Negative / Null Result ReportOpen accessComputer Science
Óscar García-Sierra, Ana Fernández-Pampillón Cesteros, Miguel Ortega-Martín · 2024 · arXiv
Subword tokenization algorithms used by Large Language Models are significantly more efficient and can independently build the necessary vocabulary of words and subwords without human intervention. However, those subwords do not always align with real morphemes, potentially impacting the models' performance, though it remains uncertain when this might occur. In previous research, we proposed a method to assess the morphological quality of vocabularies, focusing on the overlap between these vocabularies and the morphemes of a given language. Our evaluation method was built on three quality meas
View details →Negative / Null Result ReportOpen accessComputer Science
Bob de Ruiter · 2023 · arXiv
In many fields of experimental science, papers that failed to replicate continue to be cited as a result of the poor discoverability of replication studies. As a first step to creating a system that automatically finds replication studies for a given paper, 334 replication studies and 344 replicated studies were collected. Replication studies could be identified in the dataset based on text content at a higher rate than chance (AUROC = 0.886). Additionally, successful replication studies could be distinguished from failed replication studies at a higher rate than chance (AUROC = 0.664).
View details →Negative / Null Result ReportOpen accessComputer Science
James Kirby, Ioana Krehan, Michele Gubian · 2026 · arXiv
This study examines the extent to which the wav2vec2.0 architecture exhibits evidence of compensation for phonological context. We conducted a pseudo-replication of a perceptional compensation experiment on Mandarin Chinese tones, and compared the embedding similarities and probing classifier outputs between a purely self-supervised pre-trained model and a model fine-tuned for Mandarin ASR. No evidence of compensation was found in the embedding similarities of the purely pre-trained model. Probing classifiers showed some evidence of compensation in addition to the expected layer-wise improveme
View details →Negative / Null Result ReportOpen accessComputer Science
Robert McCarthy, Daniel C. H. Tan, Dominik Schmidt et al. · 2024 · arXiv
Scaling deep learning to massive and diverse internet data has driven remarkable breakthroughs in domains such as video generation and natural language processing. Robot learning, however, has thus far failed to replicate this success and remains constrained by a scarcity of available data. Learning from videos (LfV) methods aim to address this data bottleneck by augmenting traditional robot data with large-scale internet video. This video data provides foundational information regarding physical dynamics, behaviours, and tasks, and can be highly informative for general-purpose robots. This su
View details →Negative / Null Result ReportOpen accessComputer Science
Jaroslaw Kornowicz · 2024 · arXiv
This study empirically examines the "Evaluative AI" framework, which aims to enhance the decision-making process for AI users by transitioning from a recommendation-based approach to a hypothesis-driven one. Rather than offering direct recommendations, this framework presents users pro and con evidence for hypotheses to support more informed decisions. However, findings from the current behavioral experiment reveal no significant improvement in decision-making performance and limited user engagement with the evidence provided, resulting in cognitive processes similar to those observed in tradi
View details →Negative / Null Result ReportOpen accessComputer Science
Karam Ahmed, Sherif Abuelenin, Heba Soliman et al. · 2015 · arXiv
V-BLAST detection method suffers large computational complexity due to its successive detection of symbols. In this paper, we propose a modified V-BLAST algorithm to decrease the computational complexity by reducing the number of detection iterations required in MIMO communication systems. We begin by showing the existence of a maximum number of iterations, beyond which, no significant improvement is obtained. We establish a criterion for the number of maximum effective iterations. We propose a modified algorithm that uses the measured SNR to dynamically set the number of iterations to achieve
View details →Negative / Null Result ReportOpen accessComputer Science
Alp Atici · 2003 · arXiv
It is an established fact that for many of the interesting problems quantum algorithms based on queries of the standard oracle bring no significant improvement in comparison to known classical algorithms. It is conceivable that there are other oracles of algorithmic importance acting in a less intuitive fashion to which such limitations do not apply. Thus motivated this article suggests a broader understanding towards what a general quantum oracle is. We propose a general definition of a quantum oracle and give a classification of quantum oracles based on the behavior of the eigenvalues and ei
View details →Negative / Null Result ReportOpen accessComputer Science
James Large, Paul Southam, Anthony Bagnall · 2018 · arXiv
tl;dr: no, it cannot, at least not on average on the standard archive problems. We assess whether using six smoothing algorithms (moving average, exponential smoothing, Gaussian filter, Savitzky-Golay filter, Fourier approximation and a recursive median sieve) could be automatically applied to time series classification problems as a preprocessing step to improve the performance of three benchmark classifiers (1-Nearest Neighbour with Euclidean and Dynamic Time Warping distances, and Rotation Forest). We found no significant improvement over unsmoothed data even when we set the smoothing param
View details →Negative / Null Result ReportOpen accessComputer Science
J. Bouchez · 2000 · arXiv
We show that the unified method recently proposed by Feldman and Cousins to put confidence intervals on bounded parameters cannot avoid the possibility of getting null results. A modified bayesian approach is also proposed (although not advocated) which ensures no null results and proper coverage.
