Research

Open methods. Defensible math.

Published methodology, the 111-case fair-use dataset, TQ foundations, the evidentiary hierarchy framework, and 70+ cited methods.

01 · Dataset

The 111-case fair-use dataset.

Curated, validated, and reproducible. 53 fair-use rulings and 58 non-fair-use rulings, with four-factor coding and post-Warhol re-classification. Downloadable as JSONL with attribution.

Known gap: limited 8th Circuit coverage. Disclosed.
02 · TQ foundations

Transformation Quotient — full derivation.

11-dimensional feature space: 7 statistical + 4 neural. BCa bias-corrected bootstrap CIs. Adversarial perturbation budget. Reproducible from seed and parameter hashes.

03 · Evidentiary hierarchy

Tier mapping & Daubert decomposition.

SaTML 2025 tier mapping. Daubert factor decomposition. Jurisdiction-threshold table for US (circuit-by- circuit), EU, UK, DE, JP, KR.

04 · Methods cited

70+ academic papers.

  • Min-K%++
    Zhang et al., ICLR 2025
  • DE-COP
    Duarte et al., arXiv 2402.09910
  • Cooper PDE
    Cooper et al., 2024
  • nv-recall
    Stanford Algorithm 1
  • TRAK
    Park et al., ICML 2023
  • CSD style
    Somepalli et al., NeurIPS 2023
  • SSCD
    Pizzi et al., CVPR 2022
  • DINOv2
    Oquab et al., 2023
  • D-TRAK
    Zheng et al., 2024
  • Collective Dataset Inference
    CVPR 2025
  • MUSE
    Shi et al., 2024
  • MelodySim
    Internal — based on Smith et al.
Open the full methods library
05 · Sample evidence packages

Three redacted PDFs.

Text matter

Redacted sample. Daubert-tier output.

Request sample
Image matter

Redacted sample. Daubert-tier output.

Request sample
Audio matter

Redacted sample. Daubert-tier output.

Request sample
06 · Academic partnerships

Open call for research collaborations.

If you're working on attribution, MIA, fair-use NLP, or diffusion forensics — talk to us.

Propose a collaboration
Research

Open methods. Defensible math.

Every detector is published. Every score is reproducible from the chain-of-custody hash.