Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM68651
Volume:
10 |
10 |
Oct 2026
Pages:
1-6
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
Computer Science and Engineering
SNS College Of Engineering
Computer Science and Engineering
SNS College Of Engineering
Computer Science and Engineering
SNS College Of Engineering
Computer Science and Engineering
SNS College Of Engineering
Computer Science and Engineering
SNS College Of Engineering
Assistant Professor, CSE Department,
SNS College of Engineering, Coimbatore, India
Evaluating research proposals involves submissions, reviewer assignments, scoring sheets, overlap checks, and final decisions that are often handled through separate documents and message threads. This makes the process slow, difficult to audit, and sensitive to inconsistent reviewer judgement. RAPTOR AI is an AI-powered research proposal evaluation and decision support platform designed to organize these activities within a single web application. The proposed system combines proposal submission and document management, text extraction, semantic similarity analysis using sentence embeddings and a vector index, rubric-based reviewer evaluation, role-based access for administrators, researchers, and reviewers, and a decision dashboard with consolidated reports. This paper describes the system scope, workflow, architecture, prototype screens, and responsible-use considerations. The platform is intended to assist human reviewers, not to replace them: AI-generated outputs are advisory and final decisions remain with authorized people. The accuracy of similarity detection, scoring support, security-test results, system performance, and end-to-end behaviour require further validation. Accordingly, the reported outcomes should be considered design- and prototype-level observations rather than claims of measured production performance. A validation plan is outlined for assessing accuracy, reliability, security, usability, and decision-support quality before deployment.
KEYWORDS
RAPTOR AI proposes an integrated research proposal evaluation and decision support platform that connects proposal submission, document management, semantic similarity analysis, rubric-based review, and decision reporting. Its core design contribution is a centralized and organized workflow that brings proposal records and analytical insights together. The accompanying wireframes illustrate how users could review proposal status, similarity findings, and review results within a single platform. The available artifacts establish the intended workflow and interface direction but do not establish verified runtime accuracy, security, scalability, or end-to-end reliability. Future work includes completing the phased implementation, running the validation plan described above, tuning similarity thresholds on labelled data, adding explanation features for AI-assisted outputs, and studying reviewer workload and consistency in a controlled pilot.
[1] L. Bornmann, “Scientific peer review,” Annual Review of Information Science and Technology, vol. 45, no. 1, pp. 197–245, 2011, doi: 10.1002/aris.2011.1440450112. [2] E. L. Pier et al., “Low agreement among reviewers evaluating the same NIH grant applications,” Proc. Natl. Acad. Sci. U.S.A., vol. 115, no. 12, pp. 2952–2957, 2018, doi: 10.1073/pnas.1714379115. [3] J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, “BERT: Pre-training of deep bidirectional transformers for language understanding,” in Proc. NAACL-HLT, 2019, pp. 4171–4186, doi: 10.18653/v1/N19-1423. [4] N. Reimers and I. Gurevych, “Sentence-BERT: Sentence embeddings using Siamese BERT-networks,” in Proc. EMNLP-IJCNLP, 2019, pp. 3982–3992, doi: 10.18653/v1/D19-1410. [5] J. Johnson, M. Douze, and H. Jégou, “Billion-scale similarity search with GPUs,” IEEE Trans. Big Data, vol. 7, no. 3, pp. 535–547, 2021, doi: 10.1109/TBDATA.2019.2921572. [6] N. Mehrabi, F. Morstatter, N. Saxena, K. Lerman, and A. Galstyan, “A survey on bias and fairness in machine learning,” ACM Comput. Surv., vol. 54, no. 6, art. 115, 2021, doi: 10.1145/3457607. [7] E. Tabassi, Artificial Intelligence Risk Management Framework (AI RMF 1.0), NIST AI 100-1, National Institute of Standards and Technology, 2023, doi: 10.6028/NIST.AI.100-1. [8] OWASP Foundation, OWASP Application Security Verification Standard (ASVS), Version 5.0.0, 2025. [Online]. Available: https://asvs.owasp.org. [9] M. Jones, J. Bradley, and N. Sakimura, “JSON Web Token (JWT),” RFC 7519, Internet Engineering Task Force, 2015, doi: 10.17487/RFC7519.
Publication Date
10/31/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
3
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...