Cited by 62Behavioral Health and InterventionsGrit, Self-Efficacy, and MotivationDecision-Making and Behavioral Economics

A Meta-Analysis of the Effects of Mental Contrasting With Implementation Intentions on Goal Attainment

Open access
Wang, Guoxia, Wang, Yi, Gai, Xiaosong·2021·Frontiers in Psychology

Abstract

Mental contrasting with implementation intentions (MCII) is a self-regulation strategy that enhances goal attainment. This meta-analysis evaluated the efficacy of MCII for goal attainment and explored potential moderators. A total of 21 empirical studies with 24 independent effect sizes (15,907 participants) were included in the analysis. Results showed that MCII to be effective for goal attainment with a small to medium effect size (g = 0.336). The effect was mainly moderated by intervention style. Specifically, studies with interventions based on interactions between participants and experimenters (g = 0.465) had stronger effects than studies with interventions based on interactions between participants and documents (g = 0.277). The results revealed that MCII is a brief and effective strategy for goal attainment with a small to moderate effect; however, because of some publication bias, the actual effect sizes may be smaller. Due to small number of studies in this meta-analysis, additional studies are needed to determine the role of moderator variables.

AI snapshot

Written from the paper’s full text.

TL;DR

This meta-analysis found that mental contrasting with implementation intentions (MCII) improves goal attainment with a small-to-medium effect. Intervention style moderated the effect, with experimenter-led MCII outperforming document-based MCII.

Key findings

  • Across 21 articles and 24 independent effect sizes (15,907 participants), MCII had a significant small-to-medium effect on goal attainment: Hedges’ g = 0.336, 95% CI (0.229, 0.443), under a random-effects model with significant medium heterogeneity [Q(23) = 56.540, I² = 59.321%, p < 0.001].
  • Intervention type was the only significant moderator: experimenter interventions had a larger effect (g = 0.465) than document interventions [g = 0.277; Q(1) = 4.797, p < 0.05].
  • Publication status, sample age, goal domain, dependent measure, and expectation level did not significantly moderate the effect.
  • Publication bias analyses were mixed: the funnel plot showed asymmetry and Egger’s test was significant (t = 5.46, p < 0.01), while fail-safe N was 482 versus a critical value of 130; trim-and-fill adjusted the effect to g = 0.242, 95% CI (0.143, 0.342).

Methods

  • Systematic search of English and Chinese databases for empirical field intervention studies on MCII, excluding laboratory-only experiments and requiring data sufficient to calculate effect sizes and an MCII versus control comparison.
  • Included 24 independent studies from 21 articles, total N = 15,907; coded publication status, sample age, goal domain, intervention type, dependent measure, and goal success expectation.
  • Used Hedges’ g as the effect size, random-effects meta-analysis, heterogeneity tests (Q and I²), moderator analyses, and publication bias analyses (funnel plot, Rosenthal’s fail-safe N, Egger regression, trim-and-fill).

Limitations

  • Stated: the number of studies was small, which may explain why several moderators were not significant; the authors also excluded Kizilcec and Cohen (2017) from moderator analyses because its large sample would dominate subgroups, potentially making moderator results unreliable.
  • Stated: only nine studies reported expectations of success, and expectation variance was small, limiting conclusions about expectation as a moderator.
  • Evident from the text: publication bias analyses indicated possible missing small or null effects, so the actual effect size may be smaller than the unadjusted estimate; moderator variables also covaried across studies, and more MCII intervention studies are needed.

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.3389/fpsyg.2021.565202

Cites

57 of 57 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

6 of 29 cited sources checked · 6 supported · 0 flagged

  • Study design and conductreasoning
    § Limitations · p. 8

    In the moderator analysis, Kizilcec and Cohen (2017) was excluded because of the large sample size in their study, which might render the results of moderator effect unreliable.

    “Moreover, in the moderator analysis, we excluded Kizilcec and Cohen (2017) because of the large sample size in their study, which might render the results of moderator effect unreliable.”
    Quote in the paperSubstantial claim1 of 1 sources checked
    • cites Kizilcec and Cohen (2017) source
  • Findingown data
    § Moderator Analysis · p. 5

    There was no significant difference between MCII effects on self-reported and objective outcomes.

