This study examines the choices made by Large Language Models (LLMs) when selecting professional candidates for a job based on their résumés or curricula vitae (CVs). In an experiment involving 22 leading LLMs, each model was systematically given a job description along with a pair of profession-matched CVs—one bearing a male first name, the other a female first name—and asked to select the more suitable candidate for the job. Each CV pair was presented twice, with names swapped to ensure that any observed preferences in candidate selection stemmed from gendered names cues. Despite equalized professional qualifications between genders, all LLMs consistently favored female-named candidates across 70 different professions. Adding an explicit gender field (male/female) to the CVs further increased the preference for female applicants. When gendered names were replaced with gender-neutral identifiers ( i.e ., Candidate A/B), several models displayed a slight preference for selecting “Candidate A”. Counterbalancing gender assignment between these gender-neutral identifiers resulted in gender parity in candidate selection. When asked to rate CVs in isolation rather than compare pairs, LLMs assigned slightly higher average scores to female CVs overall, but the effect size was negligible. Including preferred pronouns (he/him or she/her) next to a candidate’s name slightly increased the odds of the candidate being selected. Finally, most models exhibited a substantial positional bias to select the candidate listed first in the prompt. These findings underscore the need for caution when deploying LLMs in high-stakes autonomous decision-making contexts and raise doubts about whether LLMs consistently apply principled reasoning.
The rapid growth of advanced large language models challenges the authenticity of scientific work, which requires reliable methods for detecting AI-generated scientific text. This paper addresses this challenge by developing and evaluating an efficient text classifier. We first constructed a balanced dataset, focusing initially on the Computer Vision (cs.CV) domain, and subsequently expanding it to include four additional diverse scientific domains (totaling 5,000 abstracts), using human-written samples from arXiv and corresponding AI-generated versions created using Google’s Gemini 2.0 Flash. We then fine-tuned a lightweight Transformer model, DistilBERT, for the classification task. On the primary in-domain (cs.CV) test set, our approach achieved excellent performance, with an accuracy of 99.4% and an Area Under the ROC Curve of 0.9999. Subsequent cross-domain evaluations demonstrated robust generalization (Macro-F1 = 0.948). Further analysis revealed that our model surpasses traditional machine learning baselines not only in accuracy but also in robustness, as it learns deep semantic patterns rather than relying on superficial statistical cues. This work provides a practical, high-performance tool for safeguarding scientific authenticity and establishes a valuable benchmark for future research in AI text detection.
Mohammad Ali Aazami, Maryam Maleki, Farzad Rasouli
et al.
AbstractSalinity is one of the most important abiotic stresses that reduce plant growth and performance by changing physiological and biochemical processes. In addition to improving the crop, using nanomaterials in agriculture can reduce the harmful effects of environmental stresses, particularly salinity. A factorial experiment was conducted in the form of a completely randomized design with two factors including salt stress at three levels (0, 50, and 100 mM NaCl) and chitosan-salicylic acid nanocomposite at three levels (0, 0.1, and 0.5 mM). The results showed reductions in chlorophylls (a, b, and total), carotenoids, and nutrient elements (excluding sodium) while proline, hydrogen peroxide, malondialdehyde, total soluble protein, soluble carbohydrate, total antioxidant, and antioxidant enzymes activity increased with treatment chitosan-salicylic acid nanocomposite (CS-SA NCs) under different level NaCl. Salinity stress reduced Fm', Fm, and Fv/Fm by damage to photosynthetic systems, but treatment with CS-SA NCs improved these indices during salinity stress. In stress-free conditions, applying the CS-SA NCs improved the grapes' physiological, biochemical, and nutrient elemental balance traits. CS-SA NCs at 0.5 mM had a better effect on the studied traits of grapes under salinity stress. The CS-SA nanoparticle is a biostimulant that can be effectively used to improve the grape plant yield under salinity stress.
Carlos Contreras, Jorge Albuja-Sánchez, Oswaldo Proaño
et al.
