MohammadAmin Fazli

Much of the reported progress in file-level software defect prediction (SDP) is, in reality, nothing but an illusion of accuracy. Over the last decades, machine learning and deep learning models have reported increasing performance across software versions. However, since most files persist across releases and retain their defect labels, standard evaluation rewards label-persistence bias rather than reasoning about code changes. To address this issue, we reformulate SDP as a change-aware prediction task, in which models reason over code changes of a file within successive project versions, rather than relying on static file snapshots. Building on this formulation, we propose an LLM-driven, change-aware, multi-agent debate framework. Our experiments on multiple PROMISE projects show that traditional models achieve inflated F1, while failing on rare but critical defect-transition cases. In contrast, our change-aware reasoning and multi-agent debate framework yields more balanced performance across evolution subsets and significantly improves sensitivity to defect introductions. These results highlight fundamental flaws in current SDP evaluation practices and emphasize the need for change-aware reasoning in practical defect prediction. The source code is publicly available.

The evaluation of drag based image editing models is unreliable due to a lack of standardized benchmarks and metrics. This ambiguity stems from inconsistent evaluation protocols and, critically, the absence of datasets containing ground truth target images, making objective comparisons between competing methods difficult. To address this, we introduce \textbf{RealDrag}, the first comprehensive benchmark for point based image editing that includes paired ground truth target images. Our dataset contains over 400 human annotated samples from diverse video sources, providing source/target images, handle/target points, editable region masks, and descriptive captions for both the image and the editing action. We also propose four novel, task specific metrics: Semantical Distance (SeD), Outer Mask Preserving Score (OMPS), Inner Patch Preserving Score (IPPS), and Directional Similarity (DiS). These metrics are designed to quantify pixel level matching fidelity, check preservation of non edited (out of mask) regions, and measure semantic alignment with the desired task. Using this benchmark, we conduct the first large scale systematic analysis of the field, evaluating 17 SOTA models. Our results reveal clear trade offs among current approaches and establish a robust, reproducible baseline to guide future research. Our dataset and evaluation toolkit will be made publicly available.

This research presents a computational model designed to analyze influence dynamics between classical Persian poets in producing a multi-dimensional similarity network. Using a hand-curated dataset derived from Ganjoor’s corpus, we integrate semantic, lexical, stylistic, thematic, and metrical features generating weighted similarity matrices subsequently integrated into an influence graph portraying relationships between poets. A network analysis identifies both famous poets such as Hafez, Saʿdi, and Rumi holding central positions alongside minor poets such as Khāqānī and Salmān Sāvajī whose brokerage roles become structurally informative. By using community detection via the Louvain algorithm, we further connect discovered groups to known literary schools, notably Sabk-e Khorasani, Sabk-e Hindi, and the Bazgasht-e Adabi move ment. The findings exemplify how data-driven methods can differentiate between canonical height and structural influence and hence yield new insights into the evolution of Persian poetic lineages. By integrating computational linguistics and literary analysis, our proposed outline presents a scalable and interpretable instrument suited to both historical literary studies and future digital humanities work. Throughout, we use multi-dimensional similarity as a proxy for potential influence. Centrality therefore reflects structural integration within the network rather than cultural magnitude or causal primacy; establishing directionality requires temporal and historical evidence.