CoChat
Sign Up
Cited by 209Epilepsy research and treatmentPharmacological Effects and Toxicity StudiesDiet and metabolism studies

The SANAD II study of the effectiveness and cost-effectiveness of levetiracetam, zonisamide, or lamotrigine for newly diagnosed focal epilepsy: an open-label, non-inferiority, multicentre, phase 4, randomised controlled trial

Open access
Marson, Anthony, Burnside, Girvan, Appleton, Richard, Smith, Dave, Leach, John Paul, Sills, Graeme, Tudur-Smith, Catrin, Plumpton, Catrin +126 more·2021·The Lancet
DOI 10.1016/s0140-6736(21)00247-6PMC PMC8047799
Open this paper in CoChat — free accountOpen PDF

Abstract

BACKGROUND: Levetiracetam and zonisamide are licensed as monotherapy for patients with focal epilepsy, but there is uncertainty as to whether they should be recommended as first-line treatments because of insufficient evidence of clinical effectiveness and cost-effectiveness. We aimed to assess the long-term clinical effectiveness and cost-effectiveness of levetiracetam and zonisamide compared with lamotrigine in people with newly diagnosed focal epilepsy. METHODS: This randomised, open-label, controlled trial compared levetiracetam and zonisamide with lamotrigine as first-line treatment for patients with newly diagnosed focal epilepsy. Adult and paediatric neurology services across the UK recruited participants aged 5 years or older (with no upper age limit) with two or more unprovoked focal seizures. Participants were randomly allocated (1:1:1) using a minimisation programme with a random element utilising factor to receive lamotrigine, levetiracetam, or zonisamide. Participants and investigators were not masked and were aware of treatment allocation. SANAD II was designed to assess non-inferiority of both levetiracetam and zonisamide to lamotrigine for the primary outcome of time to 12-month remission. Anti-seizure medications were taken orally and for participants aged 12 years or older the initial advised maintenance doses were lamotrigine 50 mg (morning) and 100 mg (evening), levetiracetam 500 mg twice per day, and zonisamide 100 mg twice per day. For children aged between 5 and 12 years the initial daily maintenance doses advised were lamotrigine 1·5 mg/kg twice per day, levetiracetam 20 mg/kg twice per day, and zonisamide 2·5 mg/kg twice per day. All participants were included in the intention-to-treat (ITT) analysis. The per-protocol (PP) analysis excluded participants with major protocol deviations and those who were subsequently diagnosed as not having epilepsy. Safety analysis included all participants who received one dose of any study drug. The non-inferiority limit was a hazard ratio (HR) of 1·329, which equates to an absolute difference of 10%. A HR greater than 1 indicated that an event was more likely on lamotrigine. The trial is registered with the ISRCTN registry, 30294119 (EudraCt number: 2012-001884-64). FINDINGS: 990 participants were recruited between May 2, 2013, and June 20, 2017, and followed up for a further 2 years. Patients were randomly assigned to receive lamotrigine (n=330), levetiracetam (n=332), or zonisamide (n=328). The ITT analysis included all participants and the PP analysis included 324 participants randomly assigned to lamotrigine, 320 participants randomly assigned to levetiracetam, and 315 participants randomly assigned to zonisamide. Levetiracetam did not meet the criteria for non-inferiority in the ITT analysis of time to 12-month remission versus lamotrigine (HR 1·18; 97·5% CI 0·95-1·47) but zonisamide did meet the criteria for non-inferiority in the ITT analysis versus lamotrigine (1·03; 0·83-1·28). The PP analysis showed that 12-month remission was superior with lamotrigine than both levetiracetam (HR 1·32 [97·5% CI 1·05 to 1·66]) and zonisamide (HR 1·37 [1·08-1·73]). There were 37 deaths during the trial. Adverse reactions were reported by 108 (33%) participants who started lamotrigine, 144 (44%) participants who started levetiracetam, and 146 (45%) participants who started zonisamide. Lamotrigine was superior in the cost-utility analysis, with a higher net health benefit of 1·403 QALYs (97·5% central range 1·319-1·458) compared with 1·222 (1·110-1·283) for levetiracetam and 1·232 (1·112, 1·307) for zonisamide at a cost-effectiveness threshold of £20 000 per QALY. Cost-effectiveness was based on differences between treatment groups in costs and QALYs. INTERPRETATION: These findings do not support the use of levetiracetam or zonisamide as first-line treatments for patients with focal epilepsy. Lamotrigine should remain a first-line treatment for patients with focal epilepsy and should be the standard treatment in future trials. FUNDING: National Institute for Health Research Health Technology Assessment programme.