View details →Negative / Null Result ReportOpen accessComputer Science
Hao Guo, Han Wang, Di Zhu et al. · 2025 · arXiv
Modeling spatial heterogeneity in the data generation process is essential for understanding and predicting geographical phenomena. Despite their prevalence in geospatial tasks, neural network models usually assume spatial stationarity, which could limit their performance in the presence of spatial process heterogeneity. By allowing model parameters to vary over space, several approaches have been proposed to incorporate spatial heterogeneity into neural networks. However, current geographically weighting approaches are ineffective on graph neural networks, yielding no significant improvement
View details →Negative / Null Result ReportOpen accessComputer Science
Hoyeon Chang, Jinho Park, Seonghyeon Ye et al. · 2024 · arXiv
Despite the recent observation that large language models (LLMs) can store substantial factual knowledge, there is a limited understanding of the mechanisms of how they acquire factual knowledge through pretraining. This work addresses this gap by studying how LLMs acquire factual knowledge during pretraining. The findings reveal several important insights into the dynamics of factual knowledge acquisition during pretraining. First, counterintuitively, we observe that pretraining on more data shows no significant improvement in the model's capability to acquire and maintain factual knowledge.
View details →Negative / Null Result ReportOpen accessComputer Science
Ivan Silajev, Niels Victor, Phillip Mortimer · 2022 · arXiv
This paper presents an application of the LayoutLMv3 model for semantic table detection on financial documents from the IIIT-AR-13K dataset. The motivation behind this paper's experiment was that LayoutLMv3's official paper had no results for table detection using semantic information. We concluded that our approach did not improve the model's table detection capabilities, for which we can give several possible reasons. Either the model's weights were unsuitable for our purpose, or we needed to invest more time in optimising the model's hyperparameters. It is also possible that semantic inform
View details →Negative / Null Result ReportOpen accessComputer Science
Anam Zahra, Pierre-Etienne Martin · 2021 · arXiv
This paper presents a table tennis stroke detection method from videos. The method relies on a two-stream Convolutional Neural Network processing in parallel the RGB Stream and its computed optical flow. The method has been developed as part of the MediaEval 2021 benchmark for the Sport task. Our contribution did not outperform the provided baseline on the test set but has performed the best among the other participants with regard to the mAP metric.
