Canst Thou Draw Out Leviathan with Computational Bibliography? New Angles on Printing Thomas Hobbes’ “Ornaments” Edition

Warren, Christopher N.; Wiscomb, Avery; Williams, Pierce; Lemley, Samuel V; G’Sell, Max

doi:10.1353/ecs.2021.0094

Cited by 1 publication

(7 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We evaluate our approach against other common methods for image comparison on a downstream damaged type-imprint matching dataset of English early modern (c. 1500-1800) books, a period when print censorship was prevalent. Our model's inferences are consistent with and support the findings of recent, manual bibliographical analyses of Areopagitica (Warren et al 2020) and Leviathan Ornaments (Warren et al 2021). In a deployment case study, a broader set of type from Leviathan Ornaments is matched against type from 138 candidate books and evaluated by an expert bibliographer.…”

Section: Introductionsupporting

confidence: 82%

“…Recent printer attribution work uses digital reproductions in addition to physical copies (Adams 2010;Como 2018). Warren et al (2020Warren et al ( , 2021 go one step further, employing Ocular (Berg-Kirkpatrick, Durrett, and Klein 2013b) historical OCR for automatic extraction of type-imprint images, which they later manually match to uncover the printers of important books printed in the early modern period.…”

Section: Early Modern Print and Damaged Type Piecesmentioning

confidence: 99%

“…We use two different hand-curated datasets from recent bibliographical studies that manually identified and matched damaged type-imprints for attribution of two major early modern printed works (Warren et al 2020(Warren et al , 2021.…”

Section: Ground Truth Evaluation Datasetsmentioning

confidence: 99%

“…Leviathan Ornaments test set We construct our test set from the expert-curated set of matches manually identified in a recent bibliographical study, in which Warren et al (2021) established that the book was printed in a single print shop by John Richardson in 1695-1696, thus refuting the attribution of Malcolm (2008) to a different printer, John Darby in earlier work by amassing evidence from damaged type-imprints matched manually within Leviathan Ornaments and across other books by known printers from the suspected time period of its printing. Overall, this dataset contains 217 total match groups with 858 pairwise queries.…”

Section: Ground Truth Evaluation Datasetsmentioning

confidence: 99%

“…These anomalous type pieces, when linked across printed works, can reveal which works came from the same printing apparatus, as depicted in Figure 2. Historians have, for example, leveraged the analysis of damaged type-imprints as a critical tool in identifying and studying clandestine printers who withheld their identities to avoid harsh penalties under censorship laws (Adams 2010;Como 2018;Warren et al 2020Warren et al , 2021.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Contrastive Attention Networks for Attribution of Early Modern Print

Vogler

Goyal

Reddy

et al. 2023

AAAI

View full text Add to dashboard Cite

In this paper, we develop machine learning techniques to identify unknown printers in early modern (c.~1500--1800) English printed books. Specifically, we focus on matching uniquely damaged character type-imprints in anonymously printed books to works with known printers in order to provide evidence of their origins. Until now, this work has been limited to manual investigations by analytical bibliographers. We present a Contrastive Attention-based Metric Learning approach to identify similar damage across character image pairs, which is sensitive to very subtle differences in glyph shapes, yet robust to various confounding sources of noise associated with digitized historical books. To overcome the scarce amount of supervised data, we design a random data synthesis procedure that aims to simulate bends, fractures, and inking variations induced by the early printing process. Our method successfully improves downstream damaged type-imprint matching among printed works from this period, as validated by in-domain human experts. The results of our approach on two important philosophical works from the Early Modern period demonstrate potential to extend the extant historical research about the origins and content of these books.

show abstract

Section: Introductionsupporting

confidence: 82%