• 学术搜索
  • 科研智能体
    • Research Labs
    • AI 阅读
    • AI 文库
    • 深度研究
    • 学者亮点
  • 学术资源
    • AI2000
    • 期刊/会议
    • 学者库
    • 学术API
      MCP&Skill
    • 溯源树
    • 数据集
  • 知识沉淀
    • 学术空间
订阅小程序
旧版功能
aminer vip
开通会员低至0.73元/天
一次搞定AI科研
立即登录
  • English
  • 联系方式
    S

    State Street Corporation

    企业
    346论文总数
    9,045引用总数

    State Street Corporation is an American financial services and bank holding company headquartered at One Lincoln Street in Boston with operations worldwide. It is the second-oldest continually operating United States bank; its predecessor, Union Bank, was founded in 1792. State Street is ranked 15th on the list of largest banks in the United States by assets. It is one of the largest asset management companies in the world with US$3.9 trillion under management and US$43.3 trillion under custody and administration. It is the largest custodian bank in the world, providing securities services and it is considered a systemically important bank by the Financial Stability Board.The company is ranked 316th on the Fortune 500 as of 2022. The company is on the list of the banks that are too big to fail published by the Financial Stability Board.The company is named after State Street in Boston, which was known as the "Great Street to the Sea" in the 18th century as Boston became a flourishing maritime capital. The company's logo includes a clipper to reflect the maritime industry in Boston during this time.

    论文量&引用量时间轴

    机构学者

    论文(346)

    年份
    起
    –
    止
    排序
    1When Summaries Distort Decisions: Information Fidelity in LLM-Compressed Financial Analysis
    Hoyoung Lee, Suhwan Park,Seunghan Lee,Jun Seo,Jaehoon Lee, Sungdong Yoo,Minjae Kim, CheolWon Na,Zhangyang Wang, Zach Golkhou, Minkyu Kim,Sotirios Sabanis,

    Financial decision-makers face more information than they can directly inspect, making context compression necessary. Yet when large language models (LLMs) compress financial source material, they can alter the investment judgment supported by the original source. We frame this problem as information fidelity: compression loses fidelity when it changes the decision induced by the source. In agentic systems, such losses may recur across intermediate steps and amplify throughout the decision process. Across financial filings and earnings-call transcripts, we find that LLM-based compression can produce fluent and factually plausible compressed contexts that nevertheless alter downstream decisions. We analyze two diagnostic patterns associated with fidelity loss: decontextualization, where salient evidence is retained but separated from the caveats and contextual qualifiers needed for correct interpretation, and model dependency, where different compressors expose different views of the same source. We then propose Agentic Context Compression, which generates multiple candidate compressions and audits their disagreements against the original source. Our results suggest that financial compression should be evaluated not only by efficiency or factuality, but also by its ability to preserve decision-relevant context.

    2026Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing Industry Trac...(2026)引用:3
    引用
    AI阅读
    加入学术空间
    2DESI DR2 Galaxy Luminosity Functions
    Samuel G. Moore,Shaun Cole, Michael Wilson,Peder Norberg,John Moustakas, J. Aguilar, S. Ahlen, A. Anand, D. Bianchi, D. Brooks, F. J. Castander, T. Claybaugh,

    We present galaxy luminosity functions (LFs) for the Dark Energy Spectroscopic Instrument (DESI) DR2 Bright Galaxy Survey (BGS) in the g, r, z, and wl bands over 0.002 < z < 0.6 Our analysis uses updated k-corrections and evolutionary corrections, including new polynomial kcorrection fits derived from BGS Year 1 data that supersede earlier GAMA-based prescriptions. Exploiting the statistical power of DESI, we measure LFs to very faint magnitudes, reaching M-0.1(r)- 5 logh similar to -10. Independent measurements from the North and South survey regions show excellent agreement around the LF knee, but the very small statistical uncertainties reveal that simple analytic forms fail to capture the full LF shape. The bright end departs from a pure exponential decline, while the faint end exhibits complex, non-powerlaw behaviour, including a pronounced upturn at M-0.1(r) - 5 log(h) greater than or similar to - 15, which is stronger for red galaxies than for blue. We show that our LFs are largely complete for galaxies with surface brightness mu(50) < 25 and that an apparent steepening fainter than -13 is driven primarily by local overdensity and fragmentation of large galaxies. A systematic North-South offset at the brightest magnitudes is traced to red galaxies and may reflect shallower North photometry underestimating extended earlytype profiles, although this remains inconclusive. We therefore also provide LFs based on model Petrosian magnitudes. Redshift splitting reveals small but significant residuals, indicating limitations of a simple global evolutionary model. Using the redshift limits of J. Loveday et al. (2012), we find excellent agreement with GAMA, with substantially reduced statistical errors. These measurements provide a precise reference for studies of environmental and population-dependent LFs and for testing galaxy formation models.

