CoChat
Sign Up
Cited by 15Obsessive-Compulsive Spectrum DisordersSexuality, Behavior, and TechnologyAutism Spectrum Disorder Research

Examination of outcomes among sexual minorities in treatment for obsessive-compulsive and related disorders

Open access
Bezahler, Andreas, Kuckertz, Jennie M., Schreck, Meghan, Narine, Kevin, Dattolico, Devin, Falkenstein, Martha J.·2022·Journal of Obsessive-Compulsive and Related Disorders
DOI 10.1016/j.jocrd.2022.100724PMC PMC10201929
Open this paper in CoChat — free accountOpen PDF

Abstract

The first-line psychological treatment for obsessive-compulsive and related disorders (OCRDs) is exposure and response prevention (ERP). As the first study to examine treatment outcomes for sexual minorities, it is crucial to examine: (1) how treatment-seeking individuals who identify as sexual minorities compare to heterosexual individuals in symptom severity at admission, length of stay in treatment, and (2) whether ERP is equally effective for sexual minorities. The current study explored these questions in an intensive/residential treatment (IRT) program for OCRDs. Adult participants (N = 191) completed self-reported measures of OCD severity, distress tolerance, and depression at program admission, in the first four weeks of treatment, and at discharge. No differences were found between groups for treatment outcome, although slight differences (non-significant) emerged at baseline for OCRD severity, distress tolerance, and depression. Sexual orientation was not predictive of OCRD severity at weeks 1–4, and number of days spent in treatment was not associated with sexual orientation. This is the first study exploring whether sexual orientation is predictive of treatment outcomes for individuals diagnosed with OCRDs. Results suggest that outcomes did not differ and participation in the program resulted in an overall improvement of symptoms regardless of sexual orientation, however several study limitations are discussed. Future studies should replicate these findings, attempt to collect a larger sample, incorporate qualitative feedback from treatment, and examine outcomes in gender minorities. © 2022

Verification finished with gaps

Some checks didn’t finish. The results below cover the steps that did.

  1. Registry recordVerified
  2. Full textRead the full text
  3. Reference list50 references found
  4. Reference check48 of 48 references checked
  5. StatisticsRecomputed
  6. Claims49 claims anchored to a quote
  7. Cited sourcesChecked
  8. Self-checkDidn’t finish — the rest of the report still applies.
  9. VerificationFindings verified

Integrity signals

Registry

Crossref · 10.1016/j.jocrd.2022.100724

Cites

48 of 48 references verified0 citation errors · 0 not checkable

Statistics

13 tests recomputed · 0 with the reported and recomputed p on opposite sides of .05

Claims the paper makes

10 of 35 cited sources checked · 9 supported · 0 flagged · accuracy not yet measured

  • Premisecitation

    Sexual minorities experience more lifetime depression symptoms than heterosexual individuals.

    “Moreover, sexual minorities experience more symptoms related to depression in their lifetime compared to heterosexual individuals (Zietsch, et al., 2012).”
    Quote in the paperSubstantial claim1 of 1 sources checked
    • cites Zietsch, et al., 2012 source
  • Study design and conductown data

    The study was underpowered to detect between-group differences in YBOCS change, with observed power of .49.

    “An observed (post-hoc) power analysis using G*Power (Faul et al., 2007) with 𝛼 = .05, observed effect size of d = .369, n = 34 for sexual minorities and n = 157 for heterosexual individuals, indicated that observed power was .49 to detect between-group differences in YBOCS change.”
    Quote in the paperSubstantial claim1 of 1 sources checked
    • cites Faul et al., 2007 source
  • Premisecitation

    Rates of depression are disproportionately higher in sexual minorities than in heterosexual individuals.

    “Likewise, rates of depression are disproportionately higher in sexual minorities than heterosexual individuals (Meyer, 2003).”
    Quote in the paperSubstantial claim1 of 1 sources checked
    • cites Meyer, 2003 source
  • Findingown data

    Distress tolerance increased significantly from baseline to discharge across all participants.

