twt2C: A Manually Curated Social Media Text2Cypher Benchmark

twt2C is a manually curated social media Text-to-Cypher benchmark containing 2,500 natural language–Cypher pairs grounded in the Russian Twitter Trolls graph. The benchmark covers five query categories of increasing complexity, ranging from node-level retrieval and multi-hop graph traversals to aggregation, ranking, filtering, and advanced Cypher constructs. This Zenodo record contains: twt2C.zip: the complete twt2C benchmark; MTQ-RTT.zip: a deduplicated version of the original Mind The Query dataset for the Russian Twitter Trolls graph; llama3_lora_rttt2c.zip: the LoRA adapter weights for the fine-tuned LLaMA-3.1-8B model; RTTt2c.dump: a Neo4j dump of the Russian Twitter Trolls graph used for creating twt2C and for running experiments.