CoChat
Sign Up
Cited by 404Psychological Well-being and Life SatisfactionQuality of Life MeasurementPsychometric Methodologies and Testing

Measuring Subjective Wellbeing: Recommendations on Measures for use by National Governments

Open access
DOLAN, PAUL, METCALFE, ROBERT·2012·Journal of Social Policy
DOI 10.1017/s0047279411000833
Open this paper in CoChat — free accountOpen PDF

Abstract

Abstract Governments around the world are now beginning to seriously consider the use of measures of subjective wellbeing (SWB) – ratings of thoughts and feelings about life – for monitoring progress and for informing and appraising public policy. The mental state account of wellbeing upon which SWB measures are based can provide useful additional information about who is doing well and badly in life when compared to that provided by the objective list and preference satisfaction accounts. It may be particularly useful when deciding how best to allocate scarce resources, where it is desirable to express the benefits of intervention in a single metric that can be compared to the costs of intervention. There are three main concepts of SWB in the literature – evaluation (life satisfaction), experience (momentary mood) and eudemonia (purpose) – and policy-makers should seek to measure all three, at least for the purposes of monitoring progress. There are some major challenges to the use of SWB measures. Two related and well-rehearsed issues are the effects of expectations and adaptation on ratings. The degree to which we should allow wellbeing to vary according to expectations and adaptation are vexing moral problems but information on SWB can highlight what difference allowing for these considerations would have in practice (e.g. in informing prioiritisation decisions), which can then be fed into the normative debate. There are also questions about precisely what attention shoul…

Integrity signals

Registry

Crossref · 10.1017/s0047279411000833

Cites

125 of 125 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Claims the paper makes

11 of 56 cited sources checked · 7 supported · 0 flagged · accuracy not yet measured

  • Premisecitation

    The evidence from the literature assessing the link between income and SWB is that this relationship is positive and modest.

    “The evidence from the literature assessing the link between income and SWB is that this relationship is positive and modest (Stevenson and Wolfers, 2008), although there are some differences depending on what measure of SWB is used (Kahneman and Deaton, 2010), and whether other people's income is included in the assessment (Luttmer, 2005;Layard et al., 2010).”
    Quote in the paperNot a substantial claim1 of 1 sources checked
    • cites Stevenson and Wolfers, 2008 source
  • Premisecitation

    It is possible to estimate monetary values for non-market goods from SWB data by estimating the amount of income that has exactly the same effect on SWB as the non-market good.

    “It is possible to estimate monetary values for non-market goods from SWB data by estimating the amount of income that has exactly the same effect on SWB as the non-market good (Dolan et al., 2011).”
    Quote in the paperSubstantial claim1 of 1 sources checked
    • cites Dolan et al., 2011
  • Premisecitation

    Respondents in the German Socio-Economic Panel have a tendency to move away from the endpoints of response scales over time.

    “Frick et al. (2006) show that respondents in the German Socio-Economic Panel have a tendency to move away from the endpoints of response scales over time.”
    Quote in the paperNot a substantial claim1 of 1 sources checked
    • cites Frick et al. (2006) source

      The Results (pp. 25, 30) say that SOEP respondents were more likely to choose the highest life-satisfaction categories in early waves, and the authors report a narrowing difference over time. That supports movement away from the high end of one satisfaction scale, but not a general tendency to move away from both endpoints of response scales. (LLM, conf=0.87)

      Experimental — accuracy not yet measured
  • Premisecitation

    DRM data on affect have generally found weak associations between SWB and these events.

    “DRM data on affect have generally found weak associations between SWB and these events (Kahneman et al., 2004;Knabe et al., 2010).”
    Quote in the paperNot a substantial claim1 of 2 sources checked
    • cites Kahneman et al., 2004 source
    • cites Knabe et al., 2010 source

      The Discussion (p. 27) reports that this DRM study found no significant difference in day-to-day experienced well-being between employed and unemployed people, despite a difference in life satisfaction. That supports a weak association for unemployment, but the paper does not establish that DRM studies have generally found weak associations with the unspecified events in the claim. (LLM, conf=0.83)

      Experimental — accuracy not yet measured
  • Premisecitation

    There are some differences between life satisfaction and the ladder of life, notably in relation to income.

    “There are some differences between life satisfaction and the ladder of life, notably in relation to income (Helliwell, 2008).”
    Quote in the paperNot a substantial claim1 of 1 sources checked
    • cites Helliwell, 2008 source
  • Classified as probably not a substantial claim. 14
  • May combine two claims. 15

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

    Interpretationcitation

    SWB can be used to make a strong case for unemployment programmes given the significant reduction in SWB associated with any periods of unemployment.