    “Results from DTS data revealed a significant main effect of time, F(1, 178) = 25.16, p < .001, 𝜂p2 = .124, indicating that distress tolerance increased from baseline (M = 39.74, SD = 15.14) to discharge (M = 45.41, SD = 14.64).”
    Quote in the paperNot a substantial claim
  • Findingown data

    There was no significant Group X Time interaction for OCD severity.

    “The main effect of group was not significant, F(1, 189) = 51.61, p = .368, 𝜂p2 = .004, nor was the Group X Time interaction, F(1, 189) = 3.26, p = .073, 𝜂p2 = .017.”
    Quote in the paperSubstantial claim
  • May combine two claims. 20
  • Classified as probably not a substantial claim. 15

  • May combine two claims.

    Premisecitation

    Sexual orientation-related stress may maintain or lead to lower distress tolerance in sexual minorities, increasing anxiety-related symptoms.

    “Therefore, sexual orientation-related stress may possibly maintain or lead to lower distress tolerance in sexual minorities, increasing anxiety-related symptoms (Reitzel et al., 2017).”
    Quote in the paperSubstantial claim1 of 1 sources checked
    • cites Reitzel et al., 2017 source

  • May combine two claims.

    Premisecitation

    Past research on sexual minorities with OCRDs has mostly focused on sexual orientation-related obsessions in heterosexual individuals, while experiences of sexual minority individuals with OCD have not been studied.

    “Past research involving sexual minorities with OCRDs has mostly focused on sexual orientation-related obsessions in heterosexual individuals (Williams & Farris, 2011; Williams et al., 2014), whereas the experiences of individuals with OCD who identify as a sexual minority have not been studied.”
    Quote in the paperSubstantial claim1 of 2 sources checked
    • cites Williams & Farris, 2011 source

      The Introduction (page unavailable) and Results (page unavailable) show that this study focuses on sexual-orientation obsessions among people with OCD. They do not establish that the patients were heterosexual or that past research mostly concerned heterosexual individuals. The statement about sexual minority individuals’ experiences follows the citation rather than being directly attributed to it. (LLM, conf=0.82)

      Experimental — accuracy not yet measured
    • cites Williams et al., 2014

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

  • Classified as probably not a substantial claim.

    Premisecitation

    Lower distress tolerance partially mediates the relationship between sexual orientation-related discrimination experiences and anxiety symptoms in sexual minorities.

    “In particular, lower distress tolerance has been shown to partially mediate the relationship between sexual orientation-related discrimination experiences and anxiety symptoms in sexual minorities (Reitzel et al., 2017).”
    Quote in the paperSubstantial claim1 of 1 sources checked
    • cites Reitzel et al., 2017 source

  • May combine two claims.

    Premisecitation

    Individuals diagnosed with OCD are at increased risk for suicide attempts and dying by suicide.

    “For example, individuals diagnosed with OCD are at an increased risk for suicide attempts and dying by suicide (de la Cruz et al., 2017)”
    Quote in the paperSubstantial claim1 of 1 sources checked
    • cites de la Cruz et al., 2017 source

  • May combine two claims.

    Premisecitation

    The likelihood of developing suicidal ideation or experiencing a suicide attempt is increased in sexual minorities compared to heterosexual individuals.

    “and the likelihood of developing suicidal ideation or experiencing a suicide attempt is increased compared to heterosexual individuals (Meyer, 2003; Lewis, 2009).”
    Quote in the paperSubstantial claim1 of 2 sources checked
    • cites Meyer, 2003 source
    • cites Lewis, 2009 source

  • Classified as probably not a substantial claim.

    Premisecitation

    Minority stress theory holds that sexual minorities face unique distal and proximal stressors that raise the risk for emotional disorders.

