Negative / Null Result ReportOpen accessComputer Science
Chenming Tang, Xiuyu Wu, Yunfang Wu · 2023 · arXiv
Model ensemble has been in widespread use for Grammatical Error Correction (GEC), boosting model performance. We hypothesize that model ensemble based on the perplexity (PPL) computed by pre-trained language models (PLMs) should benefit the GEC system. To this end, we explore several ensemble strategies based on strong PLMs with four sophisticated single models. However, the performance does not improve but even gets worse after the PLM-based ensemble. This surprising result sets us doing a detailed analysis on the data and coming up with some insights on GEC. The human references of correct s
Negative / Null Result ReportOpen accessComputer Science
Guanzi Chen, Jiying Zhang, Xi Xiao et al. · 2022 · arXiv
In recent years, hypergraph learning has attracted great attention due to its capacity in representing complex and high-order relationships. However, current neural network approaches designed for hypergraphs are mostly shallow, thus limiting their ability to extract information from high-order neighbors. In this paper, we show both theoretically and empirically, that the performance of hypergraph neural networks does not improve as the number of layers increases, which is known as the over-smoothing problem. To avoid this issue, we develop a new deep hypergraph convolutional network called De
Negative / Null Result ReportOpen accessEngineering
Siqi Ye, Yong Long, Il Yong Chun · 2020 · arXiv
This paper applies the recent fast iterative neural network framework, Momentum-Net, using appropriate models to low-dose X-ray computed tomography (LDCT) image reconstruction. At each layer of the proposed Momentum-Net, the model-based image reconstruction module solves the majorized penalized weighted least-square problem, and the image refining module uses a four-layer convolutional neural network (CNN). Experimental results with the NIH AAPM-Mayo Clinic Low Dose CT Grand Challenge dataset show that the proposed Momentum-Net architecture significantly improves image reconstruction accuracy,
Negative / Null Result ReportOpen accessComputer Science
Daniel Mann, Tina Raissi, Wilfried Michel et al. · 2023 · arXiv
We investigate a novel modeling approach for end-to-end neural network training using hidden Markov models (HMM) where the transition probabilities between hidden states are modeled and learned explicitly. Most contemporary sequence-to-sequence models allow for from-scratch training by summing over all possible label segmentations in a given topology. In our approach there are explicit, learnable probabilities for transitions between segments as opposed to a blank label that implicitly encodes duration statistics. We implement a GPU-based forward-backward algorithm that enables the simultaneou
Negative / Null Result ReportOpen accessAgricultural and Biological Sciences
Roy Henha Eyono, Daniel Levenstein, Arna Ghosh et al. · 2026 · arXiv
Normalization is a critical operation in neural circuits. In the brain, there is evidence that normalization is implemented via inhibitory interneurons and allows neural populations to adjust to changes in the distribution of their inputs. In artificial neural networks (ANNs), normalization is used to improve learning in tasks that involve complex input distributions. However, it is unclear whether inhibition-mediated normalization in biological neural circuits also improves learning. Here, we explore this possibility using ANNs with separate excitatory and inhibitory populations trained on an
Negative / Null Result ReportOpen accessPhysics
Susanne Still, David A. Sivak, Anthony J. Bell et al. · 2012 · arXiv
A system responding to a stochastic driving signal can be interpreted as computing, by means of its dynamics, an implicit model of the environmental variables. The system's state retains information about past environmental fluctuations, and a fraction of this information is predictive of future ones. The remaining nonpredictive information reflects model complexity that does not improve predictive power, and thus represents the ineffectiveness of the model. We expose the fundamental equivalence between this model inefficiency and thermodynamic inefficiency, measured by dissipation. Our result
Negative / Null Result ReportOpen accessComputer Science
M. M. Sargsian, S. Simula, M. I. Strikman · 2002 · arXiv