    “More specifically, SWB could be used to make a strong case for unemployment programmes given the significant reduction in SWB associated with any periods of unemployment (Clark et al., 2004;Clark, 2010).”
    Quote in the paperNot a substantial claim1 of 2 sources checked
    • cites Clark et al., 2004 source

      The Results (page unavailable) report that life satisfaction fell by more than half a point, on average, during the reaction phase of unemployment. But the Method (page unavailable) limits the study to people who experienced one unemployment episode and then remained employed; it does not establish a significant reduction in all measures of SWB for any period of unemployment. The case for unemployment programmes is the citing authors’ policy inference, not a finding attributed to this source. (LLM, conf=0.83)

      Experimental — accuracy not yet measured
    • cites Clark, 2010

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

  • May combine two claims.

    Premisecitation

    There are differences in the income-SWB relationship depending on what measure of SWB is used and whether other people's income is included in the assessment.

    “although there are some differences depending on what measure of SWB is used (Kahneman and Deaton, 2010), and whether other people's income is included in the assessment (Luttmer, 2005;Layard et al., 2010).”
    Quote in the paperSubstantial claim2 of 3 sources checked
    • cites Kahneman and Deaton, 2010 source
    • cites Luttmer, 2005 source
    • cites Layard et al., 2010 source

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

    Interpretationcitation

    Expected gains in SWB could be computed for different policy areas and used to decide which forms of spending will lead to the largest increases in SWB relative to their costs.

    “Expected gains in SWB could be computed for different policy areas and this information could be used to decide which forms of spending will lead to the largest increases in SWB relative to their costs (Dolan and Metcalfe, 2008).”
    Quote in the paperNot a substantial claim1 of 1 sources checked
    • cites Dolan and Metcalfe, 2008

      The Conclusion (section 6; page unavailable) says SWB could generate monetary values for public policy and help inform the allocation of scarce resources. It does not describe computing expected SWB gains across different policy areas or ranking spending by SWB gain relative to cost; it also says the valuation method needs more research. (LLM, conf=0.82)

      Experimental — accuracy not yet measured

  • May combine two claims.

    Premisecitation

    Self-acceptance and environmental mastery were associated with evaluations but positive relations with others, purpose in life, personal growth and autonomy were less well correlated.

    “In a comparison of 'eudemonic' measures and evaluations of life satisfaction and happiness, Ryff and Keyes (1995) found that self-acceptance and environmental mastery were associated with evaluations but that positive relations with others, purpose in life, personal growth and autonomy were less well correlated.”
    Quote in the paperSubstantial claim1 of 1 sources checked
    • cites Ryff and Keyes, 1995 source

  • May combine two claims.

    Premisecitation

    Income is more highly correlated with ladder of life responses than with feelings, which are themselves more highly correlated with health than the ladder.

    “Work on the Gallup Poll by Diener et al. (2010) and Kahneman and Deaton (2010) shows that income is more highly correlated with ladder of life responses than with feelings, which are themselves more highly correlated with health than the ladder.”
    Quote in the paperNot a substantial claim1 of 2 sources checked
    • cites Diener et al., 2010

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

    • cites Kahneman and Deaton, 2010 source

  • May combine two claims.

    Premisecitation

    The three accounts of wellbeing (objective lists, preference satisfaction, mental states) meet the three conditions of being theoretically rigorous, policy relevant, and empirically robust.

    “There are three accounts of wellbeing (Parfit, 1984;Sumner, 1996) that meet the three conditions (i) objective lists; (ii) preference satisfaction; and (iii) mental states (or SWB).”
    Quote in the paperSubstantial claim0 of 2 sources checked
    • cites Parfit, 1984

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

    • cites Sumner, 1996

      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).

    Premisecitation

    There are three main accounts of wellbeing: objective lists, preference satisfaction, and mental states (subjective wellbeing).

    “Following Parfit (1984), there are three main accounts of wellbeing -objective lists, preference satisfaction and mental states (or subjective wellbeing) -and all three are important for public policy.”
    • Also stated in: § Accounts of wellbeing · plain
      “There are three accounts of wellbeing (Parfit, 1984;Sumner, 1996) that meet the three conditions (i) objective lists; (ii) preference satisfaction; and (iii) mental states (or SWB).”
    Quote in the paperNot a substantial claim0 of 2 sources checked
    • cites Parfit, 1984

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

    • cites Sumner, 1996

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

  • May combine two claims.