    “For the dependent measures, there was no significant difference between the effect of MCII interventions on selfreported results and the effect of MCII interventions on objective results.”
    Quote in the paperNot a substantial claim
  • Findingown data
    § Moderator Analysis · p. 5

    Sample age did not significantly moderate the effect of MCII.

    “The moderator analysis found no significant moderating effect of sample age on MCII, indicating that the strategy was effective for individuals of different ages.”
    Quote in the paperNot a substantial claim
  • Findingown data
    § [A Meta-Analysis of the Effects of Mental Contrasting With Implementation Intentions on Goal Attainment](https://www.frontiersin.org/articles/10.3389/fpsyg.2021.565202/full) · p. 1

    MCII intervention has a small-to-medium significant effect on goal attainment (g = 0.336, 95% CI 0.229, 0.443) based on 24 independent studies (N = 15,907).

    “Results showed that MCII to be effective for goal attainment with a small to medium effect size (g = 0.336).”
    • Also stated in: § Main Effect · p. 4 · plain
      “Overall, MCII yielded a small to medium significant effect size, g = 0.336, 95% CI (0.229, 0.443).”
    • Also stated in: § Intervention Effect of MCII on Goal Attainment · p. 5 · plain
      “This research evaluated the effect of MCII on goal attainment, using 24 independent studies from 21 articles, with a total effect size of small to medium, g = 0.336.”
    Quote in the paperSubstantial claim
  • Findingown data
    § Publication Bias Analysis · p. 4

    The funnel plot showed strong asymmetry, indicating possible publication bias from missing studies with nonsignificant or small effects.

    “The funnel plot of the effect of MCII on goal attainment showed strong asymmetry (see Figure 2 ), with more studies on the right side than on the left, indicating that some studies with nonsignificant results or small effect sizes may have been missing from the left side, which could indicate publication bias.”
    Quote in the paperNot a substantial claim
  • May combine two claims. 25
  • Classified as probably not a substantial claim. 4
  • May combine two claims.

    Premisecitation
    § The Effect of Mental Contrasting With Implementation Intentions on Goal Attainment · p. 2

    Wittleder et al. (2019) found MCII decreased the number of drinking days for people with hazardous drinking behavior but not for people with non-hazardous drinking behavior, compared to control.

    “Wittleder et al. (2019) found that MCII decreased the number of drinking days for people with hazardous drinking behavior, but not for people with non-hazardous drinking behavior, compared to the control group.”
    Quote in the paperNot a substantial claim1 of 1 sources checked
    • cites Wittleder et al. (2019) source
  • May combine two claims.

    Premisecitation
    § The Effect of Mental Contrasting With Implementation Intentions on Goal Attainment · p. 2

    Sailer et al. (2015) found MCII improved patient exercise in autonomy-focused settings but not in a highly structured setting compared to control.

    “Sailer et al. (2015) found that MCII improved patient' exercise in autonomy-focused settings, but not in a highly structured setting, compared to control condition.”
    Quote in the paperNot a substantial claim1 of 1 sources checked
    • cites Sailer et al. (2015) source
  • May combine two claims.

    Premisecitation
    § Implementation Intention and Its Effects on Goal Attainment · p. 2

    Adriaanse et al. (2011) found implementation intention interventions had a moderate effect for promoting healthy food inclusion (d = 0.51) and smaller effects for diminishing unhealthy eating (d = 0.29).

    “Adriaanse et al. (2011) found implementation intention interventions to have a moderate effect size for promoting the inclusion of healthy food items in one's diet (Cohen's d = 0.51) and smaller effects for diminishing unhealthy eating patterns (Cohen's d = 0.29).”
    Quote in the paperNot a substantial claim1 of 1 sources checked
    • cites Adriaanse et al. (2011) source
  • May combine two claims.