A detailed study of inclusive deep inelastic scattering from mirror A = 3 nuclei at large values of Bjorken-x is presented. The main purpose is to estimate the theoretical uncertainties on the extraction of F2n from such measurements. Within the convolution approach we confirm the cancellation of nuclear effects at the level of ~1 % for x < 0.75 in overall agreement with previous findings. However, within models in which modifications of the bound nucleon structure functions are accounted for to describe the EMC effect in nuclei, we find that the nuclear effects may be canceled at a level of ~
Negative / Null Result ReportOpen accessComputer Science
Solène Tarride, Tristan Faine, Mélodie Boillet et al. · 2023 · arXiv
In this paper, we explore different ways of training a model for handwritten text recognition when multiple imperfect or noisy transcriptions are available. We consider various training configurations, such as selecting a single transcription, retaining all transcriptions, or computing an aggregated transcription from all available annotations. In addition, we evaluate the impact of quality-based data selection, where samples with low agreement are removed from the training set. Our experiments are carried out on municipal registers of the city of Belfort (France) written between 1790 and 1946
Negative / Null Result ReportOpen accessPhysics
Ilias Magoulas, Karthik Gururangan, Piotr Piecuch et al. · 2021 · arXiv
The short answer to the question in the title is 'no'. We identify classes of truncated configuration interaction (CI) wave functions for which the externally corrected coupled-cluster (ec-CC) approach using the three-body ($T_{3}$) and four-body ($T_{4}$) components of the cluster operator extracted from CI does not improve the results of the underlying CI calculations. Implications of our analysis, illustrated by numerical examples, for the ec-CC computations using truncated and selected CI methods are discussed. We also introduce a novel ec-CC approach using the $T_{3}$ and $T_{4}$ amplitud
Negative / Null Result ReportOpen accessComputer Science
Syomantak Chaudhuri, Thomas A. Courtade · 2023 · arXiv
Differential Privacy (DP) is a well-established framework to quantify privacy loss incurred by any algorithm. Traditional DP formulations impose a uniform privacy requirement for all users, which is often inconsistent with real-world scenarios in which users dictate their privacy preferences individually. This work considers the problem of mean estimation under heterogeneous DP constraints, where each user can impose their own distinct privacy level. The algorithm we propose is shown to be minimax optimal when there are two groups of users with distinct privacy levels. Our results elicit an in
Negative / Null Result ReportOpen accessComputer Science
T. C. Liu, M. A. Huang, Guey-Lin Lin · 2010 · arXiv
We discuss the reconstruction of neutrino flavor neutrino at a distant source in the very high en- ergy regime. This reconstruction procedure is relevant to the confirmation of detecting cosmogenic neutrinos, for example. To facilitate such a reconstruction, it is imperative to achieve effective flavor discriminations in terrestrial neutrino telescopes. We note that, for energies beyond few tens of PeV, a tau-lepton behaves like a track similar to a muon. Hence, while it is rather challenging to separate νμ from ντ in this case, one can expect to isolate νe from the rest by a distinctive showe
Negative / Null Result ReportOpen accessComputer Science
Seyed Arash Ghoreishi, Nidhin Sudarsanan Ragini, Sk Sazim et al. · 2024 · arXiv
Quantum labeling tasks ask one to recover the missing associations between classical outcome labels and the effects forming the POVM. We study labeling in the multiple-shot regime, allowing a finite number of uses of the device and the most general tester-based strategies, including adaptivity. For binary observables, we show that if perfect labeling is impossible in a single shot, then it remains impossible with any finite number of shots. In particular, we derive the formula for minimum-error performance and highlight its ``even-odd" behavior. For non-binary observables, we derive the optima
Negative / Null Result ReportOpen accessPhysics
Lehman H. Garrison, Michael Joyce, Daniel J. Eisenstein · 2021 · arXiv
Analysis of self-similarity in scale-free $N$-body simulations reveals the spatial and temporal scales for which statistics measured in cosmological simulations are converged to the physical continuum limit. We examine how the range of scales in which the two-point correlation function is converged depends on the force softening length and whether it is held constant in comoving or proper coordinates. We find that a proper softening that reaches roughly 1/30th of the inter-particle spacing by the end of the simulation resolves the same spatial and temporal scales as a comoving softening of the