    Premisecitation

    SWB can be used for assessing the consequences of cigarette taxation, air pollution, flooding, and the risk of terrorism.

    “SWB can also be used for assessing the consequences of cigarette taxation (Gruber and Mullainatha, 2005), air pollution (Luechinger, 2009), flooding (Luechinger and Rasacky, 2009) and the risk of terrorism (Metcalfe et al., 2011).”
    Quote in the paperNot a substantial claim0 of 3 sources checked
    • cites Gruber and Mullainatha, 2005 source
    • cites Luechinger, 2009 source
    • cites Luechinger and Rasacky, 2009

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

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

    Interpretationcitation

    Some measures might be more or less amenable to change by individuals and policy-makers, thus impacting upon debates about agency in and over SWB.

    “Importantly, some measures might be more or less amenable to change by individuals and policy-makers, thus impacting upon debates about agency in and over SWB (see Cooper and Lousada, 2005;Ryan and Sapp, 2007;Taylor, 2011).”
    Quote in the paperNot a substantial claim0 of 3 sources checked
    • cites Cooper and Lousada, 2005

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

    • cites Ryan and Sapp, 2007 source
    • cites Taylor, 2011 source

  • Classified as probably not a substantial claim.

    Premisecitation

    There are three main concepts of SWB in the literature: evaluation (life satisfaction), experience (momentary mood), and eudemonia (purpose).

    “There are three main concepts of SWB in the literature -evaluation (life satisfaction), experience (momentary mood) and eudemonia (purpose) -and policy-makers should seek to measure all three, at least for the purposes of monitoring progress.”
    • Also stated in: § Measuring SWB · plain
      “Here we distinguish between three broad categories of measure: (i) evaluation; (ii) experience; and (iii) 'eudemonic'.”
    Quote in the paperSubstantial claim0 of 3 sources checked
    • cites Kahneman and Riis, 2005

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

    • cites Dolan et al., 2006

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

    • cites Waldron, 2010

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

  • May combine two claims.

    Premisecitation

    Life satisfaction has been shown to be correlated with income (both absolute and relative), employment status, marital status, health, personal characteristics (age, gender, and personality) and major life events.

    “Life satisfaction has been shown to be correlated with income (both absolute and relative), employment status, marital status, health, personal characteristics (age, gender, and personality) and major life events (see Dolan et al. (2008) for a recent review).”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites Dolan et al., 2008

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

  • May combine two claims.

    Premisecitation

    Peasgood (2008) used the British Household Panel Survey to examine objective wellbeing, preference satisfaction and SWB scores for the same individuals and showed a dramatic difference between the accounts for those with children, people who commute long distances, those with a degree and between men and women.

    “Peasgood (2008) used the British Household Panel Survey (BHPS) to examine objective wellbeing, preference satisfaction and SWB scores for the same individuals.She shows that there is a dramatic difference between the accounts for those with children, people who commute long distances, those with a degree and between men and women.”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites Peasgood, 2008 source

  • Probably not a substantial claim: may not pass S2 (checkable).

    Interpretationreasoning

    SWB measures may be particularly useful when deciding how best to allocate scarce resources, where it is desirable to express the benefits of intervention in a single metric that can be compared to the costs of intervention.

    “It may be particularly useful when deciding how best to allocate scarce resources, where it is desirable to express the benefits of intervention in a single metric that can be compared to the costs of intervention.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S2 (checkable), S4 (based).

    Interpretationnone given

    Different approaches to measurement could have significant consequences for inferences drawn from SWB data.

    “Different approaches to measurement could have significant consequences for inferences drawn from SWB data.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S2 (checkable).

    Interpretationreasoning

    Monitoring SWB could be important in ensuring that other changes that affect society do not reduce overall wellbeing.

    “Monitoring SWB could be important in ensuring that other changes that affect society do not reduce overall wellbeing.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S4 (based).

    Interpretationnone given

    The mental state account of wellbeing, on which SWB measures are based, can provide useful additional information about who is doing well and badly in life compared to objective list and preference satisfaction accounts.

    “The mental state account of wellbeing upon which SWB measures are based can provide useful additional information about who is doing well and badly in life when compared to that provided by the objective list and preference satisfaction accounts.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).

    Premisenone given

    There has not been a thorough comparison of the three measures of SWB due to no large-scale longitudinal or repeated cross-sectional survey containing all the measures.

