Humanly: A Configurable and Traceable Environment for Human-AI Collaborative Writing

2026-07-23

AI Summary

This work addresses the limitations of current writing assessments, which rely solely on final texts and struggle to distinguish between human-, AI-, or human-AI–generated content. To overcome this, the authors propose a configurable and auditable writing platform that treats the writing process itself as verifiable evidence. By integrating fine-grained action tracking, in-platform AI interaction logs, and configuration-aware anomaly detection, the system generates tamper-resistant writing certificates embedding contextual metadata and behavioral analytics. The platform enables transparent, trustworthy authentication across multi-role writing scenarios. User studies demonstrate its practical utility for diverse user groups, while red-teaming evaluations confirm that its keystroke dynamics detector effectively differentiates manual from automated input.

Abstract

Teachers, conference chairs, and public readers all judge writing from limited evidence, seeing only a finished document and not the process that produced it. Final text alone cannot reveal whether a document was produced through human typing, AI generation, or mixed human-AI collaboration. Existing process-tracking tools help, but many are tied to host-document histories, provide coarse activity records, and offer limited control over the writing environment. Humanly is a writing platform that makes the writing process itself the evidence. Users configure writing environments for personal documents or assigned tasks and draft in a workspace that records writing activity and in-platform AI assistance. Humanly can package a completed session into a sealed writing certificate with configuration-aware anomaly behavior review. It can support writing scenarios such as course assignments, peer review, and personal certification. Our user study shows that Humanly is helpful across roles, and a red-teaming study shows that the Humanly Typing Detector distinguishes human hand typing from automated typing.

Problem

• human-AI collaboration
• writing process tracing
• authorship verification
• AI-assisted writing
• process transparency

Innovation

• Human-AI collaboration
• writing process tracing
• configurable writing environment
• typing detection
• writing certificate