About this database.

A verified, searchable record of scholarship by the current faculty and research staff of the University of Michigan School of Social Work — built so that anyone can explore what they study, and trust what they find.

3,569verified publications

71faculty & research staff

1979–2026years of scholarship

How a publication reaches your screen

BEFORE YOU EVER SEARCH — THE RECORD IS BUILT, WEEKLY

THE MOMENT YOU SEARCH

GatherWe keep a canonical roster of current faculty and research staff and run automated searches against the major scholarly data sources every week.OpenAlexCrossrefPubMedWoSDeep BlueCVs

VerifyEvery record is tied to its DOI and checked against gold-standard registries. Metadata are inherently messy, so multiple procedures resolve conflicts — deduplication, name disambiguation, and cross-source checks. An administrator reviews all corrections and monitors the automations. Nothing publishes itself.human approval required

The recordA database of real, vetted publications — every title, author, and abstract stored verbatim, never edited by software.3,569 records

Read & rankTwo very small AI models read your question for meaning and sort the records by relevance. They never write a word.reads, never writes

YouYou see the actual verified records, exactly as stored — with a link to a free, legal copy whenever one exists.

Small models that read — not generative AI

No text on any result is written by a model. Every title, author list, abstract, and citation is a stored record from a verified source, displayed verbatim.

The AI here is deliberately very small — closer in scale to a spell-checker than to a chatbot. These models do exactly two things: turn text into numerical fingerprints so similar ideas land near each other, and sort a list. They have no ability to generate text, so they cannot invent a publication, misquote an abstract, or “hallucinate.”

Technical words, translated

DOI

A publication’s permanent ID number — like an ISBN, but for articles. If two records share a DOI, they are the same paper. It’s what we verify against.

Bibliographic registry

The big public catalogs of published research — OpenAlex, Crossref, PubMed, Web of Science. Publishers deposit into them directly, which makes them our ground truth.

Deep Blue

The University of Michigan’s own open repository, where faculty work is archived and free to read.

Open access

A legal, free-to-read copy of an article. Whenever one exists, the result links straight to it.

Keyword search

The classic kind every library catalog does: find records containing the exact words you typed.

Semantic search

Search by meaning instead of exact words — “teen drug use” finds “adolescent substance abuse” even though they share no words.

Embedding

The “fingerprint of meaning”: a list of numbers a very small model assigns to a text, so that similar ideas land near each other. How semantic search works under the hood.

Reranker

A second small model that reads your question against each finalist’s title and abstract and puts the best answers first. The “% match” on a result is its relevance estimate — a ranking signal, not a probability.

“% match”

The percentage beside each search result is the reranker’s estimate of how well that record answers your question, relative to the other candidates. Use it to compare results within one search — 94% does not mean “94% certain,” and it says nothing about the quality of the publication itself.

Common questions

It starts with a canonical roster of current faculty and research staff. Automated searches run against sources scholars already rely on: the bibliographic registries — OpenAlex, Crossref, PubMed, Web of Science — which are the systems publishers themselves deposit into, plus the University’s Deep Blue repository, members’ CVs, and other publicly available information — no protected organizational data.

Every Monday, the automation sweeps those sources for anything new by the people on the roster. New arrivals wait in a review queue — the administrator approves each record before it becomes public, reviews all corrections, and monitors the automations. Nothing publishes itself.

It means the record was matched — usually by its DOI — against an authoritative registry, and the metadata you see (title, authors, journal, year, abstract) came from that registry, not from typing. Hover the pill to see which source verified it.

Records we cannot yet verify (older book chapters, technical reports, works without DOIs) are kept privately for review, and are not shown publicly until the administrator approves them.

One person: the administrator. That is the entire write path. Faculty and research staff sign in with their U-M account and can request changes — confirm a record is theirs, propose a correction, flag something that isn’t theirs, or deposit a new article with its PDF — but every request takes effect only when approved. Corrections must come with a DOI or the article PDF, so there is always something to verify against.

The public never has write access, and neither do the automated pipelines: even the weekly registry sweeps wait for human approval.

Two searches run at the same time: classic keyword matching, and semantic search — your question and every publication have been converted into numerical fingerprints of meaning, so related ideas find each other even with no words in common. The two rankings are fused, and a reranker model reads your question against each finalist and orders them by how well they actually answer you.

None of these models writes a single word of what you see. They only decide which verified records to show first.

If it’s your record: sign in with your U-M account, open My publications, and submit a correction — it goes straight to the administrator. For anything else, use the Feedback page — available to signed-in U-M users only.

Go to the Feedback page →

Designed and built by Brian E. Perron, PhD, University of Michigan School of Social Work.

QUESTIONS, CORRECTIONS, IDEASbeperron AT umich DOT edu