CoChat
Sign Up
Cited by 263Telemedicine and Telehealth ImplementationMobile Health and mHealth ApplicationsCancer survivorship and care

Digital health and telehealth in cancer care: A scoping review of reviews

Open access
Shaffer, Kelly M, Turner, Kea L, Siwik, Chelsea, Gonzalez, Brian D, Upasani, Rujula, Glazer, Jillian V, Ferguson, Robert J, Joshua, Catherine +1 more·2023·The Lancet Digital Health
DOI 10.1016/s2589-7500(23)00049-3PMC PMC10124999
Open this paper in CoChat — free account

Abstract

The COVID-19 pandemic necessitated remote cancer care delivery via the internet and telephone, rapidly accelerating an already growing care delivery model and associated research. This scoping review of reviews characterised the peer-reviewed literature reviews on digital health and telehealth interventions in cancer published from database inception up to May 1, 2022, from PubMed, Cumulated Index to Nursing and Allied Health Literature, PsycINFO, Cochrane Reviews, and Web of Science. Eligible reviews conducted a systematic literature search. Data were extracted in duplicate via a pre-defined online survey. Following screening, 134 reviews met the eligibility criteria. 77 of those reviews were published since 2020. 128 reviews summarised interventions intended for patients, 18 addressed family caregivers, and five addressed health-care providers. 56 reviews did not target a specific phase of the cancer continuum, whereas 48 reviews tended to address the active treatment phase. 29 reviews included a meta-analysis, with results showing positive effects on quality of life, psychological outcomes, and screening behaviours. 83 reviews did not report intervention implementation outcomes but when reported, 36 reported acceptability, 32 feasibility, and 29 fidelity outcomes. Several notable gaps were identified in these literature reviews on digital health and telehealth in cancer care. No reviews specifically addressed older adults, bereavement, or sustainability of interventions and only two reviews focused on comparing telehealth to in-person interventions. Addressing these gaps with rigorous systematic reviews might help guide continued innovation in remote cancer care, particularly for older adults and bereaved families, and integrate and sustain these interventions within oncology.

AI snapshot

Written from the paper’s full text.

TL;DR

This scoping review of reviews characterised 134 peer-reviewed literature reviews on digital health and telehealth interventions in cancer care published from database inception to May 1, 2022. It found a rapidly growing but uneven evidence base, with positive meta-analytic signals for some outcomes and major gaps in older adults, bereavement, provider wellness, implementation sustainability, and comparisons with in-person care.

Key findings

  • 134 reviews met eligibility criteria; 77 were published since 2020, and the median number of studies included per review was 16 (range 0–121).
  • 128 reviews (95·5%) addressed patient-level interventions, 18 (13·4%) included caregiver-level studies, and 5 (3·7%) addressed provider-level interventions; no reviews focused on older adult patients with cancer or caregivers.
  • 29 reviews (21·6%) included a meta-analysis; positive effects were most commonly reported for quality of life (11 positive, 6 null), depression (9 positive, 4 null), anxiety (8 positive, 3 null), self-efficacy (5 positive, no null), physical activity (4 positive, 1 null), and cancer screenings (4 positive, no null).
  • 83 reviews (61·9%) did not report implementation outcomes; when reported, acceptability was extracted in 36 (26·9%), feasibility in 32 (23·9%), and fidelity in 29 (21·6%), with no reviews extracting penetration or sustainability.

Methods

  • Scoping review of reviews registered in INPLASY (protocol 3635) and reported per PRISMA for Scoping Reviews; searches covered PubMed, CINAHL, PsycINFO, Cochrane Reviews, and Web of Science from database inception to May 1, 2022.
  • Eligible records were English or English-translated peer-reviewed literature reviews using a systematic search method, focused on cancer populations and digital health or telehealth interventions as defined by the US Health Resources and Services Administration.
  • Screening and data extraction were done in duplicate with Rayyan and Qualtrics; data were tabled and summarised, and implementation outcomes were categorised post hoc using Proctor and colleagues’ terminology.

Limitations

  • The paper states that as a scoping review of reviews, identified gaps only establish that a review was not identified in a given area and might not generalise to the primary literature; it also notes that restricting to cancer could miss disease-agnostic reviews and that health equity information such as racial/ethnic composition or rurality was not extracted.
  • Evident from the results: no reviews specifically addressed older adults, bereavement, sustainability of interventions, or oncology provider wellbeing, and only two reviews focused on comparing telehealth to in-person interventions.
  • Evident from the results: 44 of 134 reviews (32·8%) did not report a quality or bias assessment, and 83 of 134 (61·9%) did not report implementation-related outcomes.

