Skeptic

What it checks

1. 1

   Rates the real claim right-claim

   Does the article rate the claim as it actually circulates, rather than a weaker or stronger version, and does the conclusion stay within that claim's scope (time, place, population)?

   7 findings · 3 applied
2. 2

   Rating follows from the evidence rating-follows-evidence

   Taking the evidence exactly as stated, does it support the finding label and the answer, so a careful reviewer would choose the same label?

   4 findings · 2 applied
3. 3

   Confidence matches the evidence confidence-calibrated

   Do the confidence level, title, and summary claim no more than the evidence supports, and does the article state the limitations that matter?

   21 findings · 6 applied
4. 4

   Strongest objections answered strongest-objection

   Does the article state the strongest objections and alternative explanations, and answer them fairly with evidence rather than dismissal?

   33 findings · 8 applied
5. 5

   Evidence is independent evidence-independence

   Are the lines of evidence actually independent, or do several rest on the same underlying dataset, study, or institution?

   26 findings · 7 applied

Each check comes back as Pass, Concern (minor or material), Fail, Not applicable, or Not checked.

How it grades

The first rule that matches the check results gives the grade.

1. Any check is Fail The rating doesn't follow from the article's own evidence, or the article rates a different claim from the one it names.
2. 2 or more checks are Concern (material) The reasoning has several serious gaps, so the rating can't be relied on.
3. Any check is Concern (material) The rating is defensible, but the article overstates its case, rates a somewhat different claim, or skips its strongest challenge.
4. 2 or more checks are Concern (minor) The reasoning holds, with several minor gaps, such as secondary objections left out or confidence a step high.
5. Otherwise The rating and confidence follow from the evidence, the article rates the real claim, and the strongest objections are answered. A single minor note for the author does not lower the grade.

From its instructions

Takes the article's evidence as stated and asks whether the reasoning holds: whether the article rates the claim as it actually circulates, whether its rating label and confidence follow from its own evidence, whether it answers the strongest objections and alternative explanations, and whether its lines of evidence are really independent. It may use its own knowledge only to raise objections the article should answer, never as proof, so it cannot fail an article on its own say-so. It doesn't check whether sources say what the article claims; the Source Checker does that. One minor gap is reported to the author without lowering the grade; two or more give a B.

Recent audits

1. If I-645 passes, the tax relief for working families stays in place. Version 1 · 2 of 5 checks passed · 22 October 2026 by auditor version 2
2. After puberty, boys outrun, outjump and outswim girls by roughly 10-30%. Version 4 · 2 of 5 checks passed · 13 October 2026 by auditor version 5 · Benchmark run
3. After puberty, boys outrun, outjump and outswim girls by roughly 10-30%. Version 4 · 2 of 5 checks passed · 12 October 2026 by auditor version 2
4. Boys outperform girls by 10 to 20 percent in sports after puberty. Version 1 · 3 of 5 checks passed · 12 October 2026 by auditor version 2
5. Carrots help night vision if you lack vitamin A; no boost shown otherwise. Version 3 · 3 of 5 checks passed · 12 October 2026 by auditor version 2

All audits →

Latest findings

1. Add an objection on whether the relief has any contingency clause or depends on appropriations once I-645 repeals Sec. 202's funding distribution.

   Open Minor check strongest-objection about article:i645-relief-stays-460000-families:1 (a draft when audited) 22 October 2026 by version 2

2. Explain more directly why False rather than Misleading fits a hedged 'could' claim whose underlying budget risk the article concedes is real.

   Open Minor check rating-follows-evidence about article:i645-relief-stays-460000-families:1 (a draft when audited) 22 October 2026 by version 2

3. Add an explicit line in the conclusion and an objection on the small-business part of the claim, showing that the B&O relief in Secs. 909–911 survives.

   Open Minor check right-claim about article:i645-relief-stays-460000-families:1 (a draft when audited) 22 October 2026 by version 2

4. 2 edits: note the 19-37 Olympic count rests mostly on one 800m final run below record pace; note doping-era records caveat in the 1983-plateau answer.

   Open Minor check strongest-objection about article:boys-girls-sports-performance-gap:4 13 October 2026 by version 5

5. Change the title's 'roughly 10-30%' to per-event ranges the evidence reports, such as about 10-15% in running, 7-12% in swimming and 18-30% in jumping.

   Open Minor check confidence-calibrated about article:boys-girls-sports-performance-gap:4 13 October 2026 by version 5

All findings →