[Icicle-announce] Announcing ICICLE Release 2025-10

[Vyas, Amit]

ICICLE Release 2025-10
The ICICLE team aims to build the next generation Cyberinfrastructure (CI) to render Artificial Intelligence (AI) more accessible to everyone and to drive its democratization further in solving larger societal problems.
It is with great pleasure that we announce 2025-10 release of ICICLE CI components.
This release includes the following components:
New to ICICLE CI Catalog
Intelligent Cyberinfrastructure
AI Foundations

  *
Camera Trap Benchmark v1.0.0<https://github.com/ICICLE-ai/Camera_Trap>
     *   A benchmark for camera trap image analysis with adaptive learning capabilities.
  *
'Continually Adapt or Not' Benchmark v1.0.0<https://github.com/ICICLE-ai/CAN-Benchmark>
     *   A curated benchmark for evaluating the performance of pre-trained models and fostering the development of adaptation algorithms in the camera trap domain.

Use Inspired Science
Animal Ecology

  *   WildWing v1.0<https://github.com/jennamk14/wildwing-icicle>
     *   An open-source, autonomous and affordable UAS for animal behaviour video monitoring using Parrot Anafi drones to track group-living animals.

ICICLE CI Components Changelog
Intelligent Cyberinfrastructure
AI Foundations

  *   ScienceAgent v2.1<https://github.com/ICICLE-ai/ScienceAgentInterface>
     *   This release has UI refinements, bug fixes, and simplified local setup with filesystem storage.

AI-for-CI

  *   Iluvatar v1.2.0<https://github.com/COS-IN/iluvatar-faas>
     *   An open Serverless platform built with the goal of jumpstarting and streamlining FaaS research. It provides a system that is easy and consistent to use, highly modifiable, and directly reports experimental results.

Software Architecture and Design

  *   CT-Controller v0.0.3<https://github.com/ICICLE-ai/ct-controller>
     *
This release adds support for provisioning through a jump host and adds a demo mode where the ctcontroller can run as an API server.

Use Inspired Science
Animal Ecology

  *   Camera Traps Edge Software v0.6.0<https://github.com/tapis-project/camera-traps>
     *
This release adds support for providing a video as an input dataset for simulations and improved metric reporting.

Digital Agriculture

  *   HARVEST v1.2<https://icicleai.tapis.io/#/harvest>
     *   This release dramatically reduced problematic page load times, visual indicator enhancements and minor bug fixes.

Smart Foodsheds

  *
Food Flow Portal v1.1.0<https://github.com/ICICLE-ai/GNNFoodFlowPortal>
     *   Web-based visualization portal for exploring and interacting with predicted food flows generated by the GNNFoodFlow models, this release includes the links to other food system softwares and performance improvements.
     *
Deployed now and running on Tapis Pods.<https://feast.pods.icicleai.tapis.io/>

  *
Food Equity Access Simulation Technology (FEAST) v0.3<https://gnnfoodflowportal.pods.icicleai.tapis.io/>
     *   Agent-based simulation model to evaluate food accessibility scores
     *
Deployed now and running on Tapis Pods.<https://feast.pods.icicleai.tapis.io/>


The ICICLE team is committed to delivering the best software and CI components. We welcome your feedback and suggestions for future releases. A list of all ICICLE components can be found on our website under CI & Software<https://icicle.ai/cyberinfrastructure/software>
Please subscribe to icicle-discuss<https://lists.osu.edu/mailman/listinfo/icicle-discuss> and post to discuss all installation/build problems, performance issues, features and other miscellaneous questions related to the different software and CI components of the ICICLE project. You are welcome to post patches and enhancements to the released components.
Subscribe to our mailing list icicle-announce<https://lists.osu.edu/mailman/listinfo/icicle-announce> to stay up to date on the latest ICICLE news and releases.
Please refer to the ICICLE AI Training Catalog<https://icicle-ai.github.io/training-catalog/docs/tags/release-2025-10> for component documentation.
Acknowledgements
This release is brought to you by the National Science Foundation (NSF) funded AI institute for Intelligent Cyberinfrastructure with Computational Learning in the Environment (ICICLE) (OAC 2112606)

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.osu.edu/pipermail/icicle-announce/attachments/20251003/3890819c/attachment-0001.html>