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

Integrity signals

Registry

Crossref · 10.1016/s2589-7500(23)00049-3

Cites

155 of 155 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Claims the paper makes

0 of 20 cited sources checked · 0 supported · 0 flagged

  • Findingown data

    Seventy-seven of the included reviews had been published from 2020 onward.

    “77 of those reviews were published since 2020.”
    Quote in the paperNot a substantial claim
  • Findingown data

    One hundred twenty-eight reviews summarized interventions aimed at patients.

    “128 reviews summarised interventions intended for patients”
    Quote in the paperNot a substantial claim
  • Findingown data

    Five reviews addressed health-care providers.

    “five addressed health-care providers”
    Quote in the paperNot a substantial claim
  • Findingown data

    Fifty-six reviews did not focus on a particular phase of the cancer care continuum.

    “56 reviews did not target a specific phase of the cancer continuum”
    Quote in the paperNot a substantial claim
  • Findingown data

    The scoping review found 134 literature reviews that satisfied its eligibility criteria.

    “Following screening, 134 reviews met the eligibility criteria.”
    • Also stated in: § Results · plain
      “The remaining 134 reviews met eligibility criteria and were included in the synthesis.”
    Quote in the paperSubstantial claim
  • May combine two claims. 24
  • Classified as probably not a substantial claim. 15

  • May combine two claims.

    Findingown data

    For self-efficacy, five meta-analyses found positive effects and none found null effects.

    “self-efficacy (five positive, no null)”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Findingown data

    For anxiety, eight meta-analyses found positive effects and three found null effects.

    “anxiety (eight positive, three null)”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Findingown data

    Among the meta-analyses, quality of life was the most frequently examined outcome, with 11 reporting positive intervention effects and six reporting null findings.

    “Across meta-analyses, the most examined outcome was quality of life: 11 meta-analyses reported positive effects of interventions relative to control and six reported null findings.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Findingown data

    For depression, nine meta-analyses found positive effects and four found null effects.

    “Meta-analyses also frequently reported positive findings for interventions for outcomes including depression (nine positive effects, four null effects)”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Findingown data

    Most implementation outcome data came from early-stage research, and few reviews examined implementation into routine care.

    “Most of the implementation outcomes data were extracted from early-stage research studies, with few reviews focusing on the implementation of digital health and telehealth interventions into routine care.”
    Quote in the paperSubstantial claim

  • May combine two claims.

    Findingown data

    Reviews of interventions that could plausibly be fully automated did not require full automation, and clinical support incorporation was unclear.

    “Although there were reviews of interventions that could plausibly be fully automated,12, 13, 14, 18, 21, 36, 38, 52, 66 eligibility criteria did not require full automation, and incorporation of clinical support was unclear.”
    Quote in the paperSubstantial claim

  • May combine two claims.

    Findingown data

    For distress, two meta-analyses found positive effects and two found null effects.

    “distress (two positive, two null)”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Findingown data

    For pain, three meta-analyses found positive effects and four found null effects.

    “pain (three positive, four null)”
    Quote in the paperNot a substantial claim

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

    Findingcitation

    One review of mobile applications using AI to diagnose skin cancer or melanoma concluded that evidence was insufficient to rely on AI for all diagnoses.

    “a study of mobile applications that use AI to diagnose skin cancer or melanoma from skin lesion pictures, which concluded that evidence was insufficient (by the time of the review) to rely on AI to identify all diagnoses.22”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [22] Freeman, 2020, Algorithm based smartphone apps to assess risk of skin cancer in adults: systematic review of diagnostic accuracy studies, BMJ source

      Not checked in the free run.

  • May combine two claims.

    Findingcitation

    The 2013 review by Sanchez and colleagues applied implementation frameworks and called for more pragmatic trial designs.

    “One of the earliest identified reviews, Sanchez and colleagues’ 2013 review, stands out in its application of implementation frameworks to their review of internet-based cancer prevention and control interventions.124 This review highlighted the need for more pragmatic trial designs”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [124] Sanchez, 2013, A systematic review of eHealth cancer prevention and control interventions: new technology, same methods and designs?, Transl Behav Med source

      Not checked in the free run.

  • May combine two claims.

    Findingown data

    The included reviews dated from 2010 onward, with a marked rise starting in 2018.

    “Included reviews were published as early as 2010, with a notable increase beginning in 2018”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Findingown data

    Most reviews focused on patients in active treatment or survivorship and used eHealth, synchronous calls, or mobile applications.

