CoChat
Sign Up
Cited by 667Neural and Behavioral Psychology StudiesDecision-Making and Behavioral EconomicsMemory Processes and Influences

Metacognition in human decision-making: confidence and error monitoring

Open access
Yeung, Nick, Summerfield, Christopher·2012·Philosophical Transactions of the Royal Society B: Biological Sciences
DOI 10.1098/rstb.2011.0416PMC PMC3318764
Open this paper in CoChat — free accountOpen PDF

Abstract

People are capable of robust evaluations of their decisions: they are often aware of their mistakes even without explicit feedback, and report levels of confidence in their decisions that correlate with objective performance. These metacognitive abilities help people to avoid making the same mistakes twice, and to avoid overcommitting time or resources to decisions that are based on unreliable evidence. In this review, we consider progress in characterizing the neural and mechanistic basis of these related aspects of metacognition—confidence judgements and error monitoring—and identify crucial points of convergence between methods and theories in the two fields. This convergence suggests that common principles govern metacognitive judgements of confidence and accuracy; in particular, a shared reliance on post-decisional processing within the systems responsible for the initial decision. However, research in both fields has focused rather narrowly on simple, discrete decisions—reflecting the correspondingly restricted focus of current models of the decision process itself—raising doubts about the degree to which discovered principles will scale up to explain metacognitive evaluation of real-world decisions and actions that are fluid, temporally extended, and embedded in the broader context of evolving behavioural goals.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1098/rstb.2011.0416

Cites

13 of 13 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

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?

  • Metacognition is likely to emerge from a set of dynamically interacting internal states, some of which are world-centered while others encode beliefs about one's propositions or decisions.

    “As such, it is likely to be more fruitful to view metacognition as emerging from a set of dynamically interacting internal states, some of which are world-centered while others encode beliefs about one's propositions or decisions (Yeung & Summerfield 2012).”

    From Metacognition and Confidence: A Review and Synthesis (2024) · cites this paper as Yeung & Summerfield 2012

    The Introduction (‘Metacognition in perceptual choice’) distinguishes first-order choices from second-order estimates of confidence, and ‘Shared limitations’ describes decisions unfolding through ongoing interaction with the environment. But the paper does not describe metacognition as emerging from dynamically interacting world-centered states and states encoding beliefs about propositions or decisions; that account is more specific than the source supports. No page numbers are available in our copy. (LLM, conf=0.78)

    Experimental — accuracy not yet measured

  • Recent HCI work has begun to pursue integrating metacognitive support into GenAI systems, albeit without explicitly grounding it in metacognition.

    “Recent HCI work has begun to pursue this direction [173,204], albeit without explicitly grounding it in metacognition; we suggest that a metacognitive lens offers new research and design directions for augmenting GenAI system usability.”

    From The Metacognitive Demands and Opportunities of Generative AI (2024) · cites this paper as [204]

    The Abstract and Conclusion discuss human confidence judgments and error monitoring, not HCI or GenAI systems. Searches for HCI, generative AI, system design, and usability found no passage addressing whether recent HCI work integrates metacognitive support. (LLM, conf=0.78)

    Experimental — accuracy not yet measured

  • These difficulties were exacerbated by the many parameters available to users who grappled with understanding and using them effectively.

    “These difficulties were exacerbated by the many parameters available to users who grappled with understanding and using them effectively [70,83,204].”

    From The Metacognitive Demands and Opportunities of Generative AI (2024) · cites this paper as [204]

    The Shared limitations section discusses whether models of confidence and error monitoring apply to real-world decisions, not whether users struggle with numerous available parameters. Searches for users’ difficulty understanding and using parameters found no passage addressing that claim; the paper’s discussion of model parameters does not establish it. (LLM, conf=0.76)

    Experimental — accuracy not yet measured

  • Chaining helped participants think through the task better, and thereby make more targeted edits to improve their prompting.

    “Alongside improving the LLM's ability to execute complex tasks, chaining helped participants “think through the task better”, and thereby make more targeted edits to improve their prompting [204].”

