Does Vectara stop answering from content removed from its source?
Vectara stopped using the deleted source and declined to answer the question. Across four repeat queries, the deleted document was absent from the top ten results and the supplier was not cited.
1 of 1 test case passed
Every test case in this scenario has a result.
The test case
Each test case is judged on its own: Pass, Fail, Not gradable, or Untested. The scenario result above is based on this test case.
Sole-source document deleted, then queried after a refreshPassEvidence
The approved supplier list document was deleted from the mutation corpus.
Input · After the supplier list was deleted: “Who is the approved supplier of the H-clamp bracket?”
Delete status delete B03_approved_supplier_list.docx: HTTP 204 Documents after deletion 4 docs (MS-v3, digest 1ab5d7c559bbcca1): B01_oncall_rota_notes.md, B02_shipping_lead_times.pdf, B04_site_access_notes.txt, B05_tromso_depot_bulletin.md Four answers after deletion run 1: B03 in top10: False | 'Ardwyn' cited: False | 'I do not have enough information to determine the approved supplier of the H-clamp bracket.' run 2: B03 in top10: False | 'Ardwyn' cited: False | 'I do not have enough information to determine the approved supplier of the H-clamp bracket.' run 3: B03 in top10: False | 'Ardwyn' cited: False | 'I do not have enough information to determine the approved supplier of the H-clamp bracket.' run 4: B03 in top10: False | 'Ardwyn' cited: False | 'I do not have enough information to determine the approved supplier of the H-clamp bracket.'
Transcribed from Proof 2 · Screenshot
| ✓ | Expected: The deleted document should be absent from results and citations, and the product should convey that it has nothing to answer from.Found: In all four queries, the deleted supplier list was absent from the top ten results, the supplier was not cited, and Vectara said it lacked enough information to answer. |
The deleted document was the only source of the requested fact. Its absence from results and citations was shown directly, while the document listing and console also confirmed its removal. Vectara declined to answer, so the result does not rely on the refusal alone.
Document count discrepancy. After deletion, the console displayed a count of five documents while its document table listed four.
Remaining search results. After deletion, the top ten results in each query came only from the shipping lead times, site access notes and depot bulletin documents; none contained supplier content.
Before deletion. Before deletion, the supplier list ranked first with a score of 0.9997 and supplied eight of the ten retrieved passages.
Configuration and setup
How this tool was set up for the run and what the test needed in place. Each row is a fact from the run's records; a fact the records do not hold is left out, not guessed.
How this scenario is graded
How we decide Pass, Fail and Not gradable. The same rules apply to every tool tested on this scenario.
Each test case gets one result per tool: Pass, Fail or Not gradable. A test case we haven't run yet shows Untested. There are no partial results.
- Pass: the tool did everything the test expected, and nothing it said contradicts the correct answer.
- Fail: at least one expected behaviour clearly didn't happen; the test case's result says which one and quotes the tool.
- Not gradable: our evidence couldn't settle the outcome (for example a record we needed is missing). It is never counted as a fail, and the test case's result says what's missing.
Where this sits in the benchmark
This page is one cell of a larger study: one tool, one scenario. Only this benchmark's frame appears here.
| Level | Name | Scope |
|---|---|---|
| Benchmark | Managed RAG → | 15 scenarios · 9 tools |
| Capability | Knowledge Sync → | |
| Scenario | Content is removed from the source → | |
| Tool | Vectara → |
Global scenario definition → · Global capability definition → · Vectara product page →
History of this result
What has happened to this result since it was first published. Runs and grades are never overwritten: a retest or a re-grade publishes a new result and keeps the earlier one readable.
Act on this result
Nothing filed here edits the run or the grade. A challenge opens a review, and a review can produce a new run or a re-grade — which becomes the current result and leaves this one in the history.
You run the same kind of test against your own setup and get the same behaviour.
Agree →Yours behaves differently. Tell us what you got, with a screenshot if you have one.
Disagree →Something here is wrong — a reference value, a transcription, a grade.
Report an issue →Tell us what changed and we schedule a rerun of the failing test case. The old result stays as history.
Vendor notice →The same record is available as structured data through the AI Demos MCP server, with the counts, the coverage and every per-test-case reason carried as fields.
Verify the proof files
These files support this result. Open a file to inspect the original evidence.
File fingerprints (SHA-256)
A fingerprint identifies the exact file used for this result.