Graph Neighborhoods for Scholarly Search and Topic Expansion
We precompute neighborhoods over works, authors, communities and institutions to speed exploratory search.
Researcher profile
Mira Alvarez
Builds graph-native systems for research evaluation and discovery.
Trust snapshot
Quick read
Trust 78 - AuthorityVerification L4Unclaimed author
6works
0followers
3topics
4close collaborators
Actions
Decide how to stay connected
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 claimDirect 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
Inspect adjacent work, topics, institutions and collaborators without jumping out to a separate graph page.
work: 5author: 5
Drag to move the map, use wheel or controls to zoom.Selected author: Mira Alvarez
authorsignal 104 adjacent
Mira Alvarez
PI, Machine Intelligence Lab
Published work
6 published item(s)
Conference Paper2025The Web Conference
Probabilistic Claim Resolution for Author Entities in Scholarly Graphs
This work formalizes a claim workflow that separates platform users, researcher profiles and author entities, improving identity resolution without degrading product usability.
37 citations4 reviewsCode availableOpen access
Preprint2026arXiv
Graph Memory for Literature Agents: Persistent Neighborhoods for Scientific Search
We show that persistent graph neighborhoods and operator-facing retrieval memory improve literature navigation across papers, people and opportunities.
21 citations5 reviewsCode availableOpen access
Preprint2026arXiv
A Signal Layer for Science: Structured Reviews, Graph Context and Faster Research Triage
We present a graph-native product architecture for scholarly sensemaking where work pages, topic maps and researcher trust signals reduce time-to-understanding for new literature.
18 citations6 reviewsCode availableOpen access
Workshop Paper2025NeurIPS Datasets and Benchmarks Workshop
Calibrated Review Rubrics for AI Science Communities
We evaluate rubric design for structured reviews, moderation queues and reviewer calibration in technical communities.
17 citations10 reviewsNo code linkedOpen access
Conference Paper2026SIGIR
Sparse Embeddings for Scholarly Discovery with Human-Readable Signals
We compare dense and sparse retrieval strategies for scholarly search when operators need interpretable reasons and controllable ranking.
16 citations4 reviewsCode availableOpen access