Program Atlas dossier
HIATUS
Research on human-interpretable authorship attribution across languages and genres, paired with techniques that help authors understand or reduce identifying linguistic signals.
Saved records and display preferences remain only in this browser.
- Reading time
- 1 min
- Record type
- Program Atlas dossier
- Revised
- Content owner
- Program Atlas editorial team
- Next review
Program identity
#- Public program name
- Human Interpretable Attribution of Text Using Underlying Structure
- Accepted acronym
- HIATUS
- Responsible organization
- Intelligence Advanced Research Projects Activity
Public purpose
#Research on human-interpretable authorship attribution across languages and genres, paired with techniques that help authors understand or reduce identifying linguistic signals.
Established public facts
#- The program joins authorship attribution with author-privacy concerns.
- Interpretability is central: a score without understandable evidence is insufficient for responsible use.
- Language, genre, and translation can complicate attribution.
Technical approach
#- Authorship attribution
- Explainability
- False-positive review
- Author privacy
Evaluation and limits
#Evaluation concept
Public program descriptions emphasize measurable evaluation against defined research objectives; this portal does not reproduce restricted metrics or implementation details.
What remains uncertain
Attribution systems can produce false positives and should never be treated as identity proof on their own.
Ethics, privacy, and security
#Ethics
The educational treatment emphasizes proportionality, consent, error analysis, dual-use risk, and meaningful human review.
Privacy
The portal uses synthetic examples and does not collect biometric, location, communications, or identity data for these lessons.
Security
No current capabilities, targets, facilities, credentials, or operational procedures are published.
Important vocabulary
#- Authorship attribution
- Stylometry
- Explainability
- False positive
- Privacy
Why this program matters
#Research on human-interpretable authorship attribution across languages and genres, paired with techniques that help authors understand or reduce identifying linguistic signals.
End factual context · Begin fictional application
Authorship Evidence Lab
#Players compare synthetic writing samples, document which linguistic features support a hypothesis, and practice refusing overconfident identity claims.
Simulation mechanics
- Authorship attribution
- Explainability
- False-positive review
- Author privacy
This section does not describe a real organization’s actions, current capability, target, facility, or operation.
