reasoning / index.html
giovannioliveira's picture
Update index.html
bd719b9 verified
<!DOCTYPE html>
<html lang="en" class="scroll-smooth">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Interactive Reasoning Taxonomy Explorer</title>
<script src="https://cdn.tailwindcss.com"></script>
<script src="https://cdn.jsdelivr.net/npm/chart.js"></script>
<style>
@import url('https://fonts.googleapis.com/css2?family=Inter:wght@400;500;600;700&display=swap');
body {
font-family: 'Inter', sans-serif;
background-color: #f8fafc; /* slate-50 */
}
.nav-item.active {
background-color: #e0f2f1; /* teal-100 */
color: #0d9488; /* teal-600 */
font-weight: 600;
}
.nav-item .chevron {
transition: transform 0.2s ease-in-out;
}
.nav-item.open .chevron {
transform: rotate(90deg);
}
.content-fade-in {
animation: fadeIn 0.5s ease-in-out;
}
@keyframes fadeIn {
from { opacity: 0; transform: translateY(10px); }
to { opacity: 1; transform: translateY(0); }
}
.prose {
color: #334155; /* slate-700 */
}
.prose p {
margin-bottom: 1rem;
}
</style>
</head>
<body class="text-slate-800">
<div class="flex flex-col min-h-screen">
<header class="bg-white shadow-md z-10 sticky top-0">
<div class="max-w-8xl mx-auto px-4 sm:px-6 lg:px-8 py-4">
<h1 class="text-2xl md:text-3xl font-bold text-slate-900 flex items-center">
<svg xmlns="http://www.w3.org/2000/svg" width="28" height="28" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="text-teal-600 mr-3"><path d="M14.5 2H6a2 2 0 0 0-2 2v16a2 2 0 0 0 2 2h12a2 2 0 0 0 2-2V7.5L14.5 2z"></path><polyline points="14 2 14 8 20 8"></polyline><line x1="16" y1="13" x2="8" y2="13"></line><line x1="16" y1="17" x2="8" y2="17"></line><line x1="10" y1="9" x2="8" y2="9"></line></svg>
Framework for Complex-Reasoning Taxonomy
</h1>
</div>
</header>
<div class="flex-grow flex flex-col md:flex-row max-w-8xl mx-auto w-full p-4 sm:p-6 lg:p-8 gap-8">
<!-- Left Navigation Pane -->
<nav id="navigation-pane" class="w-full md:w-1/3 lg:w-1/4 bg-white rounded-lg shadow-lg p-4 h-full md:sticky md:top-24 self-start">
<h2 class="text-xl font-bold text-slate-800 mb-4 pb-2 border-b border-slate-200">Taxonomy Outline</h2>
<div id="nav-tree" class="overflow-y-auto"></div>
</nav>
<!-- Right Content Pane -->
<main id="content-pane" class="w-full md:w-2/3 lg:w-3/4 bg-white rounded-lg shadow-lg p-6 md:p-8">
<!-- Content will be dynamically inserted here -->
</main>
</div>
</div>
<script>
document.addEventListener('DOMContentLoaded', function () {
const promptsData = [{"prompt": "Write a Python function `is_palindrome(s)` that checks if a string is the same forwards and backwards. The function should handle case-insensitivity.", "difficulty": "medium", "taxonomies": ["Algorithm Design Tasks", "Iterative Chain-of-Thought"]},
{"prompt": "In Java, create a `Car` class with private fields for `make` and `model`. Provide public getter and setter methods for these fields to demonstrate encapsulation.", "difficulty": "medium", "taxonomies": ["Conceptual Abstraction", "Procedural Abstraction", "Decomposition Tasks"]},
{"prompt": "Write a recursive Python function to compute the factorial of a non-negative integer. Include a base case for n=0.", "difficulty": "medium", "taxonomies": ["Algorithm Design Tasks", "Mathematical Reasoning", "Iterative Chain-of-Thought"]},
{"prompt": "Write a Python script that uses the `os` module to list all files in the current directory and prints only those with a '.py' extension.", "difficulty": "medium", "taxonomies": ["Intermediate-Level Tasks", "Branching Chain-of-Thought"]},
{"prompt": "In C++, implement a function that takes a `std::vector<int>` and returns the sum of all its elements without using `std::accumulate`.", "difficulty": "medium", "taxonomies": ["Algorithm Design Tasks", "Iterative Chain-of-Thought"]},
{"prompt": "Create a Python class `BankAccount` with methods to `deposit`, `withdraw`, and `check_balance`. Ensure the balance cannot go below zero.", "difficulty": "medium", "taxonomies": ["Conceptual Abstraction", "Decomposition Tasks", "Branching Chain-of-Thought"]},
{"prompt": "Write a Java program that reads a text file line by line and prints the line number before each line.", "difficulty": "medium", "taxonomies": ["Intermediate-Level Tasks", "Iterative Chain-of-Thought"]},
{"prompt": "Implement a Python function `find_longest_word(words_list)` that returns the longest word from a list of strings.", "difficulty": "medium", "taxonomies": ["Algorithm Design Tasks", "Iterative Chain-of-Thought"]},
{"prompt": "Write a Python script to parse a JSON file named `config.json` and extract the value of the `api_key` field.", "difficulty": "medium", "taxonomies": ["Intermediate-Level Tasks", "Structural Pattern Tasks"]},
{"prompt": "In Java, create an `Animal` abstract class with an abstract method `makeSound()`. Then create `Dog` and `Cat` classes that extend `Animal` and implement the method.", "difficulty": "medium", "taxonomies": ["Conceptual Abstraction", "Deep-Level Tasks"]},
{"prompt": "Using Python's `re` module, write a regular expression to validate an email address format.", "difficulty": "medium", "taxonomies": ["Pattern Recognition Tasks", "Structural Pattern Tasks"]},
{"prompt": "Implement the Bubble Sort algorithm in Java to sort an array of integers in ascending order.", "difficulty": "hard", "taxonomies": ["Algorithm Design Tasks", "Algorithm Analysis Tasks", "Iterative Chain-of-Thought"]},
{"prompt": "Write a Python decorator `@timer` that calculates and prints the execution time of any function it wraps.", "difficulty": "hard", "taxonomies": ["Meta-Reasoning Tasks", "Procedural Abstraction", "Reflection and Evaluation"]},