    “Minority stress theory posits that sexual minorities experience unique distal stressors (e.g., external stressors) related to their identities and subsequent proximal stressors (e.g., internal stressors in response to negative external experiences) that increase the risk for emotional disorders (Meyer, 2003).”
    Quote in the paperSubstantial claim1 of 1 sources checked
    • cites Meyer, 2003 source

  • May combine two claims.

    Premisecitation

    Sexual minorities have a higher risk for psychopathology and higher levels and rates of anxiety-related disorders than heterosexual individuals.

    “sexual minorities are at increased risk for psychopathology, experiencing both higher levels and rates of anxiety-related disorders compared to heterosexual individuals (Cohen et al., 2016; Gilman et al., 2001; Potoczniak et al., 2007; Safren & Pantalone, 2006; Seelman, et al., 2017).”
    Quote in the paperNot a substantial claim1 of 3 sources checked
    • cites Cohen et al., 2016 source
    • cites Gilman et al., 2001 source
    • cites Potoczniak et al., 2007 source

  • May combine two claims.

    Findingown data

    There were no significant differences in treatment outcomes (OCD severity, depression, distress tolerance) or length of stay between sexual minority and heterosexual groups.

    “No differences were found between groups for treatment outcome, although slight differences (non-significant) emerged at baseline for OCRD severity, distress tolerance, and depression.”
    • Also stated in: § Discussion · plain
      “Contrary to our hypotheses, there were no significant differences in treatment outcomes for OCD severity, depression, or distress tolerance between groups, nor were there differences in length of stay.”
    Quote in the paperSubstantial claim

  • May combine two claims.

    Findingown data

    Baseline differences between sexual minorities and heterosexual individuals were non-significant for OCD symptoms, distress tolerance, and depression.

    “Baseline differences were non-significant for all measures, including OCD symptoms, t(189) = 1.73, p = .085, d = 0.34, distress tolerance, t(178) = −1.78, p = .078, d = 0.37, and depression symptoms, t(186) = 1.76, p = .081, d = 0.33.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Findingown data

    At baseline, sexual minority individuals had higher OCD symptoms, lower distress tolerance, and higher depression symptoms than heterosexual individuals, but these differences were small and non-significant.

    “Mean differences were in the expected direction such that sexual minority individuals demonstrated higher OCD symptoms (M = 26.53, SD = 5.68) than heterosexual individuals (M = 24.41, SD = 6.62), lower distress tolerance (M = 35.12, SD = 11.79) than heterosexual individuals (M = 40.27, SD = 15.41), and higher depression symptoms (M = 10.24, SD = 5.45) than heterosexual individuals (M = 8.46, SD =”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Findingown data

    Sexual orientation was positively and significantly associated with admission DTS and negatively and significantly associated with admission YBOCS.

    “Sexual orientation was positively and significantly associated with admission DTS (β = .81, p = .009) and negatively and significantly associated with admission YBOCS (β = −.31, p = .028).”
    Quote in the paperNot a substantial claim

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

    Premisecitation

    Individuals with more marginalized identities (race, ethnicity, sexual orientation) experience greater OCD severity and depression.

    “In another study in IRT for OCRDs, research highlights that individuals who hold more marginalized identities (e.g., race, ethnicity, sexual orientation) experience greater levels of OCD severity and depression (Wadsworth et al., 2020).”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites Wadsworth et al., 2020 source

  • Classified as probably not a substantial claim.

    Premisecitation

    Sexual minorities diagnosed with an OCRD may be at risk of worsened therapeutic interactions compared to heterosexual individuals due to anti-affirming LGBQ+ care.

    “Moreover, in a recent review, Pinciotti and colleagues (2021) describe how sexual minorities who are diagnosed with an OCRD may be at risk of worsened therapeutic interactions compared to heterosexual individuals, as a possible result of anti-affirming LGBQ+ care, historically intertwined with exposure therapy.”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites Pinciotti et al., 2021 source

  • Classified as probably not a substantial claim.

