Pakistan Science News API

{
    "totalArticles": 26296,
    "articles": [
        {
            "id": "cac9738ea9184809523c32adb361991c",
            "title": "FusionDiff: a dual-path diffusion-based framework for few-shot authenticity analysis of ceramic microstructures",
            "description": "The authenticity of ceramic components is closely tied to their microscopic structures, making automatic and accurate identification essential for quality control. However, this task is often constrained by the scarcity of labeled samples. This study investigates the potential of large-scale pretrained diffusion models as feature extractors, leveraging the rich visual priors embedded in their generative processes to provide a robust semantic foundation for small-sample learning. To address the limitations of the original U-Net in global representation modeling and the weak local-detail sensitivity of DeiT, we propose a dual-path fusion encoder, FusionDiff. Within a frozen Stable Diffusion V1.4 framework, CNN and adapter-enhanced DeiT paths operate in parallel and are deeply integrated via feature gating. Following a “self-supervised pretraining + supervised fine-tuning” paradigm, classification is performed using a Random Forest classifier. On our custom ceramic dataset, FusionDiff achieves a test accuracy of 99.07%, outperforming SD-CNN (97.44%), DeiT (96.30%), and ResNet50 (97.00%) under a unified self-supervised evaluation protocol. Even under extremely small-sample conditions ($$n = 50$$), the model attains 90.7% validation accuracy, demonstrating competitive data efficiency and cross-domain generalization capability.",
            "content": "This work was supported by the Natural Science Foundation of Fujian Province of China (No. 2026J001989). The Fujian Provincial Department of Education Undergraduate Education and Teaching Research Project (No. FBJY20230083). The Principal’s Foundatio... [1056 chars]",
            "url": "https://www.nature.com/articles/s41598-026-57035-x?error=cookies_not_supported&code=b105f7ba-1d30-48f2-aab8-967b0aefd024",
            "image": "https://www.nature.com/static/images/favicons/nature/favicon-48x48-b52890008c.png",
            "publishedAt": "2026-06-13T08:15:00Z",
            "lang": "en",
            "source": {
                "id": "7abf0df285fbe93cdccffcc7c4088737",
                "name": "Nature",
                "url": "https://www.nature.com"
            }
        },
        {
            "id": "fac08723d2444dfe6c98d5999dfafa10",
            "title": "Dark energy survives major challenge as universe keeps accelerating",
            "description": "A bold claim that the universe’s accelerating expansion was an illusion has been put to the test—and failed. Researchers found that the study behind the controversy made key mistakes when analyzing supernova data. After revisiting the evidence, astronomers concluded that cosmic acceleration remains as strong as ever.",
            "content": "The debate began in late 2025 when a group of astronomers published findings suggesting that evidence for dark energy, the mysterious phenomenon thought to drive the universe's accelerating expansion, was weakening. Their analysis raised the possibil... [3701 chars]",
            "url": "http://www.sciencedaily.com/releases/2026/06/260612032030.htm",
            "image": "https://www.sciencedaily.com/images/1920/universe-expansion-dark-energy.webp",
            "publishedAt": "2026-06-13T05:49:23Z",
            "lang": "en",
            "source": {
                "id": "8400452cd3ae520c3deec87e0653d197",
                "name": "ScienceDaily",
                "url": "http://www.sciencedaily.com"
            }
        },
        {
            "id": "d8c145ac0e53e71413c979cc08b3eb5a",
            "title": "Mountainous landscapes store far more carbon than previously thought, new research shows",
            "description": "Hilly and mountainous landscapes have a much greater ability to store carbon in the soil than previously thought, according to a new study co-led by scientists at the University of Oregon.",
            "content": "Hilly and mountainous landscapes have a much greater ability to store carbon in the soil than previously thought, according to a new study co-led by scientists at the University of Oregon.\nThe finding, published in Science Advances, could help scient... [4546 chars]",
            "url": "https://phys.org/news/2026-06-mountainous-landscapes-carbon-previously-thought.html",
            "image": "https://scx2.b-cdn.net/gfx/news/hires/2026/mountain-hike.jpg",
            "publishedAt": "2026-06-12T18:00:03Z",
            "lang": "en",
            "source": {
                "id": "6063be7565dcd637bb5d2946ed6c5329",
                "name": "Phys.org",
                "url": "https://phys.org"
            }
        }
    ]
}