    “Overall, most reviews focused on interventions delivered to patients with cancer in the active treatment and survivorship phases using eHealth programs, synchronous calls by telephone or videoconferencing, and mobile applications.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Findingown data

    The median number of primary studies per review was 16, with a range from 0 to 121.

    “The median number of studies included in the reviews was 16 (range: 0–121).”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Findingown data

    For physical activity, four meta-analyses found positive effects and one found a null effect.

    “physical activity (four positive, one null)”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Findingown data

    Reviews commonly concluded that digital health and telehealth interventions were feasible and effective, while calling for larger, more robust efficacy testing.

    “Common conclusions drawn by reviews were that digital health and telehealth interventions were feasible and effective, but the need for larger-scale and robust efficacy testing remains.”
    • Also stated in: § Opportunities in implementation outcomes · plain
      “reviews since that time frequently concluded that findings were preliminary and more robust, larger-scale studies were needed.”
    Quote in the paperSubstantial claim

  • May combine two claims.

    Findingown data

    For fatigue, five meta-analyses found positive effects and five found null effects.

    “fatigue (five positive effects, five null effects)”
    Quote in the paperNot a substantial claim

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

    Findingown data

    Five reviews included the term integrative.

    “five (3·7%) included the term integrative”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Findingcitation

    Kiss and colleagues focused on self-guided interventions but included interventions with minimal facilitation.

    “Kiss and colleagues89 focused on self-guided interventions but included those with minimal facilitation.”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [89] Kiss, 2019, Technology-supported self-guided nutrition and physical activity interventions for adults with cancer: systematic review, JMIR Mhealth Uhealth source

      Not checked in the free run.

  • May combine two claims.

    Findingown data

    For cancer screenings, four meta-analyses found positive effects and none found null effects.

    “cancer screenings (four positive, no null)”
    Quote in the paperNot a substantial claim

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

    Findingown data

    Seven reviews included the term scoping.

    “seven (5·2%) included the term scoping”
    Quote in the paperNot a substantial claim

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

    Study design and conductown data

    The data extraction form was pilot tested by coders.

    “which was pilot tested by coders.”
    Quote in the paperNot a substantial claim

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

    Study design and conductcitation

    The review protocol was registered as INPLASY protocol 3635.

    “The protocol was registered (INPLASY protocol 3635)7”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [7] Shaffer

      Not checked in the free run.

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

    Study design and conductown data

    Full-text articles were screened by two of eight authors, with disagreements resolved by KMS or RU.

    “Full-text articles were reviewed by two of eight authors (KMS, KLT, CS, BDG, RU, JVG, RJF, or CAL), with discrepancies resolved by KMS or RU.”
    Quote in the paperNot a substantial claim

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

    Study design and conductnone given

    Unpublished and grey literature were not pursued.

    “Unpublished and grey literature were not pursued.”
    Quote in the paperNot a substantial claim

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

    Study design and conductnone given

    Coders were not masked to journals or authors during screening.

    “Coders were not masked to journals or authors during screening.”
    Quote in the paperNot a substantial claim

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

    Study design and conductcitation

    The authors followed PRISMA for Scoping Reviews guidelines.

    “we adhered to PRISMA for Scoping Reviews guidelines.8”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [8] Tricco, 2018, PRISMA extension for scoping reviews (PRISMA-ScR): checklist and explanation, Ann Intern Med source

      Not checked in the free run.

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

    Study design and conductown data

    Data were extracted in duplicate using a predefined online survey.

    “Data were extracted in duplicate via a pre-defined online survey.”
    • Also stated in: § Data extraction and summary · plain
      “Data were extracted independently by two of eight authors (KMS, KLT, CS, BDG, RU, JVG, RJF, CAL), with discrepancies resolved by KMS, RU, or JVG.”
    Quote in the paperNot a substantial claim

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

    Interpretationreasoning

    Because the scoping review was restricted to cancer, disease-agnostic reviews could be relevant to the identified gaps.

    “Because we restricted the scope of our review to cancer, there could be reviews pertinent to identified gaps that are disease-agnostic.”
    Quote in the paperNot a substantial claim

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

    Study design and conductown data

    Titles and abstracts were screened by two of three coders, with disagreements resolved by consensus.

    “study titles and abstracts were reviewed by two of three coders (KMS, RU, or JVG). Discrepancies between coders were resolved by consensus.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Interpretationreasoning

    The gaps identified in the review literature only show that a review was not found in an area and may not generalise to the primary literature.

