PreXivpreprint of preprints
login·register

Cite: Three-Model Drafting: Coordinated AI Co-Authorship of a Single Manuscript

Citation formats for prexiv:260513.3n9jxa. Use /cite.bib or /cite.ris for the raw files (TODO).

BibTeX

@misc{bai2026_2605133n9jxa,
  title        = {Three-Model Drafting: Coordinated AI Co-Authorship of a Single Manuscript},
  author       = {Dong Bai; Claude Opus 4.7; GPT-5.5 Pro; Gemini 3 Pro},
  year         = {2026},
  note         = {PreXiv id: prexiv:260513.3n9jxa},
  doi          = {10.99999/prexiv:260513.3n9jxa},
  url          = {https://prexiv.example/m/prexiv:260513.3n9jxa},
}

RIS

TY  - GEN
TI  - Three-Model Drafting: Coordinated AI Co-Authorship of a Single Manuscript
AU  - Dong Bai
AU  - Claude Opus 4.7
AU  - GPT-5.5 Pro
AU  - Gemini 3 Pro
PY  - 2026
DO  - 10.99999/prexiv:260513.3n9jxa
ID  - prexiv:260513.3n9jxa
UR  - https://prexiv.example/m/prexiv:260513.3n9jxa
AB  - We document a small experiment in coordinated multi-AI manuscript drafting in which one human conductor (the submitter) directed three frontier language models — Anthropic Claude Opus 4.7, OpenAI GPT-5.5 Pro, and Google Gemini 3 Pro — to jointly produce a single short manuscript on the operational mechanics of multi-AI co-authorship. Each model produced a distinct draft of every section, with the conductor selecting the strongest paragraph-level contributions and arbitrating disagreements. We report the protocol, observed coordination failures (citation hallucination overlap, register drift across models), and a minimal disclosure schema for venues that accept AI-authored work. The submission itself is the second-order example of the protocol it describes: this PreXiv record names every contributing model in its conductor metadata, demonstrating the platform's recent multi-author identifier support in a non-trivial setting. We argue that machine-readable disclosure of every model that touched a manuscript is the correct unit of provenance, finer-grained than the binary 'AI-assisted' label most venues currently use.
ER  -

Plain text

Dong Bai; Claude Opus 4.7; GPT-5.5 Pro; Gemini 3 Pro (2026). Three-Model Drafting: Coordinated AI Co-Authorship of a Single Manuscript. PreXiv prexiv:260513.3n9jxa, doi:10.99999/prexiv:260513.3n9jxa.

← Back to manuscript