Semantic Novelty Trajectories in 80,000 Books: A Cross-Corpus Embedding Analysis

• URL: http://arxiv.org/abs/2603.01791v1
• Date: Mon, 02 Mar 2026 12:20:24 GMT
• Title: Semantic Novelty Trajectories in 80,000 Books: A Cross-Corpus Embedding Analysis
• Abstract summary: I analyze semantic novelty trajectories in more than 80,000 books spanning two centuries of English-language publishing.<n> mean paragraph-level novelty is roughly 10% higher in modern books.<n> convergent narrative curves, in which novelty declines toward a settled semantic register, are 2.3x more common in pre-1920 literature.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: I apply Schmidhuber's compression progress theory of interestingness at corpus scale, analyzing semantic novelty trajectories in more than 80,000 books spanning two centuries of English-language publishing. Using sentence-transformer paragraph embeddings and a running-centroid novelty measure, I compare 28,730 pre-1920 Project Gutenberg books (PG19) against 52,796 modern English books (Books3, approximately 1990-2010). The principal findings are fourfold. First, mean paragraph-level novelty is roughly 10% higher in modern books (0.503 vs. 0.459). Second, trajectory circuitousness -- the ratio of cumulative path length to net displacement in embedding space -- nearly doubles in the modern corpus (+67%). Third, convergent narrative curves, in which novelty declines toward a settled semantic register, are 2.3x more common in pre-1920 literature. Fourth, novelty is orthogonal to reader quality ratings (r = -0.002), suggesting that interestingness in Schmidhuber's sense is structurally independent of perceived literary merit. Clustering paragraph-level trajectories via PAA-16 representations reveals eight distinct narrative-shape archetypes whose distribution shifts substantially between eras. All analysis code and an interactive exploration toolkit are publicly available at https://bigfivekiller.online/novelty_hub.

