Skip to content
Litmus · 20 checks · deterministic

Twenty data pointsbefore your agent cites a page.

Every parse returns clean Markdown plus Litmus — twenty rule-based checks your agent can inspect before it trusts a page. No model in the path, no temperature, no second opinion that changes overnight.

litmus.json
v2
Verdict
Safe to build on
Cite
source
news · 0.82
authorship
Jane Chen · jsonld
freshness
2026-01-14 · current
trust
high · 0.92
paywall
none
reading_time
7 min
20 of 20 signals0 flags
Reading the verdict

Four patterns to check first.

The signals only matter if they change what happens next. These four cover nearly every call an agent makes.

Verdict order
drop→review→cite

A hard failure wins. If a page is gated, missing or erroring, no amount of polish elsewhere upgrades it to citable.

Cite01

Safe to build on

verdict is "cite" — authorship present, citations dense, density high, no flags. The page says what it claims and shows its work.

Cite it, and log the verdict.

Drop02

Wrong page, not wrong source

page_status fires, or a paywall is detected, or content is truncated. The agent read a gate, not the article.

Do not cite; retry elsewhere or escalate.

Review03

Right content, wrong copy

syndication is detected, or redirects crossed domains. The content is real, but you are holding a copy.

Cite the original via canonical.

Review04

Assertion dressed as evidence

Thin content, heavy hedging, no citations, no named authorship. The prose asserts more than the page can support.

Fine to mention, not fine to build on.

Every signal, with its payload

The full twenty, in four groups.

Source, trust, validity and read. Each one is deterministic — a given page and a given Litmus version produce the same signals every time, so you can cite them in your own logs.

Source

6 signals

Who wrote it, what it claims to be, who it links to, and whether it shows its work.

Page type, authority score, and the reasoning behind it.

type: "news" · authority: 0.82
type: "blog" · authority: 0.21

All 20, spelled out

One line per signal: what it measures, a good example and a bad one. Same reference as the explorer above, in plain reading order.

Source

6 signals

Who wrote it, what it claims to be, who it links to, and whether it shows its work.

source
Page type, authority score, and the reasoning behind it.
type: "news" · authority: 0.82type: "blog" · authority: 0.21
authorship
A named person, an organisation, or nobody — and where it was found.
present: true · kind: "person"present: false · kind: "unknown"
content_type
What the page actually is, not what the URL suggests.
type: "news_article"type: "thin_listing"
outbound_authority
A score plus the domains it links out to — primary sources or more blogs.
score: 0.71 · top: "who.int"score: 0.22 · top: "blog.example"
citations
References section, external links, and links per 1,000 words.
has_references: true · per_1k: 3.2has_references: false · per_1k: 0
structured_data
JSON-LD schema, OpenGraph, and the canonical URL.
json_ld: true · og: truejson_ld: false · og: false

Trust

5 signals

Is it substance, or hedging and bare assertion? These signals count what is actually on the page.

structural_trust_score
High, medium or low — with the factors behind it, so it can be inspected.
level: "high" · trust_factors: 3level: "low" · trust_factors: 1
hedge_language
Density of "reportedly", "some say", "allegedly" — claim vs rumour.
density: "low" · markers: 2density: "high" · markers: 14
content_density
Thin-content flag plus ratio of substantive sentences.
thin_content: false · ratio: 0.78thin_content: true · ratio: 0.31
boilerplate_ratio
How much is nav, ads and furniture. High ratio plus low density is the content-farm shape.
ratio: 0.18ratio: 0.74
quote_density
Attributed quotes and attribution verbs per 1,000 words.
quotes: 3 · per_1k: 0.7quotes: 0 · per_1k: 0

Validity

6 signals

Is it current, is it reachable, is it gated, is it the original, is it the page you asked for.