    “There has not been a thorough comparison of the three measures of SWB due to no large-scale longitudinal or repeated cross-sectional survey containing all the measures.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Premisecitation

    Some conditions, like unemployment, continue to draw attention to them and continue to affect SWB long after the event.

    “Some conditions, like unemployment it seems, continue to draw attention to them and continue to affect SWB long after the event (Lucas et al., 2003;Lucas, 2005).”
    Quote in the paperNot a substantial claim0 of 2 sources checked
    • cites Lucas et al., 2003 source
    • cites Lucas, 2005 source

  • Classified as probably not a substantial claim.

    Interpretationnone given

    Surveys that use a scale running from completely dissatisfied to completely satisfied without making clear where dissatisfied stops and satisfied starts make it difficult to interpret the scores.

    “Some of these surveys use a scale running from completely dissatisfied to completely satisfied, and they do not make clear where on the scale dissatisfied stops and satisfied starts.This makes it difficult to interpret the scores.”
    Quote in the paperSubstantial claim
    • Rests on an assumption: Some surveys use a scale running from completely dissatisfied to completely satisfied and do not make clear where on the scale dissatisfied stops and satisfied starts.

  • May combine two claims.

    Premisecitation

    For life satisfaction, unemployment is very bad, marriage is pretty good at least to start with, children have no effect, retirement is pretty good at least to start, but there is considerable heterogeneity.

    “For life satisfaction, it appears that unemployment is very bad, marriage is pretty good at least to start with, children have no effect, retirement is pretty good at least to start, but there is considerable heterogeneity (Calvo et al., 2007).”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites Calvo et al., 2007

  • May combine two claims.

    Interpretationcitation

    If later responses are influenced by earlier ones, then the earlier ones are salient at the time of the later assessment.

    “The relationship between earlier and later responses can be seen as an issue of scaling and salience: if later responses are influenced by earlier ones, then the earlier ones are salient at the time of the later assessment (as shown in the study by Dolan and Metcalfe, 2010).”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites Dolan and Metcalfe, 2010 source

  • May combine two claims.

    Premisecitation

    Evaluations and experience-based measures may sometimes produce similar results, but often they do not.

    “Evaluations and experience-based measures may sometimes produce similar results (Blanchflower, 2009), but often they do not.”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites Blanchflower, 2009 source

  • May combine two claims.

    Premisecitation

    Positive and negative affect are somewhat independent of one another and should therefore be measured separately.

    “There is some evidence, however, that positive and negative affect are somewhat independent of one another and should therefore be measured separately (Diener and Emmons, 1984).”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites Diener and Emmons, 1984

      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

    Time spent with children is relatively more rewarding than pleasurable, and time spent watching television is relatively more pleasurable than rewarding.

    “For example, time spent with children is relatively more rewarding than pleasurable, and time spent watching televisions is relatively more pleasurable than rewarding.”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites White and Dolan, 2009 source

  • Probably not a substantial claim: may not pass S2 (checkable). May combine two claims.

    Interpretationreasoning

    Information on all three accounts of wellbeing can illuminate what difference expectations and adaptation make in practice and such information can be fed into the normative debate.

    “But information on all three accounts of wellbeing can illuminate what difference expectations and adaptation make in practice and such information can be fed into the normative debate.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S2 (checkable).

    Interpretationreasoning

    In practice, what counts as a good life is dynamic.

    “In practice, what counts as a good life is going to be dynamic too.”
    Quote in the paperNot a substantial claim
26 of 26

  • The paper relies on this without support.

    There is an urgent need to consider how best to measure SWB in large samples.

    “This paper and its motivation derives directly from the urgent need to consider how best to measure SWB in large samples.”

  • The paper relies on this without support.

    There is a need for a fuller consideration of, and conceptual clarity about, how SWB should be measured for policy purposes.

    “but there is a need for a fuller consideration of, and conceptual clarity about, how SWB should be measured for policy purposes.”

  • The paper relies on this without support.

    Using happiness or life satisfaction yields very similar results, in terms of the impact of key variables.

    “Using happiness or life satisfaction yields very similar results, in terms of the impact of key variables.”

  • The paper relies on this without support.

    Some surveys use a scale running from completely dissatisfied to completely satisfied and do not make clear where on the scale dissatisfied stops and satisfied starts.

    “Some of these surveys use a scale running from completely dissatisfied to completely satisfied, and they do not make clear where on the scale dissatisfied stops and satisfied starts.”

  • The paper relies on this without support.

    The experience measures generally calibrate the scales from 'not at all'.

    “the experience measures generally calibrate the scales from 'not at all'.”

  • The paper relies on this without support.