{"prompt": "In Java, use a `HashMap` to count the frequency of each character in a given string and identify the character with the highest frequency.", "difficulty": "hard", "taxonomies": ["Algorithm Design Tasks", "Data Analysis Reasoning", "Iterative Chain-of-Thought"]},
{"prompt": "Write a Python script using `asyncio` to run two simple coroutines concurrently that each print a message and sleep for a different amount of time.", "difficulty": "hard", "taxonomies": ["High Cognitive Load Tasks", "Algorithmic Thinking Tasks"]},
{"prompt": "In C++, implement a `LinkedList` class from scratch with methods for `append`, `prepend`, and `delete` nodes.", "difficulty": "hard", "taxonomies": ["Conceptual Abstraction", "Algorithm Design Tasks", "Deep-Level Tasks"]},
{"prompt": "Write a Python function to perform a binary search on a sorted list of integers to find the index of a target value. Return -1 if the value is not found.", "difficulty": "hard", "taxonomies": ["Algorithm Design Tasks", "Algorithm Analysis Tasks", "Branching Chain-of-Thought"]},
{"prompt": "Implement a thread-safe singleton pattern in Java using a private constructor and a static factory method with double-checked locking.", "difficulty": "hard", "taxonomies": ["Pattern Recognition Tasks", "High Cognitive Load Tasks", "System Analysis Tasks"]},
{"prompt": "Write a Python script that scrapes all the image URLs from a specific Wikipedia page using `requests` and `BeautifulSoup`.", "difficulty": "hard", "taxonomies": ["Deep-Level Tasks", "Structural Pattern Tasks", "Iterative Chain-of-Thought"]},
{"prompt": "In C++, write a template function that can accept any container type (like `vector` or `list`) and prints all its elements to the console.", "difficulty": "hard", "taxonomies": ["Conceptual Abstraction", "Procedural Abstraction", "Deep-Level Tasks"]},
{"prompt": "Implement the Quick Sort algorithm in Python using a recursive, in-place approach.", "difficulty": "insanely difficult", "taxonomies": ["Algorithm Design Tasks", "Algorithm Analysis Tasks", "Big-O analysis problems", "High Cognitive Load Tasks"]},
{"prompt": "Design and implement a multi-threaded web crawler in Java that can fetch and parse multiple web pages concurrently. The system should manage a queue of URLs to visit, handle duplicate URLs, and respect `robots.txt` files. Use a thread pool for efficient resource management.", "difficulty": "insanely difficult", "taxonomies": ["System Analysis Tasks", "High Cognitive Load Tasks", "Algorithm Design Tasks", "Open-Ended Tasks", "Multithreading"]},
{"prompt": "Implement Dijkstra's shortest path algorithm in C++ for a graph represented by an adjacency matrix. The function should take a source vertex and return the shortest distances to all other vertices. The implementation must use a priority queue for efficiency.", "difficulty": "insanely difficult", "taxonomies": ["Algorithm Design Tasks", "Graph-pattern matching exercises", "Algorithm Analysis Tasks", "Deep-Level Tasks"]},
{"prompt": "Write a Python script to perform Principal Component Analysis (PCA) on a dataset from scratch using only NumPy. The script must calculate the covariance matrix, find the eigenvectors and eigenvalues, and project the data onto the principal components. Compare your output with scikit-learn's implementation.", "difficulty": "insanely difficult", "taxonomies": ["Algorithm Design Tasks", "Mathematical Reasoning", "Algebraic Reasoning", "Solution Evaluation Tasks", "Scientific Reasoning"]},
{"prompt": "Write a compiler for a small, custom-defined, Lisp-like programming language. The compiler, written in Python, must perform lexical analysis (tokenization), parsing (generating an Abstract Syntax Tree), and code generation into executable Python code. The language should support variables, basic arithmetic, and function definitions.", "difficulty": "insanely difficult", "taxonomies": ["Open-Ended Tasks", "Long-Form Reasoning", "Logical and Formal Reasoning", "System Analysis Tasks", "Decomposition Tasks"]},
{"prompt": "In a Spring Boot application, implement a secure, stateful WebSocket connection for a real-time chat application. The solution must integrate Spring Security for authentication, handle message broadcasting to specific chat rooms, and manage user presence (online/offline status) across multiple application instances using a message broker like RabbitMQ.", "difficulty": "insanely difficult", "taxonomies": ["System Analysis Tasks", "High Cognitive Load Tasks", "Decomposition Tasks", "Long-Form Reasoning", "Error Correction"]},
{"prompt": "Write a Python script to implement a basic spell checker. The script should read a dictionary file into a set, then check words from an input text file against the dictionary, suggesting corrections for misspelled words based on Levenshtein distance.", "difficulty": "insanely difficult", "taxonomies": ["Algorithm Design Tasks", "Open-Ended Tasks", "Data Analysis Reasoning", "Error Correction"]},
{"prompt": "In Java, create a simple dependency injection framework from scratch. It should be able to register services (classes) and inject instances of those services into other classes via constructor injection, using reflection to resolve dependencies.", "difficulty": "insanely difficult", "taxonomies": ["System Analysis Tasks", "Conceptual Abstraction", "Deep-Level Tasks", "Meta-Reasoning Tasks"]},
{"prompt": "Implement a transactional outbox pattern in a Python microservice architecture. When a primary business transaction completes (e.g., creating an order), insert an event into an 'outbox' table within the same database transaction. A separate process should then read from this table and publish the event to a message broker like RabbitMQ to ensure at-least-once delivery to other services.", "difficulty": "insanely difficult", "taxonomies": ["System Analysis Tasks", "Error Correction", "High Cognitive Load Tasks", "Algorithm Design Tasks"]},
