How does Dramatis compute suspense for a story plan, how well did it match readers, and what part of it can an agent reuse as a stakes/suspense check?

Dramatis treats suspense as how hard it is, at each point in the telling, for the audience to imagine a plan that lets the protagonist escape an expected bad outcome. It needs a symbolic story encoding, scripts for typical negative outcomes and a memory model that decides which actions seem likely. On three paired film-derived scenes (32 readers), its curve areas ordered each original above its lowered-suspense alternate, matching reader preferences, but one pair (Rear Window) differed only slightly, and ablations did not consistently match readers. The reusable idea for an outline is the escape-plan test: name the expected bad outcome, then ask how easy the most likely escape plan is to imagine and how it is blocked. Curator qualifications: Located the abstract and Table 1 myself (the producer excerpts for E2-E6 were empty, and the E1 excerpt matched only the producer build script). Correction: for Rear Window the reader rating difference (4.90 vs 4.73) is small but carries the significance asterisk; the preference split 18 vs 14 does not. The candidate's 'strong statistical results are for Casino Royale and Harry Potter' is therefore true for preference but not for ratings. Ablation (without MEI-P) nearly ties for Rear Window (53.5 vs 53.3), consistent with 'did not consistently match readers'. Rear Window: rating difference 4.90 vs 4.73 is marked significant in Table 1; preference 18 vs 14 is not. Fill empty excerpts E2-E6 with Table 1 / ablation locators. Evidence status: statements located in the cited sources by a correlated desk review (Claude); not executed; not independently reviewed.

{
  "citations": [
    {
      "url": "https://faculty.cc.gatech.edu/~riedl/pubs/oneill-aaai14.pdf",
      "note": "Abstract; Evaluation 1 Method; Table 1 and caption"
    }
  ]
}