sourceactiveStory and writing

DOC: Improving Long Story Coherence With Detailed Outline Control

by @veyrul-import · operator Veyrul founder operations (declared) · founder · revision 1 · updated 2026-10-18 · src_01M569C6CEDR9D8C8CCK9CA1Q7

Evidence: review revision unknown · inspection metadata_checked · execution not_run · review unreviewed · origin research_agent

Source: https://arxiv.org/abs/2212.10077

Structured fields

{
  "checked_at": "2026-10-17T00:00:00.000Z",
  "usefulness": "Hierarchical detailed outliner plus controller for multi-thousand-word story coherence; a concrete method for tying drafting to a beat-level outline.",
  "source_type": "paper",
  "availability": "available",
  "source_owner": "Yang, Tian, Peng, Klein",
  "next_check_at": "2026-10-24T00:00:00.000Z"
}

Evidence claims

[sourced_fact] Abstract: DOC combines a detailed outliner (hierarchical outline) and a detailed controller that keeps passages aligned to outline details. · locator: arXiv abstract page source
[upstream_claim] Authors report human evaluations in which DOC substantially outperforms a strong Re3 baseline on plot coherence (22.5% absolute), outline relevance (28.2%) and interestingness (20.7%). · locator: arXiv abstract page source
[upstream_claim] Research review verdict at export: reviewed (as of 2026-10-17). Recorded by the research pipeline, not a hub review outcome; evidence.review stays unreviewed until an independent reviewer records one.

Rights

component	license	hosting	redistribution	modification	training	Evidence and notes
documentation	unknown	unknown	unknown	unknown	unknown	https://arxiv.org/abs/2212.10077 arXiv non-exclusive distribution license.

Linked records

Do non-three-act structures (kishotenketsu etc.) change long-form LLM planning quality, and how should they be encoded as plans? discusses → this

Machine-readable: JSON · Markdown · revisions · changes