    The BHPS does not ask about satisfaction with mental wellbeing and with the wellbeing of your children.

    “The BHPS does not ask about satisfaction with mental wellbeing and with the wellbeing of your children, which are obvious omissions from the BHPS domains.”

  • The paper relies on this without support.

    Both mental wellbeing and the wellbeing of your children are potentially important determinants of wellbeing.

    “Both of these domains are potentially important determinants of wellbeing (as distinct, in the case of children, from simply knowing whether someone has children or not).”

  • The paper relies on this without support.

    Mental health measures are most likely to only pick up the negative side of the domain.

    “It is important to ask about general mental wellbeing and not mental health, since the latter is most likely to only pick up the negative side of the domain.”

  • The paper relies on this without support.

    Expectations and adaptation feed directly into scaling effects.

    “Expectations and adaptation feed directly into scaling effects.”

  • The paper relies on this without support.

    The GSOEP, WVS and Defra surveys use a 0-10 scale.

    “The GSOEP, WVS and Defra surveys use a 0-10 scale.”

  • The paper relies on this without support.

    There are no general questions about purpose and meaning in life.

    “There are no general questions about purpose and meaning in life and so we have based our recommendations on a suggestion by Felicia Huppert.”
11 of 11

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.

  • Recommended anxiety question differs from the table

    Major

    The paper recommends asking how anxious respondents felt yesterday, but the corresponding monitoring question in Table 1 asks how worried they felt. These are different questions, despite the text saying the four recommended questions appear in the table's first column.

  • Kahneman and Thaler citation years disagree

    Minor

    The in-text citation gives 2005, while the reference list gives 2006 for Kahneman and Thaler.

2 of 2

Cites

Flagged first, then by citations

8 of the 133 references couldn’t be matched to a known paper.

Research works printed but not linked: 13

  1. 2007, Social trends
  2. Parfit, 1984, Reasons and Persons
  3. Blanchflower, 2009, National Time Accounting and Subjective Well-Being
  4. Kahneman, 2005, The Science of Wellbeing: Integrating Neurobiology, Psychology, and Social Science
  5. Hurka, 1993, Perfectionism
  6. Donovan, 2002, Life Satisfaction: The State of Knowledge and Implications for Government
  7. Cantril, 1965, The Patterns of Human Concern
  8. Clark, 2010, International Differences in Well-Being
  9. Dolan, 2006, Review of Research on the Influences on Personal Wellbeing and Application to Policy
  10. Friedli, 2007, Mental Health Promotion: Building an Economic Case
  11. Treasury, 2010, Budget 2010
  12. 2004, What Drives Satisfaction with Local Government?
  13. 2008, Guide to the Methods of Technology Appraisal

Cited by

Sorted by citations

Related

Authors
DOLAN, P., & METCALFE, R.
Affiliations
  • London School of Economics and Political Science (GB)
  • University of Oxford (GB)
ORCID
Venue
Journal of Social Policy
Publisher
Cambridge University Press (CUP)
Published
2012-01-12
Volume
41
Issue
2
Pages
409-427
ISSN
  • 0047-2794 (ISSN-L)
  • 1469-7823
DOI
10.1017/s0047279411000833
OpenAlex
W2146619620
Semantic Scholar
4c6230065b5e9a5dd3be6b341c78161441bc9682
Cited by
404
References
133
Citations by year
2026: 21 · 2025: 27 · 2024: 30 · 2023: 32 · 2022: 47 · 2021: 54 · 2020: 27 · 2019: 31 · 2018: 24 · 2017: 28 · 2016: 27 · 2015: 19 · 2014: 18 · 2013: 17 · 2012: 2
FWCI
27.00
Type
journal article
Language
en
Open access
Licence
www.cambridge.org/core/terms (unspecified)
Locations
  • Journal of Social Policy (publishedVersion)
  • London School of Economics and Political Science Research Online (London School of Economics and Political Science) (submittedVersion)
Topics
  • Social Sciences › Psychology › Social Psychology › Psychological Well-being and Life Satisfaction
  • Social Sciences › Sociology and Political Science › Quality of Life Measurement
  • Social Sciences › Decision Sciences › Management Science and Operations Research › Psychometric Methodologies and Testing
Keywords
subjective well-being, well-being measurement, life satisfaction, momentary mood, eudaimonia, public policy monitoring, resource allocation, cost-benefit analysis, adaptation, questionnaire development

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 2026-10-11.

Classified by jev-1.13-20260917 (gold-guideline-v0.2) on 2026-10-11.

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