View details →Negative / Null Result ReportOpen accessComputer Science
Bob de Ruiter · 2021 · arXiv
The goal of this study was to improve the post-processing of precipitation forecasts using convolutional neural networks (CNNs). Instead of post-processing forecasts on a per-pixel basis, as is usually done when employing machine learning in meteorological post-processing, input forecast images were combined and transformed into probabilistic output forecast images using fully convolutional neural networks. CNNs did not outperform regularized logistic regression. Additionally, an ablation analysis was performed. Combining input forecasts from a global low-resolution weather model and a regiona
View details →Negative / Null Result ReportOpen accessComputer Science
Arvid Frydenlund · 2024 · arXiv
The recently introduced path-star task is a minimal task designed to exemplify limitations to the abilities of language models (Bachmann and Nagarajan, 2024). It involves a path-star graph where multiple arms radiate from a single starting node and each node is unique. Given the start node and a specified target node that ends an arm, the task is to generate the arm containing that target node. This is straightforward for a human but surprisingly difficult for language models, which did not outperform the random baseline. The authors hypothesized this is due to a deficiency in teacher-forcing
View details →Negative / Null Result ReportOpen accessComputer Science
Haresh Rengaraj Rajamohan, Yuxuan Chen, Kyunghyun Cho et al. · 2026 · arXiv
This study assesses whether self-supervised learning (SSL) improves knee osteoarthritis (OA) modeling for diagnosis and prognosis relative to ImageNet-pretrained initialization. We compared (i) image-only SSL pretrained on knee radiographs from the OAI, MOST, and NYU cohorts, and (ii) multimodal image-text SSL pretrained on hospital knee radiographs paired with radiologist impressions. For diagnostic Kellgren-Lawrence (KL) grade prediction, SSL yielded mixed results. While image-only SSL improved accuracy during linear probing (frozen encoder), it did not outperform ImageNet pretraining during
View details →Negative / Null Result ReportOpen accessComputer Science
C. Giunti · 1998 · arXiv
Several possible statistical interpretations of the null result of the KARMEN 2 neutrino oscillation experiment are discussed with the aim of clarifying the implications of the fact that KARMEN 2 did not observe any of the expected background events. The formalism that allows to take into account the error of the expected mean background in a Poisson process with background is presented and applied to the statistical analysis of the KARMEN 2 null result. The possibility of ignoring the expected mean background calculated for the KARMEN 2 experiment is discussed and it is shown that the resulti
View details →Negative / Null Result ReportOpen accessComputer Science
Zhi-zhong Xing, Zhen-hua Zhao, Ye-Ling Zhou · 2015 · arXiv
The Majorana nature of massive neutrinos will be crucially probed in the next-generation experiments of the neutrinoless double-beta ($0ν2β$) decay. The effective mass term of this process, $\langle m\rangle^{}_{ee}$, may be contaminated by new physics. So how to interpret a discovery or null result of the $0ν2β$ decay in the foreseeable future is highly nontrivial. In this paper we introduce a novel three-dimensional description of $|\langle m\rangle_{ee}^{}|$, which allows us to see its sensitivity to the lightest neutrino mass and two Majorana phases in a transparent way. We take a look at
View details →Negative / Null Result ReportOpen accessComputer Science
J. E. Ottoni, A. P. Baeta Scarpelli, Marcos Sampaio et al. · 2006 · arXiv
We apply Implicit regularization in the calculation of the one-loop graviton and gravitino corrections to the anomalous magnetic moment of the lepton in unbroken supergravity, which is known to be an important test for any regularization method. We find a null result as it is expected from supersymmetry. We compare our results with the ones obtained by using Differential Regularization and Dimensional Reduction, which are known to preserve supersymmetry at one-loop order.
View details →Negative / Null Result ReportOpen accessComputer Science
Q. Riffard, F. Mayet, G. Bélanger et al. · 2016 · arXiv
The comparison of the results of direct detection of Dark Matter, obtained with various target nuclei, requires model-dependent, or even arbitrary, assumptions. Indeed, to draw conclusions either the spin-dependent (SD) or the spin-independent (SI) interaction has to be neglected. In the light of the null results from supersymmetry searches at the LHC, the squark sector is pushed to high masses. We show that for a squark sector at the TeV scale, the framework used to extract contraints from direct detection searches can be redefined as the number of free parameters is reduced. Moreover, the co
View details →Negative / Null Result ReportOpen accessComputer Science
F. W. Sun, Z. Y. Ou, G. C. Guo · 2005 · arXiv
We construct a projection measurement process for the maximally entangled N-photon state (the NOON-state) with only linear optical elements and photodetectors. This measurement process will give null result for any N-photon state that is orthogonal to the NOON state. We examine the projection process in more detail for N=4 by applying it to a four-photon state from type-II parametric down-conversion. This demonstrates an orthogonal projection measurement with a null result. This null result corresponds to a dip in a generalized Hong-Ou-Mandel interferometer for four photons. We find that the d
