arXiv subjects

Sean Moran

Publications and source records attributed to Sean Moran.

At least 19 recordsLinked to original sources

arXiv2026

Same Pipeline, Opposite Conclusions: Sample-Surface Effects in Breaking-News Latency

Osborne and Dredze (2014) reported that Twitter was the timeliest social-media source of breaking news, trailing only newswire. Twelve years on, the platform landscape has shifted - Google+ is gone, X replaced Twitter, Bluesky and Threads have appeared - and platform data now flows almost exclusively through commercial social-listening providers that redact key fields. We revisit the question with two sampling designs run through the same downstream pipeline. Sample A draws N = 50 events from the Wikipedia Current Events Portal (WCEP) ranked by article pageviews. Sample B draws N = 109 events from Polymarket prediction markets ranked by USD trading volume, with each event's news moment pinned to the largest 1-hour trade-volume spike. Both samples are pulled from one commercial provider across nine indexed channels. We report three findings. (1) The X-vs-news direction depends on the sample. News leads X by a median of 21.6 min on Sample A (n = 6 paired); the same comparison is tied at -0.02 min on Sample B (n = 16 paired, X earliest in 38%). (2) The channel ecosystem has diversified. Bluesky, Facebook public, and YouTube together account for 24-32% of earliest channel wins; the 2014 "X versus newswire" framing no longer fits. (3) Coverage gaps are structural. Even with U.S.-relevance filtering and a pageview prior, the provider's index returns no on-topic evidence on 24% of randomly-sampled WCEP events. The paper's contribution is the cross-surface design that exposes the sample dependency in (1).

cs.SI↗

arXiv2025

Projection and Quantisation: A Unifying View of Learning to Hash, from Random Projections to the RAG Era

Approximate nearest-neighbour search underpins large-scale retrieval and retrieval-augmented generation, yet its methods are studied in communities that seldom read one another. We argue that they form one field with three design choices. We develop the projection-quantisation-organisation lens: every method places its projections, places its quantisation thresholds, and organises the resulting codes for search. We test the lens with a reproducible measurement, released as the open BitBudget benchmark, and report three findings. First, the quantisation axis delivers the largest memory savings: a one-bit code with full-precision re-ranking matches uncompressed quality for six of seven embedders, the scanned code one thirty-second of the float's size. Second, the orderings the lens anticipates, including a learned-embedding regime where binary codes overtake an inverted-file product quantiser at a matched byte budget, recur as the embedding is enlarged. Third, given class labels, an eight-byte supervised code more than doubles the retrieval quality of the two-kilobyte task-agnostic float it replaces. We also recast the semantic identifiers of generative retrieval as quantisation codes. The main contribution is a single, tested account of compact-code search, from random projections to the retrieval-augmented era.

cs.IR↗

arXiv2025

On Iterative Evaluation and Enhancement of Code Quality Using GPT-4o

This paper introduces CodeQUEST, a novel framework leveraging Large Language Models (LLMs) to iteratively evaluate and enhance code quality across multiple dimensions, including readability, maintainability, efficiency, and security. The framework is divided into two main components: an Evaluator that assesses code quality across ten dimensions, providing both quantitative scores and qualitative summaries, and an Optimizer that iteratively improves the code based on the Evaluator's feedback. Our study demonstrates that CodeQUEST can effectively and robustly evaluate code quality, with its assessments aligning closely with established code quality metrics. Through a series of experiments using a curated dataset of Python and JavaScript examples, CodeQUEST demonstrated significant improvements in code quality, achieving a mean relative percentage improvement of 52.6%. The framework's evaluations were validated against a set of proxy metrics comprising of Pylint Score, Radon Maintainability Index, and Bandit output logs, showing a meaningful correlation. This highlights the potential of LLMs in automating code quality evaluation and improvement processes, presenting a significant advancement toward enhancing software development practices. The code implementation of the framework is available at: https://github.com/jpmorganchase/CodeQuest.

cs.SE↗

arXiv2025

An Integral Field Unit for the Binospec Spectrograph

Binospec is a wide-field optical (360 to 1000 nm) spectrograph commissioned at the MMT 6.5m telescope in 2017. In direct imaging mode Binospec addresses twin 8$^\prime$ (wide) by 15$^\prime$ (slit length) fields of view. We describe an optical fiber based integral field unit (IFU) that remaps a 12$^{\prime\prime}$ x 16$^{\prime\prime}$ contiguous region onto two pseudo slits, one in each Binospec channel. The IFU, commissioned in 2023, fits into the space of a standard slit mask frame and can be deployed as desired in a mixed program of slit masks, long slits, and IFU observations. The IFU fibers are illuminated by a hexagonal lenslet array with a 0.6$^{\prime\prime}$ pitch. A separate bundle of sky fibers consists of close-packed bare fibers arranged within an 11.8$^{\prime\prime}$ circular aperture. The 640 IFU fibers and 80 sky fibers have a core diameter of 150$\mu$m, corresponding to 0.90$^{\prime\prime}$. Three gratings are available, 270lpm with R$\sim$2000, 600lpm with R$\sim$5300, and 1000 lpm with R$\sim$6000.

