BZPEERReading, trust and collaboration for research
Menu

Discover

GraphFollow connections around a paper, topic or saved view.

Workspaces

HomePick up where your research flow left off.InboxHandle requests, replies and notifications from one place.CollectionsCurate reading lists, evidence sets and shareable dossiers.ResearchSee your private provenance graph, trail and imports.CollaborationMove from discovery into focused discussion rooms.PublishDraft, preview and publish full-text research articles.

Network

ExpertsFind specialists worth following or asking for help.CommunitiesJoin research circles organized around shared work.PartnersSee external organizations active around the same topics.

Opportunities

ListingsBrowse roles, calls and collaborations with clearer fit signals.

Account

Log inReturn to your reading and collaboration workspace.Create accountStart saving work, following people and joining teams.
Log inCreate account

Researcher profile

Arjun Subramonian

Arjun Subramonian contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Artificial Intelligencecs.CYphysics.app-phphysics.ins-detphysics.med-phQuantitative Methods

Trust snapshot

Quick read

Trust 15 - UnverifiedVerification L1Unclaimed author
3works
0followers
6topics
4close collaborators

Actions

Decide how to stay connected

Follow researcher0

Identity and collaboration

How to connect with this researcher

Claiming links this public author record to a researcher profile and unlocks direct collaboration workflows.

Log in to claim

Direct collaboration

Open a focused conversation when the fit is right

Claim this author entity first to unlock direct invitations.

Research graph

See the researcher in context

Open full explorer

Inspect adjacent work, topics, institutions and collaborators without jumping out to a separate graph page.

Building this graph slice

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

3 published item(s)

preprint2026arXiv

SCRuB: Social Concept Reasoning under Rubric-Based Evaluation

While many studies of Large Language Model (LLM) reasoning capabilities emphasize mathematical or technical tasks, few address reasoning about social concepts: the abstract ideas shaping social norms, culture, and institutions. This understudied capability is essential for modern models acting as social agents, yet no systematic evaluation methodology targets it. We introduce SCRuB (Social Concept Reasoning under Rubric-Based Evaluation), a framework designed for this setting of task indeterminacy. Our goal is to measure the degree to which a model reasons about social concepts with the depth and critical rigor of a human expert. SCRuB proceeds in three phases: prompt construction from established sources, response generation by experts and models, and comparative evaluation using a five-dimensional critical thinking rubric. To enable generalization of the pipeline, we introduce a Panel of Disciplinary Perspectives ensemble validated against independent expert judges. We release SCRuBEval (n=4,711 evaluation prompts) and SCRuBAnnotations (300 expert-authored responses and 150 expert comparative judgments from 45 PhD-level scholars). Our results show that frontier models consistently outperform human experts across all five rubric dimensions. Across 1,170 pairwise comparisons, expert judges ranked a model response first in 80.8% of judgments and preferred model responses overall 74.4% of the time. Ultimately, this study provides the first expert-grounded demonstration of evaluation saturation for social concept reasoning: the single-turn exam-style format has reached its ceiling for models and humans alike.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Rebuilding Trust: Queer in AI Approach to Artificial Intelligence Risk Management

Trustworthy artificial intelligence (AI) has become an important topic because trust in AI systems and their creators has been lost. Researchers, corporations, and governments have long and painful histories of excluding marginalized groups from technology development, deployment, and oversight. As a result, these technologies are less useful and even harmful to minoritized groups. We argue that any AI development, deployment, and monitoring framework that aspires to trust must incorporate both feminist, non-exploitative participatory design principles and strong, outside, and continual monitoring and testing. We additionally explain the importance of considering aspects of trustworthiness beyond just transparency, fairness, and accountability, specifically, to consider justice and shifting power to the disempowered as core values to any trustworthy AI system. Creating trustworthy AI starts by funding, supporting, and empowering grassroots organizations like Queer in AI so the field of AI has the diversity and inclusion to credibly and effectively develop trustworthy AI. We leverage the expert knowledge Queer in AI has developed through its years of work and advocacy to discuss if and how gender, sexuality, and other aspects of queer identity should be used in datasets and AI systems and how harms along these lines should be mitigated. Based on this, we share a gendered approach to AI and further propose a queer epistemology and analyze the benefits it can bring to AI. We additionally discuss how to regulate AI with this queer epistemology in vision, proposing frameworks for making policies related to AI & gender diversity and privacy & queer data protection.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

An Automated, Cost-Effective Optical System for Accelerated Anti-microbial Susceptibility Testing (AST) using Deep Learning

Antimicrobial susceptibility testing (AST) is a standard clinical procedure used to quantify antimicrobial resistance (AMR). Currently, the gold standard method requires incubation for 18-24 h and subsequent inspection for growth by a trained medical technologist. We demonstrate an automated, cost-effective optical system that delivers early AST results, minimizing incubation time and eliminating human errors, while remaining compatible with standard phenotypic assay workflow. The system is composed of cost-effective components and eliminates the need for optomechanical scanning. A neural network processes the captured optical intensity information from an array of fiber optic cables to determine whether bacterial growth has occurred in each well of a 96-well microplate. When the system was blindly tested on isolates from 33 patients with Staphylococcus aureus infections, 95.03% of all the wells containing growth were correctly identified using our neural network, with an average of 5.72 h of incubation time required to identify growth. 90% of all wells (growth and no-growth) were correctly classified after 7 h, and 95% after 10.5 h. Our deep learning-based optical system met the FDA-defined criteria for essential and categorical agreements for all 14 antibiotics tested after an average of 6.13 h and 6.98 h, respectively. Furthermore, our system met the FDA criteria for major and very major error rates for 11 of 12 possible drugs after an average of 4.02 h, and 9 of 13 possible drugs after an average of 9.39 h, respectively. This system could enable faster, inexpensive, automated AST, especially in resource limited settings, helping to mitigate the rise of global AMR.

0 citations0 reviewsNo code linkedOpen access