    From The Metacognitive Demands and Opportunities of Generative AI (2024) · cites this paper as [204]

    The ‘Shared limitations’ section discusses human decisions chained into sequences serving longer-term goals, not chaining LLM prompts. The ‘Impact of error monitoring on behaviour’ section discusses adjustments after errors, but neither it nor passages retrieved by searching for prompting and targeted edits addresses participants making more targeted prompt edits. (LLM, conf=0.78)

    Experimental — accuracy not yet measured

Self-check

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

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 59

  1. [2]Bogacz R. Brown E. Moehlis J. Holmes P. Cohen J. D. 2006 The physics of optimal decision making: a formal analysis of models of performance in two-alternative forced-choice tasks. Psychol. Rev. 113, 700– 765 10.1037/0033-295X.113.4.700 (doi:10.1037/0033-295X.113.4.700) 17014301 · DOI
  2. [3]Ratcliff R. McKoon G. 2008 The diffusion decision model: theory and data for two-choice decision tasks. Neural Comput. 20, 873– 922 10.1162/neco.2008.12-06-420 (doi:10.1162/neco.2008.12-06-420) 18085991 PMC2474742 · DOI · Paper page
  3. [4]Smith P. L. Ratcliff R. 2004 Psychology and neurobiology of simple decisions. Trends Neurosci. 27, 161– 168 10.1016/j.tins.2004.01.006 (doi:10.1016/j.tins.2004.01.006) 15036882 · DOI · Paper page
  4. [5]Wald A. Wolfowitz J. 1949 Bayes solutions of sequential decision problems. Proc. Natl Acad. Sci. USA 35, 99– 102 10.1073/pnas.35.2.99 (doi:10.1073/pnas.35.2.99) 16588867 PMC1062969 · DOI
  5. [6]Ratcliff R. 1978 A theory of memory retrieval. Psychol. Rev. 85, 59– 108 10.1037/0033-295X.85.2.59 (doi:10.1037/0033-295X.85.2.59) · DOI · Paper page
  6. [7]Busemeyer J. R. Johnson J. G. 2004 Computational models of decision making. In Handbook of judgment and decision making (eds. Koehler D. Harvey N.), pp. 133– 154 Oxford, UK: Blackwell
  7. [9]Petrusic W. M. Baranski J. V. 2003 Judging confidence influences decision processing in comparative judgments. Psychon. Bull. Rev. 10, 177– 183 10.3758/BF03196482 (doi:10.3758/BF03196482) 12747505 · DOI
  8. [10]Galvin S. J. Podd J. V. Drga V. Whitmore J. 2003 Type 2 tasks in the theory of signal detectability: discrimination between correct and incorrect decisions. Psychon. Bull. Rev. 10, 843– 876 10.3758/BF03196546 (doi:10.3758/BF03196546) 15000533 · DOI · Paper page
  9. [11]Evans S. Azzopardi P. 2007 Evaluation of a ‘bias-free’ measure of awareness. Spat. Vis. 20, 61– 77 10.1163/156856807779369742 (doi:10.1163/156856807779369742) 17357716 · DOI · Paper page
  10. [12]Maniscalco B. Lau H. 2012 A signal detection theoretic approach for estimating metacognitive sensitivity from confidence ratings. Conscious. Cogn. 10.1016/j.concog.2011.09.021 (doi:10.1016/j.concog.2011.09.021) 22071269 · DOI · Paper page
  11. [17]Heath R. A. 1984 Random-walk and accumulator models of psychophysical discrimination—a critical evaluation. Perception 13, 57– 65 10.1068/p130057 (doi:10.1068/p130057) 6473053 · DOI
  12. [18]Vickers D. Packer J. 1982 Effects of alternating set for speed or accuracy on response-time, accuracy and confidence in a unidimensional discrimination task. Acta Psychol. 50, 179– 197 10.1016/0001-6918(82)90006-3 (doi:10.1016/0001-6918(82)90006-3) 7102359 · DOI · Paper page
  13. [19]Kepecs A. Uchida N. Zariwala H. A. Mainen Z. F. 2008 Neural correlates, computation and behavioural impact of decision confidence. Nature 455, 227– 231 10.1038/nature07200 (doi:10.1038/nature07200) 18690210 · DOI · Paper page
  14. [21]Britten K. H. Shadlen M. N. Newsome W. T. Movshon J. A. 1992 The analysis of visual motion: a comparison of neuronal and psychophysical performance. J. Neurosci. 12, 4745– 4765 1464765 PMC6575768