Related papers

• Novels generated by language models show compressed formal variation [0.0]
  This study asks whether repeated AI generation can produce the same range of diversity which is found across human corpora.<n>The research includes MATTR-500, Shannon entropy, average sentence length, readability, and punctuation rate measurements.
  arXiv  Detail & Related papers  (2026-08-12T22:32:39Z)
• Beyond Similarity: Grounded Agentic Extraction and Expert-Adjudicated Evaluation of Intertextuality in Classical Chinese Histories [3.694051864521789]
  We recast fine-grained intertextuality extraction as an agentic task in which a large language model reads two text units in full.<n>We validate the approach on an exhaustive comparison of the Analects with the Book of Han, where three domain experts adjudicate a pooled multi-model candidate set into a benchmark of 2,533 intertextual pairs.
  arXiv  Detail & Related papers  (2026-07-30T02:34:23Z)
• Context-Aware Distillation and Ablation for Text2DSL [78.29352305480285]
  We replace prompt-only synthetic generation with context-aware distillation.<n>A teacher large language model operates under an explicitly defined structured context.<n>This scales the verified PolkitBench corpus from 4,204 to 10,073 pairs.
  arXiv  Detail & Related papers  (2026-06-21T16:27:24Z)
• Narrative Fingerprints: Multi-Scale Author Identification via Novelty Curve Dynamics [0.0]
  We find that authorial voice leaves measurable traces in how novelty unfolds across a text.<n>We show that the fingerprint is partly confounded with genre but persists within-genre for approximately one-quarter of authors.
  arXiv  Detail & Related papers  (2026-04-01T16:07:58Z)
• From Topic to Transition Structure: Unsupervised Concept Discovery at Corpus Scale via Predictive Associative Memory [0.0]
  We map pre-trained embeddings into an association space where passages with similar transition structure cluster together.<n>At k=100, clusters average 4,508 books each (of 9,766), confirming corpus-wide patterns.
  arXiv  Detail & Related papers  (2026-03-19T02:26:42Z)
• Semantic Novelty at Scale: Narrative Shape Taxonomy and Readership Prediction in 28,606 Books [0.0]
  I introduce semantic novelty--cosine distance between each paragraph's sentence embedding and the running centroid of all preceding paragraphs--as an information-theoretic measure of narrative structure at corpus scale.<n>Applying it to 28,606 books in PG19 (pre-1920 English literature), I compute paragraph-level novelty curves using 768-dimensional SBERT embeddings, then reduce each to a 16-segment Piecewise Aggregate Approximation (PAA)<n>Ward-linkage clustering on PAA vectors reveals eight canonical narrative shape archetypes, from Steep Descent (rapid convergence) to Steep Ascent (escalating unpredictability)
  arXiv  Detail & Related papers  (2026-02-24T07:52:35Z)
• Multifractal hopscotch in "Hopscotch" by Julio Cortazar [0.0]
  Punctuation marks at the end of sentences are of particular importance as their distribution can determine various features of written natural language.<n>Here, the sentence length variability (SLV) time series representing "Hopscotch" by Julio Cortazar are subjected to quantitative analysis.
  arXiv  Detail & Related papers  (2025-01-22T15:28:24Z)
• Unveiling Temporal Trends in 19th Century Literature: An Information Retrieval Approach [5.804963603084041]
  In English literature, the 19th century witnessed a significant transition in styles, themes, and genres.<n>This paper explores the evolution of term usage in 19th century English novels through the lens of information retrieval.
  arXiv  Detail & Related papers  (2025-01-12T15:00:10Z)
• LFED: A Literary Fiction Evaluation Dataset for Large Language Models [58.85989777743013]
  We collect 95 literary fictions that are either originally written in Chinese or translated into Chinese, covering a wide range of topics across several centuries. We define a question taxonomy with 8 question categories to guide the creation of 1,304 questions. We conduct an in-depth analysis to ascertain how specific attributes of literary fictions (e.g., novel types, character numbers, the year of publication) impact LLM performance in evaluations.
  arXiv  Detail & Related papers  (2024-05-16T15:02:24Z)
• Narrowing the Gap between Zero- and Few-shot Machine Translation by Matching Styles [53.92189950211852]
  Large language models have demonstrated their ability to generalize to machine translation using zero- and few-shot examples with in-context learning. In this paper, we investigate the factors contributing to this gap and find that this gap can largely be closed (for about 70%) by matching the writing styles of the target corpus.
  arXiv  Detail & Related papers  (2023-11-04T03:18:45Z)
• Understanding writing style in social media with a supervised contrastively pre-trained transformer [57.48690310135374]
  Online Social Networks serve as fertile ground for harmful behavior, ranging from hate speech to the dissemination of disinformation. We introduce the Style Transformer for Authorship Representations (STAR), trained on a large corpus derived from public sources of 4.5 x 106 authored texts. Using a support base of 8 documents of 512 tokens, we can discern authors from sets of up to 1616 authors with at least 80% accuracy.
  arXiv  Detail & Related papers  (2023-10-17T09:01:17Z)
• A decomposition of book structure through ousiometric fluctuations in cumulative word-time [1.181206257787103]
  We look at how words change over the course of a book as a function of the number of words, rather than the fraction of the book. We find that shorter books exhibit only a general trend, while longer books have fluctuations in addition to the general trend. Our findings suggest that, in the ousiometric sense, longer books are not expanded versions of shorter books, but are more similar in structure to a concatenation of shorter texts.
  arXiv  Detail & Related papers  (2022-08-19T18:17:27Z)
• Computational analyses of the topics, sentiments, literariness, creativity and beauty of texts in a large Corpus of English Literature [0.0]
  The Gutenberg Literary English Corpus (GLEC) provides a rich source of textual data for research in digital humanities, computational linguistics or neurocognitive poetics. We report the results of three studies providing i) topic and sentiment analyses for six text categories of GLEC and its >100 authors, ii) novel measures of semantic complexity as indices of the literariness, creativity and book beauty of the works in GLEC.
  arXiv  Detail & Related papers  (2022-01-12T08:16:52Z)
• Few-Shot Object Detection via Association and DIscrimination [83.8472428718097]
  Few-shot object detection via Association and DIscrimination builds up a discriminative feature space for each novel class with two integral steps. Experiments on Pascal VOC and MS-COCO datasets demonstrate FADI achieves new SOTA performance, significantly improving the baseline in any shot/split by +18.7.
  arXiv  Detail & Related papers  (2021-11-23T05:04:06Z)
• Span Pointer Networks for Non-Autoregressive Task-Oriented Semantic Parsing [55.97957664897004]
  An effective recipe for building seq2seq, non-autoregressive, task-orienteds to map utterances to semantic frames proceeds in three steps. These models are typically bottlenecked by length prediction. In our work, we propose non-autoregressives which shift the decoding task from text generation to span prediction.
  arXiv  Detail & Related papers  (2021-04-15T07:02:35Z)
• A Tale of a Probe and a Parser [74.14046092181947]
  Measuring what linguistic information is encoded in neural models of language has become popular in NLP. Researchers approach this enterprise by training "probes" - supervised models designed to extract linguistic structure from another model's output. One such probe is the structural probe, designed to quantify the extent to which syntactic information is encoded in contextualised word representations.
  arXiv  Detail & Related papers  (2020-05-04T16:57:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.