    Premisecitation

    Exposure and response prevention is the first-line psychological treatment for obsessive-compulsive and related disorders.

    “The first-line psychological treatment for obsessive-compulsive and related disorders (OCRDs) is exposure and response prevention (ERP).”
    Quote in the paperSubstantial claim0 of 2 sources checked
    • cites Foa et al., 2005 source
    • cites Franklin et al., 2000 source

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

    Premisecitation

    Gender minorities report greater contamination obsessions, psychiatric comorbidities, longer lengths of stay, and less symptom improvement compared to cisgender individuals with OCD.

    “Prior research indicates that gender minorities report greater contamination obsessions, psychiatric comorbidities, longer lengths of stay in treatment, and less symptom improvement in treatment compared to cisgender individuals with OCD (Pinciotti et al., 2022).”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites Pinciotti et al., 2022 source

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

    Study design and conductcitation

    The HAMD-6 has good psychometric properties.

    “The measure has been shown to have good psychometric properties (Timmerby et al., 2017).”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites Timmerby et al., 2017 source

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

    Premisecitation

    Research in non-clinical settings suggests that sexual minorities are more likely to endorse obsessive compulsive symptoms.

    “Moreover, research in non-clinical settings also suggests that sexual minorities are more likely to endorse obsessive compulsive symptoms (Pinciotti & Orcutt, 2020).”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites Pinciotti & Orcutt, 2020 source

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

    Premisecitation

    Distress tolerance is an important facet in emotion regulation; low distress tolerance relates to difficulty experiencing negative feelings.

    “Distress tolerance is an important facet in emotion regulation; experiencing low distress tolerance often relates to difficulty an individual has in experiencing negative feelings (Blackledge & Hayes, 2001).”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites Blackledge & Hayes, 2001 source

  • May combine two claims.

    Premisecitation

    Distress tolerance is an important maintenance factor of OCRDs and has a significant association with OCD-related obsessions.

    “Distress tolerance is also an important maintenance factor of OCRDs, which has a significant association with OCD-related obsessions (Cougle et al., 2011).”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites Cougle et al., 2011 source

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

    Premisecitation

    A single-session intervention for youth with depressive disorders was similarly acceptable and efficacious among SGMs and heterosexual, cis-gender individuals.

    “however, a single-session intervention for youth with depressive disorders was found similarly acceptable and efficacious among SGMs and heterosexual, cis-gender individuals (McDanal et al., 2021).”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites McDanal et al., 2021 source

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

    Interpretationreasoning

    Sexual minorities may have acquired skills in therapy to manage symptoms and cope with identity-related stress, developed supportive relationships, and thus benefited comparably to heterosexual individuals.

    “While sexual minorities may have experienced these stressors in treatment, they may have acquired skills in therapy to manage their symptoms and cope with stressful identity-related experiences, developed supportive relationships with other sexual minority participants with OCD, and benefitted comparably to heterosexual individuals in treatment outcomes.”
    Quote in the paperNot a substantial claim

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

    Premisecitation

    Previous research on IRT for OCRDs suggests the largest amount of symptom reduction occurs within the first four weeks of treatment and that this period is most predictive of outcomes.

    “due to previous research of IRT for OCRDs suggesting the largest amount of symptom reduction occurs within the first four weeks of treatment and that this period is most predictive of outcomes (Krompinger et al., 2017).”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites Krompinger et al., 2017 source

  • May combine two claims.

    Interpretationown data

    Treatment was broadly effective in reducing OCD and depression symptoms and improving distress tolerance.

    “There were main effects of time for all measures, suggesting that treatment was broadly effective in reducing symptoms of OCD and depression, as well as improving distress tolerance.”
    Quote in the paperSubstantial claim

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

    Study design and conductcitation

    The self-report Y-BOCS has medium to strong correlations with the clinician-administered version.