AI snapshot

Written from the paper’s full text.

TL;DR

In newly diagnosed focal epilepsy, levetiracetam did not meet non-inferiority to lamotrigine for time to 12-month remission, while zonisamide did in the intention-to-treat analysis. Lamotrigine remained superior for treatment failure and cost-effectiveness, supporting its continued first-line use.

Key findings

  • Among 990 participants randomised to lamotrigine (n=330), levetiracetam (n=332), or zonisamide (n=328), levetiracetam did not meet non-inferiority versus lamotrigine for time to 12-month remission (HR 1·18; 97·5% CI 0·95–1·47), whereas zonisamide did (HR 1·03; 97·5% CI 0·83–1·28).
  • In per-protocol analysis, 12-month remission was superior with lamotrigine than levetiracetam (HR 1·32; 97·5% CI 1·05–1·66) and zonisamide (HR 1·37; 97·5% CI 1·08–1·73).
  • Lamotrigine was significantly less likely to fail than levetiracetam (HR 0·60; 95% CI 0·46–0·77) or zonisamide (HR 0·46; 95% CI 0·36–0·60); adverse reactions were reported by 108 (33%) on lamotrigine, 144 (44%) on levetiracetam, and 146 (45%) on zonisamide.
  • Lamotrigine dominated in cost-utility analysis, with net health benefit 1·403 QALYs (97·5% central range 1·319–1·458) versus 1·222 (1·110–1·283) for levetiracetam and 1·232 (1·112–1·307) for zonisamide at £20 000 per QALY.

Methods

  • Phase 4, multicentre, open-label, non-inferiority randomised controlled trial in 65 UK NHS adult and paediatric neurology services; participants were aged 5 years or older with newly diagnosed focal epilepsy and at least two unprovoked focal seizures.
  • Participants were randomly allocated 1:1:1 to lamotrigine, levetiracetam, or zonisamide; primary outcome was time to 12-month remission, with non-inferiority margin HR 1·329 and 97·5% CIs for the two primary comparisons.
  • Analyses included intention-to-treat and per-protocol populations, plus competing-risks analyses for treatment failure and a health economic cost-utility analysis using QALYs and NHS/personal social services perspective.

Limitations

  • The paper states that seizure data came from diaries and clinic reports, so seizures may have been missed or unreported; only 177 (17·9%) participants were younger than 18 years, limiting applicability to children; maintenance doses may have introduced systematic bias; QOL questionnaire return was low; and newer drugs such as lacosamide and perampanel were not assessed.
  • The paper also states economic limitations: poor questionnaire return, free-text resource-use questions, and assuming unanswered questions meant no resource use; EQ-5D-3L-Y and proxy measures were limited by unavailable value sets and use of adult tariffs.
  • Evident from the text: the trial was open-label, so participants and investigators were aware of treatment allocation, and the paediatric cost-effectiveness finding was based on a small subgroup and principally due to a single participant with an atypical medical journey.

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

Integrity signals

Registry

Crossref · 10.1016/s0140-6736(21)00247-6

Cites

29 of 29 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Claims the paper makes

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

  • Premisecitation

    There is no evidence to suggest that one syndrome or cause responds better to one specific treatment than to another.

