admission-compare

Thneoly/r2r-jev

reference corpus · status live · domain AI (AI, prompts and agents) · lane A · refresh pinned · tags GLOBAL · EVALUATION · ADMISSION · AGENTS

What an agent uses it for

an agent comparing evidence admission with a direct threshold queries this for how admission-compare runs the two-arm experiment over CSV judgment traces

Use it
xerj hub pull admission-compare
xerj "your question" --corpus admission-compare
xerj ask --def SYMBOL --corpus admission-compare

One line, no clone and no index: xerj hub pull admission-compare fetches this corpus’s signed, pre-indexed pack and checks its SHA-256 and signature before restoring it. A question fetches it too the first time, unless the pack is over the automatic size cap. The answer names the corpus, its pin date and its licence. Use --def for an exact value, signature or default. Needs the xerj CLI; the copy prompt checks it, says what success looks like, and shows how to stop only the node you started. No shell: the MCP tool xerj_hub_ask with corpus: "admission-compare", once the pack is on the machine (a tool never downloads one). Not sure this is the right corpus? The catalogue lists every one, a line each.

Sources and pins

sourcepinlicencesizereview note
Thneoly/r2r-jev 7a439382d306Apache-2.0 146.9 KB / 28 files Sibling the author asked to include in xerj-org/xerj#2310, same Apache-2.0 attribution. LICENSE at 7a439382d306 is the Apache License 2.0. git ls-files at that pin: 28 files, 150413 bytes. The commit adds the admission-compare two-arm experiment.

146.9 KB across 28 files. Added 2026-10-24.

People behind this corpus

Contributors (1)

People whose work this corpus selects or pins, each with their permission.

Thne@Thneoly

All contributors.

Rights

Apache-2.0. Redistribution permitted with attribution per the licence review. 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)

Not yet spot-checked. Queries are pre-registered in the registry before grading.

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.