ILC-11: A Curated JSON Corpus of the Constitution of India and Ten Central Statutes for Retrieval-Based Legal Question Answering

Most openly available legal corpora for India consist of court judgments, whereas systems that answer citizens' questions need the text of the provisions themselves, organised so that each provision can be located, cited and retrieved.This paper presents ILC-11, a curated collection of the Constitution of India and ten central statutes in machine-readable JSON: the Bharatiya Nyaya Sanhita, 2023, the Bharatiya Sakshya Adhiniyam, 2023, the Prevention of Corruption Act, 1988, the Consumer Protection Act, 2019, the Information Technology Act, 2000, the Motor Vehicles Act, 1988, the Protection of Children from Sexual Offences Act, 2012, the Juvenile Justice (Care and Protection of Children) Act, 2015, the Protection of Women from Domestic Violence Act, 2005 and the Environment (Protection) Act, 1986.The collection contains 756 records and about 376,800 words, drawn from official PDF editions of the enactments.The Constitution is segmented into 715 article and schedule records with part and title metadata, the Prevention of Corruption Act into 32 section records, and the remaining statutes are kept as full-text records with source metadata.We describe the sources, schema, construction process, statistics and known limitations of the collection, and discuss its use for semantic search and Retrieval-Augmented Generation (RAG) in legal assistance.