Scientific evidence intelligence

Build on science robust enough to stake your decision on.

Kaimen Rigor reads the evidence behind an asset, recomputes the numbers, and flags what won’t survive scrutiny before you commit.

Walk through a real asset-diligence case Book a 30-minute demo

A body of evidenceRead by Kaimen Terminal

Reproducible — build on these

Doesn’t hold up — set aside

Illustrative. See real runs

Recognition

Built by a research team recognized for exactly this work: rigorous, reproducible science.

Alzheimer’s Insights AI Prize

Alzheimer’s Disease Data Initiative · $1M global agentic-AI competition

NIH Replication Prize

NIH Common Fund · For advancing reproducible science

Why this matters

The cost of unreproducible early evidence isn’t just capital. It’s patient-years and delayed medicines.

Kaimen Rigor surfaces the weak evidence early, so the programs that move forward are the ones built on science that holds.

Real Kaimen Rigor reviews

Two real-world cases. The triage calls that should have been made.

Two papers behind real public assets, screened blind to the outcome. Every finding is confirmed in the source text.

Leronlimab (CytoDyn)

Single-arm, n=10 critical-COVID-19 series · International Journal of Infectious Diseases, 2020

A $185.3M FY2021 financing rode on this CCR5-blockade COVID-19 repositioning. The paper is the technical thesis behind that raise.

Confirmed verbatim in the source text

seriousCohort contradiction: the text says SARS-CoV-2 was found in the plasma of “all 10” critically ill patients; the viremia figure legend says “seven.” The paper never reconciles which patients entered the headline analysis.
seriousUnexplained missing observation: that same legend reports n=20, but seven patients at three timepoints is 21. One observation is absent with no accounting.
mediumA corrupted reference DOI (1 of 30 unresolved), and a single-arm n=10 design with no randomization, control, blinding, or trial registration behind a “novel therapeutic strategy” claim.

What happened next: The former CEO was later convicted of securities fraud over statements about the programme and sentenced in January 2026 — recorded here separately from anything Kaimen Rigor produced.

Kaimen Rigor read only the 2020 paper text, with no knowledge of any later enforcement outcome.

Open the full Kaimen Rigor review Reviewed text DOI

Olaratumab (Eli Lilly, Lartruvo)

Randomized Phase 2, advanced soft-tissue sarcoma · The Lancet, 2016

This Phase 2 was the basis for accelerated approval. The disproportionate overall-survival claim (26.5 vs 14.7 months) carried the valuation and the EU filing.

Confirmed verbatim in the source text

criticalA statistically impossible result: an 18.2% objective response rate reported with 95% CI 29.6–29.8 — an interval that excludes its own point estimate.
criticalAn independent-review PFS hazard ratio of 0.670 with 95% CI 0.04–1.12 — a lower bound implausible for 133 patients. The journal later corrected it to 0.40–1.12; Kaimen Rigor flagged it from the text alone.
seriousFour reported percentages disagree with their own counts (e.g. neutropenia “25 [39%]” against N=65), plus no data-availability statement and unidentified assay reagents.

What happened next: Confirmatory Phase 3 ANNOUNCE (JAMA 2020, n=509) found no overall-survival benefit (HR 1.05). The FDA revoked the Lartruvo license and the EMA withdrew authorisation; olaratumab is no longer approved.

Kaimen Rigor read only the 2016 paper text — it never saw the ANNOUNCE result or the journal’s correction.

Open the full Kaimen Rigor review Reviewed text DOI

A Kaimen Rigor review is a hypothesis about a paper’s evidence quality, not a finding of misconduct and not investment advice. Regulatory and enforcement facts cited here come from primary sources and are recorded separately from anything Kaimen Rigor produced.

Every Kaimen Rigor review contains

01Executive summary
02Principal claims
03Evidence sources examined
04Findings organized by materiality
05Source passage and calculation
06Confidence and verification status
07Potential decision impact
08Recommended follow-up questions
09Methods and limitations
10Versioned audit trail

Case studies

Cross the false claims off your list.

Every card is a real Kaimen Rigor run on a positive-looking early paper.

Antibody-drug conjugate

small-cell lung cancer

1★

Surrogate endpoint, no benefit link; two phantom citations

Later · Phase 3 stopped early for worse survival (2019); discontinued

Ph 1 Trial, 2017 · The Lancet Oncology · Not retractedWeak Evidence

Monoclonal antibody

soft-tissue sarcoma

1★

A 95% CI that excludes its own point estimate

Later · Phase 3 found no survival benefit (2020); approval withdrawn

Ph 2 Trial, 2016 · The Lancet · Not retractedWeak Evidence

Monoclonal antibody

osteogenesis imperfecta

1★

Efficacy rests on a bone-density surrogate; placebo arm dissolved mid-study

Later · Phase 3 missed its fracture primary (2025); BMD-only gains

Ph 2b Trial, 2024 · Journal of Bone and Mineral Research · Not retractedWeak Evidence

Bispecific T-cell engager

small-cell lung cancer

2.5★

Same target, same disease; no critical findings

Later · Advanced in the clinic; accelerated approval (2024)

Ph 1 Trial, 2023 · Journal of Clinical Oncology · Not retractedPassed Kaimen Rigor

Monoclonal antibody

early Alzheimer's

3★

One reconciled count discrepancy, nothing disqualifying

Later · Phase 3 confirmed benefit; approved (2023)

Ph 2b Trial, 2021 · Alzheimer's Research & Therapy · Not retractedPassed Kaimen Rigor

Monoclonal antibody

refractory hypercholesterolemia

3.25★

Clean design, complete reporting

Later · Confirmed and approved (2021)

Ph 2 Trial, 2020 · New England Journal of Medicine · Not retractedPassed Kaimen Rigor

3 flagged weak here later failed in Phase 3 or lost approval.