    “Although focal epilepsies can be classified according to site of seizure onset and cause, there is no evidence to suggest that one syndrome or cause responds better to one specific treatment than to another.8”
    Quote in the paperSubstantial claim1 of 1 sources checked
    • cites [8] Bonnett L Smith CT Smith D Williamson P Chadwick D Marson AG Prognostic factors for time to treatment failure and time to 12 months of remission for patients with focal epilepsy: post-hoc, subgroup analyses of data from the SANAD trial Lancet Neurol 11 2012 331 340 22377180 source

      The Interpretation (page unavailable) says that predictors of seizure control have not yet been established, which is consistent with the claim’s general caution. The Prognostic modelling section classifies focal epilepsy by site of onset, but our copy does not establish that no syndrome or cause responds preferentially to a particular treatment. (LLM, conf=0.72)

      Experimental — accuracy not yet measured
  • Findingown data

    Zonisamide did meet the criteria for non-inferiority in the intention-to-treat analysis versus lamotrigine (HR 1·03; 97·5% CI 0·83-1·28).

    “but zonisamide did meet the criteria for non-inferiority in the ITT analysis versus lamotrigine (1·03; 0·83–1·28)”
    Quote in the paperSubstantial claim
  • Findingown data

    No significant difference was found in time to 24-month remission (ITT analysis) for lamotrigine versus zonisamide (HR 0.96 [95% CI 0.75-1.23]).

    “or for lamotrigine versus zonisamide (0·96 [0·75–1·23])”
    Quote in the paperSubstantial claim
  • Findingown data

    In the per-protocol analysis, 12-month remission was superior with lamotrigine than zonisamide (HR 1·37 [97·5% CI 1·08-1·73]).

    “and zonisamide (HR 1·37 [1·08–1·73])”
    Quote in the paperSubstantial claim
  • Findingown data

    Levetiracetam did not meet the criteria for non-inferiority in the intention-to-treat analysis of time to 12-month remission versus lamotrigine (HR 1·18; 97·5% CI 0·95-1·47).

    “Levetiracetam did not meet the criteria for non-inferiority in the ITT analysis of time to 12-month remission versus lamotrigine (HR 1·18; 97·5% CI 0·95–1·47)”
    Quote in the paperSubstantial claim
  • Classified as probably not a substantial claim. 10
  • May combine two claims. 14

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

    Premisecitation

    Lamotrigine is non-inferior to carbamazepine for time to 12-month remission and superior to carbamazepine, gabapentin, oxcarbazepine, and topiramate for time to treatment failure (SANAD I).

    “which identified lamotrigine as non-inferior to carbamazepine for time to 12-month remission and superior to carbamazepine, gabapentin, oxcarbazepine, and topiramate for time to treatment failure.”
    Quote in the paperSubstantial claim1 of 1 sources checked
    • cites [10] Marson AG Al-Kharusi AM Alwaidh M The SANAD study of effectiveness of carbamazepine, gabapentin, lamotrigine, oxcarbazepine, or topiramate for treatment of partial epilepsy: an unblinded randomised controlled trial Lancet 369 2007 1000 1015 17382827 PMC2080688 source

      The Discussion reports that lamotrigine was non-inferior to carbamazepine for time to 12-month remission and significantly better than carbamazepine, gabapentin, and topiramate for time to treatment failure. The Abstract Findings describe its advantage over oxcarbazepine as non-significant, so the claim of superiority to oxcarbazepine is not supported. (LLM, conf=0.94)

      Experimental — accuracy not yet measured

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

    Findingown data

    There were 37 deaths during the trial.

    “There were 37 deaths during the trial.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Findingown data

    Adverse reactions were reported by 33% of participants who started lamotrigine, 44% who started levetiracetam, and 45% who started zonisamide.

    “Adverse reactions were reported by 108 (33%) participants who started lamotrigine, 144 (44%) participants who started levetiracetam, and 146 (45%) participants who started zonisamide.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Findingown data

    The intention-to-treat analysis included all participants and the per-protocol analysis included 324 participants randomly assigned to lamotrigine, 320 to levetiracetam, and 315 to zonisamide.