astro-ph.IM↗

arXiv2024

Model-Agnostic Utility-Preserving Biometric Information Anonymization

The recent rapid advancements in both sensing and machine learning technologies have given rise to the universal collection and utilization of people's biometrics, such as fingerprints, voices, retina/facial scans, or gait/motion/gestures data, enabling a wide range of applications including authentication, health monitoring, or much more sophisticated analytics. While providing better user experiences and deeper business insights, the use of biometrics has raised serious privacy concerns due to their intrinsic sensitive nature and the accompanying high risk of leaking sensitive information such as identity or medical conditions. In this paper, we propose a novel modality-agnostic data transformation framework that is capable of anonymizing biometric data by suppressing its sensitive attributes and retaining features relevant to downstream machine learning-based analyses that are of research and business values. We carried out a thorough experimental evaluation using publicly available facial, voice, and motion datasets. Results show that our proposed framework can achieve a \highlight{high suppression level for sensitive information}, while at the same time retain underlying data utility such that subsequent analyses on the anonymized biometric data could still be carried out to yield satisfactory accuracy.

cs.LG↗

arXiv2024

A Generative AI Assistant to Accelerate Cloud Migration

We present a tool that leverages generative AI to accelerate the migration of on-premises applications to the cloud. The Cloud Migration LLM accepts input from the user specifying the parameters of their migration, and outputs a migration strategy with an architecture diagram. A user study suggests that the migration LLM can assist inexperienced users in finding the right cloud migration profile, while avoiding complexities of a manual approach.

cs.AI↗

arXiv2024

Using AI/ML to Find and Remediate Enterprise Secrets in Code & Document Sharing Platforms

We introduce a new challenge to the software development community: 1) leveraging AI to accurately detect and flag up secrets in code and on popular document sharing platforms that frequently used by developers, such as Confluence and 2) automatically remediating the detections (e.g. by suggesting password vault functionality). This is a challenging, and mostly unaddressed task. Existing methods leverage heuristics and regular expressions, that can be very noisy, and therefore increase toil on developers. The next step - modifying code itself - to automatically remediate a detection, is a complex task. We introduce two baseline AI models that have good detection performance and propose an automatic mechanism for remediating secrets found in code, opening up the study of this task to the wider community.

cs.SE↗

arXiv2023

DeepClean: Machine Unlearning on the Cheap by Resetting Privacy Sensitive Weights using the Fisher Diagonal

Machine learning models trained on sensitive or private data can inadvertently memorize and leak that information. Machine unlearning seeks to retroactively remove such details from model weights to protect privacy. We contribute a lightweight unlearning algorithm that leverages the Fisher Information Matrix (FIM) for selective forgetting. Prior work in this area requires full retraining or large matrix inversions, which are computationally expensive. Our key insight is that the diagonal elements of the FIM, which measure the sensitivity of log-likelihood to changes in weights, contain sufficient information for effective forgetting. Specifically, we compute the FIM diagonal over two subsets -- the data to retain and forget -- for all trainable weights. This diagonal representation approximates the complete FIM while dramatically reducing computation. We then use it to selectively update weights to maximize forgetting of the sensitive subset while minimizing impact on the retained subset. Experiments show that our algorithm can successfully forget any randomly selected subsets of training data across neural network architectures. By leveraging the FIM diagonal, our approach provides an interpretable, lightweight, and efficient solution for machine unlearning with practical privacy benefits.

cs.LG↗

arXiv2023

Early Spectroscopy and Dense Circumstellar Medium Interaction in SN 2023ixf

We present the optical spectroscopic evolution of SN~2023ixf seen in sub-night cadence spectra from 1.18 to 14 days after explosion. We identify high-ionization emission features, signatures of interaction with material surrounding the progenitor star, that fade over the first 7 days, with rapid evolution between spectra observed within the same night. We compare the emission lines present and their relative strength to those of other supernovae with early interaction, finding a close match to SN~2020pni and SN~2017ahn in the first spectrum and SN~2014G at later epochs. To physically interpret our observations we compare them to CMFGEN models with confined, dense circumstellar material around a red supergiant progenitor from the literature. We find that very few models reproduce the blended \NC{} emission lines observed in the first few spectra and their rapid disappearance thereafter, making this a unique diagnostic. From the best models, we find a mass-loss rate of $10^{-3}-10^{-2}$ \mlunit{}, which far exceeds the mass-loss rate for any steady wind, especially for a red supergiant in the initial mass range of the detected progenitor. These mass-loss rates are, however, similar to rates inferred for other supernovae with early circumstellar interaction. Using the phase when the narrow emission features disappear, we calculate an outer dense radius of circumstellar material $R_\mathrm{CSM, out}\sim5\times10^{14}~\mathrm{cm}$ and a mean circumstellar material density of $\rho=5.6\times10^{-14}~\mathrm{g\,cm^{-3}}$. This is consistent with the lower limit on the outer radius of the circumstellar material we calculate from the peak \Halpha{} emission flux, $R_\text{CSM, out}\gtrsim9\times10^{13}~\mathrm{cm}$.