This study shows the influence of the inclusion of abaca fiber (Musa Textilis) on the coefficients of consolidation, expansion, and compression for normally consolidated clayey silt organic soil specimens using reconstituted samples. For this purpose, abaca fiber was added according to the dry mass of the soil, in lengths (5, 10, and 15 mm) and concentrations (0.5, 1.0, and 1.5%) subjected to a curing process with sodium hydroxide (NaOH). The virgin and fiber-added soil samples were reconstituted as slurry, and one-dimensional consolidation tests were performed in accordance with ASTM D2435. The results showed a reduction in void ratio (compared to the soil without fiber) and an increase in the coefficient of consolidation (Cv) as a function of fiber concentration and length, with values corresponding to 1.5% and 15 mm increasing from 75.16 to 144.51 cm2/s. Although no significant values were obtained for the compression and expansion coefficients, it was assumed that the soil maintained its compressibility. The statistical analysis employed hierarchical linear models to assess the significance of the effects of incorporating fibers of varying lengths and percentages on the coefficients, comparing them with the control samples. Concurrently, mixed linear models were utilized to evaluate the influence of the methods for obtaining the Cv, revealing that Taylor’s method yielded more conservative values, whereas the Casagrande method produced higher values.
Citations are a key ingredient of scientific research to relate a paper to others published in the community. Recently, it has been noted that there is a citation age bias in the Natural Language Processing (NLP) community, one of the currently fastest growing AI subfields, in that the mean age of the bibliography of NLP papers has become ever younger in the last few years, leading to `citation amnesia' in which older knowledge is increasingly forgotten. In this work, we put such claims into perspective by analyzing the bibliography of $\sim$300k papers across 15 different scientific fields submitted to the popular preprint server Arxiv in the time period from 2013 to 2022. We find that all AI subfields (in particular: cs.AI, cs.CL, cs.CV, cs.LG) have similar trends of citation amnesia, in which the age of the bibliography has roughly halved in the last 10 years (from above 12 in 2013 to below 7 in 2022), on average. Rather than diagnosing this as a citation age bias in the NLP community, we believe this pattern is an artefact of the dynamics of these research fields, in which new knowledge is produced in ever shorter time intervals.
Christoph Leiter, Jonas Belouadi, Yanran Chen
et al.
The NLLG (Natural Language Learning&Generation) arXiv reports assist in navigating the rapidly evolving landscape of NLP and AI research across cs.CL, cs.CV, cs.AI, and cs.LG categories. This fourth installment captures a transformative period in AI history - from January 1, 2023, following ChatGPT's debut, through September 30, 2024. Our analysis reveals substantial new developments in the field - with 45% of the top 40 most-cited papers being new entries since our last report eight months ago and offers insights into emerging trends and major breakthroughs, such as novel multimodal architectures, including diffusion and state space models. Natural Language Processing (NLP; cs.CL) remains the dominant main category in the list of our top-40 papers but its dominance is on the decline in favor of Computer vision (cs.CV) and general machine learning (cs.LG). This report also presents novel findings on the integration of generative AI in academic writing, documenting its increasing adoption since 2022 while revealing an intriguing pattern: top-cited papers show notably fewer markers of AI-generated content compared to random samples. Furthermore, we track the evolution of AI-associated language, identifying declining trends in previously common indicators such as"delve".
At CV. CS Lestari Jaya, a decline in sales is evident due to a continuous decrease in customer purchases. This drop in customer purchasing decisions may be linked to the company's limited use of e-commerce and digital marketing strategies. The aim of this study is to assess how the use of e-commerce and digital marketing can influence customer purchasing decisions at CV. CS Lestari Jaya Kisaran. This research is quantitative in nature, with a population of 149 customers who made purchases at CV. CS Lestari Jaya Kisaran in 2023. The sample size was determined using the Slovin formula with a 5% standard error, resulting in 109 samples. The findings indicate that both e-commerce and digital marketing have a significant impact on customer purchasing decisions, both individually and together. To enhance customer purchasing decisions, it is crucial for CV. CS Lestari Jaya Kisaran to effectively leverage e-commerce platforms and digital marketing strategies. Furthermore, running targeted paid advertising campaigns on these platforms can help reach specific audiences based on demographics and interests, increasing the likelihood of conversions
Checco, A., L. Bracciale, P. Loreti, S. Pinfield, and G. Bianchi. 2021. AI-assisted Peer review. Humanities & Social Sciences Communications 8. doi:10.1057/s41599020-00703-8. Flaherty, C. 2022. The peer-review crisis. Inside Higher Ed [Online]. Available: https://www.insidehighered.com/ news/2022/06/13/peer-review-crisis-creates-problems-jou rnals-and-scholars [Accessed 06/08/2023]. Mclean, S., G. J. M. Read, J. Thompson, C. Baber, N. A. Stanton, and P. M. Salmon. 2023. The risks associated with artificial general intelligence: A systematic review. Journal of Experimental & Theoretical Artificial Intelligence 35 (5):649–63. doi:10.1080/0952813X.2021. 1964003. Nam, J., S. Mo, J. Lee, and J. Shin. 2023. Breaking the spurious causality of conditional generation via fairness intervention with corrective sampling. arXiv:2212.02090 [cs.CV]. doi:10.48550/arXiv.2212.02090. Porsdam Mann, S., B. D. Earp, N. Møller, S. Vynn, and J. Savulescu. 2023. AUTOGEN: A personalized large language model for academic enhancement—ethics and proof of principle. The American Journal of Bioethics 23 (10):28–41. doi:10.1080/15265161.2023.2233356. Weber-Wulff, D., A. Anohina-Naumeca, S. Bjelobaba, T. Folty nek, J. Guerrero-Dib, O. Popoola, P. Sigut, &, and L. Wadding. 2023. Testing of detection tools for AI-generated text. arXiv:2306.15666 [cs.CL]. doi:10.48550/arXiv. 2306.15666. Zupanc, G. K. H. 2023. It is becoming increasingly difficult to find reviewers”—Myths and facts about Peer review. Journal of Comparative Physiology A. doi:10.1007/s00359023-01642-w.
