Negative / Null Result ReportOpen accessComputer Science
Arpit Agarwal · 2021 · arXiv
Predicting the outcome of liquid droplet collisions is an extensively studied phenomenon but the current physics based models for predicting the outcomes are poor (accuracy $\approx 43\%$). The key weakness of these models is their limited complexity. They only account for 3 features while there are many more relevant features that go unaccounted for. This limitation of traditional models can be easily overcome through machine learning modeling of the problem. In an ML setting this problem directly translates to a classification problem with 4 classes. Here we compile a large labelled dataset
View details →Negative / Null Result ReportOpen accessComputer Science
Jimmy Lin, Daniel Campos, Nick Craswell et al. · 2021 · arXiv
Leaderboards are a ubiquitous part of modern research in applied machine learning. By design, they sort entries into some linear order, where the top-scoring entry is recognized as the "state of the art" (SOTA). Due to the rapid progress being made in information retrieval today, particularly with neural models, the top entry in a leaderboard is replaced with some regularity. These are touted as improvements in the state of the art. Such pronouncements, however, are almost never qualified with significance testing. In the context of the MS MARCO document ranking leaderboard, we pose a specific
View details →Negative / Null Result ReportOpen accessComputer Science
Xiaolong Jin, Xuandong Zhao, Wenbo Guo et al. · 2026 · arXiv
Reinforcement learning with verifiable rewards (RLVR) has driven substantial progress in large language model reasoning, but relies on ground-truth supervision that is costly or infeasible, especially in coding tasks. Recent work addresses this by deriving rewards from a model's own signals, such as majority voting or confidence-based scores, achieving notable success on mathematical reasoning benchmarks. However, code generation poses distinct challenges: programs are structurally complex, semantically equivalent solutions may differ syntactically, and verification typically requires executio
View details →Negative / Null Result ReportOpen accessComputer Science
Hamed R. Tavakoli, Rakshith Shetty, Ali Borji et al. · 2017 · arXiv
To bridge the gap between humans and machines in image understanding and describing, we need further insight into how people describe a perceived scene. In this paper, we study the agreement between bottom-up saliency-based visual attention and object referrals in scene description constructs. We investigate the properties of human-written descriptions and machine-generated ones. We then propose a saliency-boosted image captioning model in order to investigate benefits from low-level cues in language models. We learn that (1) humans mention more salient objects earlier than less salient ones i
View details →Negative / Null Result ReportOpen accessComputer Science
Wataru Masaka, Mitsuki Sakamoto, Kenshi Abe et al. · 2025 · arXiv
We investigate how perturbation does and does not improve the Follow-the-Regularized-Leader (FTRL) algorithm in solving imperfect-information extensive-form games under sampling, where payoffs are estimated from sampled trajectories. While optimistic algorithms are effective under full feedback, they often become unstable in the presence of sampling noise. Payoff perturbation offers a promising alternative for stabilizing learning and achieving \textit{last-iterate convergence}. We present a unified framework for \textit{Perturbed FTRL} algorithms and study two variants: PFTRL-KL (standard KL
View details →Negative / Null Result ReportOpen accessComputer Science
Jason Dury · 2026 · arXiv
Dense retrieval systems rank passages by embedding similarity to a query, but multi-hop questions require passages that are associatively related through shared reasoning chains. We introduce Association-Augmented Retrieval (AAR), a lightweight transductive reranking method that trains a small MLP (4.2M parameters) to learn associative relationships between passages in embedding space using contrastive learning on co-occurrence annotations. At inference time, AAR reranks an initial dense retrieval candidate set using bi-directional association scoring. On HotpotQA, AAR improves passage Recall@
View details →Short NoteOpen accessComputer Science
Abhijit Bandyopadhyay, Sandhya Choubey, Srubabati Goswami et al. · 2003 · arXiv
A new reactor power plant Shika-2, with a power of approximately 4 GW and at a distance of about 88 km from the KamLAND detector is scheduled to start operating in March 2006. We study the impact of the $\barν_e$ flux from this reactor on the sensitivity of the KamLAND experiment to the solar neutrino oscillation parameters. We present results on prospective determination of $Δm^2_\odot$ and $\sin^2θ_\odot$ using the combined data from KamLAND and the solar neutrino experiments, including the effect of the Shika-2 contribution to the KamLAND signal and the latest data from the salt enriched ph
View details →Negative / Null Result ReportOpen accessComputer Science
Arwa Arif · 2025 · arXiv
