • National Heart, Lung, and Blood Institute (K24HL143055)
Topics
  • Social Sciences › Psychology › Experimental and Cognitive Psychology › Sleep and related disorders
  • Health Sciences › Medicine › Physiology › Obstructive Sleep Apnea Research
  • Social Sciences › Psychology › Experimental and Cognitive Psychology › Anxiety, Depression, Psychometrics, Treatment, Cognitive Processes
Keywords
cognitive behavioral therapy for insomnia, women veterans, post-traumatic stress disorder, insomnia, sleep quality, nightmares, quality of life, psychiatric symptoms, anxiety, PTSD symptom reduction, sleep efficiency
MeSH terms
Female, Humans, Sleep Initiation and Maintenance Disorders, Quality of Life, Stress Disorders, Post-Traumatic, Veterans, Cognitive Behavioral Therapy

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.

Claims read by deepseek-v4.1-flash under definition version 3 (extract-v3) on 2026-09-28.

Classified by jev-1.13-20260917 (gold-guideline-v0.2) on 2026-09-28.

Cited sources are checked by gpt-6-sol.

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