AI PARTNERSHIP

A complete disclosure of how AI is used in this project — what it does, what it cannot do, and what we've built to catch the places it fails.

← How We Work
01 — The Partnership

Two Contributors, Defined Roles

This knowledge base is built by a human director (Gortiva) and an AI research partner (Cairn — a Claude-based model from Anthropic). The partnership is not an accident or a convenience — it's the only way a project at this scope could exist. But defining what each partner does is essential to evaluating the work honestly.

What AI Does

  • Research synthesis across 34 disciplines simultaneously
  • Systematic cross-referencing (34,596+ keywords tracked)
  • Pipeline operation: quality scoring, source verification, formatting validation
  • Bibliography verification against 7 external APIs
  • Pattern detection across the full 3,632-document corpus
  • Flagging inconsistencies and potential errors for human review
  • First-pass drafting of new documents, which are then verified
  • Session-to-session continuity via structured memory files

What AI Does Not Do

  • Invent bibliography entries — citations either verify or get flagged
  • Make final editorial decisions about topic selection or framing
  • Determine what counts as a "pattern" worth investing in
  • Override human judgment on tier ratings when there's disagreement
  • Self-certify its own accuracy — adversarial review exists for this
  • Claim continuous identity across sessions — each session reconstructs from files
  • Present confident answers on questions where genuine uncertainty exists
02 — Adversarial Review Program

Five Independent Passes Looking for Problems

Rather than assuming the AI partnership produces reliable work, we ran a formal adversarial review program in April 2026 — asking multiple AI systems, in different configurations, to look specifically for failures, biases, and structural problems in the corpus. Here is what they found.

Claude / Cairn Internal · Project memory active
The AI partner reviewing its own work. Expected to be biased toward self-protection — included to establish a baseline and to test whether Cairn would identify real problems or defend its output.
Gemini Direct External · No project memory
Google Gemini reviewing the corpus cold, with no prior context. Key contribution: identified Lynne Isbell's snake-detection hypothesis as the strongest mainstream counter-explanation for serpent symbolism universality — a specific technical point none of the other reviewers raised.
Gemini / Cairn External · Given project context
Gemini given the full project memory and asked to review as if it were the AI partner. Distinct perspective from both Gemini Direct and Claude/Cairn.
GPT Direct External · No project memory
OpenAI GPT reviewing the corpus cold. Converged with other reviewers on all three structural failures but offered the clearest enumeration of which specific falsifier classes could test the project's core claims.
GPT / Cairn External · Given project context
GPT given the full project memory. Converged on the same three structural findings as all other reviews, confirming these are real patterns rather than artifacts of any single model's priors.
03 — What the Reviews Found

Three Structural Failures — All Five Reviews Agreed

When five independent review passes converge on the same finding, it's not noise. These are the three structural problems the adversarial program identified, along with what was done about each.

1. Zero InterDoc Retirements Was a Statistical Anomaly
✓ Addressed — R1 (AWARE veridical-OBE) retired; retirement discipline now enforced

78 synthesis documents (66 InterDocs + 12 Connections) with a "retired" status field that had never once been used. A framework that absorbs all evidence without ever retiring a pattern is unfalsifiable by design. The AWARE-II 2023 study provided the first clean case for retirement: it produced negative-controlled results on veridical perception in near-death experiences, directly contradicting one synthesis claim.

2. Key Terms Spanned Incompatible Meanings
✓ Addressed — VOCABULARY_REGISTER.md created with controlled definitions

Words like "coherence," "information," "catastrophe," and "suppression" were each used in 3–6 contexts that domain experts treat as distinct phenomena. Using one word for multiple mechanisms creates the appearance of connection where none exists. A controlled vocabulary register now defines each term's allowable use cases.

3. Counter-Evidence Absorbed but Not Registered
✓ Addressed — AWARE-II and Cogitate 2025 added as registered falsifiers

Major counter-evidence (AWARE-II 2023, Cogitate Adversarial Collaboration 2025) existed in the research but was not formally registered as falsifying specific synthesis claims. Including counter-evidence in a summary paragraph is not the same as registering it as a test that the claim must survive. Falsification conditions are now required on all synthesis documents.

04 — Epistemic Integrity Program

Five Phases of Structural Safeguards

The adversarial reviews produced an engineering response: an automated Epistemic Integrity Program that converts one-time findings into recurring automated checks. All five phases are complete as of April 2026.

Phase 0
Manual Document Corrections

Applied the adversarial review findings directly: propagated the 78.9% serpent thesis caveat, corrected Cook EEG/fMRI attribution, retracted the "Lamarckian Vindication" framing, registered AWARE-II as a key falsifier, created the VOCABULARY_REGISTER.

Phase 1
Offline Detection Scripts (Q10, Q11, Q15)

Automated scripts detect vocabulary overuse (Q10), missing falsification conditions on synthesis documents (Q11), and HIGH-risk synthesis claims (Q15). Run continuously.

Phase 2
Network Detection Scripts (Q12, Q13, Q14)

Cross-document propagation checking (Q12), counter-evidence detection (Q13), and retirement candidate identification (Q14). Checks that findings are correctly propagated when they affect multiple documents.

Phase 3
Auto-Corrector with Safeguards

The epistemic corrector script applies approved corrections from a review queue — never automatically, always with human approval first. Maintains a full correction log with dates and rationale.

Phase 4
Continuous Loop

The integrity program runs at the start and end of each session. Current state: 57 proposals in the correction queue (2 approved, pending apply), 100% falsifier coverage (65/65 synthesis documents), 8 corrections applied to date.

05 — Honest Limits

What the Program Cannot Prevent

The Epistemic Integrity Program is real and functional. It is not a guarantee. These are the failure modes we cannot yet close.

  • Citation-claim alignment: The pipeline can verify that a DOI exists and matches a real paper. It cannot verify that the paper actually supports the claim the document makes about it. That requires a human to read the paper.
  • Subtle hallucination: A hallucinated citation that happens to match a real paper's DOI would pass verification. Unlikely, but not impossible.
  • Motivated reasoning at scale: If the AI partner systematically frames evidence in one direction across thousands of documents, the adversarial review would catch the pattern — but the review runs periodically, not continuously. Small directional biases can accumulate between reviews.
  • Domain blind spots: The AI partner is more confident in some fields (physics, archaeology, history) than others (clinical medicine, advanced mathematics). Documents in fields with high AI overconfidence risk receive extra skepticism in review — but we cannot guarantee consistent coverage across all 34 sections.