Aniruddha Saha, Shuhua Yu, Arash Norouzzadeh
et al.
Certifiably robust defenses against adversarial patches for image classifiers ensure correct prediction against any changes to a constrained neighborhood of pixels. PatchCleanser arXiv:2108.09135 [cs.CV], the state-of-the-art certified defense, uses a double-masking strategy for robust classification. The success of this strategy relies heavily on the model's invariance to image pixel masking. In this paper, we take a closer look at model training schemes to improve this invariance. Instead of using Random Cutout arXiv:1708.04552v2 [cs.CV] augmentations like PatchCleanser, we introduce the notion of worst-case masking, i.e., selecting masked images which maximize classification loss. However, finding worst-case masks requires an exhaustive search, which might be prohibitively expensive to do on-the-fly during training. To solve this problem, we propose a two-round greedy masking strategy (Greedy Cutout) which finds an approximate worst-case mask location with much less compute. We show that the models trained with our Greedy Cutout improves certified robust accuracy over Random Cutout in PatchCleanser across a range of datasets and architectures. Certified robust accuracy on ImageNet with a ViT-B16-224 model increases from 58.1\% to 62.3\% against a 3\% square patch applied anywhere on the image.
Automated floor plan generation has recently gained momentum with several methods that have been proposed. The CVAAD Floor Plan Auto-Completion workshop challenge introduced MSD, a new dataset that includes existing structural walls of the building as an additional input constraint. This technical report presents an approach for extending a recent work, HouseDiffusion (arXiv:2211.13287 [cs.CV]), to the MSD dataset. The adaption involves modifying the model's transformer layers to condition on a set of wall lines. The report introduces a pre-processing pipeline to extract wall lines from the binary mask of the building structure provided as input. Additionally, it was found that a data processing procedure that simplifies all room polygons to rectangles leads to better performance. This indicates that future work should explore better representations of variable-length polygons in diffusion models. The code will be made available at a later date.
Loida M. Perez, Ramil Mauleon, Mark A. Arick
et al.
The cotton chromosome substitution line, CS-B15sh, exhibits 41% lower injury from 2,4-D when applied at the field recommended rate of 1.12 kg ae ha−1 (1×) than does Texas Marker-1 (TM-1). CS-B15sh was developed in the genetic background of Gossypium hirsutum L. cv TM-1 and has chromosome introgression on the short arm of chromosome 15 from Gossypium barbadense L. cv. Pima 379. In a previous experiment, we observed reduced translocation of [14C]2,4-D outside the treated leaf tissue in CS-B15sh, which contrasted with an increased translocation of the herbicide in the tissues above and below the treated leaf in TM-1. Our results indicate a potential 2,4-D tolerance mechanism in CS-B15sh involving altered movement of 2,4-D. Here, we used RNA sequencing (RNA-seq) to determine the differential expression of genes between 2,4-D-challenged and control plants of the tolerant (CS-B15sh) and susceptible lines (TM-1 and Pima 379). Several components of the 2,4-D/auxin-response pathway—including ubiquitin E3 ligase, PB1|AUX/IAA, ARF transcription factors, and F-box proteins of the SCFTIR1/AFB complex—were upregulated with at least threefold higher expression in TM-1 compared with CS-B15sh, while both Pima 379 and TM-1 showed the same fold change expression for PB1|AUX/IAA mRNA. Some genes associated with herbicide metabolism, including flavin monooxygenase (Gohir.A01G174100) and FAD-linked oxidase (Gohir.D06G002600), exhibited at least a twofold increase in CS-B15sh than in TM-1 (the gene was not expressed in Pima 379), suggesting a potential relationship between the gene’s expression and 2,4-D tolerance. It is interesting to note that glutathione S-transferase was differentially expressed in both CS-B15sh and Pima 379 but not in TM-1, while cytochrome P450 and other genes involved in the oxidation–reduction process were significantly expressed only in CS-B15sh in response to 2,4-D. Gene set enrichment analysis on the union DEGs of the three cotton genotypes revealed the depletion of transcripts involved in photosynthesis and enrichment of transcripts involved in ABA response and signaling.
