Pipeline Inspection, Visualization, and Interoperability in PyTerrier

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lionis, Emmanouil Georgios, Macdonald, Craig, MacAvaney, Sean
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915763388940288
author Lionis, Emmanouil Georgios
Macdonald, Craig
MacAvaney, Sean
author_facet Lionis, Emmanouil Georgios
Macdonald, Craig
MacAvaney, Sean
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_17502
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Pipeline Inspection, Visualization, and Interoperability in PyTerrier
Lionis, Emmanouil Georgios
Macdonald, Craig
MacAvaney, Sean
Information Retrieval
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.
title Pipeline Inspection, Visualization, and Interoperability in PyTerrier
topic Information Retrieval
url https://arxiv.org/abs/2601.17502