  15. [24]Smith J. D. Couchman J. J. Beran M. J. 2012 The highs and lows of theoretical interpretation in animal-metacognition research. Phil. Trans. R. Soc. B 367, 1297– 1309 10.1098/rstb.2011.0366 (doi:10.1098/rstb.2011.0366) PMC3318761 22492748 · DOI
  16. [25]Kepecs A. Mainen Z. F. 2012 A computational framework for the study of confidence in humans and animals. Phil. Trans. R. Soc. B 367, 1322– 1337 10.1098/rstb.2012.0037 (doi:10.1098/rstb.2012.0037) PMC3318772 22492750 · DOI · Paper page
  17. [26]Resulaj A. Kiani R. Wolpert D. M. Shadlen M. N. 2009 Changes of mind in decision-making. Nature 461, 263– 266 10.1038/nature08275 (doi:10.1038/nature08275) 19693010 PMC2875179 · DOI · Paper page
  18. [27]Rabbitt P. M. A. 1966 Errors and error correction in choice-response tasks. J. Exp. Psychol. 71, 264– 272 10.1037/h0022853 (doi:10.1037/h0022853) 5948188 · DOI
  19. [29]Rabbitt P. M. A. 2002 Consciousness is slower than you think. Quart. J. Exp. Psychol. A 55, 1081– 1092 10.1080/02724980244000080 (doi:10.1080/02724980244000080) 12420985 · DOI
  20. [30]Jentzsch I. Dudschig C. 2009 Why do we slow down after an error? Mechanisms underlying the effects of posterror slowing. Quart. J. Exp. Psychol. 62, 209– 218 10.1080/17470210802240655 (doi:10.1080/17470210802240655) 18720281 · DOI
  21. [32]Steinhauser M. Maier M. Hubner R. 2008 Modeling behavioral measures of error detection in choice tasks: response monitoring versus conflict monitoring. J. Exp. Psychol. Hum. Percept. Perform. 34, 158– 176 10.1037/0096-1523.34.1.158 (doi:10.1037/0096-1523.34.1.158) 18248146 · DOI
  22. [33]Joordens S. Piercey C. D. Azarbehi R. 2009 Modeling performance at the trial level within a diffusion framework: a simple yet powerful method for increasing efficiency via error detection and correction. Can. J. Exp. Psychol. 63, 81– 93 19485599
  23. [34]Yeung N. Botvinick M. M. Cohen J. D. 2004 The neural basis of error detection: conflict monitoring and the error-related negativity. Psychol. Rev. 111, 931– 959 10.1037/0033-295X.111.4.931 (doi:10.1037/0033-295X.111.4.931) 15482068 · DOI · Paper page
  24. [35]Holroyd C. B. Coles M. G. H. 2002 The neural basis of human error processing: reinforcement learning, dopamine, and the error-related negativity. Psychol. Rev. 109, 679– 709 10.1037/0033-295X.109.4.679 (doi:10.1037/0033-295X.109.4.679) 12374324 · DOI · Paper page
  25. [36]Rabbitt P. M. A. Cumming G. Vyas S. M. 1978 Some errors of perceptual analysis in visual search can be detected and corrected. Quart. J. Exp. Psychol. 30, 319– 332 10.1080/14640747808400679 (doi:10.1080/14640747808400679) 674542 · DOI
  26. [37]Rabbitt P. M. A. Rodgers B. 1977 What does a man do after he makes an error? An analysis of response programming. Quart. J. Exp. Psychol. 29, 727– 743 10.1080/14640747708400645 (doi:10.1080/14640747708400645) · DOI
  27. [38]Nieuwenhuis S. Ridderinkhof K. R. Blom J. Band G. P. H. Kok A. 2001 Error-related brain potentials are differentially related to awareness of response errors: evidence from an antisaccade task. Psychophysiology 38, 752– 760 10.1111/1469-8986.3850752 (doi:10.1111/1469-8986.3850752) 11577898 · DOI · Paper page
  28. [39]Debener S. Ullsperger M. Siegel M. Fiehler K. von Cramon D. Y. Engel A. K. 2005 Trial-by-trial coupling of concurrent electroencephalogram and functional magnetic resonance imaging identifies the dynamics of performance monitoring. J. Neurosci. 25, 11 730– 11 737 10.1523/JNEUROSCI.3286-05.2005 (doi:10.1523/JNEUROSCI.3286-05.2005) PMC6726024 16354931 · DOI