{"prompt": "Write a Java program that uses the Fork/Join framework to parallelize the merge sort algorithm for sorting a large array of integers.", "difficulty": "insanely difficult", "taxonomies": ["Algorithm Design Tasks", "High Cognitive Load Tasks", "Multithreading", "Decomposition Tasks"]},
{"prompt": "In Python, create a context manager class that measures the execution time of the code block within the `with` statement and logs it to a file, including the timestamp and the file where the context manager was used.", "difficulty": "hard", "taxonomies": ["Meta-Reasoning Tasks", "Procedural Abstraction", "Self-Monitoring Tasks"]},
{"prompt": "Write a C++ program that simulates a simple traffic light system at an intersection using threads. One thread should cycle the state of the traffic light (Green, Yellow, Red) at fixed intervals, while other threads represent cars that must wait for a green light to 'cross' the intersection.", "difficulty": "hard", "taxonomies": ["System Analysis Tasks", "Multithreading", "High Cognitive Load Tasks"]},
{"prompt": "In Java, use the Stream API to find the top 5 most frequent words in a large text file. The process should be case-insensitive and ignore common punctuation.", "difficulty": "hard", "taxonomies": ["Data Analysis Reasoning", "Algorithm Design Tasks", "Procedural Abstraction"]},
{"prompt": "Create a Python script that connects to a remote FTP server, lists all the files in a specific directory, and downloads any new files that are not already present locally.", "difficulty": "hard", "taxonomies": ["System Analysis Tasks", "Iterative Chain-of-Thought", "Error Correction"]},
{"prompt": "Implement a C++ class that represents a 2D point and overload the `+` and `-` operators to perform vector addition and subtraction.", "difficulty": "medium", "taxonomies": ["Conceptual Abstraction", "Procedural Abstraction", "Mathematical Reasoning"]},
{"prompt": "Write a Java servlet that handles a POST request from an HTML form, retrieves the form data (e.g., username, email), and prints it to the server console.", "difficulty": "medium", "taxonomies": ["System Analysis Tasks", "Decomposition Tasks"]},
{"prompt": "In Python, write a function that takes a directory path and recursively finds all files within that directory and its subdirectories that have a `.log` extension, returning a list of their full paths.", "difficulty": "medium", "taxonomies": ["Algorithm Design Tasks", "Iterative Chain-of-Thought", "Decomposition Tasks"]},
{"prompt": "Create a C++ program that reads integers from a file, stores them in a `std::set` to automatically handle sorting and uniqueness, and then writes the sorted integers to a new file.", "difficulty": "medium", "taxonomies": ["Intermediate-Level Tasks", "Data Analysis Reasoning"]},
{"prompt": "Write a Python script that defines a simple generator function to yield the Fibonacci sequence up to a given number `n`.", "difficulty": "medium", "taxonomies": ["Procedural Abstraction", "Mathematical Reasoning", "Iterative Chain-of-Thought"]},
{"prompt": "In Java, write a method that accepts a list of strings and returns a new list containing only the strings that have more than 5 characters.", "difficulty": "medium", "taxonomies": ["Algorithm Design Tasks", "Branching Chain-of-Thought"]},
{"prompt": "Write a Python script to connect to a SQLite database, create a table named `inventory` with columns for `item_name` and `quantity`, and insert a few rows of data.", "difficulty": "medium", "taxonomies": ["Decomposition Tasks", "Intermediate-Level Tasks"]},
{"prompt": "In C++, create a simple class hierarchy where a `Manager` class inherits from an `Employee` class, and both have a method to calculate their weekly pay (with managers getting a bonus).", "difficulty": "medium", "taxonomies": ["Conceptual Abstraction", "Decomposition Tasks", "Mathematical Reasoning"]},
{"prompt": "Write a Java program that uses the `java.time` package to calculate the number of days between two given dates.", "difficulty": "medium", "taxonomies": ["Intermediate-Level Tasks", "Mathematical Reasoning"]},
{"prompt": "In Python, use a list comprehension to create a new list containing the uppercase version of each string in an existing list of strings.", "difficulty": "medium", "taxonomies": ["Procedural Abstraction", "Iterative Chain-of-Thought"]},
{"prompt": "Write a Java method that takes an array of integers and returns the average value.", "difficulty": "medium", "taxonomies": ["Algorithm Design Tasks", "Mathematical Reasoning"]},
{"prompt": "In C++, write a function that swaps the values of two integer variables using pointers.", "difficulty": "medium", "taxonomies": ["Deep-Level Tasks", "Procedural Abstraction"]},
{"prompt": "Create a Python script that uses the `json` module to serialize a Python dictionary to a JSON formatted string.", "difficulty": "medium", "taxonomies": ["Intermediate-Level Tasks", "Structural Pattern Tasks"]},
{"prompt": "Write a Java program to check if a given year is a leap year.", "difficulty": "medium", "taxonomies": ["Branching Chain-of-Thought", "Logical and Formal Reasoning"]},
{"prompt": "In Python, implement a simple command-line argument parser using the `argparse` module to accept an input filename and an optional flag.", "difficulty": "hard", "taxonomies": ["System Analysis Tasks", "Decomposition Tasks"]},
{"prompt": "Write a C++ program that reads a text file and counts the occurrences of each word, storing the results in a `std::map`. The program should be case-insensitive.", "difficulty": "hard", "taxonomies": ["Algorithm Design Tasks", "Data Analysis Reasoning", "Iterative Chain-of-Thought"]},