    “The ITT analysis included all participants and the PP analysis included 324 participants randomly assigned to lamotrigine, 320 participants randomly assigned to levetiracetam, and 315 participants randomly assigned to zonisamide.”
    Quote in the paperNot a substantial claim

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

    Findingown data

    990 participants were recruited between May 2, 2013, and June 20, 2017, and followed up for a further 2 years.

    “990 participants were recruited between May 2, 2013, and June 20, 2017, and followed up for a further 2 years.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Findingown data

    The Kaplan-Meier estimates of median time to achieve 12-month remission were 516 days (95% CI 457-577) for lamotrigine, 588 days (472-706) for levetiracetam, and 530 days (453-601) for zonisamide.

    “The Kaplan-Meier estimates of the median time to achieve 12-month remission were 516 days (95% CI 457–577) for lamotrigine, 588 days (472–706) for levetiracetam, and 530 days (453–601) for zonisamide (figure 2).”
    Quote in the paperNot a substantial claim

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

    Study design and conductown data

    Participants and investigators were not masked and were aware of treatment allocation.

    “Participants and investigators were not masked and were all aware of treatment allocation.”
    Quote in the paperSubstantial claim

  • May combine two claims.

    Study design and conductown data

    Completeness of follow-up for the primary outcome was 77% for lamotrigine, 78% for levetiracetam, and 76% for zonisamide.

    “with completeness of follow-up statistics for the primary outcome of 77% for lamotrigine, 78% for levetiracetam, and 76% for zonisamide.”
    Quote in the paperNot a substantial claim

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

    Study design and conductown data

    Interim monitoring was done by an independent data safety and monitoring committee.

    “Interim monitoring was done by an independent data safety and monitoring committee, meeting approximately annually.”
    Quote in the paperNot a substantial claim

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

    Study design and conductnone given

    The statistical and health economic analysis plans were developed before doing the final analyses.

    “The statistical and health economic analysis plans were developed before doing the final analyses and are available in appendix 1 and appendix 2.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Interpretationown data

    These findings do not support the use of levetiracetam or zonisamide as first-line treatments for patients with focal epilepsy.

    “These findings do not support the use of levetiracetam or zonisamide as first-line treatments for patients with focal epilepsy.”
    Quote in the paperSubstantial claim

  • May combine two claims.

    Interpretationnone given

    The study is pragmatic in design and recruited a cohort of participants older than 5 years from routine UK National Health Service clinics, and the results are relevant to every day clinical practice.

    “The study is pragmatic in design and recruited a cohort of participants older than 5 years from routine UK National Health Service clinics, and the results are relevant to every day clinical practice.”
    Quote in the paperSubstantial claim

  • May combine two claims.

    Study design and conductreasoning

    The trial was designed with 80% power and a one-sided alpha of 0·025 to detect a hazard ratio of 1, requiring 330 patients per treatment group, allowing for 5% losses to follow-up.

    “Therefore, assuming a HR of 1 and 80% power with a one-sided alpha of 0·025, 330 patients were required in each of three treatment groups, allowing for 5% losses to follow-up, as occurred in SANAD I (990 total patients).”
    Quote in the paperSubstantial claim

  • Classified as probably not a substantial claim.

    Study design and conductnone given

    The assumption of proportional hazards was investigated by examining Schoenfeld residual plots and incorporating time-dependent covariates in all models.

    “The assumption of proportional hazards was investigated by examining Schoenfeld residual plots and incorporating time-dependent covariates in all models.”
    Quote in the paperSubstantial claim

  • Classified as probably not a substantial claim.

    Study design and conductnone given

    All participants were included in the intention-to-treat analysis.

    “All participants were included in the intention-to-treat (ITT) analysis.”
    Quote in the paperSubstantial claim

  • May combine two claims.

    Study design and conductnone given

    The trial was powered for non-inferiority but was also designed to show superiority.