  29. [40]Ridderinkhof K. R. Ramautar J. R. Wijnen J. G. 2009 To P(E) or not to P(E): a P3-like ERP component reflecting the processing of response errors. Psychophysiology 46, 531– 538 10.1111/j.1469-8986.2009.00790.x (doi:10.1111/j.1469-8986.2009.00790.x) 19226310 · DOI · Paper page
  30. [41]Linden D. E. 2005 The P300: where in the brain is it produced and what does it tell us? Neuroscientist 11, 563– 576 10.1177/1073858405280524 (doi:10.1177/1073858405280524) 16282597 · DOI · Paper page
  31. [42]Nieuwenhuis S. Aston-Jones G. Cohen J. D. 2005 Decision making, the P3, and the locus coeruleus-norepinephrine system. Psychol. Bull. 131, 510– 532 10.1037/0033-2909.131.4.510 (doi:10.1037/0033-2909.131.4.510) 16060800 · DOI · Paper page
  32. [43]Overbeek T. J. M. Nieuwenhuis S. Ridderinkhof K. R. 2005 Dissociable components of error processing: on the functional significance of the Pe vis-à-vis the ERN/Ne. J. Psychophysiol. 19, 319– 329 10.1027/0269-8803.19.4.319 (doi:10.1027/0269-8803.19.4.319) · DOI · Paper page
  33. [45]Rodriguez-Fornells A. Kurzbuch A. R. Muente T. F. 2002 Time course of error detection and correction in humans: neurophysiological evidence. J. Neurosci. 22, 9990– 9996 12427856 PMC6757828
  34. [46]Gehring W. J. Goss B. Coles M. G. H. Meyer D. E. Donchin E. 1993 A neural system for error detection and compensation. Psychol. Sci. 4, 385– 390 10.1111/j.1467-9280.1993.tb00586.x (doi:10.1111/j.1467-9280.1993.tb00586.x) · DOI · Paper page
  35. [47]Hughes G. Yeung N. 2011 Dissociable correlates of response conflict and error awareness in error-related brain activity. Neuropsychologia 49, 405– 415 10.1016/j.neuropsychologia.2010.11.036 (doi:10.1016/j.neuropsychologia.2010.11.036) 21130788 PMC3034820 · DOI
  36. [49]Steinhauser M. Yeung N. 2010 Decision processes in human performance monitoring. J. Neurosci. 30, 15 643– 15 653 10.1523/JNEUROSCI.1899-10.2010 (doi:10.1523/JNEUROSCI.1899-10.2010) PMC3073548 21084620 · DOI · Paper page
  37. [50]Notebaert W. Houtman F. Van Opstal F. Gevers W. Fias W. Verguts T. 2009 Post-error slowing: an orienting account. Cognition 111, 275– 279 10.1016/j.cognition.2009.02.002 (doi:10.1016/j.cognition.2009.02.002) 19285310 · DOI
  38. [51]Bogacz R. Wagenmakers E. J. Forstmann B. U. Nieuwenhuis S. 2010 The neural basis of the speed-accuracy tradeoff. Trends Neurosci. 33, 10– 16 10.1016/j.tins.2009.09.002 (doi:10.1016/j.tins.2009.09.002) 19819033 · DOI
  39. [52]Botvinick M. M. Braver T. S. Carter C. S. Barch D. M. Cohen J. D. 2001 Conflict monitoring and cognitive control. Psychol. Rev. 108, 624– 652 10.1037/0033-295X.108.3.624 (doi:10.1037/0033-295X.108.3.624) 11488380 · DOI · Paper page
  40. [53]Ratcliff R. Frank M. J. 2012 Reinforcement-based decision making in corticostriatal circuits: mutual constraints by neurocomputational and diffusion models. Neural Comput. 24, 1– 44 10.1162/NECO_a_00270 (doi:10.1162/NECO_a_00270) 22295983 · DOI
  41. [54]Schultz W. Dayan P. Montague P. R. 1997 A neural substrate of prediction and reward. Science 275, 1593– 1599 10.1126/science.275.5306.1593 (doi:10.1126/science.275.5306.1593) 9054347 · DOI · Paper page
  42. [55]Hester R. Barre N. Murphy K. Silk T. J. Mattingley J. B. 2008 Human medial frontal cortex activity predicts learning from errors. Cerebral Cortex 18, 1933– 1940 10.1093/cercor/bhm219 (doi:10.1093/cercor/bhm219) 18063560 · DOI
  43. [56]Hester R. Madeley J. Murphy K. Mattingley J. B. 2009 Learning from errors: error-related neural activity predicts improvements in future inhibitory control performance. J. Neurosci. 29, 7158– 7165 10.1523/JNEUROSCI.4337-08.2009 (doi:10.1523/JNEUROSCI.4337-08.2009) 19494138 PMC6666478 · DOI