{"prompt": "In Java, implement a generic `Pair` class that can hold two objects of any type.", "difficulty": "hard", "taxonomies": ["Conceptual Abstraction", "Procedural Abstraction"]},
{"prompt": "Create a Python script that acts as a simple TCP echo server. It should listen on a port, accept a connection, receive data from the client, and send the same data back.", "difficulty": "hard", "taxonomies": ["System Analysis Tasks", "High Cognitive Load Tasks"]},
{"prompt": "Write a Java program that uses reflection to inspect a class and print the names of all its methods.", "difficulty": "hard", "taxonomies": ["Meta-Reasoning Tasks", "Deep-Level Tasks"]},
{"prompt": "In C++, use smart pointers (`std::unique_ptr` and `std::shared_ptr`) to manage the memory of objects in a simple class hierarchy, demonstrating how they prevent memory leaks.", "difficulty": "hard", "taxonomies": ["Deep-Level Tasks", "Conceptual Abstraction", "Error Correction"]},
{"prompt": "Write a Python script that connects to a public API (e.g., a weather API), fetches data for a specific city, and prints a formatted summary of the current weather conditions.", "difficulty": "hard", "taxonomies": ["System Analysis Tasks", "Data Analysis Reasoning"]},
{"prompt": "Implement a basic version of the A* search algorithm in Python to find the shortest path in a 2D grid with obstacles.", "difficulty": "insanely difficult", "taxonomies": ["Algorithm Design Tasks", "Graph-pattern matching exercises", "High Cognitive Load Tasks", "Strategy Selection Tasks"]},
{"prompt": "In Java, write a program that uses `java.nio` channels and buffers to efficiently copy a large file from one location to another.", "difficulty": "hard", "taxonomies": ["System Analysis Tasks", "Deep-Level Tasks"]},
{"prompt": "Develop a C++ program that uses multiple threads to parallelize the calculation of the sum of elements in a very large array. Ensure the solution is thread-safe when accumulating the final result.", "difficulty": "hard", "taxonomies": ["Multithreading", "High Cognitive Load Tasks", "Decomposition Tasks", "Algorithm Design Tasks"]},
{"prompt": "Write a Python metaclass that enforces a specific coding standard on any class that uses it, such as ensuring all public methods have docstrings.", "difficulty": "insanely difficult", "taxonomies": ["Meta-Reasoning Tasks", "Conceptual Abstraction", "Reflection and Evaluation", "Open-Ended Tasks"]},
{"prompt": "In Java, implement a custom annotation `@Loggable` that, when applied to a method, uses Aspect-Oriented Programming (AOP with AspectJ or Spring AOP) to log method entry, exit, and execution time.", "difficulty": "insanely difficult", "taxonomies": ["System Analysis Tasks", "Meta-Reasoning Tasks", "Procedural Abstraction", "Deep-Level Tasks"]},
{"prompt": "Create a C++ program that implements a simple expression evaluator for arithmetic expressions involving `+`, `-`, `*`, `/`, and parentheses. The program should take an infix expression as a string and calculate the result using the Shunting-yard algorithm and a stack-based evaluation.", "difficulty": "insanely difficult", "taxonomies": ["Algorithm Design Tasks", "Logical and Formal Reasoning", "Decomposition Tasks", "Long-Form Reasoning"]},
{"prompt": "Write a Python script that uses the `ctypes` library to call a function from a shared library (`.dll` or `.so`) written in C. The C function should perform a complex calculation, and the Python script should handle passing data to it and retrieving the result.", "difficulty": "insanely difficult", "taxonomies": ["System Analysis Tasks", "Deep-Level Tasks", "Learning Transfer Tasks"]},
{"prompt": "In Java, build a simple object-relational mapping (ORM) framework from scratch. It should be able to map a POJO (Plain Old Java Object) to a database table, handle basic CRUD operations using JDBC, and use annotations to define table and column mappings.", "difficulty": "insanely difficult", "taxonomies": ["System Analysis Tasks", "Open-Ended Tasks", "Conceptual Abstraction", "Decomposition Tasks", "Long-Form Reasoning"]},
{"prompt": "Write a C++ program that uses template metaprogramming to compute the factorial of a number at compile time.", "difficulty": "insanely difficult", "taxonomies": ["Meta-Reasoning Tasks", "Mathematical Reasoning", "Deep-Level Tasks", "Logical and Formal Reasoning"]},
{"prompt": "Implement a distributed locking service using Redis in Python. The service should provide `acquire` and `release` methods and handle lock timeouts to prevent deadlocks.", "difficulty": "insanely difficult", "taxonomies": ["System Analysis Tasks", "Algorithm Design Tasks", "High Cognitive Load Tasks", "Error Correction"]},
{"prompt": "Write a Python script to train a simple Generative Adversarial Network (GAN) using PyTorch or TensorFlow/Keras on a dataset like MNIST. The script should define both the generator and discriminator networks and include the training loop that alternates between training them.", "difficulty": "insanely difficult", "taxonomies": ["Scientific Reasoning", "Mathematical Reasoning", "Algorithm Design Tasks", "Long-Form Reasoning", "Open-Ended Tasks"]},
{"prompt": "In Java, create a simple garbage collector for a custom memory management system. It should use a mark-and-sweep algorithm to identify and reclaim unreachable objects from a simulated heap.", "difficulty": "insanely difficult", "taxonomies": ["System Analysis Tasks", "Algorithm Design Tasks", "High Cognitive Load Tasks", "Open-Ended Tasks"]},
