DAPFAM: A Domain-Aware Family-level Dataset to benchmark cross ___domain patent retrieval

Patent prior-art retrieval becomes especially challenging when relevant disclosures cross technological boundaries. Existing benchmarks lack explicit ___domain partitions, making it difficult to assess how retrieval systems cope with such shifts. We introduce DAPFAM, a family-level benchmark with explicit IN-___domain and OUT-___domain partitions defined by a new IPC3 overlap scheme. The dataset contains 1,247 query families and 45,336 target families aggregated at the family level to reduce international redundancy, with citation based relevance judgments. We conduct 249 controlled experiments spanning lexical (BM25) and dense (transformer) backends, document and passage level retrieval, multiple query and document representations, aggregation strategies, and hybrid fusion via Reciprocal Rank Fusion (RRF). Results reveal a pronounced ___domain gap: OUT-___domain performance remains roughly five times lower than IN-___domain across all configurations. Passage-level retrieval consistently outperforms document-level, and dense methods provide modest gains over BM25, but none close the OUT-___domain gap. Document-level RRF yields strong effectiveness efficiency trade-offs with minimal overhead. By exposing the persistent challenge of cross-___domain retrieval, DAPFAM provides a reproducible, compute-aware testbed for developing more robust patent IR systems. The dataset is publicly available on huggingface at https://huggingface.co/datasets/datalyes/DAPFAM_patent.