  44. [57]Rushworth M. F. S. Behrens T. E. Rudebeck P. H. Walton M. E. 2007 Contrasting roles for cingulate and orbitofrontal cortex in decisions and social behaviour. Trends Cogn. Sci. 11, 168– 176 10.1016/j.tics.2007.01.004 (doi:10.1016/j.tics.2007.01.004) 17337237 · DOI · Paper page
  45. [58]Gratton G. Coles M. G. H. Sirevaag E. J. Eriksen C. W. Donchin E. 1988 Pre- and poststimulus activation of response channels: a psychophysiological analysis. J. Exp. Psychol. Hum. Percep. Perform 14, 331– 344 10.1037/0096-1523.14.3.331 (doi:10.1037/0096-1523.14.3.331) 2971764 · DOI · Paper page
  46. [59]Graziano M. Poloseki P. Shalom D. E. Sigman M. 2011 Parsing a perceptual decision into a sequence of moments of thought. Front. Integr. Neurosci. 5, 45 10.3389/fnint.2011.00045 (doi:10.3389/fnint.2011.00045) 21941470 PMC3170920 · DOI
  47. [60]Krajbich I. Armel C. Rangel A. 2010 Visual fixations and the computation and comparison of value in simple choice. Nat. Neurosci. 13, 1292– 1298 10.1038/nn.2635 (doi:10.1038/nn.2635) 20835253 · DOI · Paper page
  48. [61]Burle B. Roger C. Allain S. Vidal F. Hasbroucq T. 2008 Error negativity does not reflect conflict: a reappraisal of conflict monitoring and anterior cingulate cortex activity. J. Cogn. Neurosci. 20, 1637– 1655 10.1162/jocn.2008.20110 (doi:10.1162/jocn.2008.20110) 18345992 · DOI
  49. [62]Lashley K. S. 1951 The problem of serial order in behavior. In Cerebral mechanisms in behavior: the Hixon Symposium (ed. Jeffress L. A.), pp. 112– 136 New York, NY: Wiley
  50. [63]Botvinick M. M. 2008 Hierarchical models of behavior and prefrontal function. Trends Cogn. Sci. 12, 201– 208 10.1016/j.tics.2008.02.009 (doi:10.1016/j.tics.2008.02.009) 18420448 PMC2957875 · DOI · Paper page
  51. [64]Koechlin E. Summerfield C. 2007 An information theoretical approach to prefrontal executive function. Trends Cogn. Sci. 11, 229– 235 10.1016/j.tics.2007.04.005 (doi:10.1016/j.tics.2007.04.005) 17475536 · DOI · Paper page
  52. [66]Krigolson O. E. Holroyd C. B. 2006 Evidence for hierarchical error processing in the human brain. Neuroscience 137, 13– 17 10.1016/j.neuroscience.2005.10.064 (doi:10.1016/j.neuroscience.2005.10.064) 16343779 · DOI
  53. [67]Montgomery D. A. Sorkin R. D. 1996 Observer sensitivity to element reliability in a multielement visual display. Hum. Factors 38, 484– 494 10.1518/001872096778702024 (doi:10.1518/001872096778702024) · DOI
  54. [68]Schultz W. Preuschoff K. Camerer C. Hsu M. Fiorillo C. D. Tobler P. N. Bossaerts P. 2008 Explicit neural signals reflecting reward uncertainty. Phil. Trans. R. Soc. B 363, 3801– 3811 10.1098/rstb.2008.0152 (doi:10.1098/rstb.2008.0152) 18829433 PMC2581779 · DOI · Paper page
  55. [69]O'Neill M. Schultz W. 2011 Coding of reward risk by orbitofrontal neurons is mostly distinct from coding of reward value. Neuron 68, 789– 800 10.1016/j.neuron.2010.09.031 (doi:10.1016/j.neuron.2010.09.031) 21092866 · DOI
  56. [71]Beck J. M. Ma W. J. Kiani R. Hanks T. Churchland A. K. Roitman J. Shadlen M. N. Latham P. E. Pouget A. 2008 Probabilistic population codes for Bayesian decision making. Neuron 60, 1142– 1152 10.1016/j.neuron.2008.09.021 (doi:10.1016/j.neuron.2008.09.021) 19109917 PMC2742921 · DOI · Paper page
  57. [72]Ma W. J. Beck J. M. Latham P. E. Pouget A. 2006 Bayesian inference with probabilistic population codes. Nat. Neurosci. 9, 1432– 1438 10.1038/nn1790 (doi:10.1038/nn1790) 17057707 · DOI · Paper page
  58. [73]Ratcliff R. Starns J. J. 2009 Modeling confidence and response time in recognition memory. Psychol. Rev. 116, 59– 83 10.1037/a0014086 (doi:10.1037/a0014086) 19159148 PMC2693899 · DOI
  59. [75]de Gardelle V. Summerfield C. 2011 Robust averaging during perceptual judgment. Proc. Natl Acad. Sci. USA 108, 13 341– 13 346 10.1073/pnas.1104517108 (doi:10.1073/pnas.1104517108) PMC3156162 21788517 · DOI

