PHAROS · HYGEIA active

Earlier safety signals.
No causality cosplay.

JourdanLabs’ clinical-safety flagship — COSMIC applied to pharmacovigilance. PHAROS reads FAERS-scale adverse-event reports, ranks drug–event pairs that deserve review, and refuses to score when confidence isn’t there. Triage for safety teams — not medical advice, not regulatory action, not proof of causality.

PHAROS · signal triage

pair tofacitinib · thrombosis · FAERS corpus through 2023 Q4

comparators ROR elevated · PRR below threshold · BCPNN elevated

trajectory ECLIPSE — rising quarter-over-quarter since 2021 Q2

stability PULSAR — holds under adversarial drop tests

confidence AURORA calibrated · above signal threshold

PRIORITIZE

alt MONITOR · ABSTAIN when evidence is thin or unstable

Illustrative console — real pipeline runs deterministic engines + AURORA gate on sealed FAERS snapshots.

Why it exists

Post-market drug safety still runs on four disproportionality formulas from 1998–2002. They flag patterns but ship raw scores with no calibrated confidence — so teams drown in false alarms while real Black Box Warnings arrive months or years after the signal was already visible in FDA’s own database. PHAROS matches the best legacy methods on detection and lead time, and adds what none of them have: honest abstention.

Five-engine pipeline

Deterministic Python pipeline — LLM-free in every scoring path, bit-for-bit identical across runs. 947/947 tests passed.

METEOREntity resolution — brand, generic, and chemical names mapped to one drug identity, with as-of-date audit so nothing from the future leaks into the score.resolve
NOVADisproportionality scoring — classic PRR/ROR/BCPNN/MGPS comparators plus bias adjustment on the observed report counts.score
ECLIPSETemporal trajectory — is the drug–event pattern strengthening quarter over quarter, or noise?trend
PULSARAdversarial stability — stress-test the signal by dropping reports and challenging confounds before anything ships.challenge
AURORACalibrated gate — logistic confidence, signal vs abstention thresholds. No output below threshold instead of a guess dressed as a number.gate

SIGNAL benchmark

SIGNAL is the benchmark receipt — product on the glass is PHAROS. Ground truth sealed before labels were opened.

SIGNAL · sealed corpus

pairs 36 FDA Black Box drug–event pairs (2018–2025)

corpus 17.76M unique FAERS reports · 44 quarters (2015 Q1 – 2025 Q4)

integrity 0 temporal-leakage violations · predictions SHA-256 sealed pre-label

determinism 5/5 runs identical · frozen-output hash verified

benchmark SIGNAL F1 0.639 benchmark name — product is PHAROS

Headline results

Frozen run against 36 labeled pairs. PHAROS at statistical parity with ROR and BCPNN under bootstrap resampling.

PRR (1998)22 / 36 detected · 61.1% · ~27 months median leadlegacy
ROR (2002)23 / 36 detected · 63.9% · ~28 months median leadlegacy
BCPNN (1998)23 / 36 detected · 63.9% · ~28 months median leadlegacy
MGPS (FDA)19 / 36 detected · 52.8% · ~20 months median leadlegacy
PHAROS23 / 36 detected · 63.9% · 24.3 months median lead · calibrated abstentionproduct

Calibrated abstention

Old methods always return a number — even when they shouldn’t. PHAROS ranks by confidence and stops guessing.

PrioritizeConfidence above signal threshold — pair belongs at the top of the safety review queue.review
MonitorDirectional signal but not yet decisive — watch the trajectory, don’t close the file.watch
AbstainBelow confidence threshold — PHAROS names the gap instead of flooding the queue with noise.refuse

Rank PHAROS predictions by maximum confidence: the top 23 are 100% correct. PRR makes its first ranked error at position 21.

Early-warning examples

Months before FDA’s actual Black Box announcement — from sealed backtests, not retroactive storytelling.

Isotretinoin · depression+62 months lead — danger visible in patient reports years before the official warning.+62m
Ciprofloxacin · aortic aneurysm+42 months lead — major vessel risk flagged from FAERS trajectory.+42m
Tofacitinib · thrombosis+22 months lead — PHAROS caught it; PRR missed this pair entirely.+22m

Plain English

PHAROS reads the FDA’s giant database of patient side-effect reports and looks for drugs that might be hurting people earlier than the agency usually catches them. It catches as many real dangers as the best 30-year-old formulas and flags them roughly two years sooner — but unlike those formulas, it tells you when it isn’t sure enough to act. That refusal is the product: fewer false alarms, more time on the signals that matter.

Boundaries

PHAROS lives under HYGEIA — regulated clinical safety and pharmacovigilance. It is not HELIX. Output is safety-review triage from spontaneous report data: prioritize, monitor, or abstain. It does not prove causality, does not replace a qualified drug-safety officer, and does not constitute medical or regulatory advice.

First external-domain validation of COSMIC in medicine · LLM-free scoring · 947/947 tests · sealed SIGNAL receipts on the benchmark wall.