{"prompt": "Develop a C++ library for performing matrix operations (addition, multiplication, inversion) using expression templates to avoid creating temporary objects and improve performance.", "difficulty": "insanely difficult", "taxonomies": ["Algorithm Design Tasks", "Mathematical Reasoning", "Algebraic Reasoning", "Deep-Level Tasks", "Meta-Reasoning Tasks"]},
{"prompt": "Write a Python function to find the median of a list of numbers without sorting the entire list. Implement the median of medians algorithm.", "difficulty": "hard", "taxonomies": ["Algorithm Design Tasks", "Algorithm Analysis Tasks", "Mathematical Reasoning"]},
{"prompt": "In Java, create a class that represents a playing card and another class for a deck of cards. The deck class should have methods to shuffle and deal cards.", "difficulty": "medium", "taxonomies": ["Conceptual Abstraction", "Decomposition Tasks", "Algorithm Design Tasks"]},
{"prompt": "In Python, use the `collections.Counter` class to count the frequency of items in a list.", "difficulty": "medium", "taxonomies": ["Data Analysis Reasoning", "Procedural Abstraction"]},
{"prompt": "Write a Java program that demonstrates method overloading by creating three methods with the same name `printData` but with different parameter types (e.g., `String`, `int`, `double`).", "difficulty": "medium", "taxonomies": ["Conceptual Abstraction", "Procedural Abstraction"]},
{"prompt": "In C++, create a function that takes a string as input and returns a reversed version of the string.", "difficulty": "medium", "taxonomies": ["Algorithm Design Tasks", "Iterative Chain-of-Thought"]},
{"prompt": "Write a Python script that defines a simple class and then uses the `__str__` method to provide a user-friendly string representation of its objects.", "difficulty": "medium", "taxonomies": ["Conceptual Abstraction", "Procedural Abstraction"]},
{"prompt": "In Java, implement the `Comparable` interface in a `Student` class to allow sorting a list of students based on their GPA.", "difficulty": "hard", "taxonomies": ["Conceptual Abstraction", "Algorithm Design Tasks", "Data Analysis Reasoning"]},
{"prompt": "Write a C++ program that demonstrates the use of `static` members in a class by creating a counter that tracks how many objects of the class have been instantiated.", "difficulty": "hard", "taxonomies": ["Conceptual Abstraction", "Self-Monitoring Tasks"]},
{"prompt": "In Python, write a function that takes a list of integers and uses a `try-except` block to handle potential `TypeError` if the list contains non-integer values, returning an error message.", "difficulty": "hard", "taxonomies": ["Error Correction", "Self-Monitoring Tasks", "Strategy Adaptation"]},
{"prompt": "Write a Java program that uses JDBC to connect to a MySQL database, execute a query to select all records from a `products` table, and display the results.", "difficulty": "hard", "taxonomies": ["System Analysis Tasks", "Decomposition Tasks", "Data Analysis Reasoning"]},
{"prompt": "In C++, implement a simple RAII (Resource Acquisition Is Initialization) wrapper for a file handle (`FILE*`) to ensure the file is automatically closed when the wrapper object goes out of scope.", "difficulty": "hard", "taxonomies": ["Conceptual Abstraction", "Error Correction", "Deep-Level Tasks"]},
{"prompt": "In Java, create a simple producer-consumer problem solution using `wait()` and `notify()` on a shared buffer object to demonstrate thread communication and synchronization.", "difficulty": "insanely difficult", "taxonomies": ["High Cognitive Load Tasks", "System Analysis Tasks", "Multithreading", "Algorithm Design Tasks"]},
{"prompt": "Write a C++ program that implements a simple observer design pattern. Create a `Subject` class that maintains a list of `Observer` objects and notifies them whenever its state changes.", "difficulty": "insanely difficult", "taxonomies": ["System Analysis Tasks", "Conceptual Abstraction", "Decomposition Tasks", "Pattern Recognition Tasks"]},
{"prompt": "In Python, implement a breadth-first search (BFS) algorithm to traverse a graph represented by an adjacency list and find the shortest path between two nodes.", "difficulty": "insanely difficult", "taxonomies": ["Algorithm Design Tasks", "Graph-pattern matching exercises", "Algorithm Analysis Tasks"]},
{"prompt": "Write a Java application that uses the JAX-RS (Jersey) framework to create a RESTful web service with endpoints for CRUD operations on a list of in-memory objects.", "difficulty": "insanely difficult", "taxonomies": ["System Analysis Tasks", "Decomposition Tasks", "Algorithmic Thinking Tasks", "Long-Form Reasoning"]},
{"prompt": "In C++, create a program that uses the `<chrono>` library to benchmark the performance of sorting a large vector using `std::sort` versus your own implementation of bubble sort.", "difficulty": "hard", "taxonomies": ["Reflection and Evaluation", "Solution Evaluation Tasks", "Algorithm Analysis Tasks"]},
{"prompt": "Write a Python script that uses `BeautifulSoup` and `requests` to scrape a table from an HTML page and convert it into a pandas DataFrame.", "difficulty": "hard", "taxonomies": ["Structural Pattern Tasks", "Data Analysis Reasoning", "Decomposition Tasks"]},
{"prompt": "In Java, write a program that uses a `ReentrantLock` to protect a critical section of code accessed by multiple threads, demonstrating its use over intrinsic locks.", "difficulty": "hard", "taxonomies": ["High Cognitive Load Tasks", "Multithreading", "System Analysis Tasks"]},
{"prompt": "Create a Python function that implements a Caesar cipher, taking a string and a shift value as input and returning the encrypted string.", "difficulty": "medium", "taxonomies": ["Algorithm Design Tasks", "Mathematical Reasoning"]},
