Research

Every claim ships with its data.

Published Research & Verification

The Replication Gap

Computational research rests on runs nobody else can repeat. Results arrive as figures and summary statistics; the seeds, the configurations and the code paths that produced them stay behind.

A reviewer can check the argument, and rarely the result. When a stochastic model returns a different answer on the second run, a disagreement over findings turns into a disagreement over noise.

A claim that cannot be re-executed is a claim taken on trust.

The Standard of Proof

Every claim on this site is backed by a deterministic experiment, with seeds, scenarios and traces published alongside the result. Falsification criteria are fixed before the first run, and raw outputs and standalone validation scripts ship with every study, so anyone can check the findings without our engine.

Latest study

SAF-001 · Robotics

1,800 scenarios. A velocity-blind baseline gate accepted 1,200 collision hazards. The KAIROS layer accepted zero, and kept 81% of the recoverable motion moving by slowing it to a safe speed.

Read the findings

Robotics

  1. CMP-001 · RoboticsTwenty-One of Twenty-Four. Scored Once.24 sealed targets. One look. A pass bar fixed before the score. 21 of 24 reached, a Wilson lower bound of 0.725 against a 0.50 bar, and five of five certified policies cleared it.

AI Safety

  1. AI SafetyCalibrating the AI Safety AdapterCalibrating the AI safety adapter against METR, GAIA, SWE-bench, τ-bench, AISI, Microsoft AIRT, and MAST across 86,400 trajectory snapshots.
  2. BND-001 · AI SafetyThe Gate Holds. Every Time.120 runs. 48 risky tool calls. 20 low-alignment states. Zero false negatives. Zero false positives. The KAIROS safety gate holds with mathematical certainty.

Cybersecurity

  1. CyberCalibrating the Cybersecurity AdapterCalibrating KAIROS Cyber against DBIR, NIST, CIS, OCSF, LANL, and DARPA references across 5.2 million zone snapshots.

Engine

  1. EXP-004 · Game TheoryRobust Cooperation from Stability PhysicsWithout payoff matrices, game rules, or a single pre-scripted event, a stability physics engine reproduced Axelrod's cooperation results across 291,600 tournaments, and revealed that a single measurable parameter determines whether a system faces a cooperation dilemma at all.
  2. EXP-003 · Systemic RiskCooperators Get Punished. The System Survives AnywaySubsidies make the death cheaper but don't prevent it. Across 180,320 simulations, we mapped exactly which governance mechanisms save a collapsing commons, and which are structurally doomed.
  3. EXP-001 · AI SafetyWe Defeated the Paperclip MaximizerThe simplest agent (a one-rule safety constraint) outlasted and outscored sophisticated planning AIs across 3.6 million test runs.

Research in numbers

The numbers behind the studies.

  • 4.07MSimulation runs4,071,920 runs across the published studies, each one seeded.
  • 3,570Parameter configurationsPublished with the studies, so every cell can be re-run.
  • 1,800+Tests passingAcross the engine and the research pipeline.

Every run is seeded and replayable; the raw outputs are published with each study.Browse the studies

Work with us

Bring your own hypothesis.

  • Chief Scientist

    Open role

    We are looking for a PhD-level scientist in complex systems or mathematical physics to lead our research and formalise its theoretical framework.

    Get in touch

  • Academic collaboration

    Engine access

    Test your own structural-risk hypotheses on the KAIROS engine, under academic access.

    Request access

Privacy Policy

Effective: October 2026

1. Data Controller

AnankeLabs AB (Ogan 12, 153 95 Järna, Stockholms län, Sweden) is the data controller for personal data submitted through anankelabs.io under the EU General Data Protection Regulation (GDPR).

2. Data Collected

AnankeLabs collects only the information voluntarily submitted through our contact, evaluation-scoping, and newsletter forms: name, email address, organization, role, domain of interest, and inquiry message. On-premise deployments of KAIROS Substrate operate offline and transmit no runtime telemetry to AnankeLabs. Design-partner calibration datasets are governed by a separate mutual NDA and local redaction protocol.

3. Purpose & Legal Basis

Submitted information is processed solely to respond to commercial, research, compliance, or investor inquiries (GDPR Art. 6(1)(b) and 6(1)(f)) or to deliver research and product dispatches following explicit subscription confirmation (GDPR Art. 6(1)(a)). AnankeLabs does not sell, rent, or broker personal data to third parties.

4. Cookies & Infrastructure Logs

This website uses no third-party advertising trackers or behavioral analytics cookies. Strictly necessary session cookies are used only where authenticated account features are enabled. Standard edge and server logs (IP address, request path, timestamp) are processed transiently for security, rate limiting, and abuse prevention.

5. Storage & Retention

Submitted records are stored on encrypted European and Cloudflare edge infrastructure. Inquiry records are retained only for the duration of the business relationship or evaluation, and newsletter subscriptions are retained until unsubscribed.

6. Data Subject Rights

Under the GDPR, individuals have the right to access, rectify, erase, restrict, or export their personal data, and to withdraw consent at any time. Requests are processed within 30 days. Individuals also have the right to lodge a complaint with the Swedish Authority for Privacy Protection (Integritetsskyddsmyndigheten, IMY).

7. Contact

For privacy requests or inquiries, email privacy@anankelabs.io.

Terms of Use

Effective: October 2026

1. Acceptance

Accessing and using anankelabs.io constitutes acceptance of these Terms of Use.

2. Intellectual Property

All software, documentation, research studies, calibration artifacts, and content on this site are the intellectual property of AnankeLabs AB. KAIROS Substrate, the KAIROS domain adapters (Robotics, AI Safety, and Cybersecurity), and the Spindle verification framework are proprietary technologies. No license to commercial binaries or patents is granted except under a written agreement or as explicitly stated in an open reproduction bundle.

3. Evaluations & Early Access

Scoped evaluations, partner calibration harnesses, and early-access software are provided under separate written evaluation or licensing agreements.

4. Integration & Safety Responsibility

Published studies, benchmarks, and documentation on this site are provided for technical informational purposes. Production deployment of KAIROS Substrate in physical machinery, autonomous agents, or security operations requires embodiment-specific calibration, system-level safety validation, and adherence to applicable statutory and hardware interlock requirements.

5. Limitation of Liability

This website and its public materials are provided "as is" without warranty of any kind. To the maximum extent permitted by law, AnankeLabs AB is not liable for indirect or consequential damages arising from the use of this website or reliance on its public informational materials.

6. Governing Law

These terms are governed by the laws of Sweden, with exclusive jurisdiction in the courts of Stockholm.

7. Contact

For legal inquiries, email legal@anankelabs.io.