    2026MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY(2026)引用:1
    引用
    AI阅读
    加入学术空间
    3Watermelon Crinkle Leaf-Associated Virus 1 and Watermelon Mosaic Virus Mixed Infecting Watermelon ( Citrullus Lanatus ) in Indiana
    Ronan Keener,Joana Serrano,Robert Alvarez-Quinto,Wenjing Guan,Tom Creswell, John Bonkowski, Cesar Escalante

    Watermelon (Citrullus lanatus) production in the USA was valued at $787 million in 2023, with most of the production concentrated in Florida, California, and Georgia. In the Midwest, Indiana leads watermelon production with a value of $49 million (USDA-NASS, 2024). In August 2024, watermelon plants (cv. Guardsman) showing virus-like symptoms, including mosaic, yellowing, leaf deformation, and wrinkling, were observed in southern Indiana (Knox County). No insect vectors were observed in the fields during the site visits. Samples were collected from three plants in each of four separate watermelon fields. A preliminary serological screening using ImmunoStrip® tests (Agdia, Elkhart, IN) for the general potyvirus group and melon severe mosaic virus was performed. Only the ImmunoStrip® tests for the potyvirus group showed positive results. Total RNA was extracted from a symptomatic representative sample from each field using the Spectrum Plant Total RNA kit (Sigma-Aldrich, St. Louis, MO). A pool of total RNA from four individual samples was then submitted for high-throughput sequencing (HTS) using an Illumina NovaSeqX platform as 150 bp paired-end reads (Psomagen, Rockville, MD). The library was prepared using the TruSeq Stranded Total RNA with Plant Ribo-Zero kit. HTS generated 58 million reads. Sequence reads were trimmed with BBDuk software, de novo assembled using SPAdes v3.15, and submitted to the NCBI. Viral contigs were identified using Blastx against the full non-redundant database (as of November 2024). Watermelon crinkle leaf-associated virus 1 (WCLaV-1) was assembled into three contigs: 6.6 Kb viral polymerase (RNA1, 47,009 reads; coverage 1,122X; acc. PQ621806), 1.4 Kb movement protein (RNA2, 6,932 reads; coverage 1,193X; acc. PQ621807), and 1.3 Kb nucleocapsid (RNA2, 5,300 reads; coverage 1,006X; acc. PQ621808). The highest level of nucleotide identity detected ranged from 98.0-99.9% compared with WCLaV-1 isolate Pi-01 from Brazil (LC636068-9). Additionally, a nearly full-length watermelon mosaic virus (WMV) genome (~10 Kb) with >99% identity compared with WMV isolate C05-270 from France (EU660585) was assembled (17,871,776 reads; coverage 24,638X; acc. PQ855772). Putative mycovirus sequences were also detected through HTS; however, further analysis was not conducted due to the incompleteness of the sequences and the limited number of hits. The occurrence of each virus in the individual samples was further validated by RT-PCR using sequence-specific primers designed in this study. WCLaV-1 was detected in 2/4 watermelon samples, while WMV was detected in 2/4 samples, with one sample being infected by both viruses. Three amplicons were sequenced using Nanopore Technology (Plasmidsaurus, Eugene, OR), compared to homologous sequences in GenBank, and uploaded to the NCBI under accessions PV030975-PV030977. Interestingly, HTS did not detect WCLaV-2, commonly detected in mixed infections with WCLaV-1. Although WCLaV-1 and WCLaV-2 were previously associated with symptoms (Xin et al. 2017), the effect on growth and yield is still unknown (Hendricks and Roberts 2023). To the best of our knowledge, this is the first report of WCLaV-1 and WMV infecting watermelons in Indiana, highlighting the need for additional research on the impact of single and mixed infections of these viruses on cucurbit crops.

