SSScott Seidenberger

Scott Seidenberger

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Scott Seidenberger has a total of 8 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Prompt and Circumstances: Evaluating the Efficacy of Human Prompt Inference in AI-Generated Art

    by Khoi Trinh, Scott Seidenberger, Joseph Spracklen, Raveen Wijewickrama, Bimal Viswanath, Murtuza Jadliwala, Anindya Maiti

    The emerging field of AI-generated art has witnessed the rise of prompt marketplaces, where creators can purchase, sell, or share prompts to generate unique artworks. These marketplaces often assert ownership over prompts, claiming them as intellectual property. This paper investigates whether concealed prompts sold on prompt marketplaces can be considered bona fide intellectual property, given that humans and AI tools may be able to infer the prompts based on publicly advertised sample images accompanying each prompt on sale. Specifically, our study aims to assess (i) how accurately humans can infer the original prompt solely by examining an AI-generated image, with the goal of generating images similar to the original image, and (ii) the possibility of improving upon individual human and AI prompt inferences by crafting combined human and AI prompts with the help of a large language model. Although previous research has explored AI-driven prompt inference and protection strategies, our work is the first to incorporate a human subject study and examine collaborative human-AI prompt inference in depth. Our findings indicate that while prompts inferred by humans and prompts inferred through a combined human and AI effort can generate images with a moderate level of similarity, they are not as successful as using the original prompt. Moreover, combining human- and AI-inferred prompts using our suggested merging techniques did not improve performance over purely human-inferred prompts.

  • Open Access

    From Big Data to Valued Data: A Dataset Value Taxonomy for AI-Native Empirical Research

    by Scott Seidenberger, Anindya Maiti

    Artificial intelligence is rapidly commoditizing many stages of empirical research, including code generation, statistical analysis, visualization, and manuscript drafting, yet its gains accrue unevenly across disciplines. As the marginal cost of these downstream tasks falls, the decisive bottleneck shifts to the data itself. The era of training and testing neural networks with ever-larger datasets is giving way to one in which the value of the data matters more than its volume. Building on but significantly revising earlier “Big Data” taxonomies, we introduce a Dataset Value Taxonomy (DVT) that reassesses the epistemic importance of datasets in an age where AI is commoditizing analytical labor. We argue that humans, as physically embodied agents, retain a comparative advantage in acquiring and curating observations from the world; partnered with AI, they can channel this advantage into higher-impact scholarship. To guide funders, evaluators, and researchers, we introduce a three-construct taxonomy: Temporal Investment, Scale, and Accessibility, each decomposed into measurable dimensions with ordinal class labels. We further operationalize these constructs through a calibrated scoring scheme that disciplines can adapt to field-specific conventions, enabling cross-field comparability while respecting contextual nuance. By quantifying how temporal investment, observational breadth, and access barriers jointly determine dataset salience, the framework helps allocate resources toward datasets that are most likely to advance knowledge. Ultimately, our taxonomy positions dataset creation as the new core site of human and AI cooperation and provides an actionable roadmap for recognizing, funding, and stewarding high-value data assets across the empirical sciences.

  • Open Access

    A Picture is Worth a Thousand Prompts? Efficacy of Iterative Human-Driven Prompt Refinement in Image Regeneration Tasks

    by Khoi Trinh, Scott Seidenberger, Raveen Wijewickrama, Murtuza Jadliwala, Anindya Maiti

    With AI-generated content becoming widespread across digital platforms, it is important to understand how such content is inspired and produced. This study explores the underexamined task of image regeneration, where a human operator iteratively refines prompts to recreate a specific target image. Unlike typical image generation, regeneration begins with a visual reference. A key challenge is whether existing image similarity metrics (ISMs) align with human judgments and can serve as useful feedback in this process. We conduct a structured user study to evaluate how iterative prompt refinement affects similarity to target images and whether ISMs reflect the improvements perceived by human observers. Our results show that prompt adjustments significantly improve alignment, both subjectively and quantitatively, highlighting the potential of iterative workflows in enhancing generative image quality.


