Metraipolis › archive › dc_d0fd5bf99ab9

D2C-Routing: Dimension-to-Composition Evidence Routing for Mixed-Origin AI-Generated Text Detection — arXiv:2608.27380

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.27380
License (as archived)
CC0-1.0
Archived
2026-10-17T15:20:38.968Z
SHA-256 of the archived text
84f4bee7e81937d76dcbcc705adc75b4a113b115aa9e29a5fff344fbdecf8a5b
Stable URL of this page
https://metraipolis.com/documento/dc_d0fd5bf99ab9

How to cite

D2C-Routing: Dimension-to-Composition Evidence Routing for Mixed-Origin AI-Generated Text Detection — arXiv:2608.27380 — arXiv (en), https://arxiv.org/abs/2608.27380 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d0fd5bf99ab9 (Metraipolis archive dc_d0fd5bf99ab9, sha256 84f4bee7e81937d76dcbcc705adc75b4a113b115aa9e29a5fff344fbdecf8a5b)
BibTeX
@misc{dcd0fd5bf99ab9,
  title = {D2C-Routing: Dimension-to-Composition Evidence Routing for Mixed-Origin AI-Generated Text Detection — arXiv:2608.27380},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.27380},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d0fd5bf99ab9; sha256 84f4bee7e81937d76dcbcc705adc75b4a113b115aa9e29a5fff344fbdecf8a5b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.27380. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

AI-generated text detection is commonly framed as a binary document-level judgment about whether a text is human-written or machine-generated. This framing breaks down for mixed-origin writing, where content origin and expression origin may differ. We cast mixed-origin detection as dimension-to-composition source attribution, inferring content origin and expression origin before composing them into four collaboration types. We propose Dimension-to-Composition Routing (D2C-Routing), which routes content-side and expression-side evidence to supervised dimension heads before a learned gated composition layer predicts the final label. On MixD2C, a reconstructed split derived from the HART mixed-origin benchmark, our disclosed D2C-Routing-based detector system reaches 0.8603 four-way Avg TPR@1%FPR, 6.5 points above the same-split RACE-local rerun. Core ablations support the routing design, while error analysis shows that distinguishing AI-content/human-expression from fully AI-generated text remains the hardest boundary. Code is available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-28 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2608.27380 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T15:15:18.098Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).