astro-ph.HE↗

arXiv2023

Dwarf early-type galaxies in the Coma cluster: internal dynamics, stellar populations

We present preliminary results from our spectroscopic survey of low-luminosity early-type galaxies in the Coma cluster conducted with the Binospec spectrograph at the 6.5~m MMT. From spatially-resolved profiles of internal kinematics and stellar population properties complemented with high-resolution images, we placed several low-luminosity dEs on the fundamental plane in the low-luminosity extension of the available literature data. We also discovered unusual kpc-sized kinematically-decoupled cores in several dwarf galaxies, which had been probably formed before these galaxies entered the cluster.

astro-ph.GA↗

arXiv2023

Dark matter content and dynamical masses of ultra-diffuse galaxies in the Coma cluster

Ultra-diffuse galaxies (UDGs) are spatially extended, low surface brightness stellar systems with regular elliptical-like morphology found in large numbers in galaxy clusters and groups. Studies of the internal dynamics and dark matter content of UDGs have been hampered by their low surface brightnesses. We identified a sample of low-mass early-type post-starburst galaxies, `future UDGs' in the Coma cluster still populated with young stars, which will passively evolve into UDGs in the next 5$-$10 Gyr. We collected deep observations for a sample of low-mass early-type galaxies in the Coma cluster using MMT Binospec, which includes present-day and future UDGs. We derived their dark matter content within a half-light radius (70$-$95%) and total dynamical masses ($M_{200}=5.5\cdot10^9-1.4\cdot10^{11} M_{\odot}$) assuming the Burkert density profile and assess how different proposed evolutionary channels affect dark and visible matter in UDGs. We also discuss observational methodology of present and future UDG studies.

astro-ph.GA↗

arXiv2023

Estimating class separability of text embeddings with persistent homology

This paper introduces an unsupervised method to estimate the class separability of text datasets from a topological point of view. Using persistent homology, we demonstrate how tracking the evolution of embedding manifolds during training can inform about class separability. More specifically, we show how this technique can be applied to detect when the training process stops improving the separability of the embeddings. Our results, validated across binary and multi-class text classification tasks, show that the proposed method's estimates of class separability align with those obtained from supervised methods. This approach offers a novel perspective on monitoring and improving the fine-tuning of sentence transformers for classification tasks, particularly in scenarios where labeled data is scarce. We also discuss how tracking these quantities can provide additional insights into the properties of the trained classifier.

cs.LG↗

arXiv2023

Spam-T5: Benchmarking Large Language Models for Few-Shot Email Spam Detection

This paper investigates the effectiveness of large language models (LLMs) in email spam detection by comparing prominent models from three distinct families: BERT-like, Sentence Transformers, and Seq2Seq. Additionally, we examine well-established machine learning techniques for spam detection, such as Na\"ive Bayes and LightGBM, as baseline methods. We assess the performance of these models across four public datasets, utilizing different numbers of training samples (full training set and few-shot settings). Our findings reveal that, in the majority of cases, LLMs surpass the performance of the popular baseline techniques, particularly in few-shot scenarios. This adaptability renders LLMs uniquely suited to spam detection tasks, where labeled samples are limited in number and models require frequent updates. Additionally, we introduce Spam-T5, a Flan-T5 model that has been specifically adapted and fine-tuned for the purpose of detecting email spam. Our results demonstrate that Spam-T5 surpasses baseline models and other LLMs in the majority of scenarios, particularly when there are a limited number of training samples available. Our code is publicly available at https://github.com/jpmorganchase/emailspamdetection.