    “the identified gaps in the literature only establish that a review was not identified in a given area of remote cancer care, which might not generalise to the primary literature.”
    Quote in the paperNot a substantial claim

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

    Study design and conductnone given

    Articles were not blinded during data extraction.

    “Articles were not blinded during data extraction.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Premisecitation

    Telephone and internet delivery can reduce time burdens of cancer treatment and extend access to evidence-based interventions.

    “Delivering interventions by telephone and internet—via phone calls, videoconferencing, mobile applications, and web pages—can reduce the time burdens of cancer treatment1 and extend access to evidence-based interventions”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites [1] Gupta, 2022, The time toxicity of cancer treatment, J Clin Oncol source

      Not checked in the free run.

  • Classified as probably not a substantial claim.

    Study design and conductnone given

    Included reviews had to meet a priori eligibility criteria.

    “The included reviews were required to meet a priori eligibility criteria”
    Quote in the paperSubstantial claim

  • Classified as probably not a substantial claim.

    Premisecitation

    The COVID-19 pandemic had a serious toll on health-care workers.

    “Given the serious toll of the COVID-19 pandemic on health-care workers,160”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites [160] Dillon, 2022, Women, younger clinicians', and caregivers' experiences of burnout and well-being during COVID-19 in a US healthcare system, J Gen Intern Med source

      Not checked in the free run.

  • May combine two claims.

    Premisecitation

    Fully automated interventions offer greater scalability, accessibility, and cost-effectiveness.

    “fully automated interventions provide greater scalability, accessibility, and cost-effectiveness.163”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [163] Muñoz, 2022, Harnessing psychology and technology to contribute to making health care a universal human right, Cogn Behav Pract source

      Not checked in the free run.

  • May combine two claims.

    Premisecitation

    One study suggests older and younger uro-oncology patients have similar interest in remote monitoring, and older patients were more willing to engage in trials.

    “one study of patients with uro-oncological cancer suggests similar interest in remote patient monitoring with digital technologies between older and younger patients, with older patients even reporting to be willing to engage with digital technologies as part of trials more frequently than younger patients.152”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [152] Rodler, 2021, Patients' perspective on digital technologies in advanced genitourinary cancers, Clin Genitourin Cancer source

      Not checked in the free run.

  • May combine two claims.

    Premisecitation

    Caregivers' health-related needs and grief reactions vary by disease context.

    “As caregivers’ health-related needs and grief reactions differ by disease context,158, 159”
    Quote in the paperSubstantial claim0 of 2 sources checked
    • cites [158] Secinti, 2021, Health-related quality of life: a comparative analysis of caregivers of people with dementia, cancer, COPD/emphysema, and diabetes and noncaregivers, 2015–2018 BRFSS, Ann Behav Med source

      Not checked in the free run.

    • cites [159] Houck, 2007, A comparison of grief reactions in cancer, HIV/AIDS, and suicide bereavement, J HIV AIDS Soc Serv source

      Not checked in the free run.

37 of 37

  • The paper relies on this without support.

    The COVID-19 pandemic required remote cancer care delivery and accelerated its growth.

    “The COVID-19 pandemic necessitated remote cancer care delivery via the internet and telephone, rapidly accelerating an already growing care delivery model and associated research.”

  • The paper relies on this without support.

    Digital health and telehealth practices can facilitate collaborative care across disciplines and overcome barriers family caregivers face in accessing their own health care.

    “Digital health and telehealth practices hold promise for facilitating more collaborative care across health-care disciplines, and for overcoming many of the barriers family caregivers face to accessing their own health care.”

  • The paper relies on this without support.

    Digital health practices can scale interventions to be more accessible and cost-effective by reducing reliance on health-care personnel.

    “digital health practices are rapidly evolving and hold considerable promise for scaling interventions to be more accessible and cost-effective by reducing reliance on health-care personnel.”

  • The paper relies on this without support.

    Bereavement care for families is traditionally part of comprehensive palliative care.

    “Although bereavement care for families is traditionally a component of comprehensive palliative care”

  • The paper relies on this without support.

    This review is the first comprehensive scoping review of reviews on digital health and telehealth interventions across the cancer continuum.

    “In this first-of-its-kind comprehensive scoping review of reviews on digital health and telehealth interventions across the cancer continuum, we summarised the existing review literature and identified several gaps.”
5 of 5

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?

  • The COVID-19 pandemic accelerated an unprecedented period of health system innovation and workforce transformation.

    “However, the pandemic also accelerated an unprecedented period of health system innovation and workforce transformation [5,6].”