    “This self-report version of the YBOCS is commonly utilized (Steketee et al., 1996), and displays medium to strong correlations with the clinically administered measure (Federici et al., 2010; Hauschildt et al., 2019; Storch et al., 2017).”
    Quote in the paperNot a substantial claim0 of 3 sources checked
    • cites Federici et al., 2010 source
    • cites Hauschildt et al., 2019 source
    • cites Storch et al., 2017 source

  • Classified as probably not a substantial claim.

    Premisecitation

    The presence of non-affirming care interferes with treatment for sexual minorities.

    “given that past research has highlighted how the presence of non-affirming care interferes with treatment for sexual minorities (Pinciotti et al., 2021).”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites Pinciotti et al., 2021 source

  • May combine two claims.

    Interpretationreasoning

    The sample exclusively includes individuals who can take time away from work or family obligations, so results may not represent those with such obligations.

    “As such, our results might not be capturing a representative sample among those who are employed or have other obligations at home.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Interpretationown data

    At admission, sexual minorities had slightly worse symptomology, but these differences dissipated by discharge, where outcomes were comparable regardless of sexual orientation.

    “Although non-significant, findings suggested that at admission sexual minorities experience slightly worse levels of symptomology, however, these differences dissipated by program discharge, where outcomes were comparable regardless of sexual orientation.”
    Quote in the paperSubstantial claim

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

    Interpretationreasoning

    The sociocultural context of the program cannot be generalized to all clinicians or programs.

    “Nonetheless, this sociocultural context cannot be generalized to assume similar attitudes among all clinicians or programs, nor does the context necessarily indicate that clinicians will demonstrate awareness of microaggressions or will integrate considerations around participants’ identities into their clinical work.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Interpretationown data

    The sample was predominantly non-Hispanic White and college-educated, which is not generalizable to all individuals with an OCRD.

    “Second, the sample was predominantly non-Hispanic White, holding a bachelor’s degree or some level of college experience, which is not generalizable to all individuals with an OCRD.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Interpretationreasoning

    The study did not examine gender minorities because questions allowing endorsement of non-cisgender identities were not initially included.

    “Lastly, this study did not examine participants identifying as gender minorities because we did not initially include questions that appropriately allow people to endorse non-cisgender identities.”
    Quote in the paperNot a substantial claim
30 of 30

  • The paper relies on this without support.

    No prior studies have examined treatment outcomes for sexual minorities in an intensive/residential treatment program for OCRDs.

    “To the best of our knowledge, no past studies have examined treatment outcomes for sexual minorities in IRT setting for OCRDs”

  • The paper relies on this without support.

    The majority of OCD treatment research has been conducted in predominantly White, cisgender, and heterosexual samples, so it is unclear if first-line treatments remain effective among diverse populations.

    “However, the majority of research on OCD and its treatment has been conducted in samples that comprise predominantly White, cisgender, and heterosexual individuals, thus it is unclear if first-line treatments remain such among diverse populations.”
2 of 2

Statistics that don’t add up

Each reported p-value recomputed from its test statistic and degrees of freedom.

  • Statistic does not fit its p-value and effect size: F(1, 189) = 51.61, p = .368

    Minor

    The paper reports p = .368 here; recomputing from the test statistic and its degrees of freedom gives p < .001. The partial eta squared printed with it (ηp² = .004) corresponds to F ≈ 0.76 and p = .385, which fits the reported p-value and not the statistic: the statistic appears to be the misprint.

    Reported p = .368 · recomputed p < .001

  • Inconsistent p-value: F(1, 186) = 0.80, p = .797

    Minor

    The paper reports p = .797 here; recomputing from the test statistic and its degrees of freedom gives p = .372. The check cannot tell whether the statistic or the p-value is the misprint.

    Reported p = .797 · recomputed p = .372

2 of 2

Statistics recomputed

Every reported test result, recomputed from its test statistic and degrees of freedom. A result shows as not adding up only once an independent check has confirmed it.