Cited by

Sorted by citations

Authors
Yeung, N., & Summerfield, C.
Affiliations
University of Oxford (GB)
Corresponding author
Yeung, Nick
ORCID
Venue
Philosophical Transactions of the Royal Society B: Biological Sciences
Publisher
The Royal Society
Published
2012-05-19
Volume
367
Issue
1594
Pages
1310-1321
ISSN
  • 0962-8436 (ISSN-L)
  • 1471-2970
DOI
10.1098/rstb.2011.0416
PMC
PMC3318764
OpenAlex
W2149129640
Cited by
667
References
13
Citations by year
2026: 59 · 2025: 61 · 2024: 71 · 2023: 61 · 2022: 55 · 2021: 62 · 2020: 53 · 2019: 49 · 2018: 46 · 2017: 46 · 2016: 39 · 2015: 25 · 2014: 21 · 2013: 10 · 2012: 8
FWCI
1.62
Type
journal article
Language
en
Open access
Licence
Locations
  • Philosophical Transactions of the Royal Society B Biological Sciences (publishedVersion, cc-by)
  • Europe PMC (PubMed Central) (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
Funders
  • Wellcome Trust (WT092646AIA)
  • National Institute of Mental Health (P50 MH62196, P50MH062196)
Topics
  • Life Sciences › Neuroscience › Cognitive Neuroscience › Neural and Behavioral Psychology Studies
  • Social Sciences › Decision Sciences › General Decision Sciences › Decision-Making and Behavioral Economics
  • Life Sciences › Neuroscience › Cognitive Neuroscience › Memory Processes and Influences
Keywords
metacognition, confidence judgments, error monitoring, decision-making, metacognitive accuracy, decision models
MeSH terms
Cognition, Decision Making, Humans, Models, Psychological

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.

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