In this paper, we shed new light on the authenticity of the Corpus Caesarianum, a group of five commentaries describing the campaigns of Julius Caesar (100-44 BC), the founder of the Roman empire. While Caesar himself has authored at least part of these commentaries, the authorship of the rest of the texts remains a puzzle that has persisted for nineteen centuries. In particular, the role of Caesar's general Aulus Hirtius, who has claimed a role in shaping the corpus, has remained in contention. Determining the authorship of documents is an increasingly important authentication problem in information and computer science, with valuable applications, ranging from the domain of art history to counter-terrorism research.We describe two state-of-the-art authorship verification systems and benchmark them on 6 present-day evaluation corpora, as well as a Latin benchmark dataset. Regarding Caesar's writings, our analysis allow us to establish that Hirtius's claims to part of the corpus must be considered legitimate. We thus demonstrate how computational methods constitute a valuable methodological complement to traditional, expert-based approaches to document authentication.

We discuss a real-world application of a recently proposed machine learning method for authorship verification. Authorship verification is considered an extremely difficult task in computational text classification, because it does not assume that the correct author of an anonymous text is included in the candidate authors available. To determine whether 2 documents have been written by the same author, the verification method discussed uses repeated feature subsampling and a pool of impostor authors. We use this technique to attribute a newly discovered Latin text from antiquity (the Compendiosa expositio) to Apuleius. This North African writer was one of the most important authors of the Roman Empire in the 2 nd century and authored one of the world's first novels. This attribution has profound and wide-reaching cultural value, because it has been over a century since a new text by a major author from antiquity was discovered. This research therefore illustrates the rapidly growing potential of computational methods for studying the global textual heritage.

This paper presents a new manuscript of part of the Historia Augusta from Erlangen, which vindicates a more than century-old hypothesis by E. Patzig: that the 1489 Venice edition of the work is textually valuable. On this basis, and building on the recent work of R. Modonutti, I present five new passages that are not printed in modern editions of the HA, six lacunose passages restored, and propose that the lost Murbach manuscript is the source. Armed with this new evidence, I re-examine the question of the great lacuna between the Lives of Maximus and Balbinus and the Lives of the Two Valerians, showing that it is a codicological — and not authorial — feature.

The case of the Historia Augusta, a collection of imperial biographies from Hadrian to Carus supposedly written by six different authors, provided the impetus for the introduction of computational methods into the Echtheitskritik of ancient authors in 1979. After a flurry of studies in the 1990s, interest waned, particularly because most of those studies seemed to support conclusions incompatible with the scholarly consensus on the question. In the paper, we approach this question with the new tool of authorship verification – one of the most promising approaches in forensic stylometry today – as well as the established method of principal components analysis to demonstrate that there is no simple alternative between single and multiple authorship, and that the results of a computational analysis are in fact compatible with the results obtained from historical, literary, and philological analysis.