Backtranslation BT is widely used in low resource machine translation MT to generate additional synthetic training data using monolingual corpora. While this approach has shown strong improvements for many language pairs, its effectiveness in high quality, low resource settings remains unclear. In this work, we explore the effectiveness of backtranslation for English Gujarati translation using the multilingual pretrained MBART50 model. Our baseline system, trained on a high quality parallel corpus of approximately 50,000 sentence pairs, achieves a BLEU score of 43.8 on a validation set. We aug
View details →Negative / Null Result ReportOpen accessComputer Science
Yining Lu, Dixuan Wang, Tianjian Li et al. · 2024 · arXiv
As LLMs become increasingly prevalent, it is interesting to consider how ``creative'' these models can be. From cognitive science, creativity consists of at least two key characteristics: \emph{convergent} thinking (purposefulness to achieve a given goal) and \emph{divergent} thinking (adaptability to explore new environments or constraints) \citep{runco2003critical}. In this work, we introduce a framework for quantifying LLM creativity that incorporates the two design ingredients: (1) We introduce DENIAL PROMPTING which pushes LLMs to develop more creative solutions to a given problem by incr
View details →Negative / Null Result ReportOpen accessComputer Science
F. de Jong, H. Lenske · 1997 · arXiv
We present a calculation of nuclear matter which goes beyond the usual quasi-particle approximation in that it includes part of the off-shell dependence of the self-energy in the self-consistent solution of the single-particle spectrum. The spectral function is separated in contributions for energies above and below the chemical potential. For holes we approximate the spectral function for energies below the chemical potential by a $δ$-function at the quasi-particle peak and retain the standard form for energies above the chemical potential. For particles a similar procedure is followed. The a
View details →Negative / Null Result ReportOpen accessComputer Science
Lawrence Clegg, John Cartlidge · 2025 · arXiv
Intransitive player dominance, where player A beats B, B beats C, but C beats A, is common in competitive tennis. Yet, there are few known attempts to incorporate it within forecasting methods. We address this problem with a graph neural network approach that explicitly models these intransitive relationships through temporal directed graphs, with players as nodes and their historical match outcomes as directed edges. Our model (65.7% accuracy, 0.214 Brier score) forecasts competitively with established rating systems such as Weighted Elo. Although it does not improve on the baseline in uncond
View details →Negative / Null Result ReportOpen accessComputer Science
Asahi Ushio, Jose Camacho-Collados · 2024 · arXiv
In machine learning, temporal shifts occur when there are differences between training and test splits in terms of time. For streaming data such as news or social media, models are commonly trained on a fixed corpus from a certain period of time, and they can become obsolete due to the dynamism and evolving nature of online content. This paper focuses on temporal shifts in social media and, in particular, Twitter. We propose a unified evaluation scheme to assess the performance of language models (LMs) under temporal shift on standard social media tasks. LMs are tested on five diverse social m
View details →Negative / Null Result ReportOpen accessComputer Science
Osvaldo Simeone, Haim H. Permuter · 2011 · arXiv
For memoryless sources, delayed side information at the decoder does not improve the rate-distortion function. However, this is not the case for more general sources with memory, as demonstrated by a number of works focusing on the special case of (delayed) feedforward. In this paper, a setting is studied in which the encoder is potentially uncertain about the delay with which measurements of the side information are acquired at the decoder. Assuming a hidden Markov model for the sources, at first, a single-letter characterization is given for the set-up where the side information delay is arb
View details →Negative / Null Result ReportOpen accessComputer Science
Fabian Hoppe, Filip Ilievski, Jan-Christoph Kalo · 2025 · arXiv
Large Language Models (LLMs) have been shown to achieve impressive results for many reasoning-based NLP tasks, suggesting a degree of deductive reasoning capability. However, it remains unclear to which extent LLMs, in both informal and autoformalisation methods, are robust on logical deduction tasks. Moreover, while many LLM-based deduction methods have been proposed, a systematic study that analyses the impact of their design components is lacking. Addressing these two challenges, we propose the first study of the robustness of formal and informal LLM-based deductive reasoning methods. We de
View details →Negative / Null Result ReportOpen accessComputer Science
Rajat Talak, Sertac Karaman, Eytan Modiano · 2017 · arXiv
We study broadcast capacity and minimum delay scaling laws for highly mobile wireless networks, in which each node has to disseminate or broadcast packets to all other nodes in the network. In particular, we consider a cell partitioned network under the simplified independent and identically distributed (IID) mobility model, in which each node chooses a new cell at random every time slot. We derive scaling laws for broadcast capacity and minimum delay as a function of the cell size. We propose a simple first-come-first-serve (FCFS) flooding scheme that nearly achieves both capacity and minimum
View details →Failed Experiment ReportOpen accessComputer Science
