For Partners

The problem

Disinformation operates at a scale and sophistication that individual fact-checkers cannot match. Claims are engineered to exploit specific weaknesses in human evaluation, using true facts to create false impressions, laundering unreliable sources through credible outlets, and weaponizing the degradation of institutions that people have been taught to trust.

Existing fact-checking organizations do essential work, but they face structural challenges: editorial processes that are difficult to scale, implicit decision-making that is difficult to audit, and limited systematic defenses against adversarial disinformation techniques.

The approach

The cooperative’s suite is three structured methodologies that each provide an explicit, step-by-step process for a different question — and a shared discipline that addresses these challenges directly:

  • Veridi — Is this claim true? Fact-checking with source hierarchy, gaming detection, and calibrated confidence.
  • Pragma — What does the evidence suggest about this policy? Policy synthesis with transferability assessment, normative reasoning, and Implementation-Constraint analysis.
  • Praxis — What can a specific person actually do? Individual-action synthesis with leverage matching across 9 change pathways, sustainability risk, and counter-strategy awareness.

Scalable. Each methodology is implemented as a prompt system for AI, meaning it can process inputs at machine speed while following documented procedures. A single assessment takes minutes, not hours.

Auditable. Every step is documented. Source classification, evidence quality grading, gaming countermeasure checks, decision tree paths, confidence reasoning — all visible in the output. When a system makes an error, the process shows where and why.

Adversarial-aware. Pragma includes explicit countermeasures for 14 documented disinformation and motivated-reasoning techniques (canonical count after the v1.2 audit). Praxis adds 6 native vectors plus 8 inherited from Pragma. This is the suite’s most distinctive feature: treating reasoning under contestation as an adversarial problem where bad actors are actively trying to defeat the process.

Adaptive to institutional change. A shared Institutional Reliability Index tracks when formerly authoritative sources have been compromised by political interference or defunding, and provides alternative sources to consult. This matters in an era when some of the most effective disinformation correctly attributes false claims to institutions that were once trustworthy.

Calibrated by outcome. v1.3 ships a calibration feedback loop: consenting users report outcomes at intervals after their original submission (1 week, 1 month, 6 months, 1 year), the system computes Brier-lite scores per pathway and per recommendation, and drift flags surface for methodology-maintainer review. Auto-flag, NOT auto-adjust — methodology files are never modified by code.

The evidence

The combined v1.2 validation across the three methodologies tested 192 claims and scenarios:

  • Veridi v2.6: 96 of 97 claims pass (98.97%); 1 partial, 0 failed. 24 adversarial scenarios, 4 real-world disinformation patterns, 6 contested topics, 4 non-English languages tested.
  • Pragma v1.2: 54 of 55 claims pass (98.2%); 1 robust-regardless arithmetic-path note, 0 failed. Closes the 2026-03-22 cross-methodology audit backlog.
  • Praxis v1.2: 39 of 40 scenarios pass (97.5%); 1 documentation-level reconciliation, 0 failed. Resolves all six prior golden-scenario partials.
  • Combined: 189 of 192 (98.4%).

The full validation report documents the testing methodology, per-product results, and limitations. The changelog details every methodology revision.

The cooperative

The suite is built by a small Canadian cooperative-in-formation with a lean operating budget. The cooperative:

  • Has no venture capital, advertising model, or growth-at-all-costs pressure
  • Publishes the full methodology files for all three products for external inspection
  • Documents its limitations alongside its successes
  • Positions the suite as complementary to existing fact-checking organizations, policy research institutions, and movement-building infrastructure — not competitive

Pipeline integration

The three products form a complete evidence-to-action chain. A Veridi fact-check (“is this claim true?”) feeds into Pragma (“what does the evidence suggest about a related policy?”) which feeds into Praxis (“what can a specific person do about it?”). Pipeline integration — passing a Veridi assessment into Pragma and then into Praxis — was validated in v2.5 with 10 end-to-end scenarios (30/30 stage executions PASS) and remains current as of v1.2.

What’s next

The methodology is validated and ready for controlled deployment: real-world use by trained volunteers with ongoing quality monitoring. Next steps include:

  1. Usability testing with human volunteers to verify the methodology can be followed correctly by non-experts
  2. Brier score calibration to measure whether confidence ratings match real-world outcomes over time
  3. Scale testing in continuous production
  4. Red-teaming by external parties attempting to find claims the methodology handles incorrectly

Contact

veridi [at] nettercap.net

For technical questions about the methodology, see the researcher documentation. For the full methodology files, see open methodology.