    “although this trial was powered for non-inferiority, it was also designed to show superiority.”
    Quote in the paperSubstantial claim

  • May combine two claims.

    Study design and conductown data

    The per-protocol analysis for time to 12-month remission excluded patients with major protocol deviations (15 participants; 1.5%) and patients later diagnosed as not meeting the diagnosis of epilepsy (16 participants; 1.6%), and accounted for treatment failures before achieving 12-month remission in a competing risks analysis.

    “The PP analyses (using the Fine and Gray model) for time to 12-month remission (appendix 3 p 3) excluded patients with major protocol deviations (15 participants; 1·5%) and patients later diagnosed as not meeting the diagnosis of epilepsy (16 participants; 1·6%), and accounted for treatment failures before achieving 12-month remission”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Premisecitation

    The National Institute for Health and Care Excellence epilepsy guidelines do not recommend levetiracetam or zonisamide as first-line treatments.

    “This knowledge gap is reflected in the National Institute for Health and Care Excellence epilepsy guidelines, which do not recommend either drug as a first-line treatment.”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites [9] National Institute for Health and Clinical Excellence Epilepsies: diagnosis and management https://www.nice.org.uk/guidance/cg137 2012

      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).

    Study design and conductnone given

    The funder had no role in study design, data collection, data analysis, data interpretation, or writing of the report.

    “The funder of the study had no role in study design, data collection, data analysis, data interpretation, or writing of the report.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Interpretationown data

    Neither levetiracetam nor zonisamide were found to be cost-effective alternatives.

    “Neither levetiracetam or zonisamide were found to be cost-effective alternatives.”
    Quote in the paperSubstantial claim

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

    Interpretationreasoning

    A 6-month seizure freedom primary outcome is too short a timeframe to assess clinical effectiveness in a long-term condition such as epilepsy.

    “The primary outcome in those trials was 6-month seizure freedom, which is too short a timeframe to assess clinical effectiveness in a long-term condition such as epilepsy.”
    Quote in the paperNot a substantial claim
21 of 21

  • The paper relies on this without support.

    To the best of our knowledge, this study is the first randomised controlled trial to assess the longer term clinical effectiveness and cost-effectiveness of levetiracetam and zonisamide as first-line treatments for patients with newly diagnosed focal epilepsy.

    “To the best of our knowledge, this study is the first randomised controlled trial to assess the longer term clinical effectiveness and cost-effectiveness of levetiracetam and zonisamide as first-line treatments for patients with newly diagnosed focal epilepsy.”
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.

  • Conflicting one-sided alpha levels for the primary comparisons

    Minor

    The statistical analysis says the two primary comparisons required a one-sided alpha of 0.0125, but the subsequent sample-size calculation assumes 0.025.

  • Levetiracetam treatment-failure percentage does not match the count

    Minor

    The per-protocol levetiracetam group had 320 participants, so 177 treatment failures would be 55.3%, not 35%. Even using all 332 participants assigned to levetiracetam gives 53.3%.