    Premisecitation
    § The Effect of Mental Contrasting With Implementation Intentions on Goal Attainment · p. 2

    Kizilcec and Cohen (2017) found MCII could increase individual goal attainment (MOOCs completion rates) in individualist cultures but not collectivist cultures.

    “For example, Kizilcec and Cohen (2017) found that MCII could increase individual goal attainment (massive open online courses, abbreviated by MOOCs, completion rates) in individualist cultures but not collectivist cultures.”
    Quote in the paperSubstantial claim1 of 1 sources checked
    • cites Kizilcec and Cohen (2017) source
  • Classified as probably not a substantial claim. May combine two claims.

    Premisecitation
    § Future Research Direction · p. 8

    Kizilcec and Cohen's (2017) studies on completing MOOCs found MCII to be effective for learners in individualist cultures but not learners in collectivist cultures.

    “Kizilcec and Cohen's (2017) studies on completing MOOCsincluded Western and Eastern subjects and found MCII to be effective for learners in individualist cultures but not learners in collectivist cultures.”
    Quote in the paperSubstantial claim1 of 1 sources checked
    • cites Kizilcec and Cohen's (2017) source
  • May combine two claims.

    Findingown data
    § Moderator Analysis · p. 5

    Goal domain did not significantly moderate the effect of MCII; the effect size in the academic context (g = 0.255) was not significantly different from other contexts.

    “Although the effect size in the academic context ( g = 0.255) was relatively lower than in other contexts, the difference was not significant [ Q (3) = 3.075, p = 0.380].”
    Quote in the paperNot a substantial claim
  • May combine two claims.

    Findingown data
    § Publication Bias Analysis · p. 4

    Fail-safe N was 482, greater than the critical value of 130, indicating that the results were reliable and there was no publication bias.

    “Fail-safe N for this study was 482, greater than the critical value of 130 (5 k + 10), indicating that the results were reliable, and there was no publication bias.”
    Quote in the paperSubstantial claim
  • May combine two claims.

    Findingown data
    § [A Meta-Analysis of the Effects of Mental Contrasting With Implementation Intentions on Goal Attainment](https://www.frontiersin.org/articles/10.3389/fpsyg.2021.565202/full) · p. 1

    Type of intervention significantly moderates the MCII effect; experimenter interventions (g = 0.465) have a larger effect than document interventions (g = 0.277).

    “The effect was mainly moderated by intervention style. Specifically, studies with interventions based on interactions between participants and experimenters (g = 0.465) had stronger effects than studies with interventions based on interactions between participants and documents (g = 0.277).”
    Quote in the paperSubstantial claim
  • May combine two claims.

    Findingown data
    § Moderator Analysis · p. 5

    Expectation level did not significantly moderate the MCII effect; effect sizes for high expectation (g = 0.297) and low expectation (g = 0.481) did not differ significantly.

    “The expectation level was not a significant moderator either, and the effect size of MCII on high expectation ( g = 0.297) and low expectation goals ( g = 0.481) did not differ significantly.”
    Quote in the paperNot a substantial claim
  • May combine two claims.

    Findingown data
    § Publication Bias Analysis · p. 4

    The trim-and-fill method trimmed eight studies, and the adjusted effect size was 0.242, 95% CI (0.143, 0.342).

    “Finally, we used the 'trim-and-fill' method to trim eight studies, and the adjusted values were 0.242, 95% CI (0.143, 0.342).”
    Quote in the paperSubstantial claim
  • May combine two claims.

    Findingown data
    § Intervention Effect of MCII on Goal Attainment · p. 6

    MCII effectively promotes individual goal achievement, with a small to medium overall effect size (g = 0.336).

    “This meta-analysis found MCII to be a concise, low-cost, and effective self-regulation strategy for goal achievement, which can be used to promote goal attainment.”
    • Also stated in: § CONCLUSIONS · p. 9 · plain
      “(1) MCII can effectively promote individual goal achievement, with a small to medium overall effect size ( g = 0.336)”
    • Also stated in: § Future Research Direction · p. 8 · plain
      “Although the overall effect size of the MCII strategy was small to medium, as expected”
    Quote in the paperSubstantial claim
  • May combine two claims.