cs.CL↗

arXiv2023

A Benchmark Generative Probabilistic Model for Weak Supervised Learning

Finding relevant and high-quality datasets to train machine learning models is a major bottleneck for practitioners. Furthermore, to address ambitious real-world use-cases there is usually the requirement that the data come labelled with high-quality annotations that can facilitate the training of a supervised model. Manually labelling data with high-quality labels is generally a time-consuming and challenging task and often this turns out to be the bottleneck in a machine learning project. Weak Supervised Learning (WSL) approaches have been developed to alleviate the annotation burden by offering an automatic way of assigning approximate labels (pseudo-labels) to unlabelled data based on heuristics, distant supervision and knowledge bases. We apply probabilistic generative latent variable models (PLVMs), trained on heuristic labelling representations of the original dataset, as an accurate, fast and cost-effective way to generate pseudo-labels. We show that the PLVMs achieve state-of-the-art performance across four datasets. For example, they achieve 22% points higher F1 score than Snorkel in the class-imbalanced Spouse dataset. PLVMs are plug-and-playable and are a drop-in replacement to existing WSL frameworks (e.g. Snorkel) or they can be used as benchmark models for more complicated algorithms, giving practitioners a compelling accuracy boost.

cs.LG↗

arXiv2023

Learning a Consensus Sub-Network with Polarization Regularization and One Pass Training

The subject of green AI has been gaining attention within the deep learning community given the recent trend of ever larger and more complex neural network models. Existing solutions for reducing the computational load of training at inference time usually involve pruning the network parameters. Pruning schemes often create extra overhead either by iterative training and fine-tuning for static pruning or repeated computation of a dynamic pruning graph. We propose a new parameter pruning strategy for learning a lighter-weight sub-network that minimizes the energy cost while maintaining comparable performance to the fully parameterised network on given downstream tasks. Our proposed pruning scheme is green-oriented, as it only requires a one-off training to discover the optimal static sub-networks by dynamic pruning methods. The pruning scheme consists of a binary gating module and a polarizing loss function to uncover sub-networks with user-defined sparsity. Our method enables pruning and training simultaneously, which saves energy in both the training and inference phases and avoids extra computational overhead from gating modules at inference time. Our results on CIFAR-10, CIFAR-100, and Tiny Imagenet suggest that our scheme can remove 50% of connections in deep networks with <1% reduction in classification accuracy. Compared to other related pruning methods, our method demonstrates a lower drop in accuracy for equivalent reductions in computational cost.

cs.LG↗

arXiv2022

API-Miner: an API-to-API Specification Recommendation Engine

When designing a new API for a large project, developers need to make smart design choices so that their code base can grow sustainably. To ensure that new API components are well designed, developers can learn from existing API components. However, the lack of standardized methods for comparing API designs makes this learning process time-consuming and difficult. To address this gap we developed API-Miner, to the best of our knowledge, one of the first API-to-API specification recommendation engines. API-Miner retrieves relevant specification components written in OpenAPI (a widely adopted language used to describe web APIs). API-miner presents several significant contributions, including: (1) novel methods of processing and extracting key information from OpenAPI specifications, (2) innovative feature extraction techniques that are optimized for the highly technical API specification domain, and (3) a novel log-linear probabilistic model that combines multiple signals to retrieve relevant and high quality OpenAPI specification components given a query specification. We evaluate API-Miner in both quantitative and qualitative tasks and achieve an overall of 91.7% recall@1 and 56.2% F1, which surpasses baseline performance by 15.4% in recall@1 and 3.2% in F1. Overall, API-Miner will allow developers to retrieve relevant OpenAPI specification components from a public or internal database in the early stages of the API development cycle, so that they can learn from existing established examples and potentially identify redundancies in their work. It provides the guidance developers need to accelerate development process and contribute thoughtfully designed APIs that promote code maintainability and quality. Code is available on GitHub at https://github.com/jpmorganchase/api-miner.

cs.SE↗

arXiv2022

Code Librarian: A Software Package Recommendation System

The use of packaged libraries can significantly shorten the software development cycle by improving the quality and readability of code. In this paper, we present a recommendation engine called Librarian for open source libraries. A candidate library package is recommended for a given context if: 1) it has been frequently used with the imported libraries in the program; 2) it has similar functionality to the imported libraries in the program; 3) it has similar functionality to the developer's implementation, and 4) it can be used efficiently in the context of the provided code. We apply the state-of-the-art CodeBERT-based model for analysing the context of the source code to deliver relevant library recommendations to users.

cs.SE↗

arXiv2022

Topical: Learning Repository Embeddings from Source Code using Attention

This paper presents Topical, a novel deep neural network for repository level embeddings. Existing methods, reliant on natural language documentation or naive aggregation techniques, are outperformed by Topical's utilization of an attention mechanism. This mechanism generates repository-level representations from source code, full dependency graphs, and script level textual data. Trained on publicly accessible GitHub repositories, Topical surpasses multiple baselines in tasks such as repository auto-tagging, highlighting the attention mechanism's efficacy over traditional aggregation methods. Topical also demonstrates scalability and efficiency, making it a valuable contribution to repository-level representation computation. For further research, the accompanying tools, code, and training dataset are provided at: https://github.com/jpmorganchase/topical.

cs.SE↗