Refactor text on LLM capabilities in paper.md

Removed redundant text about LLM capabilities and CodebookAI.

Author: tmaier-kettering

paper.md

@@ -40,7 +40,7 @@ Deductive qualitative coding is a methodological cornerstone of qualitative cont
 
 Existing computational tools address this challenge inadequately. Keyword-matching approaches fail on semantically complex text. Supervised machine-learning pipelines require labeled training data, data-science expertise, and large datasets before they achieve acceptable accuracy. Commercial qualitative data analysis software (e.g., NVivo, ATLAS.ti, MAXQDA) supports manual coding workflows but does not integrate LLM-based classification. General-purpose LLM chat interfaces such as ChatGPT do not provide the structured outputs, batch processing, or codebook integration that systematic research requires.
 
-LLMs demonstrate strong zero-shot text classification capabilities—assigning labels to previously unseen text without task-specific training [@brown2020]. CodebookAI operationalizes this capability in a researcher-facing tool that requires no programming knowledge. It enforces codebook fidelity through a JSON schema derived at runtime from the user-defined codebook, so the model is structurally prevented from producing labels outside the allowed set [@openai2024]. The **batch processing** mode (via OpenAI's Batch API) reduces costs by up to 50% compared to synchronous calls and scales to tens of thousands of segments per job with results typically available within 24 hours. The integrated reliability module closes the qualitative workflow loop by enabling immediate quantitative comparison of LLM-generated codes with human-generated codes.
+LLMs demonstrate strong zero-shot text classification capabilities—assigning labels to previously unseen text without task-specific training. CodebookAI operationalizes this capability in a researcher-facing tool that requires no programming knowledge. It enforces codebook fidelity through a JSON schema derived at runtime from the user-defined codebook, so the model is structurally prevented from producing labels outside the allowed set [@openai2024]. The **batch processing** mode (via OpenAI's Batch API) reduces costs by up to 50% compared to synchronous calls and scales to tens of thousands of segments per job with results typically available within 24 hours. The integrated reliability module closes the qualitative workflow loop by enabling immediate quantitative comparison of LLM-generated codes with human-generated codes.
 
 ## Functionality