    From A Scoping Review of Implemented Innovations in Cancer Care: Implications for Pan-Canadian Scaling (2026) · cites this paper as [5]

    The Introduction (page not provided) says research in remote cancer-care delivery accelerated abruptly during the pandemic, and the Abstract describes rapid growth in that care model. Those passages support acceleration in one area of care, but not the broader claim of an unprecedented period of health-system innovation or workforce transformation. (LLM, conf=0.85)

    Experimental — accuracy not yet measured

  • Many adaptations initially introduced as emergency responses are moving towards becoming sustainable and are increasingly recognized as important strategies for addressing ongoing workforce shortages, improving access, and strengthening health system resilience in the post-pandemic era.

    “Many of these adaptations, initially introduced as emergency responses, are moving towards becoming sustainable and are being increasingly recognized as important strategies for addressing ongoing workforce shortages, improving access, and strengthening health system resilience in the post-pandemic era [2,3,5,6].”

    From A Scoping Review of Implemented Innovations in Cancer Care: Implications for Pan-Canadian Scaling (2026) · cites this paper as [5]

    Split into 2 atoms — 0 confirmed, 2 partially supported, 0 disputed, 0 misattributed, 0 unverifiable. Expand the claim to see per-atom verdicts.

    Experimental — accuracy not yet measured

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.

  • Economic-outcome proportion rounds to 32%, not 31%

    Minor

    Six of 19 studies is 31.6%, which rounds to 32% at the reported whole-percent precision.

    Reported 31 · recomputed 31.578947

  • Pearce citation points to the wrong reference

    Minor

    The text cites references 154 and 155 for Dionne-Odom and Pearce, respectively, but Pearce and colleagues appear as reference 156.

2 of 2

Cites

Flagged first, then by citations

1 of the 156 references couldn’t be matched to a known paper.

Research works printed but not linked: 2

  1. Moretto, 2019, Santo FH do E. Telephone follow-up as a nursing intervention for patients receiving outpatient chemotherapy: integrative review, Rev Gaucha Enferm, 40
  2. Son, 2019, Use of health information technologies for cancer survivorship care: a comprehensive review of the literature, J Inform Nurs, 4, 6

Cited by

Sorted by citations

Related

Authors
Shaffer, K. M., Turner, K. L., Siwik, C., Gonzalez, B. D., Upasani, R., Glazer, J. V., Ferguson, R. J., Joshua, C., & Low, C. A.
Affiliations
  • University of Virginia (US)
  • Moffitt Cancer Center (US)
  • University of California, San Francisco (US)
  • University of Pittsburgh (US)
Corresponding author
Shaffer, Kelly M
ORCID
Venue
The Lancet Digital Health
Publisher
Elsevier BV
Published
2023-05
Volume
5
Issue
5
Pages
e316-e327
ISSN
2589-7500 (ISSN-L)
DOI
10.1016/s2589-7500(23)00049-3
PMC
PMC10124999
OpenAlex
W4366818779
Semantic Scholar
36b38e0cea6f96900f44dbc9e69c6a4fe4cf7e1d
Cited by
263
References
156
Citations by year
2026: 98 · 2025: 87 · 2024: 67 · 2023: 11
FWCI
13.00
Type
journal article
Language
en
Open access
Licence
Locations
  • The Lancet Digital Health (publishedVersion, cc-by-nc-nd)
  • PubMed Central (publishedVersion, cc-by-nc-nd)
  • PubMed (publishedVersion)
  • OSF Preprints (OSF Preprints) (submittedVersion)
Funders
  • National Cancer Institute (P30CA076292, R37CA242545, P30CA047904)
  • National Center for Complementary and Integrative Health (L30 AT011624, T32AT003997)
Topics
  • Health Sciences › Medicine › Public Health, Environmental and Occupational Health › Telemedicine and Telehealth Implementation
  • Health Sciences › Health Professions › General Health Professions › Mobile Health and mHealth Applications
  • Health Sciences › Medicine › Oncology › Cancer survivorship and care
Keywords
digital health, telemedicine, cancer care, COVID-19 pandemic, family caregivers, quality of life, psychological outcomes, cancer screening, older adults, bereavement, intervention sustainability
MeSH terms
COVID-19, Aged, Delivery of Health Care, Humans, Neoplasms, Quality of Life, Review Literature as Topic, Telemedicine, Pandemics

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 2026-10-08.

Classified by jev-1.13-20260917 (gold-guideline-v0.2) on 2026-10-08.

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