[upstream-sync] README.md from ai-boost/awesome-ai-for-science@5910b3b3 [catalogue]

Reviewed-on: #56

upstream/ai-boost-awesome-ai-for-science/catalogue/README.md

@@ -2,9 +2,9 @@
 title: "Readme"
 task: ""
 lineage_type: import
-upstream_source: https://github.com/ai-boost/awesome-ai-for-science/blob/086e63bb/README.md
-upstream_sha: 086e63bb
-imported_at: 2026-07-19
+upstream_source: https://github.com/ai-boost/awesome-ai-for-science/blob/5910b3b3/README.md
+upstream_sha: 5910b3b3
+imported_at: 2026-07-21
 prompt_class: catalogue
 upstream_changes: accepted
 author: upstream
@@ -292,6 +292,7 @@ validated: false
 - [ARA (Agent-Native Research Artifact)](https://github.com/ARA-Labs/Agent-Native-Research-Artifact) - Research ecosystem for rigorous and trustworthy AI scientists — a protocol and skill bundle that makes autonomous research verifiable, crystallized, and observable through structured, machine-executable research artifacts and five agent skills for research management, compilation, verification, visualization, and publication (ARA-Labs, 447+ stars, MIT License, 2026)
 - [Scholar Loop](https://github.com/renee-jia/scholar-loop) - Autonomous multi-agent AI scientist that mirrors a PhD workflow: literature review → grounded hypothesis → real ML experiments → self-critique → write-up; features a deterministic harness with frozen-metric scoring, edit allowlists, and a verified registry to make reward-hacking and hallucination impossible, plus 108 unit tests runnable without API keys or GPUs (461+ stars, MIT License, 2026)
 - [ResearchStudio (Microsoft)](https://github.com/microsoft/ResearchStudio) - AI co-author covering the entire research lifecycle — from an under-specified research direction to a published paper; includes ResearchStudio-Idea for evidence-grounded research ideation and ResearchStudio-Reel for turning finished papers into posters, narrated videos, blogs, and interactive reels; runs as skills on Claude Code and Codex (1.2K+ stars, MIT License, 2026)
+- [Principia](https://github.com/pzqpzq/Principia) - Principle-first scientific idea discovery framework that extracts reusable principles from public literature and private research materials, composes them into traceable Idea Cards with prior-art comparisons, and exports validation-ready research packs; emphasizes inspectable scientific objects, risk disclosure, and falsification paths (ICML 2026, 411+ stars, MIT License)
 
 ### Evaluation & Benchmarking
 - [ScienceAgentBench (ICLR 2025)](https://github.com/OSU-NLP-Group/ScienceAgentBench) - 102 executable tasks from 44 peer-reviewed papers across 4 disciplines with containerized evaluation
@@ -305,6 +306,7 @@ validated: false
 - [SciBench](https://arxiv.org/abs/2307.10635) - College-level scientific problem-solving evaluation across multiple domains
 - [NewtonBench (ICLR 2026)](https://github.com/HKUST-KnowComp/NewtonBench) - First benchmark evaluating LLMs' ability to rediscover scientific laws through interactive experimentation across 324 tasks in 12 physics domains, featuring memorization-resistant metaphysical shifts of canonical laws (HKUST)
 - [ResearchClawBench (InternScience, arXiv 2026)](https://github.com/InternScience/ResearchClawBench) - Benchmark evaluating AI agents for end-to-end automated research from re-discovery to new-discovery, with 40 real-science tasks across 10 disciplines, curated datasets from published papers, and expert-curated multimodal rubrics (170+ stars, MIT License)
+- [Terminal-Bench Science (Harbor Framework, 2026)](https://github.com/harbor-framework/terminal-bench-science) - Benchmark evaluating AI agents on complex real-world scientific workflows in terminal environments across life, physical, earth, and mathematical sciences; featured on model cards for Claude Opus 4.7, GPT-5.5, and Gemini 3.1 Pro (200+ stars, Apache 2.0)
 
 ### Academic Review & Evaluation
 - [AgentReview](https://agentreview.github.io/) - LLM agents simulating academic peer review ecosystems