Negative / Null Result ReportOpen accessComputer Science
Michele Filannino, Gavin Brown, Goran Nenadic · 2013 · arXiv
This paper describes a temporal expression identification and normalization system, ManTIME, developed for the TempEval-3 challenge. The identification phase combines the use of conditional random fields along with a post-processing identification pipeline, whereas the normalization phase is carried out using NorMA, an open-source rule-based temporal normalizer. We investigate the performance variation with respect to different feature types. Specifically, we show that the use of WordNet-based features in the identification task negatively affects the overall performance, and that there is no
Negative / Null Result ReportOpen accessComputer Science
Marc-Antoine Allard, Matin Ansaripour, Maria Yuffa et al. · 2024 · arXiv
Large Language Models (LLMs) often struggle with tasks requiring mathematical reasoning, particularly multiple-choice questions (MCQs). To address this issue, we developed LLaMa-SciQ, an educational chatbot designed to assist college students in solving and understanding MCQs in STEM fields. We begin by fine-tuning and aligning the models to human preferences. After comparing the performance of Mistral-7B and LLaMa-8B, we selected the latter as the base model due to its higher evaluation accuracy. To further enhance accuracy, we implement Retrieval-Augmented Generation (RAG) and apply quantiza
Negative / Null Result ReportOpen accessComputer Science
Matthias Otth, Jonas Hübotter, Ido Hakimi et al. · 2025 · arXiv
Recent work has shown that language models can self-improve by maximizing their own confidence in their predictions, without relying on external verifiers or reward signals. In this work, we study the test-time scaling of language models for mathematical reasoning tasks, where the model's own confidence is used to select the most promising attempts. Surprisingly, we find that we can achieve significant performance gains by continuing only the most promising attempt, selected by the model's prefix-confidence. We systematically evaluate prefix-confidence scaling on five mathematical reasoning da
Negative / Null Result ReportOpen accessComputer Science
Yuto Nishida, Makoto Morishita, Hiroyuki Deguchi et al. · 2025 · arXiv
The $k$-nearest-neighbor language model ($k$NN-LM), one of the retrieval-augmented language models, improves the perplexity for given text by directly accessing a large datastore built from any text data during inference. A widely held hypothesis for the success of $k$NN-LM is that its explicit memory, i.e., the datastore, enhances predictions for long-tail phenomena. However, prior works have primarily shown its ability to retrieve long-tail contexts, leaving the model's performance remain underexplored in estimating the probabilities of long-tail target tokens during inference. In this paper
Negative / Null Result ReportOpen accessComputer Science
Hassan Bassereh, Vahid Salari, Farhad Shahbazi et al. · 2015 · arXiv
We consider quantum excitation energy transport (EET) in a network of two-state nodes in the Markovian approximation by employing the Lindblad formulation. We find that EET from an initial site, where the excitation is inserted to the sink, is generally inefficient due to the inhibition of transport by localization of the excitation wave packet in a symmetric, fully-connected network. We demonstrate that the EET efficiency can be significantly increased up to %100 by perturbing hopping transport between the initial node and the one connected directly to the sink, while the rate of energy trans
Negative / Null Result ReportOpen accessComputer Science
Hugo Meric, Jose Miguel Piquer · 2013 · arXiv
We study the design of a DVB-S2 system in order to maximise spectrum efficiency. This task is usually challenging due to channel variability. Modern satellite communications systems such as DVB-SH and DVB-S2 rely mainly on a time sharing strategy to optimise the spectrum efficiency. Recently, we showed that combining time sharing with hierarchical modulation can provide significant gains (in terms of spectrum efficiency) compared to the best time sharing strategy. However, our previous design does not improve the DVB-S2 performance when all the receivers experience low or large signal-to-noise
Negative / Null Result ReportOpen accessComputer Science
Samuel F. Dodge, Lina J. Karam · 2013 · arXiv