freshness
Published date, age, Last-Modified, staleness, and corrections.
published: "2026-01-14" · stale: falsepublished: "2019" · stale: true
page_status
Soft 404, login wall, captcha, JS shell. A 200 is not proof you got the article.
kind: null — a real pagekind: "soft_404" — not the article
paywall
Detected or not, with a note — a gate never passes as content.
detected: falsedetected: true
syndication
Is this a copy of something published elsewhere? Cite the original.
detected: falsedetected: true
is_archived
Presence in the Wayback Machine and archive.today.
wayback: truewayback: false
redirects
Final URL, hop count, and whether it crossed domains.
hops: 0 · cross_domain: falsehops: 2 · cross_domain: true

Read

3 signals

What it says and how long it takes — enough to triage before you spend context.

tldr
A one-line summary of what the page says — extractive, not generated.
"A 20-year cohort study links…""" — nothing extracted
key_figures
The numbers on the page, each with the context it appeared in.
7.3 yr — "increase in life expectancy"0 figures
reading_time
Minutes, to budget context before you spend it.
minutes: 7minutes: 1
The whole payload

One response. Markdown and the verdict, together.

No second endpoint, no second charge. The Markdown is the page; the signals are its vitals. Every field is inspectable, and every unknown is returned as null or "unknown" rather than guessed.

Nearly everything comes from the rendered page
DOM, Markdown, response headers — measured, not inferred.
Two signals look outside the page
is_archived queries the Wayback Machine; source.authority leans on a domain reference list.
Versioned, so runs can be compared
The Litmus version is pinned to the response. Same page plus same version equals the same signals.
Fails visibly
A missing signal is null or "unknown", never a confident fabrication.
litmus_version 220 groupsdeterministic
POST /fetch — 200 response
{  "url": "https://example.org/cohort-study",  "markdown": "# Study Finds Correlation Between Diet and Longevity …",  "litmus": {    "litmus_version": "2",    "verdict": "cite",    "flags": [],    "source": {      "type": "news",      "authority": 0.82,      "rationale": "established publisher"    },    "authorship": {      "present": true,      "name": "Jane Chen",      "kind": "person",      "source": "jsonld"    },    "content_type": {      "type": "news_article"    },    "outbound_authority": {      "score": 0.71,      "top_domains": [        "who.int",        "thelancet.com"      ]    },    "citations": {      "has_references": true,      "external_links": 12,      "external_per_1k_words": 3.2,      "primary_domain_links": 5    },    "structured_data": {      "json_ld": true,      "schema_types": [        "NewsArticle"      ],      "open_graph": true,      "canonical": "https://example.org/cohort-study",      "meta_description": true    },    "structural_trust_score": {      "level": "high",      "trust_factors": [        "High-authority source",        "Named authorship",        "Dense citations"      ]    },    "hedge_language": {      "density": "low",      "markers": 2    },    "content_density": {      "thin_content": false,      "ratio": 0.78    },    "boilerplate_ratio": {      "ratio": 0.18,      "confidence": "high"    },    "quote_density": {      "attributed_quotes": 3,      "attribution_verbs": 5,      "per_1k_words": 0.7    },    "freshness": {      "published": "2026-01-14",      "age_days": 276,      "stale_warning": false,      "correction_noted": false    },    "page_status": {      "is_error_page": false,      "kind": null,      "confidence": "high"    },    "paywall": {      "detected": false,      "note": null    },    "syndication": {      "detected": false,      "canonical_url": null    },    "is_archived": {      "wayback": true,      "archive_today": false    },    "redirects": {      "final_url": "https://example.org/cohort-study",      "hops": 0,      "cross_domain": false    },    "tldr": {      "text": "A 20-year cohort study links the Mediterranean diet to a 7.3-year increase in average lifespan."    },    "key_figures": [      {        "value": "7.3 yr",        "context": "increase in life expectancy on the Mediterranean diet"      },      {        "value": "24,200",        "context": "participants across seven countries"      }    ],    "reading_time": {      "minutes": 7    }  }}
scroll

abbreviated markdown · full signal block

Run it on your own URL.

No account, no wallet. Three free tries, then $0.002 per parse. A test costs less than one wrong citation.

10 free parses a month · no account · no API key