See the case studies Full reports on a demo

A simple principle

Concise. Robust. Elegant.

A rigor review should surface the finding that could change the decision, give you the evidence to defend it, and spare you everything else.

Numerical and statistical consistency

Recompute reported statistics and check denominators, confidence intervals, P values, and tables against the underlying data.

Protocol-to-publication concordance

Compare protocols, SAPs, registries, and publications to surface deviations from what was prespecified.

Claim-to-evidence verification

Test whether each consequential claim is actually supported by the evidence presented.

Reporting and ethics completeness

Flag reporting omissions, missing disclosures, and ethics or registration gaps, without treating omission as misconduct.

Reproducibility and decision-risk assessment

Assess whether the analysis can be reproduced and where the decision risk concentrates.

Why Kaimen Rigor

What Kaimen Rigor guards against.

Human upselling

Interested parties show weak data in its best light. Kaimen Rigor recomputes the key numbers and separates what the evidence shows from how it is framed.

AI hallucination

A general assistant summarizes with confidence and invents what it cannot find. Every Kaimen Rigor finding links to its source and is checked against it.

Human and AI error

The number that undercuts a claim often sits documents away, rarely re-checked. Kaimen Rigor reads the full evidence base as one system, so nothing consequential is skipped.

What Kaimen Rigor runs

One deliverable on top. This much runs underneath.

Every Kaimen Rigor review runs the same battery of checks, each finding traceable to its source.

8: dimensions of rigor scored, from scientific premise to reporting transparency
5: evidence sources read as one system: publication, protocol, SAP, registry, CONSORT
100%: of findings linked to their source passage, with a confidence and a materiality

Statistical recomputation

P values, CIs, and percentages recomputed from the source.

Citation integrity

Every reference audited by DOI; retractions surfaced.

Protocol-to-publication concordance

Publication reconciled against protocol, SAP, and registry.

Claim-to-evidence audit

Each claim tested against the evidence actually shown.

Surrogate & endpoint scrutiny

Flags efficacy resting on a surrogate or a moved endpoint.

Independent reviewer panel

Parallel reviewers; only convergent findings carry.

BD and R&D

The same rigor, two jobs.

For business development

Know what the evidence is worth before you license the asset.

In-licensing and acquisition diligence
Clinical-trial evidence review
Competitive and landscape evidence assessment
Data-room and claim verification
Portfolio and indication prioritization
Decision-ready evidence reports

Explore BD diligence

For R&D

Know if the science is solid enough to build on.

Foundational-evidence validation before you commit a program
Protocol, SAP, and registry-to-publication concordance
Reproducibility and statistical review
Internal prepublication and data-package QC
Evaluation of AI-generated scientific work
Systematic comparison of competing claims

Explore R&D validation

Built to be trusted

A reproducibility research team, and your evidence handled with care.

The team

Built by researchers recognized for exactly this work.

Kaimen Terminal is built by a research team working on reproducibility and scientific rigor. The standard we hold your evidence to is the one our own work is measured by.

Alzheimer’s Insights AI Prize — Alzheimer’s Disease Data Initiative. $1M global agentic-AI competition.
NIH Replication Prize — NIH Common Fund. For advancing reproducible science.

Security & data handling

How we handle your evidence.

Encrypted in transit and at rest.
An NDA and DPA are available before any documents are shared.
Your evidence is never used to train models.
You control retention, deletion, and export.
Subprocessors named on request.

No SOC 2 or HIPAA certification claimed. A security overview is shared under NDA.

Every finding is a candidate for human review, not a final verdict.

How a pilot works

A private, defined pilot on one real decision.

Scope: One real decision — an in-licensing asset, a program, or a manuscript — agreed up front.
Turnaround: About two weeks from data access to a readout with your team.
Success metrics: Set with you, so results are judged against a bar you set.

Get started

Bring decision-grade verification into your workflow.

For business development

See Kaimen Terminal on a live in-licensing or diligence decision: the pivotal trials behind an asset, a data room, or a competing evidence base. Start with a demo; we scope a private pilot when it is a fit.

For R&D

See Kaimen Terminal on the science you are deciding whether to build on: a protocol, an analysis, a data package, or a scientific-agent workflow. Start with a demo; scope a pilot on a real decision.

Request a demo Explore an R&D use case

Prefer to look first? See two real Kaimen Rigor reviews.

Bring decision-grade verification into your workflow.

For business development

For R&D

See Kaimen Terminal on the science you are deciding whether to build on: a protocol, an analysis, a data package, or a scientific-agent workflow. Start with a demo; scope a pilot on a real decision.