Cited references
Every DOI is resolved to its PubMed record and checked for a retraction, retraction notice, or published erratum. A retracted citation is an automatic reject, with the retraction-notice PMID as the receipt.
How it works
Why you can trust a biosingularity verdict — and exactly what it checks. No model is in the verdict path, so the same input always yields the same result, and it can't invent a "looks fine".
One verdict, always with a receipt
Every answer, claim, or discovery resolves to one of three recommendations, plus a grounded-confidence score (the share of checkable claims that resolved to a real source):
PASScheckable claims grounded, nothing flagged.
REVIEWweak, single-source, or unverifiable — a human should look.
REJECTgrounded on retracted, contradicted, or unsafe evidence.
The cardinal rule: biosingularity never asserts a claim is grounded without a receipt —
a link to the exact record behind the verdict. A confident false "pass" is the only unforgivable failure,
so anything it cannot verify is held for review, never waved through. Verdicts are deterministic:
the same input yields the same result every time.
This is a design property, not a marketing number: a claim is only marked grounded when a receipt exists, and a discovery is only publish when something positively grounded — everything unverifiable degrades to review. The verifier is measured against a labelled claim set (precision / recall over known-good and known-bad claims) that grows with every rule and source added.
What it checks — and the rule behind each
Each checkable part of an answer is verified against a primary source. No single heuristic decides anything — the verdict is the evidence.
Variant pathogenicity
A "pathogenic" claim is checked against ClinVar, its population frequency in gnomAD (ACMG BA1 ≥5% → reject, BS1 ≥1% → review, using the highest sub-population / popmax), and the dbNSFP in-silico panel (SIFT / PolyPhen / CADD / REVEL / AlphaMissense, ACMG PP3 / BP4). A variant claimed pathogenic but common in the population is contradicted by its own frequency.
Gene–disease links
An association is corroborated across DisGeNET, Open Targets, and the GWAS Catalog. Two or more independent sources → corroborated; one → single-source (review); none → unsupported. Overlapping sources are down-weighted so agreement isn't double-counted.
Drugs & interactions
A drug is checked against ChEMBL (market withdrawal → reject; FDA black-box → review) and the FDA Orange Book (approval, patent / exclusivity). Two interacting drugs are checked against DDInter — a MAJOR interaction is flagged, not waved through as "no interaction found".
Generated discoveries
An AI-generated discovery is gated: its hypothesis, entities, and cited papers are all verified, and it is only publish if something positively grounded — single-source or uncheckable is review, never auto-published.
Coverage & staleness
A verdict is only as current as its source. biosingularity discloses the age of each dataset and marks stale sources; the reference / retraction check is always live. It reports how much of an answer it actually checked (coverage) and holds a low-coverage answer for review rather than passing it.
The browser demo vs. the full depth
This site runs the public-API subset (PubMed, Open Targets, ChEMBL, ClinicalTrials.gov) — enough to catch retracted citations, weak gene–disease support, and withdrawn / black-box drugs, with no sign-up. The full depth — variant pathogenicity over gnomAD / dbNSFP, drug interactions, drug regulatory status, discovery verification, and multi-source corroboration over a 493 GB integrated datalake — runs via the CLI, the MCP connector, or the hosted API, because that data can't live in a browser function. Nothing is asserted without a receipt in either mode.