{"prompt": "In C++, write a program that dynamically allocates a 2D array of integers, fills it with values, and then properly deallocates the memory.", "difficulty": "medium", "taxonomies": ["Deep-Level Tasks", "Error Correction"]},
{"prompt": "Write a Java class that has a method that might throw a custom exception, and then call this method within a `try-catch-finally` block.", "difficulty": "medium", "taxonomies": ["Error Correction", "Self-Monitoring Tasks"]},
{"prompt": "Write a Java program that uses a `BufferedReader` to read a text file more efficiently than a simple `FileReader`.", "difficulty": "medium", "taxonomies": ["System Analysis Tasks", "Intermediate-Level Tasks"]},
{"prompt": "Write a C++ program that uses `std::vector::erase` to remove a specific element from a vector.", "difficulty": "easy", "taxonomies": ["Surface-Level Tasks"]},
{"prompt": "In Python, write a one-liner to reverse a string.", "difficulty": "easy", "taxonomies": ["Procedural Abstraction"]},
{"prompt": "Write a Java program that checks if two strings are anagrams of each other.", "difficulty": "medium", "taxonomies": ["Algorithm Design Tasks", "Data Analysis Reasoning"]},
{"prompt": "In C++, create a function that takes an integer and returns `true` if it's a prime number and `false` otherwise.", "difficulty": "medium", "taxonomies": ["Algorithm Design Tasks", "Mathematical Reasoning", "Branching Chain-of-Thought"]},
{"prompt": "Write a Python script that uses the `glob` module to find all files in a directory matching a specific pattern (e.g., `*.txt`).", "difficulty": "medium", "taxonomies": ["Structural Pattern Tasks", "Intermediate-Level Tasks"]},
{"prompt": "In Java, create a program that demonstrates the use of a `static` block for one-time initialization of a class.", "difficulty": "medium", "taxonomies": ["Conceptual Abstraction", "System Analysis Tasks"]},
{"prompt": "Write a C++ program that uses `std::transform` and a lambda function to create a new vector containing the squares of the elements of an original vector.", "difficulty": "hard", "taxonomies": ["Procedural Abstraction", "Iterative Chain-of-Thought", "Data Analysis Reasoning"]},
{"prompt": "In Python, write a class that overloads the addition operator (`__add__`) to allow for the addition of two custom objects.", "difficulty": "hard", "taxonomies": ["Conceptual Abstraction", "Procedural Abstraction", "Deep-Level Tasks"]},
{"prompt": "Write a Java program that uses a `Semaphore` to limit the number of threads that can access a particular resource simultaneously.", "difficulty": "hard", "taxonomies": ["High Cognitive Load Tasks", "System Analysis Tasks", "Multithreading"]},
{"prompt": "In C++, implement a function to check if a singly linked list has a cycle.", "difficulty": "hard", "taxonomies": ["Algorithm Design Tasks", "Graph-pattern matching exercises", "Deep-Level Tasks"]},
{"prompt": "Write a Python script that uses `argparse` to create a command-line interface with sub-commands (e.g., `git push`, `git pull`).", "difficulty": "insanely difficult", "taxonomies": ["System Analysis Tasks", "Decomposition Tasks", "Long-Form Reasoning"]},
{"prompt": "In Java, write a program that uses the `java.nio.file` package to watch a directory for changes (creation, deletion, modification of files).", "difficulty": "insanely difficult", "taxonomies": ["System Analysis Tasks", "High Cognitive Load Tasks", "Event-Driven Programming"]},
{"prompt": "Write a C++ program that implements a simple futures and promises mechanism from scratch to manage asynchronous operations.", "difficulty": "insanely difficult", "taxonomies": ["System Analysis Tasks", "High Cognitive Load Tasks", "Multithreading", "Algorithm Design Tasks", "Conceptual Abstraction"]},
{"prompt": "In Python, write a script that uses `scipy.optimize` to find the minimum of a mathematical function.", "difficulty": "hard", "taxonomies": ["Mathematical Reasoning", "Scientific Reasoning", "Algorithmic Thinking Tasks"]},
{"prompt": "Write a Java program that uses the Builder design pattern to construct a complex `User` object with multiple optional fields.", "difficulty": "hard", "taxonomies": ["Pattern Recognition Tasks", "Conceptual Abstraction", "Decomposition Tasks"]},
{"prompt": "Write a Python script that uses a `set` to find the elements that are common to two lists.", "difficulty": "medium", "taxonomies": ["Data Analysis Reasoning", "Procedural Abstraction"]},
{"prompt": "Write a C++ program that uses `dynamic_cast` to safely downcast a base class pointer to a derived class pointer, with a check to ensure the cast is valid.", "difficulty": "hard", "taxonomies": ["Conceptual Abstraction", "Deep-Level Tasks", "Error Correction"]},
{"prompt": "In Python, create a simple context manager using a generator function and the `@contextmanager` decorator from `contextlib`.", "difficulty": "hard", "taxonomies": ["Procedural Abstraction", "Conceptual Abstraction", "Deep-Level Tasks"]},
{"prompt": "Write a Java program that uses a `CyclicBarrier` to synchronize a group of threads at a certain point, making them wait until all threads have reached the barrier.", "difficulty": "insanely difficult", "taxonomies": ["High Cognitive Load Tasks", "System Analysis Tasks", "Multithreading", "Algorithm Design Tasks"]},
{"prompt": "In C++, implement a function that serializes a `std::map<std::string, int>` to a binary file and another function to deserialize it.", "difficulty": "insanely difficult", "taxonomies": ["Algorithm Design Tasks", "System Analysis Tasks", "Structural Pattern Tasks", "Deep-Level Tasks"]},
{"prompt": "Write a Python script that uses the `async/await` syntax with `asyncio.gather` to run multiple asynchronous operations concurrently and wait for all of them to complete.", "difficulty": "insanely difficult", "taxonomies": ["High Cognitive Load Tasks", "System Analysis Tasks", "Algorithmic Thinking Tasks", "Decomposition Tasks"]},
