SUPPLEMENT FACTS, CONTINUEDreconciled 2026-07-05

Where every number comes from

Every fact in Litmus traces to a named public source, and this page is the supply chain. It is the same catalog we hold ourselves to internally, published, including the parts a marketing page would normally leave out.

The sources

NIH Dietary Supplement Label Database (DSLD)Public domain (CC0)

Product labels and their ingredient lines. The catalog: every product page starts as a DSLD label, loaded in bulk and upserted deterministically.

NIH Office of Dietary Supplements fact sheetsPublic domain

What the evidence says per nutrient. The Health Professional fact sheets; our evidence summaries are extracted from these, with the source URL kept on every row.

PubMed / NCBIMetadata public; citations only

Research paper metadata and citations. We store the citation (PMID, title, journal, authors, link) and never the abstract or full text: those belong to the publishers.

NIH iCitePublic (CC0)

Citation-impact ranking for papers. Field- and age-normalized impact, so a flashy pilot study cannot outrank a meta-analysis.

openFDA enforcement recordsPublic domain (CC0)

Product recalls. Recall facts matched by exact firm name only: fuzzy matching a recall to the wrong brand is a bell you cannot un-ring.

NLM MeSHFree, attribution

The outcome vocabulary. Health outcomes are named with real Medical Subject Headings descriptors, not labels we made up.

The counts

214,788

products · from the DSLD bulk load

75,113

ingredients · name-normalized, synonym-merged

2.78M

label lines · one per ingredient per label

1,091

papers linked · PubMed citations, iCite-ranked

359

evidence rows · all but one carrying the exact source URL

98

recall facts · openFDA, exact firm match

Counts as of the last catalog reconciliation, 2026-07-05. When the catalog changes, this page changes in the same release.

What involves AI, exactly

Honesty requires precision here, so: two things in the Litmus data involve a language model, and neither invents facts.

Everything else, the catalog, ingredients, brands, papers, and recall facts, is deterministic ingestion of the public sources above. No model writes product data.

What we do not know yet

The commitments