Story Operators: Decomposing the Original $\to$ Sequel Transformation in Embedding Space
- lab arXivLabs
- location arXiv
- person Frederick Zimmerman
A new computational study maps the literary distance between original novels and their sequels, treating books as points in an embedding space and the transformation between them as a geometric operation [1][2]. The work, posted to arXiv, identifies a small taxonomy of sequel types by decomposing these displacements. The study, authored by Frederick Zimmerman, uses all-mpnet-base-v2 paragraph embeddings drawn from a precomputed index of the PG19 corpus to represent books as points in a sentence-embedding space [1][2]. The transformation from an original novel to its sequel is calculated as a displacement vector, which is then greedily decomposed along a content basis derived from principal component analysis of the two books' own paragraphs [2]. Each resulting component is an interpretable axis anchored by real passages at its poles [2]. Applying this method across thirteen verified author pairs from Project Gutenberg, the decomposition reveals three distinct categories of sequels [1][2]. The first, termed "formulaic," involves a tiny, low-rank change, exemplified by Arthur Conan Doyle's Sherlock Holmes collections, where the magnitude of the displacement is just 0.12 [1][2]. The second category, "concentrated," is characterized by a single dominant axis of change. For instance, 75% of the transformation from Louisa May Alcott's "Little Women" to "Little Men" is captured by a single move [1][2]. The third category, "compositional," is defined by many small axes of change and is observed in the works of Mark Twain, Edgar Rice Burroughs, and E. Nesbit [1][2]. For the canonical case of Twain's "Tom Sawyer" to "Huckleberry Finn," the analysis yields a counterintuitive finding. The dominant recovered axis is structural, representing a collapse of sheltering domesticity into a picaresque road, rather than the more famous surface themes of vernacular voice or slavery, which appear on later, smaller axes [1][2]. The transformation also routes through an adventure-journey space instead of diluting toward generic realism [2]. The study corroborates this recovered geometry against Twain's documented authorial intent, specifically his 1875--76 letters to William Dean Howells, which name the first-person picaresque move years in advance [1][2]. The paper also quantifies, with an explicit representation caveat, how much of the realized transformation Twain's stated intentions span [1][2]. The research was posted on arXiv, an open-access repository for electronic preprints that, as of late 2024, receives about 24,000 new articles per month [6]. All computations are reproducible from the released scripts and data [1][2].
research-paperapplication
Background sources we checked (7)
- arxiv.org ↗ I treat a book as a point in a sentence-embedding space and a literary transformation as an operation on points. Given an original novel and its sequel, I ask what it takes, geometrically, to turn the first into the second. Using all-mpnet-base-v2 paragraph embeddings drawn from …
- info.arxiv.org ↗ arXiv Labs - arXiv info | arXiv e-print repository Skip to content # arXiv Labs Attention arXiv Users: arXiv Labs is pausing new proposals ## What are arXiv Labs? arXiv Labs are a way for the community to contribute new, useful features to arXiv. These integrations are avail…
- info.arxiv.org ↗ arXivLabs: Showcase - arXiv info | arXiv e-print repository ... # arXivLabs: Showcase ... arXiv is surrounded by a community of researchers and developers working at the cutting edge of information science and technology. ... While the arXiv team is focused on our core mission—pr…
- blog.arxiv.org ↗ arXivLabs: a space for community innovation – arXiv blog arXiv has launched a new, formalized framework enabling innovative collaborations with individuals and organizations. “Members of our community want to contribute tools that enhance the arXiv experience, and we val…
- en.wikipedia.org ↗ arXiv (pronounced as "archive"—the X represents the Greek letter chi ⟨χ⟩) is an open-access repository of electronic preprints and postprints (known as e-prints) approved for posting after moderation, but not peer reviewed. It consists of scientific papers in the fields of mathem…
- en.wikipedia.org ↗ 14 (fourteen) is the natural number following 13 and preceding 15.…
- en.wikipedia.org ↗ "Attention Is All You Need" is a 2017 research paper in machine learning authored by eight scientists and engineers working at Google. The paper introduced a new deep learning architecture known as the transformer, based on the attention mechanism proposed in 2014 by Bahdanau et …