{"prompt": "In Java, create a program that uses the `java.lang.instrument` API and a bytecode manipulation library like ASM or ByteBuddy to dynamically add logging to the entry and exit of a specific method in another class at runtime.", "difficulty": "insanely difficult", "taxonomies": ["Meta-Reasoning Tasks", "System Analysis Tasks", "Deep-Level Tasks", "High Cognitive Load Tasks", "Reflection and Evaluation"]}]
const taxonomyData = {
"id": "root",
"name": "Framework for Complex-Reasoning Taxonomy",
"children": [
{
"id": "intro",
"name": "Introduction",
"content": "\n <h2 class=\"text-2xl font-bold text-teal-700 mb-4\">A Comprehensive Analysis of Evaluation Datasets</h2>\n <p class=\"mb-4\">This application presents a detailed analysis and compilation of evaluation datasets for the \"Framework for Complex-Reasoning Taxonomy.\" The primary objective is to systematically explore the \"Evaluation Datasets\" for each category by synthesizing empirical findings from cognitive science, education, and artificial intelligence.</p>\n <p class=\"mb-4\">A significant theme that emerges is the parallel and increasingly convergent evolution of datasets for human and artificial intelligence. Historically, assessment has followed two distinct tracks: one rooted in cognitive psychology (e.g., Wason Selection Task) and another driven by Large Language Models (LLMs) using large-scale datasets (e.g., GSM8K). This explorer illuminates the dynamic interplay between these two traditions.</p>\n <div class=\"chart-container my-8\">\n <canvas id=\"datasetChart\"></canvas>\n </div>\n <p class=\"text-sm text-slate-600 text-center\">Chart: High-level overview of the primary dataset categories discussed throughout this report.</p>\n "
},
{
"id": "foundational",
"name": "1. Foundational Framework",
"score": null,
"content": "<p>This section addresses the overarching theoretical models that frame the study of complex reasoning. The datasets here are designed to validate the core tenets of these theories by operationalizing their central constructs.</p>",
"children": [
{
"id": "bloom",
"name": "Bloom’s Taxonomy Integration",
"score": 0.95,
"content": "<p>Mapping reasoning tasks onto Bloom’s six cognitive levels (remember→create), guiding alignment of objectives, activities, and assessments.</p>",
"datasets": [
{
"name": "Revised Bloom’s Taxonomy-aligned performance tasks and rubrics",
"link": "https://www.coloradocollege.edu/other/assessment/how-to-assess-learning/learning-outcomes/blooms-revised-taxonomy.html"
}
]
},
{
"id": "dual_process",
"name": "Dual-Process Theory",
"score": 0.9,
"content": "<p>Distinguishes fast, intuitive (System 1) vs. slow, analytical (System 2) reasoning processes; informs when each process dominates.</p>",
"datasets": [
{
"name": "Cognitive Reflection Test (CRT) for detecting System 1 override; implicit-association tasks assessing interplay",
"link": "https://www.jstor.org/stable/30033704"
}
]
},
{
"id": "metacognitive_framework",
"name": "Metacognitive Framework",
"score": 0.88,
"content": "<p>Meta-Reasoning processes that monitor (feelings of rightness) and control (strategy shifts) ongoing reasoning and problem-solving.</p>",
"datasets": [
{
"name": "Meta-Reasoning paradigms using think-aloud protocols and process-tracing (e.g., Felt-Rightness ratings)",
"link": "https://dacemirror.sci-hub.se/journal-article/c2286260f7ebbc44e1d06675e66fc87d/ackerman2017.pdf"
}
]
}
]
},
{
"id": "level1",
"name": "1.1 Level 1: Cognitive Complexity Dimensions",
"score": null,
"content": "<p>This level deconstructs reasoning into its fundamental operational components. Datasets here focus on the intrinsic complexity of the cognitive operations required by a task and the formal type of reasoning being employed.</p>",
"children": [
{
"id": "depth_processing",
"name": "1.1.1 Depth of Processing",
"score": null,
"children": [
{
"id": "surface_tasks",
"name": "Surface-Level Tasks",
"score": 0.6,
"content": "<p>Reliance on shallow perceptual or structural analyses (e.g., font, letter shapes) with minimal semantic engagement.</p>",
"datasets": [
{
"name": "Recognition tasks with form-based cues (DOK Level 1)",
"link": "https://www.structural-learning.com/post/webbs-depth-of-knowledge"
}
]
},
{
"id": "intermediate_tasks",
"name": "Intermediate-Level Tasks",
"score": 0.7,
"content": "<p>Incorporates phonemic or moderate semantic processing (e.g., rhyming, basic categorization).</p>",
"datasets": [
{
"name": "Simple application tasks (DOK Level 2)",
"link": "https://www.structural-learning.com/post/webbs-depth-of-knowledge"
}
]
},
{
"id": "deep_tasks",
"name": "Deep-Level Tasks",
"score": 0.8,
"content": "<p>Engages rich semantic elaboration, integration with prior knowledge, and meaning-based encoding.</p>",
"datasets": [
{
"name": "Extended reasoning items (DOK Levels 3–4)",
"link": "https://www.structural-learning.com/post/webbs-depth-of-knowledge"
}
]
}
]
},
{
"id": "reasoning_type_classification",
"name": "1.1.2 Reasoning Type Classification",
"score": null,
"children": [
{
"id": "deductive_tasks",
"name": "Deductive Reasoning Tasks",
"score": 0.85,
"content": "<p>Deriving specific conclusions from general premises; guarantee of truth if premises valid.</p>",
"datasets": [
{
"name": "Syllogistic reasoning tests and deductive logic puzzles",
"link": "https://en.wikipedia.org/wiki/Syllogism"
}
]
},
{
"id": "inductive_tasks",
"name": "Inductive Reasoning Tasks",
"score": 0.8,
"content": "<p>Generalizing from specific instances; probabilistic support for conclusions.</p>",
"datasets": [
{
"name": "Hypothesis-generation tasks; pattern generalization benchmarks",