    Reported 35 · recomputed 55.3125

2 of 2

Cites

Flagged first, then by citations

Cited by

Sorted by citations

Related

Authors
Marson, A., Burnside, G., Appleton, R., Smith, D., Leach, J. P., Sills, G., Tudur-Smith, C., Plumpton, C., Hughes, D. A., Williamson, P., Baker, G. A., Balabanova, S., Taylor, C., Brown, R., Hindley, D., Howell, S., Maguire, M., Mohanraj, R., Smith, P. E., Lanyon, K., Manford, M., Chitre, M., Parker, A., Swiderska, N., Appleton, R., Pauling, J., Hughes, A., Gupta, R., Hanif, S., Awadh, M., Ragunathan, S., Cable, N., Cooper, P., Hindley, D., Rakshi, K., Molloy, S., Reuber, M., Ayonrinde, K., Wilson, M., Saladi, S., Gibb, J., Funston, L.-A., Cassidy, D., Boyd, J., Ratnayaka, M., Faza, H., Sadler, M., Al-Moasseb, H., Galtrey, C., Wren, D., Olabi, A., Fuller, G., Khan, M., Kallappa, C., Chinthapalli, R., Aji, B., Davies, R., Foster, K., Hitiris, N., Maguire, M., Hussain, N., Dowson, S., Ellison, J., Sharrack, B., Gandhi, V., Powell, R., Tittensor, P., Summers, B., Shashikiran, S., Dison, P. J., Samarasekera, S., McCorry, D., White, K., Nithi, K., Richardson, M., Brown, R., Page, R., Deekollu, D., Slaght, S., Warriner, S., Ahmed, M., Chaudhuri, A., Chow, G., Artal, J., Kucinskiene, D., Sreenivasa, H., Velmurugan, Zipitis, C. S., McLean, B., Lal, V., Gregoriou, A., Maddison, P., Pickersgill, T., Anderson, J., Lawthom, C., Howell, S., Whitlingum, G., Rakowicz, W., Kinton, L., McLellan, A., Zuberi, S., Kelso, A., Hughes, I., Martland, J., Emsley, H., de Goede, C., Singh, R., Moor, C.-C., Aram, J., Mohanraj, R., Sakthivel, K., Nelapatla, S., Rittey, C., Pinto, A., Leach, J. P., Cock, H., Richardson, A., Houston, E., Cooper, C., Lawson, G., Massarano, A., Burness, C., Marson, A., Smith, D., Wieshmann, U., Dey, I., Sivakumar, P., Yeung, L.-K., Smith, P., Bentur, H., Heafield, T., Mathew, A., Smith, D., & Jauhari, P.
Affiliations
  • University of Liverpool (GB)
  • Bangor University (GB)
  • Bolton NHS Foundation Trust (GB)
  • University of Glasgow (GB)
  • Salford Royal NHS Foundation Trust (GB)
  • University Hospital of Wales (GB)
  • Royal Hallamshire Hospital (GB)
ORCID
Venue
The Lancet
Publisher
Elsevier BV
Published
2021-04
Volume
397
Issue
10282
Pages
1363-1374
ISSN
  • 0099-5355 (ISSN-L)
  • 0140-6736
DOI
10.1016/s0140-6736(21)00247-6
PMC
PMC8047799
OpenAlex
W3147714437
Cited by
208
References
29
Citations by year
2026: 33 · 2025: 40 · 2024: 44 · 2023: 37 · 2022: 39 · 2021: 15
FWCI
24.40
Type
journal article
Language
en
Update notices
erratum (2021-05-15)
Open access
Licence
Locations
  • The Lancet (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam) (acceptedVersion, cc-by-sa)
  • ORCA Online Research @Cardiff (Cardiff University) (acceptedVersion)
  • Research Explorer (The University of Manchester) (submittedVersion, cc-by)
  • Bangor University Research Portal (Bangor University) (submittedVersion, other-oa)
Funders
National Institute for Health Research
Topics
  • Health Sciences › Medicine › Psychiatry and Mental health › Epilepsy research and treatment
  • Health Sciences › Medicine › Pediatrics, Perinatology and Child Health › Pharmacological Effects and Toxicity Studies
  • Health Sciences › Medicine › Physiology › Diet and metabolism studies
Keywords
focal epilepsy, newly diagnosed epilepsy, levetiracetam, zonisamide, lamotrigine, non-inferiority, seizure remission, cost-effectiveness, antiepileptic drugs, pediatric epilepsy, adults with epilepsy, drug safety, drug tolerability
MeSH terms
Lamotrigine, Levetiracetam, Zonisamide, Administration, Oral, Adolescent, Adult, Aged, Anticonvulsants, Child, Cost-Benefit Analysis, Epilepsies, Partial, Female, Humans, Male, Middle Aged, Treatment Outcome, Young Adult

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 2026-10-30.

Classified by jev-1.13-20260917 (gold-guideline-v0.2) on 2026-10-30.

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