    Premisecitation
    § Implementation Intention and Its Effects on Goal Attainment · p. 2

    Implementation intentions promote accessibility of situation cues and strengthen links between the anticipated situation and expected behavior so that goal-relevant behavior appears automatically upon encountering cues.

    “Implementation intentions promote accessibility of situation cues (Sheeran and Webb, 2004) and strengthen the links between the anticipated situation and the expected behavior so that, upon encountering the relevant cues, goal-relevant behavior would appear automatically (Webb and Sheeran, 2007).”
    Quote in the paperSubstantial claim0 of 2 sources checked
    • cites Sheeran and Webb, 2004

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

    • cites Webb and Sheeran, 2007 source
  • May combine two claims.

    Premisecitation
    § Mental Contrasting and Its Effects on Goal Attainment · p. 1

    Mental contrasting activates expectations of success: high expectations lead to commitment and pursuit; low expectations lead to postponing or abandoning wishes.

    “Mentally contrasting a desired future with impeding reality can activate expectations of success: when expectations of success are high, people fully commit and pursue their goals; when expectations of success are low, people postpone or abandon the fulfillment of their wishes (Oettingen, 2000, 2012).”
    Quote in the paperSubstantial claim0 of 2 sources checked
    • cites Oettingen, 2000 source
    • cites Oettingen, 2012 source
  • May combine two claims.

    Interpretationown data
    § [A Meta-Analysis of the Effects of Mental Contrasting With Implementation Intentions on Goal Attainment](https://www.frontiersin.org/articles/10.3389/fpsyg.2021.565202/full) · p. 1

    MCII is a brief and effective strategy for goal attainment with a small to moderate effect.

    “The results revealed that MCII is a brief and effective strategy for goal attainment with a small to moderate effect; however, because of some publication bias, the actual effect sizes may be smaller.”
    Quote in the paperSubstantial claim
  • May combine two claims.

    Premisecitation
    § Mental Contrasting and Its Effects on Goal Attainment · p. 2

    Cross and Sheffield (2019) found a main effect of a mental contrasting intervention on adults' physical health outcomes, with adjusted Hedges' g = 0.28, 95% CI (0.13, 0.43) at up to 4 weeks, and an increased effect g = 0.38, 95% CI (0.20, 0.55) at up to 3 months.

    “A meta-analysis by Cross and Sheffield (2019) found a main effect of a mental contrasting intervention on adults' physical health outcomes, with adjusted Hedges' g = 0.28, 95% CI (0.13, 0.43) at up to 4 weeks, and an increased effect [ g = 0.38, 95% CI (0.20, 0.55)] at up to 3 months.”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites Cross and Sheffield (2019) source
  • May combine two claims.

    Interpretationreasoning
    § Publication Bias Analysis · p. 4

    The main conclusion of the meta-analysis was relatively effective and reliable despite some possible publication bias.

    “In conclusion, while analyses indicated that the current study might have had some publication bias, the main conclusion of this meta-analysis was found to be relatively effective and reliable.”
    Quote in the paperSubstantial claim
  • May combine two claims.

    Premisecitation
    § Mental Contrasting and Its Effects on Goal Attainment · p. 1

    Mental contrasting can transform positive fantasies into binding goals, urging people to overcome obstacles to attain goals.

    “After imagining a positive future, thinking about obstacles that impede the realization of wishes (i.e., mental contrasting) can transform people's positive fantasies into binding goals, urging them to overcome obstacles in reality to attain their goals (Oettingen, 2000).”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites Oettingen, 2000 source
  • May combine two claims.

    Premisecitation
    § Mental Contrasting and Its Effects on Goal Attainment · p. 1

    Thinking only about positive future outcomes decreases goal-relevant efforts and the likelihood of goal achievement.

    “Several studies by Oettingen and colleagues found that thinking only about positive future outcomes decreases goal-relevant efforts, as well as the likelihood of goal achievement (e.g., Oettingen and Mayer, 2002; Kappes H. B. et al., 2012; Oettingen et al., 2016).”
    Quote in the paperSubstantial claim0 of 3 sources checked
    • cites Oettingen and Mayer, 2002 source
    • cites Kappes H. B. et al., 2012 source
    • cites Oettingen et al., 2016 source
  • May combine two claims.

