CogniPrint Research Initiative

Independent AI safety research · Open source · Reproducible by design

From statistical text traces to portable evidence for AI workflows.

CogniPrint began with interpretable statistical measurement of text transformations. That mathematical core became working software, controlled benchmarks, and a broader research programme for portable, privacy-aware evidence in multi-principal AI systems.

Roman Adriashkin — Independent Researcher-Engineer & Founder, CogniPrint Research Initiative

The project started with measurement, not detection.

The research question is which measurable traces survive editing, translation, paraphrasing, summarization, model-to-model rewriting, and mixed human/AI production chains—and where the correct conclusion is that evidence is insufficient.

01

Hypothesis. Statistical regularities in text can be represented reproducibly.

02

Theory. Define an interpretable feature map φ(T) and separate measurement from inference.

03

Program. Implement deterministic extraction, distances, perturbation analysis, entropy, and n-grams.

04

Benchmark. Freeze a leakage-safe pilot and compare against transparent baselines.

05

Next layer. Extend the evidence discipline to multi-principal agent workflows.

Mathematical core

φ(T) = [f₁(T), f₂(T), …, f₁₂(T)] ∈ ℝ¹²

The current v2 profile uses twelve interpretable coordinates: mean word length, type-token ratio, character entropy, word entropy, punctuation ratio, uppercase ratio, mean syllables per word, character-bigram uniqueness, Simpson diversity, digit-token ratio, mean sentence length, and reading ease.

Entropy

H(X) = −Σ p(x) log₂ p(x)

Cosine similarity

cos(a,b) = (a·b)/(‖a‖‖b‖)

Euclidean distance

d₂(a,b) = √Σ(aᵢ−bᵢ)²

Perturbation

Δφ = φ(T′) − φ(T)

Inspect the exact feature-map implementation →

Theory became executable evidence.

The public implementation includes deterministic feature extraction, documented normalization, cosine and Euclidean geometry, controlled perturbation tests, corpus aggregation, entropy and word/character n-gram analysis, reproducibility scripts, tests, and versioned evidence artifacts.

Fixed Stage A: the baseline won.

The fixed descriptive pilot uses a 351/149 grouped train/test split across five classes with zero train/test lineage overlap. Simple hashed TF-IDF baselines outperform the current 12D nearest-centroid profile.

Macro-F1
Word 1–2 TF-IDF0.5952
Character 3–5 TF-IDF0.5788
CogniPrint 12D0.5359
Length-only0.2474
MethodAccuracyMacro-F1
Word 1–2 hashed TF-IDF0.59730.5952
Character 3–5 hashed TF-IDF0.58390.5788
CogniPrint 12D0.53690.5359
Length-only0.29530.2474

Interpretation: the compact 12D profile is not currently a stronger classifier than simple surface baselines on this controlled task. The negative result is retained because it constrains the theory and defines what future attribution research must beat.

Portable Evidence Capsules for Multi-Principal Agent Workflows

The current multi-agent research extends the same methodology from content measurement toward provenance and failure tracing under incomplete or conflicting records.

Statistical text measurementTransformation evidencePortable Evidence CapsulesMulti-principal provenanceFailure tracingPrivacy-preserving verification

Multi-principal provenance

Represent event, delegation, version, authorization, and lineage evidence across independently controlled systems.

Failure tracing

Test whether evidence can localize broken action paths without assigning responsibility to the wrong principal.

Privacy-preserving verification

Evaluate what can be checked from hashes, bounded metadata, and structured records when raw payloads cannot be shared.

Fail-closed uncertainty

Preserve UNKNOWN and abstention states when records are incomplete, conflicting, replayed, or insufficient.

Research status: active direction. Future empirical milestones are not presented as completed results.

Scientific boundary

Current scientific readiness remains descriptive_only. Limitations follow the evidence rather than replacing it.

Supported today
  • Descriptive statistical profiles
  • Controlled transformations and comparisons
  • Entropy and n-gram diagnostics
  • Versioned evidence artifacts
  • Explicit uncertainty states
Not established
  • Author identity or intent
  • Unique or exact source model from text similarity
  • Definitive AI origin
  • Generation-lineage reconstruction
  • Legal responsibility or forensic provenance

Optional third-party model API integration. Provider names describe technical integrations only and do not imply employment, sponsorship, partnership, or organizational affiliation.

Reviewer entry points

Public source and research repository · Research vision · Failure charter · Researcher profile · ORCID