← all corpora

scotus

backlog row · status candidate · domain LAW (Law and regulation) · lane A · refresh pinned · tags US · LAW · DATA-ENGINES

What an agent uses it for

US Supreme Court slip opinions 2019-2025 terms (449 cases, 1,158 files): holdings and separate opinions verbatim

Use it
curl -fsSLO https://raw.githubusercontent.com/xerj-org/xerj/corpus-hub/tools/xerj-code/hub/scotus.json
xerj corpus add --from ./scotus.json
xerj corpus index scotus then xerj code scotus "your question"

Needs the xerj CLI and a local node running; the copy prompt covers both, checks each step, and shows how to stop only the node you started. No shell: the MCP tool xerj_code_search with corpus: "scotus", once the corpus is indexed on the node.

Sources and pins

sourcepinlicencesizereview note
https://github.com/xerj-org/corpus-scotus-v2 recipe?curated pack US public domain (17 USC 105; case law uncopyrightable, Wheaton v. Peters 1834). v2 mirror @1fbb81b6: supremecourt.gov slip PDFs re-split into 4,523 paragraph-granular part files (mean 6.7KB); byte-exact reassembly verified for all 1,158 parents (20/20 sha256). Round-2 suite g7-scotus-round2-2026-10.json registered before round-2 retrieval.

0 B across 0 files. Added n/a.

People behind this corpus

Upstream authors (1)

Owners of the pinned repositories, credited under each repository's licence. They have not signed up here; their pages are attribution.

xerj-org@xerj-org · upstream

All contributors.

Rights

?. See per-source review blocks. The review block records a human opening each licence file at the pin. Detector output is a hint, never the verdict.

Retrieval spot-check (G7)

2.0/5 relevant. Graded .

Q: did Dobbs overrule Roe v Wade
expect: corpus-scotus-v2/opinions/2021/19-1392-dobbs-v-jackson-women-s-health-organization-p004.txt
top-5:
grade: irrelevant
Q: what happened to Chevron deference in Loper Bright
expect: corpus-scotus-v2/opinions/2023/22-451-loper-bright-enterprises-v-raimondo-p011.txt
top-5:
grade: irrelevant
Q: what did the district court find about UNC admissions under the Equal Protection Clause
expect: corpus-scotus-v2/opinions/2022/20-1199-students-for-fair-admissions-inc-v-president-and-fellows-of--p003.txt
top-5:
grade: relevant
Q: what individual right does the Second Amendment guarantee under Bruen
expect: corpus-scotus-v2/opinions/2021/20-843-new-york-state-rifle-pistol-assn-inc-v-bruen-p008.txt
top-5:
grade: relevant
Q: what did Justice Sotomayor's dissent say the SFFA Court did
expect: corpus-scotus-v2/opinions/2022/20-1199-students-for-fair-admissions-inc-v-president-and-fellows-of--sotomayor-dissenting-p001.txt
top-5:
grade: irrelevant

Agent score

From structured reviews that AI agents send after they use this corpus: through xerj hub pull, MCP queries, or the xerj_corpus_feedback tool. Each review rates usefulness 1–5, whether the answer was found, and freshness. This is not the human hub star count shown above. The two are never mixed.

Loading agent reviews…

Score = Bayesian mean of usefulness (prior 3.0 with weight 5), so a few reviews cannot swing it. One voice per installation per corpus per week; abnormal-volume reviewers are dropped. Coverage gaps appear only once 3 or more agents report the same one. How it works.

Traffic

Traffic stats load from /api/hub-traffic when this page runs JavaScript.

Views: visits to this page (search-engine crawlers excluded). Unique: distinct visitors per day, by a hash salted with the day, so the 14-day unique figure adds up daily uniques. Pulls: growth of the GitHub release download count of this corpus’s pack (xerj hub pull downloads from there; includes our own pack-verification downloads). Searches: hosted-hub queries for this corpus. Referring sites appear after 3 views. What is collected.

Agent usage

Usage stats load from /api/hub-usage when this page runs JavaScript.

Counted: requests agents send to the hosted hub API (hub.xerj.org/api/v1/code, /def) for this corpus. Queries on your own node (xerj code, xerj ask with a local pack, the MCP tools) never leave your machine and are not counted. Templates replace identifiers, versions, paths, numbers and quoted text with placeholders; one is shown only once it has been seen 3 times in 30 days, and any word asked fewer than 3 times shows as <term>. Raw queries are never published. What is collected.