  • Doesn’t add upF(1, 189) = 51.61reported p = .368 · recomputed p < .001

    “F(1, 189) = 51.61, p = .368”

  • Doesn’t add upF(1, 186) = 0.8reported p = .797 · recomputed p = .372

    “F(1, 186) = 0.80, p = .797”

  • Consistentt(188) = 1.07reported p = .428 · recomputed p = .286

    “t(188) = 1.07, p = .428”

    The paper states a correction for multiple tests

  • ConsistentF(1, 189) = 261.86reported p < .001 · recomputed p < .001

    “F(1, 189) = 261.86, p < .001”

  • ConsistentF(1, 189) = 3.26reported p = .073 · recomputed p = .073

    “F(1, 189) = 3.26, p = .073”

  • ConsistentF(1, 178) = 25.16reported p < .001 · recomputed p < .001

    “F(1, 178) = 25.16, p < .001”

  • ConsistentF(1, 178) = 1reported p = .32 · recomputed p = .319

    “F(1, 178) = 1.00, p = .320”

  • ConsistentF(1, 178) = 3.3reported p = .071 · recomputed p = .071

    “F(1, 178) = 3.30, p = .071”

  • ConsistentF(1, 186) = 62.7reported p < .001 · recomputed p < .001

    “F(1, 186) = 62.70, p < .001”

  • ConsistentF(1, 186) = 2.42reported p = .122 · recomputed p = .121

    “F(1, 186) = 2.42, p = .122”

  • Consistentt(189) = 1.73reported p = .085 · recomputed p = .085

    “t(189) = 1.73, p = .085”

  • Consistentt(178) = -1.78reported p = .078 · recomputed p = .077

    “t(178) = −1.78, p = .078”

  • Consistentt(186) = 1.76reported p = .081 · recomputed p = .080

    “t(186) = 1.76, p = .081”

13 of 13

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

This check didn’t finish.

Cites

Flagged first, then by citations

2 of the 50 references couldn’t be matched to a known paper.

Research works printed but not linked: 1

  1. Williams, 2014, Sexual orientation symptoms in obsessive compulsive disorder: Assessment and treatment with cognitive behavioral therapy, Directions in Psychiatry, 34, 37

Cited by

Sorted by citations

Related

Authors
Bezahler, A., Kuckertz, J. M., Schreck, M., Narine, K., Dattolico, D., & Falkenstein, M. J.
Affiliations
  • Harvard University (US)
  • William James College (US)
Corresponding author
Bezahler, Andreas
ORCID
Venue
Journal of Obsessive-Compulsive and Related Disorders
Publisher
Elsevier BV
Published
2022-04
Volume
33
Pages
100724
ISSN
2211-3649 (ISSN-L)
DOI
10.1016/j.jocrd.2022.100724
PMC
PMC10201929
OpenAlex
W4224903107
Semantic Scholar
e6e5861a870de2ecae98b3591e2caa52d48156b9
Cited by
15
References
50
Citations by year
2026: 4 · 2025: 4 · 2024: 5 · 2023: 1 · 2022: 1
FWCI
2.17
Type
journal article
Language
en
Open access
Licence
Locations
  • Journal of Obsessive-Compulsive and Related Disorders (publishedVersion)
  • PubMed (publishedVersion)
  • PubMed Central (submittedVersion)
Topics
  • Social Sciences › Psychology › Clinical Psychology › Obsessive-Compulsive Spectrum Disorders
  • Social Sciences › Psychology › Clinical Psychology › Sexuality, Behavior, and Technology
  • Life Sciences › Neuroscience › Cognitive Neuroscience › Autism Spectrum Disorder Research
Keywords
obsessive-compulsive and related disorders, sexual minorities, exposure and response prevention, treatment outcomes, sexual orientation, treatment-seeking behavior, symptom severity, distress tolerance

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