Benchmark human-labeled answer claims against cited, locally exported evidence. The tool keeps three things separate: the supplied human label, a deliberately narrow deterministic numerical signal, and an optional locally supplied grader label. A citation's mere presence never proves a claim supported.
This walkthrough uses the tool's public README and checked-in example files. Run the command from a repository checkout with Node.js 22+; inspect the source before using it on your own files.
Run the checked-in example
node bin/citation-grounding-benchmark.mjs --input examples/supported.json --json
node bin/citation-grounding-benchmark.mjs --input examples/unsupported.json --json
node bin/citation-grounding-benchmark.mjs --input examples/supported.json --grader examples/grader-disagrees.json --json
npm run checkRead the result
The first example passes (exit 0). The unsupported fixture and the local grader disagreement fail (exit 1). examples/missing-citation.json is incomplete (exit 2). The CLI writes only the JSON report to stdout. Without --json, a short operational summary goes to stderr. It reads files, but writes no files and never calls a model, provider, database, browser or network service.
Where this check stops
Each bound accepts exactly N and reports N+1 as incomplete. The library accepts an injected clock for deterministic testing; the CLI uses a monotonic clock. Timeout is cooperative, not preemptive: a synchronous JSON parse, filesystem call, native string scan or sort can overrun it before the next checkpoint. No time value is written into the report.
Before adapting the command to your own workflow, review the accepted inputs, exit codes and safety boundaries in the README.
Compiled with AI assistance from checked-in public documentation and example scripts. Run the example and review the repository's current documentation before relying on its result.