    Interpretationnone given
    § Publication Bias Analysis · p. 4

    Five unpublished master's theses and doctoral dissertations were included, accounting for 21% of the corpus, sufficient to eliminate publication bias.

    “Five unpublished master's theses and doctoral dissertations were included in the meta-analysis, accounting for 21% of the corpus-sufficient to eliminate publication bias.”
    Quote in the paperNot a substantial claim
  • May combine two claims.

    Premisecitation
    § Implementation Intention and Its Effects on Goal Attainment · p. 2

    Belanger-Gravel, Godin and Amireault's (2013) meta-analysis found implementation intention interventions on physical activity had a small to medium effect at postintervention (g = 0.31, 95% CI 0.11, 0.51) and follow-up (g = 0.24, 95% CI 0.13, 0.35).

    “Belanger-Gravel, Godin and Amireault's (2013) meta-analysis of implementation intention interventions on physical activity found small to medium effect size [Hedge's g = 0.31 (95% CI = 0.11, 0.51) at postintervention; Hedge's g = 0.24 (95% CI = 0.13, 0.35) at follow-up].”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites Belanger-Gravel, Godin and Amireault's (2013) source
  • May combine two claims.

    Premisecitation
    § Implementation Intention and Its Effects on Goal Attainment · p. 2

    Presseau et al. (2017) found action and/or coping planning interventions had a small to medium effect on objectively assessed health behavior (d 0.14-0.37) and a medium effect on self-reported health behavior (d 0.19-0.77).

    “Presseau et al. (2017) found that action and/or coping planning (implementation intention) interventions had a small to medium effect on objectively assessed health behavior (Cohen's d ranged from 0.14 to 0.37) and a medium effect on self-reported health behavior (Cohen's d ranged from 0.19 to 0.77).”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites Presseau et al. (2017)

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

  • May combine two claims.

    Premisecitation
    § Implementation Intention and Its Effects on Goal Attainment · p. 2

    Gollwitzer and Sheeran (2006) found implementation intentions had a positive effect on goal attainment in achievements, relationships, and health, with a medium to large effect size Cohen's d = 0.65 (95% CI = 0.6, 0.7).

    “Gollwitzer and Sheeran (2006) found that implementation intentions had a positive effect on improving goal attainment in terms of achievements, relationships, and health, with a medium to large effect size [Cohen' d = 0.65 (95% CI = 0.6, 0.7)].”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites Gollwitzer and Sheeran (2006) source
  • Classified as probably not a substantial claim.

    Premisecitation
    § Type of Intervention · p. 3

    Face-to-face interactions have a better effect on behavior change than document interventions.

    “As face-to-face interactions have been found to have a better effect on behavior change than documents interventions (Elder et al., 2005), we hypothesized that experimenter interventions would have a larger effect size than document interventions.”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites Elder et al., 2005 source
  • Classified as probably not a substantial claim.

    Premisecitation
    § Intervention Effect of MCII on Goal Attainment · p. 6

    Mental contrasting and implementation intention complement each other.

    “Although we found that effect size of MCII interventions was similar to interventions employing either mental contrasting or implementation intentions, we recommend using MCII as mental contrasting and implementation intention complement each other (Kappes et al., 2012b, 2013; Oettingen, 2012).”
    Quote in the paperSubstantial claim0 of 2 sources checked
    • cites Kappes et al., 2012b, 2013

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

    • cites Oettingen, 2012 source
  • May combine two claims.

    Interpretationown data
    § Moderators of the Effect of MCII on Goal Attainment · p. 8

    MCII was effective for people of different ages, for goal pursuit in different domains, and for different measures of behavior change.

    “In addition, the effect size did not vary with sample age, goal domain, or dependent measures, revealing that MCII was effective for people of different ages, for goal pursuit in different domains, and for different measures of behavior change.”
    Quote in the paperSubstantial claim
  • May combine two claims.