  • Open Access

    MagnetDB: A Longitudinal Torrent Discovery Dataset with IMDb-Matched Movies and TV Shows

    by Scott Seidenberger, Noah Pursell, Anindya Maiti

    BitTorrent remains a prominent channel for illicit distribution of copyrighted material, yet the supply side of such content remains understudied. We introduce MagnetDB, a longitudinal dataset of torrents discovered through the BitTorrent DHT between 2018 and 2024, containing more than 28.6 million torrents and metadata of more than 950 million files. While our primary focus is on enabling research based on the supply of pirated movies and TV shows, the dataset also encompasses other legitimate and illegitimate torrents. By applying IMDb-matching and annotation to movie and TV show torrents, MagnetDB facilitates detailed analyses of pirated content evolution in the BitTorrent network. Researchers can leverage MagnetDB to examine distribution trends, subcultural practices, and the gift economy within piracy ecosystems. Through its scale and temporal scope, MagnetDB presents a unique opportunity for investigating the broader dynamics of BitTorrent and advancing empirical knowledge on digital piracy.


  • Open Access

    A Picture is Worth a Thousand Prompts? Efficacy of Iterative Human-Driven Prompt Refinement in Image Regeneration Tasks

    by Khoi Trinh, Scott Seidenberger, Raveen Wijewickrama, Murtuza Jadliwala, Anindya Maiti

    With AI-generated content becoming ubiquitous across the web, social media, and other digital platforms, it is vital to examine how such content are inspired and generated. The creation of AI-generated images often involves refining the input prompt iteratively to achieve desired visual outcomes. This study focuses on the relatively underexplored concept of image regeneration using AI, in which a human operator attempts to closely recreate a specific target image by iteratively refining their prompt. Image regeneration is distinct from normal image generation, which lacks any predefined visual reference. A separate challenge lies in determining whether existing image similarity metrics (ISMs) can provide reliable, objective feedback in iterative workflows, given that we do not fully understand if subjective human judgments of similarity align with these metrics. Consequently, we must first validate their alignment with human perception before assessing their potential as a feedback mechanism in the iterative prompt refinement process. To address these research gaps, we present a structured user study evaluating how iterative prompt refinement affects the similarity of regenerated images relative to their targets, while also examining whether ISMs capture the same improvements perceived by human observers. Our findings suggest that incremental prompt adjustments substantially improve alignment, verified through both subjective evaluations and quantitative measures, underscoring the broader potential of iterative workflows to enhance generative AI content creation across various application domains.

  • Open Access

    MagnetDB: A Longitudinal Torrent Discovery Dataset with IMDb-Matched Movies and TV Shows

    by Scott Seidenberger, Noah Pursell, Anindya Maiti

    BitTorrent remains a prominent channel for illicit distribution of copyrighted material, yet the supply side of such content remains understudied. We introduce MagnetDB, a longitudinal dataset of torrents discovered through the BitTorrent DHT between 2018 and 2024, containing more than 28.6 million torrents and metadata of more than 950 million files. While our primary focus is on enabling research based on the supply of pirated movies and TV shows, the dataset also encompasses other legitimate and illegitimate torrents. By applying IMDb-matching and annotation to movie and TV show torrents, MagnetDB facilitates detailed analyses of pirated content evolution in the BitTorrent network. Researchers can leverage MagnetDB to examine distribution trends, subcultural practices, and the gift economy within piracy ecosystems. Through its scale and temporal scope, MagnetDB presents a unique opportunity for investigating the broader dynamics of BitTorrent and advancing empirical knowledge on digital piracy.

  • Open Access

    NinjaDoH: A Censorship-Resistant Moving Target DoH Server Using Hyperscalers and IPNS

    by Scott Seidenberger, Marc Beret, Raveen Wijewickrama, Murtuza Jadliwala, Anindya Maiti

    We introduce NinjaDoH, a novel DNS over HTTPS (DoH) protocol that leverages the InterPlanetary Name System (IPNS), along with public cloud infrastructure, to create a censorship-resistant moving target DoH service. NinjaDoH is specifically designed to evade traditional censorship methods that involve blocking DoH servers by IP addresses or domains by continually altering the server's network identifiers, significantly increasing the complexity of effectively censoring NinjaDoH traffic without disruption of other web traffic. We also present an analysis that quantifies the DNS query latency and financial costs of running our implementation of this protocol as a service. Further tests assess the ability of NinjaDoH to elude detection mechanisms, including both commercial firewall products and advanced machine learning-based detection systems. The results broadly support NinjaDoH's efficacy as a robust, moving target DNS solution that can ensure continuous and secure internet access in environments with heavy DNS-based censorship.