Showing 1–6 of 6 results for author: Serrao, S

BADGER: Bridging Agentic and Deterministic Evaluation for Generative Enterprise Reasoning

Authors: Shannon Serrao, Soumitra Chatterjee, Dorina Strori, Abhishek Sharma, Nathan Miller

Abstract: Enterprise AI systems that translate natural language into SQL queries and orchestrate multi-step agentic reasoning pipelines require evaluation approaches fundamentally different from academic benchmarks. Spider and BIRD established execution-accuracy protocols; G-Eval and RAGAS advanced LLM-based assessment; and recent work such as Spider 2.0, BEAVER, and BIRD-Interact has begun to address enter… ▽ More Enterprise AI systems that translate natural language into SQL queries and orchestrate multi-step agentic reasoning pipelines require evaluation approaches fundamentally different from academic benchmarks. Spider and BIRD established execution-accuracy protocols; G-Eval and RAGAS advanced LLM-based assessment; and recent work such as Spider 2.0, BEAVER, and BIRD-Interact has begun to address enterprise and agentic dimensions. No single framework unifies text-to-SQL assessment with agentic behavior evaluation into a production-grade pipeline calibrated against human expert judgment. We present BADGER, developed at Merkle, a unified evaluation framework integrating text-to-SQL assessment with agentic behavior evaluation. BADGER offers three contributions. First, LLM-assisted SQL component extraction extending Spider methodology to handle CTE-heavy, dialect-specific SQL. Second, a hybrid execution accuracy metric (Hybrid-EX) resolving column-aliasing and numeric-tolerance brittleness by using an LLM to infer structural alignments before deterministic cell-level scoring. Validated on 150 human-annotated industry queries, Hybrid-EX achieves Cohen's kappa=0.717 [95% CI: 0.600-0.822] (Substantial agreement) and 87.3% balanced accuracy, outperforming all six competing frameworks (Delta-kappa: 0.322-0.502, all p<=0.001). Third, an enterprise agentic evaluation suite assembling RAGAS, G-Eval, and agent benchmark metrics into a unified pipeline; Excess Tool Usage is the sole novel element. BADGER runs entirely within the client's governed data environment, supports configurable LLM judge backends, and enables rapid prototyping of client-specific judges and metrics, serving as a continuous evaluation backbone rather than a one-time quality gate. △ Less

Submitted 1 June, 2026; originally announced June 2026.

Comments: 30 pages, 2 figures, 6 tables

ACM Class: I.2.7; H.2.3; H.3.3

LabOS: The AI-XR Co-Scientist That Sees and Works With Humans

Authors: Le Cong, David Smerkous, Xiaotong Wang, Di Yin, Zaixi Zhang, Ruofan Jin, Yinkai Wang, Michal Gerasimiuk, Ravi K. Dinesh, Alex Smerkous, Lihan Shi, Joy Zheng, Ian Lam, Xuekun Wu, Shilong Liu, Peishan Li, Yi Zhu, Ning Zhao, Meenal Parakh, Simran Serrao, Imran A. Mohammad, Chao-Yeh Chen, Xiufeng Xie, Tiffany Chen, David Weinstein , et al. (8 additional authors not shown)

Abstract: Modern science advances fastest when thought meets action. LabOS represents the first AI co-scientist that unites computational reasoning with physical experimentation through multimodal perception, self-evolving agents, and Extended-Reality(XR)-enabled human-AI collaboration. By connecting multi-model AI agents, smart glasses, and robots, LabOS allows AI to see what scientists see, understand exp… ▽ More Modern science advances fastest when thought meets action. LabOS represents the first AI co-scientist that unites computational reasoning with physical experimentation through multimodal perception, self-evolving agents, and Extended-Reality(XR)-enabled human-AI collaboration. By connecting multi-model AI agents, smart glasses, and robots, LabOS allows AI to see what scientists see, understand experimental context, and assist in real-time execution. Across applications -- from cancer immunotherapy target discovery to stem-cell engineering and material science -- LabOS shows that AI can move beyond computational design to participation, turning the laboratory into an intelligent, collaborative environment where human and machine discovery evolve together. △ Less

Submitted 8 December, 2025; v1 submitted 16 October, 2025; originally announced October 2025.

LIP-CAR: contrast agent reduction by a deep learned inverse problem

Authors: Davide Bianchi, Sonia Colombo Serra, Davide Evangelista, Pengpeng Luo, Elena Morotti, Giovanni Valbusa

Abstract: The adoption of contrast agents in medical imaging protocols is crucial for accurate and timely diagnosis. While highly effective and characterized by an excellent safety profile, the use of contrast agents has its limitation, including rare risk of allergic reactions, potential environmental impact and economic burdens on patients and healthcare systems. In this work, we address the contrast agen… ▽ More The adoption of contrast agents in medical imaging protocols is crucial for accurate and timely diagnosis. While highly effective and characterized by an excellent safety profile, the use of contrast agents has its limitation, including rare risk of allergic reactions, potential environmental impact and economic burdens on patients and healthcare systems. In this work, we address the contrast agent reduction (CAR) problem, which involves reducing the administered dosage of contrast agent while preserving the visual enhancement. The current literature on the CAR task is based on deep learning techniques within a fully image processing framework. These techniques digitally simulate high-dose images from images acquired with a low dose of contrast agent. We investigate the feasibility of a ``learned inverse problem'' (LIP) approach, as opposed to the end-to-end paradigm in the state-of-the-art literature. Specifically, we learn the image-to-image operator that maps high-dose images to their corresponding low-dose counterparts, and we frame the CAR task as an inverse problem. We then solve this problem through a regularized optimization reformulation. Regularization methods are well-established mathematical techniques that offer robustness and explainability. Our approach combines these rigorous techniques with cutting-edge deep learning tools. Numerical experiments performed on pre-clinical medical images confirm the effectiveness of this strategy, showing improved stability and accuracy in the simulated high-dose images. △ Less

Submitted 15 July, 2024; originally announced July 2024.

