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

Shashank Srivastava

Shashank Srivastava contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Artificial IntelligenceComputation and Languagecond-mat.supr-conDiscrete MathematicsMachine Learningmath.CO

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
6works
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

6 published item(s)

preprint2026arXiv

Observation of Time-Reversal Symmetry Breaking in the Type-I Superconductor YbSb$_2$

The spontaneous breaking of time-reversal symmetry is a hallmark of unconventional superconductivity, typically observed in type-II superconductors. Here, we report evidence of time-reversal symmetry breaking in the type-I superconductor YbSb$_2$. Zero-field $μ$SR measurements reveal spontaneous internal magnetic fields emerging just below the superconducting transition, while transverse-field $μ$SR confirms a fully gapped type-I superconducting state. Our first-principles calculations identify YbSb$_2$ as a ${\mathbb Z}_2$ topological metal hosting a Dirac nodal line near the Fermi level. Symmetry analysis within the Ginzburg Landau framework indicates an internally antisymmetric nonunitary triplet (INT) state as the most probable superconducting ground state. Calculations based on an effective low-energy model further demonstrate that this INT state hosts gapless Majorana surface modes, establishing YbSb$_2$ as a topological superconductor. Our results highlight YbSb$_2$ as a unique material platform where type-I superconductivity coexists with triplet-pairing and nontrivial topology.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Socratic Students: Teaching Language Models to Learn by Asking Questions

Large language Models (LLMs) are usually used to answer questions, but many high-stakes applications (e.g., tutoring, clinical support) require the complementary skill of asking questions: detecting missing information, requesting clarifications, and using them to solve tasks. We study this skill in reasoning-heavy domains where progress depends on inquiry rather than factual recall. We define an interactive protocol where a student model engages a stronger teacher under a small turn budget. After each teacher reply, we evaluate the student on the original task with Pass@k. We propose Outcome-Driven Question optimization Strategy (ODQS ), a training framework that learns a questioning policy from downstream task outcomes. At each turn, we sample multiple candidate questions; query the teacher with each, then score the student's resulting performance. Using these scores, we train the student via supervised fine-tuning followed by Direct Preference Optimization (DPO), without any human labels. On GSM8K, HumanEval, and OpenCoder, ODQS produces large gains over interactive baselines, boosting Pass@5 by up to 54.7% (absolute) on math and 22.9% (absolute) on coding, and matching baseline performance in three fewer turns. Thus, question asking can be explicitly trained from task outcomes, improving both accuracy and efficiency in interactive reasoning.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

The Point of No Return: Counterfactual Localization of Deceptive Commitment in Language-Model Reasoning

Existing deception datasets label completed outputs as honest or deceptive, treating deception as a property of the final response rather than a function of the model's reasoning trace. This obscures a more fundamental question: when does a language model become committed to deception? We introduce counterfactual localization: for each sentence prefix in a reasoning trace, we fix the prefix, resample continuations, and estimate the probability of a deceptive outcome. To scale this, we construct five environments (spanning strategic bluffing, maze guidance, financial advice, used-car sales, and offer negotiation) in which deception is never prompted but emerges from strategic incentives and labels follow mechanically from environment state rather than subjective human judgment. The resulting corpus localizes $\sim$1.46M sentences across four reasoning models, drawn from over 94.1M sampled continuations, 91.5B generated tokens, and over 100K scenarios. Sentence-level human evaluation confirms that detected commitment points correspond to interpretable shifts in decision state. Using this resource, we show that lexical cues for commitment prediction transfer poorly across environments, whereas attention-based transition features generalize out of distribution, suggesting that deceptive commitment is reflected in reusable changes in reasoning dynamics rather than surface form. We further identify compact attention-head sets (under 10% of heads) that, selected on one environment, causally suppress deceptive commitment across held-out environments. We release the corpus as a substrate for studying deception, and more broadly commitment, in language-model reasoning.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

CLUES: A Benchmark for Learning Classifiers using Natural Language Explanations

Supervised learning has traditionally focused on inductive learning by observing labeled examples of a task. In contrast, humans have the ability to learn new concepts from language. Here, we explore training zero-shot classifiers for structured data purely from language. For this, we introduce CLUES, a benchmark for Classifier Learning Using natural language ExplanationS, consisting of a range of classification tasks over structured data along with natural language supervision in the form of explanations. CLUES consists of 36 real-world and 144 synthetic classification tasks. It contains crowdsourced explanations describing real-world tasks from multiple teachers and programmatically generated explanations for the synthetic tasks. To model the influence of explanations in classifying an example, we develop ExEnt, an entailment-based model that learns classifiers using explanations. ExEnt generalizes up to 18% better (relative) on novel tasks than a baseline that does not use explanations. We delineate key challenges for automated learning from explanations, addressing which can lead to progress on CLUES in the future. Code and datasets are available at: https://clues-benchmark.github.io.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

ePiC: Employing Proverbs in Context as a Benchmark for Abstract Language Understanding

While large language models have shown exciting progress on several NLP benchmarks, evaluating their ability for complex analogical reasoning remains under-explored. Here, we introduce a high-quality crowdsourced dataset of narratives for employing proverbs in context as a benchmark for abstract language understanding. The dataset provides fine-grained annotation of aligned spans between proverbs and narratives, and contains minimal lexical overlaps between narratives and proverbs, ensuring that models need to go beyond surface-level reasoning to succeed. We explore three tasks: (1) proverb recommendation and alignment prediction, (2) narrative generation for a given proverb and topic, and (3) identifying narratives with similar motifs. Our experiments show that neural language models struggle on these tasks compared to humans, and these tasks pose multiple learning challenges.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Modular and fractional L-intersecting families of vector spaces

In the first part of this paper, we prove a theorem which is the $q$-analogue of a generalized modular Ray-Chaudhuri-Wilson Theorem shown in [Alon, Babai, Suzuki, J. Combin. Theory Series A, 1991]. It is also a generalization of the main theorem in [Frankl and Graham, European J. Combin. 1985] under certain circumstances. In the second part of this paper, we prove $q$-analogues of results on a recent notion called \emph{fractional $L$-intersecting family} for families of subspaces of a given vector space. We use the above theorem to obtain a general upper bound to the cardinality of such families. We give an improvement to this general upper bound in certain special cases.

0 citations0 reviewsNo code linkedOpen access