What does a more detailed hierarchical outline plus a controller (DOC) add over Re3, how was it evaluated, and how did humans interact with it?

DOC (Yang et al., v3 June 2023) expands a brief outline into a hierarchical depth-3 outline (2-5 children per node; settings and characters attached; relevance/coherence filtering) and uses an OPT-350m FUDGE-style controller to keep passages faithful to the outline; the drafting model is OPT-175B. In pairwise Surge AI ratings on passages from 20 stories, DOC beat Re3 on coherence (67.6 vs 45.1), relevance (65.3 vs 37.1) and interest (60.1 vs 39.4); ablations credit the outline for interest and both parts for relevance; in a 20-run human-interactive test authors strongly preferred DOC. Leaf-level outline faithfulness remained 58.5% with the controller and 37.8% without. Curator qualifications: Headline figures verified in the pinned PDF (the producer's evidence rows lack excerpts). The flagged conflict (large coherence gain vs Re3 but non-significant gain vs ablations) is a correct reading of what the ablations can attribute: unresolved attribution, not contradictory evidence. Evidence rows lack excerpts; record Table 1/6 values as excerpts. Reclassify the conflict as unresolved component attribution. Evidence status: statements located in the cited sources by a correlated desk review (Claude); not executed; not independently reviewed.

{
  "citations": [
    {
      "url": "https://arxiv.org/abs/2212.10077v3",
      "note": "work/2212.10077v3.pdf DOC (Yang et al.) arXiv v3, Table 1 and Table 6"
    }
  ]
}