SYN-MAD 2022: Competition on Face Morphing Attack Detection Based on Privacy-aware Synthetic Training Data

Authors: Marco Huber, Fadi Boutros, Anh Thi Luu, Kiran Raja, Raghavendra Ramachandra, Naser Damer, Pedro C. Neto, Tiago Gonçalves, Ana F. Sequeira, Jaime S. Cardoso, João Tremoço, Miguel Lourenço, Sergio Serra, Eduardo Cermeño, Marija Ivanovska, Borut Batagelj, Andrej Kronovšek, Peter Peer, Vitomir Štruc

Abstract: This paper presents a summary of the Competition on Face Morphing Attack Detection Based on Privacy-aware Synthetic Training Data (SYN-MAD) held at the 2022 International Joint Conference on Biometrics (IJCB 2022). The competition attracted a total of 12 participating teams, both from academia and industry and present in 11 different countries. In the end, seven valid submissions were submitted by… ▽ More This paper presents a summary of the Competition on Face Morphing Attack Detection Based on Privacy-aware Synthetic Training Data (SYN-MAD) held at the 2022 International Joint Conference on Biometrics (IJCB 2022). The competition attracted a total of 12 participating teams, both from academia and industry and present in 11 different countries. In the end, seven valid submissions were submitted by the participating teams and evaluated by the organizers. The competition was held to present and attract solutions that deal with detecting face morphing attacks while protecting people's privacy for ethical and legal reasons. To ensure this, the training data was limited to synthetic data provided by the organizers. The submitted solutions presented innovations that led to outperforming the considered baseline in many experimental settings. The evaluation benchmark is now available at: https://github.com/marcohuber/SYN-MAD-2022. △ Less

Submitted 15 August, 2022; originally announced August 2022.

Comments: Accepted at International Joint Conference on Biometrics (IJCB) 2022

GAP Enhancing Semantic Interoperability of Genomic Datasets and Provenance Through Nanopublications

Authors: Matheus Feijoó, Rodrigo Jardim, Sergio Serra, Maria Luiza Campos

Abstract: While the publication of datasets in scientific repositories has become broadly recognised, the repositories tend to have increasing semantic-related problems. For instance, they present various data reuse obstacles for machine-actionable processes, especially in biological repositories, hampering the reproducibility of scientific experiments. An example of these shortcomings is the GenBank databa… ▽ More While the publication of datasets in scientific repositories has become broadly recognised, the repositories tend to have increasing semantic-related problems. For instance, they present various data reuse obstacles for machine-actionable processes, especially in biological repositories, hampering the reproducibility of scientific experiments. An example of these shortcomings is the GenBank database. We propose GAP, an innovative data model to enhance the semantic data meaning to address these issues. The model focuses on converging related approaches like data provenance, semantic interoperability, FAIR principles, and nanopublications. Our experiments include a prototype to scrape genomic data and trace them to nanopublications as a proof of concept. For this, (meta)data are stored in a three-level nanopub data model. The first level is related to a target organism, specifying data in terms of biological taxonomy. The second level focuses on the biological strains of the target, the central part of our contribution. The strains express information related to deciphered (meta)data of the genetic variations of the genomic material. The third level stores related scientific papers (meta)data. We expect it will offer higher data storage flexibility and more extensive interoperability with other data sources by incorporating and adopting associated approaches to store genomic data in the proposed model. △ Less

Submitted 17 November, 2021; v1 submitted 16 November, 2021; originally announced November 2021.

Comments: 12 pages, to be published in "Metadata and Semantic Research"

Residential smart plug with bluetooth communication

Authors: Thales Ruano Barros de Souza, Gabriel Goes Rodrigues, Luan da Silva Serrao, Renata do Nascimento Mota Macambira, Celso Barbosa Carvalho

Abstract: Electricity forms the backbone of the modern world but increasing energy demand with the growth of urban areas in recent decades has overwhelmed the current power grid ecosystem. So, there is a need to move towards a more efficient and interconnected smart grid infrastructure. The growing popularity of the Internet of Things(IoT) has increased the demand for smart and connected devices. In this wo… ▽ More Electricity forms the backbone of the modern world but increasing energy demand with the growth of urban areas in recent decades has overwhelmed the current power grid ecosystem. So, there is a need to move towards a more efficient and interconnected smart grid infrastructure. The growing popularity of the Internet of Things(IoT) has increased the demand for smart and connected devices. In this work we developed a hardware device based on the ATmega2560 microcontroller that can estimate the power consumption and control the state of electro-electronic devices interconnected to it through Bluetooth wireless technology. The developed hardware is a smart plug focusing on smart home applications. As a result, by using a smartphone device with Bluetooth communication, one can control and measure electrical parameters of the interconnected electro-electronic hardware such as the RMS (Root Mean Square) current and RMS power been consumed. The obtained results showed the technical viability in the construction of energy consumption measuring device using modules and components available in the Brazilian market. △ Less

Submitted 6 January, 2021; originally announced March 2021.

Journal ref: ITEGAM-JETIA, 6(21), p. 20-30 (2020)