    2026Plant Disease(2026)
    引用
    AI阅读
    加入学术空间
    4A Multi-agent Self-optimizing Framework for Real-Time LLM Model Selection and Routing
    Raghu Katikeri, Chiranjeevi Bhagavan, R Anush Jain, Priya Sinha, Giri Sainath Peruri, Khushi Lamichaney, Amit Vaid

    The increasing complexity and diversity of user interactions with LLM Applications demand adaptive strategies for model selection and optimization. Relying on a single, static model often leads to inefficiencies, especially in dynamic environments where query types, user intent, and performance constraints vary significantly. This paper introduces a self-governing, agent-based framework for real-time model orchestration that intelligently routes user queries to the most appropriate language model based on contextual understanding and system metrics. The proposed architecture integrates a lightweight query classifier, a modular agent router, and a centralized model registry enriched with metadata such as domain specialization, latency, and cost. These components work in tandem to enable dynamic model selection, ensuring optimal trade-offs between response quality, efficiency, and resource utilization. The system also incorporates feedback loops, long-term memory modules, and benchmarking pipelines to support continuous learning and robust model lifecycle management. Empirical evaluations across multiple use cases demonstrate the framework’s ability to improve performance, reduce latency, and enhance personalization. The paper also discusses key deployment challenges, including scalability, explainability, and cold start mitigation, and outlines future directions involving reinforcement learning, meta-learning, and cross-domain model coordination. This work contributes a scalable and intelligent solution for adaptive model governance in next-generation conversational AI systems driven by LLM’s.

    2026Emerging Trends in Artificial Intelligence and Applications(2026)
    引用
    AI阅读
    加入学术空间
    5Autonomous Quality Assurance of Enterprise Platforms and Products Using Agentic AI
    Nathan Marconi, Kiran Chandaka, Kirti Mohanty, Satish Jha, Raghavendra Rao Sivalenka, Megha Gupta

    The growing adoption of Agentic AI and Large Language Model (LLM)-driven systems in enterprise platforms has introduced new challenges for quality assurance. Traditional testing approaches, which depend on deterministic outputs and exact validations, are often insufficient for systems whose behavior is probabilistic, context-aware, and dynamically evolving. This paper presents LLMTest-MCP, an autonomous quality assurance framework designed to address these challenges in modern enterprise environments. The framework utilizes an LLM in two complementary roles—as a test design assistant and as a scenario execution controller—enabling end-to-end automation of the testing lifecycle. By leveraging the Model Context Protocol (MCP), the system interacts directly with live browser sessions, allowing realistic and scalable validation of enterprise applications. LLMTest-MCP follows a structured six-stage pipeline, including test case ingestion, scenario generation, domain-specific test data creation, browser-based execution using Playwright via JSON-RPC, outcome evaluation through natural language assertions, and report generation compatible with enterprise tools such as JIRA Xray. To improve reliability, the framework incorporates a multi-pass JSON recovery mechanism to handle inconsistent LLM outputs, along with a deterministic fallback mode that ensures continuity in restricted environments. The framework was evaluated on a production-grade financial services platform. Results indicate a 2.76 times improvement in scenario coverage compared to manual testing, with scenario generation completed in under three minutes for a set of 21 test cases. Additionally, the system achieved a step classification accuracy of 94.1%. These findings demonstrate that Agentic AI, combined with MCP-based execution, can provide a practical and scalable approach to autonomous quality assurance in enterprise systems.

    20262026 International Conference on Emerging Techniques in Computational Intelligence (ICETCI)(2026)
    引用
    AI阅读
    加入学术空间
    立即登录,查看全部 346 篇论文

    机构统计