    Premisecitation
    § Expectations of Success · p. 3

    When expectations of success are high, people firmly commit to pursuing the desired outcome; when low, they postpone or abandon achievement.

    “When expectations of success are high, people will firmly commit to pursuing the desired outcome; when expectations of success are low, people will postpone or abandon the achievement of their goals (Oettingen, 2012).”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites Oettingen, 2012 source
  • Probably not a substantial claim: may not pass S1 (asserted), S3 (load-bearing). May combine two claims.

    Interpretationreasoning
    § Future Research Direction · p. 8

    MCII should not lead to enhanced effort when members of collectivist cultures focus on individualist wishes, but it should increase effort and goal attainment when people focus on their collectivist wishes.

    “MCII should not lead to enhanced effort when members of collectivist cultures focus on individualist wishes, but it should increase effort and goal attainment when people focus on their collectivist wishes.”
    Quote in the paperNot a substantial claim
    • The authors state this as an assumption: MCII could have a similar effect size on collectivist wishes and goals in collectivist cultures as on individualist wishes and goals in individualist cultures.
27 of 27
  • The paper relies on this without support.

    Studies with significant results are easier to publish, so published articles might overestimate the effect of MCII.

    “Studies with significant results could be easier to publish, so published articles might overestimate the effect of MCII.”
  • The authors state this as an assumption.

    MCII could have a similar effect size on collectivist wishes and goals in collectivist cultures as on individualist wishes and goals in individualist cultures.

    “We assumed that MCII could have the similar effect size on collectivist wishes and goals in collectivist cultures as on individualist wishes and goals in individualist cultures.”
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.

  • ConsistentQ(3) = 3.075reported p = .38 · recomputed p = .380

    “Q (3) = 3.075, p = .380”

1 of 1

Self-check

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

Each contradiction between two passages listed here was confirmed by an independent check.

  • Publication bias is described as both eliminated and present

    Minor

    The results state that including unpublished studies was sufficient to eliminate publication bias, while the abstract says that some publication bias remains.

  • Wang and Gai study has conflicting goal-domain classifications

    Minor

    The text places Wang and Gai (2016) in the personal goal domain, whereas Table 1 classifies it as Academic.

2 of 2

Cites

Flagged first, then by citations

Research works printed but not linked: 4

  1. Oettingen, 2016, Problems with positive thinking and how to overcome them, 547
  2. Presseau, 2017, Cochrane review and meta-analysis of trials of action and/or coping planning for health behaviour change [Abstract], Euro. Health Psychol., 19, 885
  3. Sheeran, 2004, Implementation intentions and goal achievement: experimental tests of explanatory processes, Psychol. Health, 19, 157
  4. Wang, 2014, The effect of mental contrasting with implementation intention on goal pursuit

Cited by

Sorted by citations

Authors
Wang, G., Wang, Y., & Gai, X.
Affiliations
Northeast Normal University (CN)
Corresponding author
Wang, Guoxia
Venue
Frontiers in Psychology
Published
2021-05-12
Volume
12
Pages
565202-565202
ISSN
1664-1078 (ISSN-L)
OpenAlex
W3160299755
Cited by
62
References
57
Citations by year
2026: 4 · 2025: 19 · 2024: 13 · 2023: 21 · 2022: 4 · 2021: 1
FWCI
1.93
Type
journal article
Language
en
Open access
Locations
  • Frontiers in Psychology (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • PubMed Central (submittedVersion, cc-by)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Topics
  • Social Sciences › Psychology › Applied Psychology › Behavioral Health and Interventions
  • Social Sciences › Psychology › Social Psychology › Grit, Self-Efficacy, and Motivation
  • Social Sciences › Decision Sciences › General Decision Sciences › Decision-Making and Behavioral Economics
Keywords
mental contrasting with implementation intentions, goal achievement, self-regulation, implementation intentions, mental contrasting, moderators of intervention effectiveness, brief intervention

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 2026-10-12.

Classified by jev-1.13-20260917 (gold-guideline-v0.2) on 2026-10-12.

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