Article

Topological Data Analysis for Distinguishing Human Written and AI Generated Abstracts

2025-05-06

Abstract excerpt

Distinguishing human written text from machine generated text is a widely studied topic. In our approach we intend to apply this to purely academic text, and compute Vietoris-Rips up to H2 to produce persistence diagrams which we can statistically analyze. We contribute a classification process with promising success rates. Later, we analyze the transformer structure using Alpha complex filtration.

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 582daf98-0a6e-51ff-9463-59ddf993dc8c
DOI: 10.20944/preprints202505.0097.v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 8 closest

Topological Data Analysis for Distinguishing Human Written and AI Generated AbstractsDOI 10.20944/preprints202505.0097.v1Read

Algebraic Morphology of DNA--RNA Transcription and RegulationSemantic proximity Read

Improving Detection of ChatGPT-Generated Fake Science Using Real Publication Text: Introducing xFakeBibs a Supervised-Learning Network AlgorithmSemantic proximity Read

DNA sequence and structure under the prism of group theory and algebraic surfacesSemantic proximity Read

Intrinsic Thematic Separability in Sentence-Transformer Embeddings: A Controlled Geometric Study from Synthetic to Real-World TextSemantic proximity Read

The embedded homology of hypergraphs and applicationsSemantic proximity Read

Graffiti3 : Compact Theory Libraries for Automated Mathematical DiscoverySemantic proximity Read

Robustness and Explainability in Arabic Authorship Models: Tackling the Challenge of AI-Generated TextsSemantic proximity Read

DEDICAITE — DEtecting AI-generated TExts in a DIdactic ContextSemantic proximity Read