Rebuild program schedule from sheet

Author: github-actions[bot]

_data/menus/program.yml

@@ -0,0 +1,11 @@
+# Generated by scripts/build-program.js — do not edit by hand.
+- label: Program
+  items:
+    - name: Full Program
+      link: program/
+    - name: Birds of a Feather
+      link: program/bofs/
+    - name: Papers
+      link: program/papers/
+    - name: Talks
+      link: program/talks/

_data/program.json

@@ -0,0 +1,12 @@
+---
+layout: page
+title: Birds of a Feather
+description: Bird of a Feather abstracts at USRSE'26
+menubar: program
+permalink: program/bofs/
+menubar_toc: true
+set_last_modified: true
+---
+<!-- Generated by scripts/build-program.js — do not edit by hand. -->
+
+## [BoF] How to train an RSE: A discussion of RSE skill training - past, future, and present by Ellianna Abrahams, Lauren Milechin, Jeffrey Carver, Daniel Woulfin, Patrick Diehl and Gabrielle O'Brien {#bof-how-to-train-an-rse-a-discussion-of-rse-skill-training-past-future-and-present-by-ellianna-abrahams-lauren-milechin-jeffrey-carver-daniel-woulfin-patrick-diehl-and-gabrielle-o-brien}

_includes/program-schedule.html

@@ -0,0 +1,20 @@
+---
+layout: page
+title: Papers
+description: Paper abstracts at USRSE'26
+menubar: program
+permalink: program/papers/
+menubar_toc: true
+set_last_modified: true
+---
+<!-- Generated by scripts/build-program.js — do not edit by hand. -->
+
+## AquiLLM: Evaluating Faithfulness in Open-Weight RAG-LLM Systems for Scientific Research {#aquillm-evaluating-faithfulness-in-open-weight-rag-llm-systems-for-scientific-research}
+
+_Bernie Boscoe, Tuan Do, Jack Stark, Srinath Saikrishnan, Vikram Seenivasan, PJ Allen, Morgan Himes, Jonathan Soriano, Andrew Lizarraga_
+
+Scientific research increasingly relies on large, heterogeneous data sources, motivating interest in retrievalaugmented generation (RAG) systems that provide natural language access to scientific knowledge and research workflows. Researchers are exploring the viability of these systems as natural language interfaces for document search and for generating analysis code and pipeline components. At the same time, concerns about data privacy and control over research infrastructure have motivated interest in open-weight models and open-source deployments hosted within research institutions.
+
+In astronomy, this development follows a long history of computational infrastructure development, from archival databases and SQL-based systems to LLM-assisted research tools. This paper presents a domain-expert evaluation of faithfulness for AquiLLM, an open-weight, offline RAG-LLM platform designed to support scientific research groups in the use and preservation of tacit and formal knowledge.
+
+We define faithfulness as the extent to which generated responses remain grounded in retrieved scientific context without unsupported claims or omissions. We report results from an astronomy case study evaluating AquiLLM across retrieval and scientific analysis tasks. AquiLLM performs most reliably on explicit retrieval-oriented questions grounded in the RAG collection, while faithfulness degrades for queries requiring synthesis or ambiguity resolution. These results highlight both the promise and limitations of open-weight RAG-LLM systems for scientific research and demonstrate the importance of domain-expert evaluation beyond standard benchmark leaderboards.

pages/program/abstracts/bofs.md

@@ -0,0 +1,40 @@
+---
+layout: page
+title: Talks
+description: Talk abstracts at USRSE'26
+menubar: program
+permalink: program/talks/
+menubar_toc: true
+set_last_modified: true
+---
+<!-- Generated by scripts/build-program.js — do not edit by hand. -->
+
+## LZ Oracle: an AI-assisted knowledge retrieval platform for the LUX-ZEPLIN dark matter experiment {#lz-oracle-an-ai-assisted-knowledge-retrieval-platform-for-the-lux-zeplin-dark-matter-experiment}
+
+_Maris Arthurs, Jeonghwa Kim, Ibles Olcina_
+
+LUX-ZEPLIN (LZ) is the world's largest dark matter direct detection experiment using a dual-phase xenon time projection chamber with a 7-ton active volume, situated a mile underground at the Sanford Underground Research Facility, South Dakota, USA.
+
+Large experimental physics collaborations, such as LZ, produce and maintain a broad range of technical knowledge, including detector documentation, operation records, analysis notes, software repositories, and data-processing workflows. While this information is essential for scientific productivity, it is often distributed across many platforms and evolves continuously over the lifetime of an experiment. This creates a practical challenge for collaboration members. Finding context-aware answers often requires knowing where to search, which terminology to use, and which information is current.
+
+We present LZ Oracle, an AI-assisted platform being developed for the LZ dark matter experiment to improve access to collaboration knowledge and support scientific and operational workflows. The system combines retrieval-augmented generation with an agentic exploration that can search indexed documentation, inspect relevant context, and synthesize responses grounded in collaboration materials. Current development focuses on improving reliability, expanding knowledge coverage, and designing evaluation workflows that allow domain experts to benchmark answer quality and provide structured feedback.
+
+This talk will describe the design goals, architecture, deployment considerations, and lessons learned from developing an AI-assisted knowledge retrieval platform for the LZ collaboration.
+
+------
+
+## Data Sherpa: An AI-Powered Assistant for Scientific Collaboration Knowledge Management {#data-sherpa-an-ai-powered-assistant-for-scientific-collaboration-knowledge-management}
+
+_Fabián Araneda-Baltierra and Felipe Menanteau_
+
+------
+
+## AskALCF: A RAG Assistant for HPC User Support {#askalcf-a-rag-assistant-for-hpc-user-support}
+
+_Jingyan Jiang, Huihuo Zheng, Akhilesh Bondapalli, Krishna Rauniyar, Murat Keceli, Yasaman Ghadar, Venkatram Vishwanath, Rong Ge and Haritha Siddabathuni Som_
+
+------
+
+## OSC-IS: Research Software Infrastructure for Scientific Artifact Preservation, Provenance, and Reproducible Collaboration by Fernando Garzon, Steven Yeu, Scott Sakai, and Subhashini Sivagnanam {#osc-is-research-software-infrastructure-for-scientific-artifact-preservation-provenance-and-reproducible-collaboration-by-fernando-garzon-steven-yeu-scott-sakai-and-subhashini-sivagnanam}
+
+_Fernando Garzon, Steven Yeu, Scott Sakai, and Subhashini Sivagnanam_