Pipeline Inspection, Visualization, and Interoperability in PyTerrier

pdf bibtex demonstration paper

Authors: Emmanouil Georgios Lionis, Craig Macdonald, Sean MacAvaney

Appeared in: 48th European Conference on Information Retrieval (ECIR 2026)

Links/IDs:

DOI 10.1007/978-3-032-21321-1_23 DBLP conf/ecir/LionisMM26 arXiv 2601.17502 Google Scholar 7wWfoDgAAAAJ:wbdj-CoPYUoC Semantic Scholar 71eb819692416973057c090f126fca589c771479 Enlighten 374745 smac.pub ecir2026-ptpipeline

Abstract:

PyTerrier provides a declarative framework for building and experimenting with Information Retrieval (IR) pipelines. In this demonstration, we highlight several recent pipeline operations that improve their ability to be programmatically inspected, visualized, and integrated with other tools (via the Model Context Protocol, MCP). These capabilities aim to make it easier for researchers, students, and AI agents to understand and use a wide array of IR pipelines.

BibTeX @inproceedings{lionis:ecir2026-ptpipeline, author = {Lionis, Emmanouil Georgios and Macdonald, Craig and MacAvaney, Sean}, title = {Pipeline Inspection, Visualization, and Interoperability in PyTerrier}, booktitle = {48th European Conference on Information Retrieval}, year = {2026}, url = {https://arxiv.org/abs/2601.17502}, doi = {10.1007/978-3-032-21321-1_23}, pages = {159--165} }