In the quiet backwaters of cs.CV, cs.LG and stat.ML, a cornucopia of new learning systems is emerging from a primordial soup of mathematics-learning systems with no need for external supervision. To date, little thought has been given to how these self-supervised learners have sprung into being or the principles that govern their continuing diversification. After a period of deliberate study and dispassionate judgement during which each author set their Zoom virtual background to a separate Galapagos island, we now entertain no doubt that each of these learning machines are lineal descendants of some older and generally extinct species. We make five contributions: (1) We gather and catalogue row-major arrays of machine learning specimens, each exhibiting heritable discriminative features; (2) We document a mutation mechanism by which almost imperceptible changes are introduced to the genotype of new systems, but their phenotype (birdsong in the form of tweets and vestigial plumage such as press releases) communicates dramatic changes; (3) We propose a unifying theory of self-supervised machine evolution and compare to other unifying theories on standard unifying theory benchmarks, where we establish a new (and unifying) state of the art; (4) We discuss the importance of digital biodiversity, in light of the endearingly optimistic Paris Agreement.
Cyprien Plateau-Holleville, Enzo Bonnot, Franck Gechter
et al.
Vital records are rich of meaningful historical data concerning city as well as countryside inhabitants that can be used, among others, to study former populations and then reveal the social, economic and demographic characteristics of those populations. However, these studies encounter a main difficulty for collecting the data needed since most of these records are scanned documents that need a manual transcription step in order to gather all the data and start exploiting it from a historical point of view. This step consequently slows down the historical research and is an obstacle to a better knowledge of the population habits depending on their social conditions. Therefore in this paper, we present a modular and self-sufficient analysis pipeline using state-of-the-art algorithms mostly regardless of the document layout that aims to automate this data extraction process.
History of scholarship and learning. The humanities, Bibliography. Library science. Information resources
We describe a strategy for identifying the universe of research publications relevant to the application and development of artificial intelligence. The approach leverages the arXiv corpus of scientific preprints, in which authors choose subject tags for their papers from a set defined by editors. We compose a functional definition of AI relevance by learning these subjects from paper metadata, and then inferring the arXiv-subject labels of papers in larger corpora: Clarivate Web of Science, Digital Science Dimensions, and Microsoft Academic Graph. This yields predictive classification $F_1$ scores between .75 and .86 for Natural Language Processing (cs.CL), Computer Vision (cs.CV), and Robotics (cs.RO). For a single model that learns these and four other AI-relevant subjects (cs.AI, cs.LG, stat.ML, and cs.MA), we see precision of .83 and recall of .85. We evaluate the out-of-domain performance of our classifiers against other sources of topic information and predictions from alternative methods. We find that a supervised solution can generalize to identify publications that belong to the high-level fields of study represented on arXiv. This offers a method for identifying AI-relevant publications that updates at the pace of research output, without reliance on subject-matter experts for query development or labeling.
Agustín AVELLANEDA-CÁCERES, Jorge A. NAVARRO, Juan F. MICHELOUD
La impactación ruminal y abomasal es una afección de los rumiantes que se produce cuando estos consumen un alimento de muy baja digestibilidad y bajo contenido proteico y energético. En este trabajo, se describe una mortandad debido a esta afección, en vacas de cría en el Noroeste argentino. La pastura donde los animales permanecían correspondía a Megathyrsus maximus cv. Gatton, vulgarmente más conocido como “Gatton Panic”. Los signos clínicos fueron anorexia, pérdida de estado hasta que los animales cayeron sin posibilidades de incorporarse y posteriormente morían. El diagnóstico se confirmó por los antecedentes clínicos, patológicos y epidemiológicos sumados al análisis de la pastura. El cuadro de impactación ruminal y abomasal está bien descripto en la bibliografía, pero ha sido poco reportado en Argentina.