The human visual system employs a selective attention mechanism to understand the visual world in an eficient manner. In this paper, we show how computational models of this mechanism can be exploited for the computer vision application of scene recognition. First, we consider saliency weighting and saliency pruning, and provide a comparison of the performance of different attention models in these approaches in terms of classification accuracy. Pruning can achieve a high degree of computational savings without significantly sacrificing classification accuracy. In saliency weighting, however,
Negative / Null Result ReportOpen accessComputer Science
Taisuke Kobayashi · 2020 · arXiv
This paper proposes a new optimizer for deep learning, named d-AmsGrad. In the real-world data, noise and outliers cannot be excluded from dataset to be used for learning robot skills. This problem is especially striking for robots that learn by collecting data in real time, which cannot be sorted manually. Several noise-robust optimizers have therefore been developed to resolve this problem, and one of them, named AmsGrad, which is a variant of Adam optimizer, has a proof of its convergence. However, in practice, it does not improve learning performance in robotics scenarios. This reason is h
Negative / Null Result ReportOpen accessComputer Science
Domenic Rosati · 2023 · arXiv
Communication of scientific findings to the public is important for keeping non-experts informed of developments such as life-saving medical treatments. However, generating readable lay summaries from scientific documents is challenging, and currently, these summaries suffer from critical factual errors. One popular intervention for improving factuality is using additional external knowledge to provide factual grounding. However, it is unclear how these grounding sources should be retrieved, selected, or integrated, and how supplementary grounding documents might affect the readability or rele
Negative / Null Result ReportOpen accessComputer Science
Ushak Rahaman, Soebur Razzaque · 2021 · arXiv
The $ν_μ\to ν_e$ oscillation probability over short baseline ($\lesssim 1$~km) would be negligible in case the mixing matrix for three active neutrinos is unitary. However, in case of non-unitary mixing of three neutrinos, this probability would be non-negligible due to the so-called "zero distance" effect. Hence, the near detector of the accelerator experiments such as NO$ν$A can provide strong constraints on the parameters of the non-unitary mixing with very large statistics. By analyzing the NO$ν$A near detector data we find that the non-unitary mixing does not improve fits to the $ν_e$ or
Negative / Null Result ReportOpen accessComputer Science
Ewout van den Berg, Michael P. Friedlander · 2009 · arXiv
The joint-sparse recovery problem aims to recover, from sets of compressed measurements, unknown sparse matrices with nonzero entries restricted to a subset of rows. This is an extension of the single-measurement-vector (SMV) problem widely studied in compressed sensing. We analyze the recovery properties for two types of recovery algorithms. First, we show that recovery using sum-of-norm minimization cannot exceed the uniform recovery rate of sequential SMV using $\ell_1$ minimization, and that there are problems that can be solved with one approach but not with the other. Second, we analyze
Negative / Null Result ReportMedicine
Orhan B, Nauta M · 2026 · Death studies
Meaning Management Theory suggests that engaging with meaning-related resources helps individuals constructively regulate consciously experienced death anxiety. Consistent with that theory, we tested whether a single-session, online…
View details →DOI: 10.1080/07481187.2026.2659888 Negative / Null Result ReportOpen accessAgricultural and Biological Sciences
Louis Jalouzot, Alexis Thual, Yair Lakretz et al. · 2025 · arXiv
We investigate optimal strategies for decoding perceived natural speech from fMRI data acquired from a limited number of participants. Leveraging Lebel et al. (2023)'s dataset of 8 participants, we first demonstrate the effectiveness of training deep neural networks to predict LLM-derived text representations from fMRI activity. Then, in this data regime, we observe that multi-subject training does not improve decoding accuracy compared to single-subject approach. Furthermore, training on similar or different stimuli across subjects has a negligible effect on decoding accuracy. Finally, we fin
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
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
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
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