Florian Domingo, Sebastian Paßehr · 2021 · arXiv
The connection between gauge and Higgs sectors makes supersymmetric extensions of the Standard Model predictive frameworks for the derivation of Higgs masses. In this paper, we study the contamination of such predictions by field-renormalization constants, in the MSSM with two-loop gaugeless corrections of $\mathcal{O}{\left(α_{t,b}\,α_s,\,α_{t,b}^2\right)}$ and full momentum dependence, and demonstrate how strict perturbative expansions allow to systematically neutralize the dependence on such unphysical objects. On the other hand, the popular procedure consisting in an iterative pole search
View details →Negative / Null Result ReportOpen accessComputer Science
C. Fernandez-Ramirez, A. M. Bernstein · 2012 · arXiv
With the availability of the new neutral pion photoproduction from the proton data from the A2 and CB-TAPS Collaborations at Mainz it is mandatory to revisit Heavy Baryon Chiral Perturbation Theory (HBChPT) and address the extraction of the partial waves as well as other issues such as the value of the low-energy constants, the energy range where the calculation provides a good agreement with the data and the impact of unitarity. We find that, within the current experimental status, HBChPT with the fitted LECs gives a good agreement with the existing neutral pion photoproduction data up to $\s
View details →Negative / Null Result ReportOpen accessComputer Science
Tovly Deutsch, Masoud Jasbi, Stuart Shieber · 2020 · arXiv
Readability assessment aims to automatically classify text by the level appropriate for learning readers. Traditional approaches to this task utilize a variety of linguistically motivated features paired with simple machine learning models. More recent methods have improved performance by discarding these features and utilizing deep learning models. However, it is unknown whether augmenting deep learning models with linguistically motivated features would improve performance further. This paper combines these two approaches with the goal of improving overall model performance and addressing th
View details →Negative / Null Result ReportOpen accessComputer Science
Tristan Piater, Niklas Penzel, Gideon Stein et al. · 2024 · arXiv
A substantial body of research has focused on developing systems that assist medical professionals during labor-intensive early screening processes, many based on convolutional deep-learning architectures. Recently, multiple studies explored the application of so-called self-attention mechanisms in the vision domain. These studies often report empirical improvements over fully convolutional approaches on various datasets and tasks. To evaluate this trend for medical imaging, we extend two widely adopted convolutional architectures with different self-attention variants on two different medical
View details →Negative / Null Result ReportOpen accessComputer Science
Yeskendir Koishekenov · 2023 · arXiv
Graph Neural Networks (GNNs) have achieved a lot of success with graph-structured data. However, it is observed that the performance of GNNs does not improve (or even worsen) as the number of layers increases. This effect has known as over-smoothing, which means that the representations of the graph nodes of different classes would become indistinguishable when stacking multiple layers. In this work, we propose a new simple, and efficient method to alleviate the effect of the over-smoothing problem in GNNs by explicitly using relations between node embeddings. Experiments on real-world dataset
View details →Negative / Null Result ReportOpen accessComputer Science
Seyed Amir Kasaei, Arash Marioriyad, Mahbod Khaleti et al. · 2026 · arXiv
Large Vision-Language Models (LVLMs) have achieved remarkable proficiency in explicit visual recognition, effectively describing what is directly visible in an image. However, a critical cognitive gap emerges when the visual input serves only as a clue rather than the answer. We identify that current models struggle with the complex, multi-step reasoning required to solve problems where information is not explicitly depicted. Successfully solving a rebus puzzle requires a distinct cognitive workflow: the model must extract visual and textual attributes, retrieve linguistic prior knowledge (suc
View details →Negative / Null Result ReportOpen accessComputer Science
Iva Bojic, Qi Chwen Ong, Shafiq Joty et al. · 2023 · arXiv
Non-communicable diseases (NCDs) are a leading cause of global deaths, necessitating a focus on primary prevention and lifestyle behavior change. Health coaching, coupled with Question Answering (QA) systems, has the potential to transform preventive healthcare. This paper presents a human-Artificial Intelligence (AI) health coaching model incorporating a domain-specific extractive QA system. A sleep-focused dataset, SleepQA, was manually assembled and used to fine-tune domain-specific BERT models. The QA system was evaluated using automatic and human methods. A data-centric framework enhanced
View details →Negative / Null Result ReportOpen accessComputer Science
Jan Tiemann, Matthew McGinity, Ulrik Günther · 2026 · arXiv
