> ## Documentation Index
> Fetch the complete documentation index at: https://rapidreview.io/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Running a literature sweep

> The repeatable pattern for a topic sweep, from fan-out to a BibTeX file.

Everything except step 4 is direct and free.

<Steps>
  <Step title="Fan out the topic">
    ```bash theme={"theme":{"light":"github-light","dark":"dark-plus"}}
    nisa search \
      --query "retrieval reranking LLM" \
      --query "listwise reranking" \
      --query "cross-encoder reranking efficiency" \
      --max-results 40 --date-from 2023 > sweep.json
    nisa semantic-search "how to rerank retrieved passages cheaply" --max-results 20 > sweep-sem.json
    ```

    Keep the raw JSON — its `index_latest_pub_month` is your record of what the index held.
  </Step>

  <Step title="Expand from anchors">
    ```bash theme={"theme":{"light":"github-light","dark":"dark-plus"}}
    nisa related 2407.08608 --n 15
    nisa related 2312.02724 --n 15
    ```

    Ids that appear in more than one neighbourhood are usually worth reading.
  </Step>

  <Step title="Verify claims in the text">
    ```bash theme={"theme":{"light":"github-light","dark":"dark-plus"}}
    nisa excerpts 2407.08608 --query "latency" --max 5
    nisa excerpts 2407.08608 --query "\"exact match\"" --max 3
    ```

    If `doc_found` or `full_text_indexed` is false, read the PDF: `nisa pdf 2407.08608 --out paper.pdf`.
  </Step>

  <Step title="Batch the judgment calls">
    <Badge color="orange">usage-tracked</Badge> One question per line in `qs.txt`:

    ```bash theme={"theme":{"light":"github-light","dark":"dark-plus"}}
    nisa ask-batch --timeout 90 --schema '{"verdict":"string","arxiv_ids":["string"]}' < qs.txt > out.jsonl
    jq -c 'select(.ok == false)' out.jsonl        # failures to retry
    ```

    Sequential by design; one invocation, one rate-limit slot.
  </Step>

  <Step title="Save and export">
    ```bash theme={"theme":{"light":"github-light","dark":"dark-plus"}}
    LIST=$(nisa create-list "reranking-sweep" --emoji "🔎" | jq -r .id)
    nisa add-to-list "$LIST" 2407.08608 --note "strong baseline"
    nisa list-papers "$LIST" --format bibtex > sweep.bib
    ```

    <Check>The list is in the web app too.</Check>
  </Step>
</Steps>