TQA experimental results. by Jin Lu (428513)

“…We evaluated our proposed system on five educational datasets—AI2_ARC, OpenBookQA, E-EVAL, TQA, and ScienceQA—which represent diverse question types and domains. Compared to vanilla Large Language Models (LLMs), our approach combining Retrieval-Augmented Generation (RAG) with Code Interpreters achieved an average accuracy improvement of 10−15 percentage points. …”

E-EVAL experimental results. by Jin Lu (428513)

“…We evaluated our proposed system on five educational datasets—AI2_ARC, OpenBookQA, E-EVAL, TQA, and ScienceQA—which represent diverse question types and domains. Compared to vanilla Large Language Models (LLMs), our approach combining Retrieval-Augmented Generation (RAG) with Code Interpreters achieved an average accuracy improvement of 10−15 percentage points. …”

TQA Accuracy Comparison Chart on different LLM. by Jin Lu (428513)

“…We evaluated our proposed system on five educational datasets—AI2_ARC, OpenBookQA, E-EVAL, TQA, and ScienceQA—which represent diverse question types and domains. Compared to vanilla Large Language Models (LLMs), our approach combining Retrieval-Augmented Generation (RAG) with Code Interpreters achieved an average accuracy improvement of 10−15 percentage points. …”

ScienceQA experimental results. by Jin Lu (428513)

“…We evaluated our proposed system on five educational datasets—AI2_ARC, OpenBookQA, E-EVAL, TQA, and ScienceQA—which represent diverse question types and domains. Compared to vanilla Large Language Models (LLMs), our approach combining Retrieval-Augmented Generation (RAG) with Code Interpreters achieved an average accuracy improvement of 10−15 percentage points. …”

Local Python Code Protector Script: A Tool for Source Code Protection and Secure Code Sharing by Pavel Izosimov (20096259)

“…<p dir="ltr">Local Python Code Protector Script: Advanced Tool for Python Code Protection and Secure Sharing</p><h2>Introduction</h2><p dir="ltr">The <b>Local Python Code Protector Script</b> is a powerful command-line tool designed to provide <a href="https://xn--mxac.net/local-python-code-protector.html" target="_blank"><b>source code protection</b></a> and <a href="https://xn--mxac.net/local-python-code-protector.html" target="_blank"><b>secure code sharing</b></a> for Python scripts. …”

Pseudo live-stream of EEG data is generated, and a simple pick-and-place flowchart is designed for channel selection and filtering. by Gursimran Singh (575288)

Results obtained from the Bistable Gut Inflammation Detector model. by Fabricio Cravo (21387854)

Subjects:

Segmentation module training details. by Khelina Fedorchuk (19130089)

PTPC-UHT bounce by David Parry (22169299)

“…<br>It contains the full Python implementation of the PTPC bounce model (<code>PTPC_UHT_bounce.py</code>) and representative outputs used to generate the figures in the paper. …”

(a) System dynamics: schematic representation of all the reactions in the Tree model, which are aging, reproduction, color cycle, and competition. by Fabricio Cravo (21387854)

Subjects:

Comparison of BlueRecording with existing tools by Joseph James Tharayil (21416715)

“…To enable efficient calculation of extracellular signals from large neural network simulations, we have developed <i>BlueRecording</i>, a pipeline consisting of standalone Python code, along with extensions to the Neurodamus simulation control application, the CoreNEURON computation engine, and the SONATA data format, to permit online calculation of such signals. …”

Correlation (a) and Mean-Absolute-Error (b) between frequencies at a reference cutoff, δ₀, and different frequencies, , at different cutoff-values, δ_scan ∊ [3... by Guillermo Pérez-Hernández (21156182)

Left schematic of the XOR gate implementation [11]. by Fabricio Cravo (21387854)

Subjects:

Simulated dynamics of the Mutual Annihilation protocol [26]. by Fabricio Cravo (21387854)

Subjects:

Heatmap showing the simulated output of the XOR circuit by Tamsir <i>et al</i>. [11]. by Fabricio Cravo (21387854)

Subjects:

Simulation results for the phage communication circuit from Pathania <i>et al</i>. [5]. by Fabricio Cravo (21387854)

Subjects:

Matching products with reactants for the example meta-reaction where S1 and S2 are distinct meta-species. by Fabricio Cravo (21387854)

Subjects:

Simulation results of the quorum sensing circuit by Omar Din <i>et al</i>. [28]. by Fabricio Cravo (21387854)

Subjects:

LBQANA python code + Merged Gene Expression Dataset from GSE10810, GSE17907, GSE20711, GSE42568, GSE45827, and GSE61304 for Breast Cancer Biomarker Discovery by M RN (9866504)

PythonForRoyalSociety.py from The formation energy of triple lines by Paul Twine (22587761)