In contemporary biology and medicine, 3D microscopy is one of the most widely-used techniques for imaging and manipulation of various kinds of samples. Navigating such a micrometer-sized, 3-dimensional sample under the microscope -- e.g. to find relevant imaging regions -- can pose a tedious challenge for the experimenter. In this paper, we examine whether 2D desktop, 3D desktop, or Virtual Reality (VR) interfaces provide the best user experience and performance for the exploration of 3D samples. We invited 12 skilled microscope operators to perform two different exploration tasks in 2D, 3D an
View details →Failed Experiment ReportOpen accessComputer Science
Marco Pop-Mihali, Adrian Groza · 2023 · arXiv
We aim at development white-box machine learning algorithms. We focus here on algorithms for learning axioms in description logic. We extend the Class Expression Learning for Ontology Engineering (CELOE) algorithm contained in the DL-Learner tool. The approach uses multiple search trees and a shared pool of refinements in order to split the search space in smaller subspaces. We introduce the conjunction operation of best class expressions from each tree, keeping the results which give the most information. The aim is to foster exploration from a diverse set of starting classes and to streamlin
View details →Negative / Null Result ReportOpen accessComputer Science
Mitchell A. Gordon, Kevin Duh, Nicholas Andrews · 2020 · arXiv
Pre-trained universal feature extractors, such as BERT for natural language processing and VGG for computer vision, have become effective methods for improving deep learning models without requiring more labeled data. While effective, feature extractors like BERT may be prohibitively large for some deployment scenarios. We explore weight pruning for BERT and ask: how does compression during pre-training affect transfer learning? We find that pruning affects transfer learning in three broad regimes. Low levels of pruning (30-40%) do not affect pre-training loss or transfer to downstream tasks a
View details →Negative / Null Result ReportOpen accessComputer Science
Ramin Mohammadi, Sarthak Jain, Stephen Agboola et al. · 2019 · arXiv
Hypertension is a major risk factor for stroke, cardiovascular disease, and end-stage renal disease, and its prevalence is expected to rise dramatically. Effective hypertension management is thus critical. A particular priority is decreasing the incidence of uncontrolled hypertension. Early identification of patients at risk for uncontrolled hypertension would allow targeted use of personalized, proactive treatments. We develop machine learning models (logistic regression and recurrent neural networks) to stratify patients with respect to the risk of exhibiting uncontrolled hypertension within
View details →Negative / Null Result ReportOpen accessComputer Science
Hyeong Kyu Choi, Xiaojin Zhu, Sharon Li · 2025 · arXiv
Multi-Agent Debate~(MAD) has emerged as a promising paradigm for improving the performance of large language models through collaborative reasoning. Despite recent advances, the key factors driving MAD's effectiveness remain unclear. In this work, we disentangle MAD into two key components--Majority Voting and inter-agent Debate--and assess their respective contributions. Through extensive experiments across seven NLP benchmarks, we find that Majority Voting alone accounts for most of the performance gains typically attributed to MAD. To explain this, we propose a theoretical framework that mo
View details →Negative / Null Result ReportOpen accessComputer Science
AJ Alvero, Ruohong Dong, Klint Kanopka et al. · 2025 · arXiv
Computational sociology is growing in popularity, yet the analytic tools employed differ widely in power, transparency, and interpretability. In computer science, methods gain popularity after surpassing benchmarks of predictive accuracy, becoming the "state of the art." Computer scientists favor novelty and innovation for different reasons, but prioritizing technical prestige over methodological fit could unintentionally limit the scope of sociological inquiry. To illustrate, we focus on computational text analysis and revisit a prior study of college admissions essays, comparing analyses wit
View details →Failed Experiment ReportOpen accessComputer Science
Sándor Kisfaludi-Bak, Jesper Nederlof, Erik Jan van Leeuwen · 2018 · arXiv
The Planar Steiner Tree problem is one of the most fundamental NP-complete problems as it models many network design problems. Recall that an instance of this problem consists of a graph with edge weights, and a subset of vertices (often called terminals); the goal is to find a subtree of the graph of minimum total weight that connects all terminals. A seminal paper by Erickson et al. [Math. Oper. Res., 1987] considers instances where the underlying graph is planar and all terminals can be covered by the boundary of $k$ faces. Erickson et al. show that the problem can be solved by an algorithm
View details →Negative / Null Result ReportOpen accessComputer Science
Yulin Chen, He He, Chen Zhao · 2026 · arXiv
Reinforcement Learning with Verifiable Reward (RLVR) has proven effective in improving Large Language Model's (LLM) reasoning ability. However, the learning dynamics of RLVR remain underexplored. In this paper, we reveal a counterintuitive phenomenon: among hard examples that the model initially struggles with, a substantial subset remains unlearnable even when correct rollouts are present. To understand the phenomenon, we first demonstrate that existing optimization and sampling techniques fail to resolve unlearnability. With cross-example gradient analysis, we show that unlearnable examples
View details →