View details →Negative / Null Result ReportOpen accessComputer Science
Giuseppe Bimonte · 2019 · arXiv
A recent experiment [R. A. Norte et al. Phys. Rev. Lett. {\bf 121}, 030405 (2018)] probed the variation of the Casimir force between two closely spaced thin Al films, as they transition into a superconducting state, observing a null result. We present here computations of the Casimir effect for superconductors, based on the Mattis-Bardeen formula for their optical response. We show that for the Al cavity used in the experiment the effect of the transition is over two hundred and fifty times smaller than the experimental sensitivity, in agreement with the observed null result. We demonstrate th
View details →Negative / Null Result ReportOpen accessComputer Science
H. C. Eggers, B. Buschbeck · 2013 · arXiv
A detailed understanding of all effects and influences on higher-order correlations is essential. At low charged multiplicity, the effect of a nonpoissonian multiplicity distribution can significantly distort correlations. Evidently, the reference samples with respect to which correlations are measured should yield a null result in the absence of correlations. We show how the careful specification of desired properties necessarily leads to an average-of-multinomials reference sample. The resulting internal cumulants and their averaging over several multiplicities fulfil all requirements of cor
View details →Negative / Null Result ReportOpen accessComputer Science
Soichiro Kuwahara, Kipp Cannon · 2023 · arXiv
We previously described the development of a detection system for a novel class of transient gravitational-wave sources taking the form of Cherenkov-like bursts. Here, we have applied the system to the data of the LIGO/Virgo/KAGRA O3 science run, and report a null result. The ad hoc waveform model is motivated by the conjectured emission of gravitational waves from a curvature source moving at super-luminal speed, and while there is no plausible natural or artificial source of such waves, we nevertheless use the null result to infer a tongue-in-cheek upper bound on the number density of near-E
View details →Negative / Null Result ReportOpen accessComputer Science
A. Boveia · 2009 · arXiv
I describe recent signature-based searches for anomalous physics processes using up to 2.9/fb of data from the CDF or D0 detectors at the Fermilab Tevatron. While each search conveys its sensitivity by interpreting a null result in terms of one or more specific exotic models, the searches are designed to be broadly sensitive to many models.
View details →Negative / Null Result ReportOpen accessComputer Science
L. Cooper, G. E. Stedman · 1995 · arXiv
A ring-laser experiment, similar to the Canterbury ring laser, to detect axion- and {\sc qed}-induced vacuum birefringence is proposed. It uses a slowly modulated magnetic field and a novel polarization geometry. Both axion coupling and vacuum birefringence would modulate the Sagnac beat frequency. A null result could place sensitive bounds on the axion mass and on two-photon coupling.
View details →Negative / Null Result ReportOpen accessComputer Science
Andy Hocker · 1999 · arXiv
The most recently available results from searches conducted by the four LEP experiments at 189 GeV center-of-mass energy for Higgs bosons of the Minimal Supersymmetric Standard Model (MSSM) are presented. No evidence for a signal has been observed, and the null result is used by the experiments, both individually and collectively, to exclude regions of the MSSM parameter space and to set lower limits on Higgs boson masses at 95% confidence level in constrained MSSM scenarios.
View details →Negative / Null Result ReportOpen accessComputer Science
G. Kaelbermann, J. M. Eisenberg, Andreas Schaefer · 1994 · arXiv
It is well known that in lowest order the skyrmion model of the nucleon gives vanishing spin content. With new data indicating a proton spin content $ΔΣ= 0.22\pm 0.14,$ it is an increasing challenge to find ways in which the skyrmion can move away from the null result. We show here that a particular term in the skyrmion lagrangian in SU(3) involving six derivatives of the field can, with plausible parameters, yield a spin content consistent with present experiment.
View details →Negative / Null Result ReportOpen accessComputer Science
CDF Collaboration · 2006 · arXiv
We present the results of a search for new physics in the jets plus missing transverse energy data sample collected from 368 pb^{-1} of ppbar collisions at sqrt{s}=1.96 TeV recorded by the Collider Detector at Fermilab. We compare the number of events observed in the data with a data-based estimate of the Standard Model backgrounds contributing to this signature. We observe no significant excess of events, and we interpret this null result in terms of lower limits on the fundamental Planck scale for a large extra dimensions scenario.
View details →Negative / Null Result ReportOpen accessComputer Science
Kargi Chauhan · 2026 · arXiv
AI scientist systems are beginning to automate the production, evaluation, and iteration of scientific hypotheses. Their promise is speed; their risk is that speed also scales errors embedded in the scientific record. We argue that a near-term risk is corpus failure: AI scientist systems are trained on and grounded in a literature that over-represents positive results and under-represents null findings. We formalise this distortion as the null result gap, estimate it across three domains (drug discovery ~0.60, psychology ~0.56, cancer biology ~0.35), and introduce an amplification index for re
View details →