def corpus_qa_baseline(question, pdf_paths, *, client=None, top_k=3):
    rows = []
    for pdf in pdf_paths:
        answer = pdf_qa_baseline(pdf, question, top_k=top_k, client=client)
        text = answer.answer.strip()
        rows.append({
            "doc_id": Path(pdf).stem,
            "answer": answer.answer,
            "start_page": answer.start_page_num,
            "confidence": answer.confidence,
            "has_answer": bool(text) and text.upper() != "NA",
        })
    per_doc = pd.DataFrame(rows).sort_values(
        ["has_answer", "confidence"], ascending=[False, False]
    ).reset_index(drop=True)
    return CorpusAnswer(question=question, per_doc=per_doc)