How it works

Why you can trust a biosingularity verdict — and exactly what it checks.

← back to the verifier

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):

🟢 pass — checkable claims grounded, nothing flagged 🟠 review — weak, single-source, or unverifiable; a human should look 🔴 reject — grounded 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.

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.

Source: PubMed / NCBI E-utilities (live).

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 consensus, ACMG PP3/BP4). A variant claimed pathogenic but common in the population is contradicted by its own frequency.

Source: ClinVar · gnomAD · dbNSFP (datalake).

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.

Source: DisGeNET · Open Targets · GWAS Catalog.

Drugs & interactions

A drug is checked against ChEMBL (market withdrawal → reject; FDA black-box → review) and the FDA Orange Book (approval, patent / exclusivity status). Two interacting drugs are checked against DDInter — a MAJOR interaction is flagged, not waved through as “no interaction found.”

Source: ChEMBL · FDA Orange Book · DDInter.

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.

The trust gate for autonomous research platforms.

Freshness & honesty

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 never hides a weak or absent result behind a green.

See biosingularity freshness / health.

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.

Read the source and docs on GitHub →  ·  Request access to the full-depth API →