"link": "https://www.sciencedirect.com/topics/psychology/hypothesis-testing"
}
]
},
{
"id": "abductive_tasks",
"name": "Abductive Reasoning Tasks",
"score": 0.75,
"content": "<p>Inferring the best explanation for given data; reasoning to the most likely hypothesis.</p>",
"datasets": [
{
"name": "Medical diagnosis simulations; abductive inference drills",
"link": "https://en.wikipedia.org/wiki/Abductive_reasoning"
}
]
},
{
"id": "analogical_tasks",
"name": "Analogical Reasoning Tasks",
"score": 0.88,
"content": "<p>Mapping relational structure from one domain to another, recognizing similarity in relations.</p>",
"datasets": [
{
"name": "Analogical mapping tests (e.g., Raven’s Analogies)",
"link": "https://en.wikipedia.org/wiki/Raven%27s_Progressive_Matrices"
}
]
}
]
}
]
},
{
"id": "level2",
"name": "1.2 Level 2: Computational Thinking",
"score": null,
"content": "<p>Computational Thinking (CT) is a problem-solving methodology. Its evaluation has evolved from programming-specific tasks to more generalized, cross-curricular assessments.</p>",
"children": [
{
"id": "decomposition_tasks",
"name": "2.1 Decomposition Tasks",
"score": 0.83,
"content": "<p>Breaking complex problems into manageable sub-problems or system components.</p>",
"datasets": [
{
"name": "Programming assignments scored by decomposition quality rubrics",
"link": "https://sites.udel.edu/ctal/project-based-learning/computational-thinking-rubric/"
}
],
"children": [
{
"id": "problem_breaking",
"name": "Problem Breaking Tasks",
"score": 0.8,
"content": "<p>Identifying constituent elements of a problem and formulating subgoals.</p>",
"datasets": [
{
"name": "Code-trace decomposition questions",
"link": "#"
}
]
},
{
"id": "system_analysis",
"name": "System Analysis Tasks",
"score": 0.85,
"content": "<p>Modeling and analyzing interactions within system components.</p>",
"datasets": [
{
"name": "Systems modeling labs with rubric-referenced evaluation",
"link": "https://ieeexplore.ieee.org/document/10837599/"
}
]
}
]
},
{
"id": "pattern_recognition_tasks",
"name": "2.2 Pattern Recognition Tasks",
"score": 0.82,
"content": "<p>Identifying meaningful patterns, sequences, or structures in data.</p>",
"datasets": [
{
"name": "Sequence prediction benchmarks (e.g., BerCal CT challenges)",
"link": "https://sainshumanika.utm.my/index.php/sainshumanika/article/view/1987"
}
],
"children": [
{
"id": "sequential_pattern",
"name": "Sequential Pattern Tasks",
"score": 0.8,
"content": "<p>Detecting chronological or ordered patterns.</p>",
"datasets": [
{
"name": "Algorithmic sequence detection quizzes",
"link": "#"
}
]
},
{
"id": "structural_pattern",
"name": "Structural Pattern Tasks",
"score": 0.84,
"content": "<p>Recognizing spatial or relational structures.</p>",
"datasets": [
{
"name": "Graph-pattern matching exercises",
"link": "#"
}
]
}
]
},
{
"id": "abstraction_tasks",
"name": "2.3 Abstraction Tasks",
"score": 0.86,
"content": "<p>Formulating high-level representations, generalizing from specifics.</p>",
"datasets": [
{
"name": "Abstraction matrix tasks in CT rubrics",
"link": "https://sites.udel.edu/ctal/project-based-learning/computational-thinking-rubric/"
}
],
"children": [
{
"id": "conceptual_abstraction",
"name": "Conceptual Abstraction",
"score": 0.88,
"content": "<p>Extracting core concepts from complex details.</p>",
"datasets": [
{
"name": "Model-building assessments",
"link": "#"
}
]
},
{
"id": "procedural_abstraction",
"name": "Procedural Abstraction",
"score": 0.84,
"content": "<p>Encapsulating repeated procedures or operations.</p>",
"datasets": [
{
"name": "Function design tasks in coding rubrics",
"link": "https://sites.udel.edu/ctal/project-based-learning/computational-thinking-rubric/"
}
]
}
]
},
{
"id": "algorithmic_thinking_tasks",
"name": "2.4 Algorithmic Thinking Tasks",
"score": 0.87,
"content": "<p>Designing and analyzing step-by-step procedures to solve problems.</p>",
"datasets": [
{
"name": "Algorithm design and analysis labs with scoring rubrics",
"link": "https://sites.udel.edu/ctal/project-based-learning/computational-thinking-rubric/"
}
],
"children": [
{
"id": "algorithm_design",
"name": "Algorithm Design Tasks",
"score": 0.88,
"content": "<p>Crafting correct, efficient algorithms for specified problems.</p>",
"datasets": [
{
"name": "Pseudocode/rubric-scored assignments",
"link": "#"
}
]
},
{
"id": "algorithm_analysis",
"name": "Algorithm Analysis Tasks",
"score": 0.86,
"content": "<p>Reasoning about algorithm correctness and complexity.</p>",
"datasets": [
{
"name": "Big-O analysis problems",
"link": "https://www.bigocheatsheet.com/"
}
]
}
]
}
]
},
{
"id": "level3",
"name": "1.3 Level 3: Chain-of-Thought Reasoning",
"score": null,
"content": "<p>This level addresses datasets specifically designed to evaluate explicit, step-by-step reasoning processes, an area that has evolved rapidly with the advent of Large Language Models (LLMs).</p>",
"children": [
{
"id": "sequential_reasoning_tasks",
"name": "3.1 Sequential Reasoning Tasks",
"score": 0.89,
"content": "<p>Evaluating reasoning as a linear or branching sequence of inferences.</p>",
"datasets": [
{
"name": "Chain-of-Thought benchmarks such as GSM8K-Verification",
"link": "https://www.emergentmind.com/topics/gsm8k-verification"
}
],
"children": [
{
"id": "linear_cot",
"name": "Linear Chain-of-Thought",
"score": 0.88,
"content": "<p>Single-threaded deduction from premises to conclusion.</p>",
"datasets": [
{
"name": "Linear CoT challenges (GSM8K)",
"link": "https://github.com/openai/grade-school-math"
}
]
},
{
"id": "branching_cot",
"name": "Branching Chain-of-Thought",
"score": 0.9,
"content": "<p>Exploring alternative inference paths before selecting final outcome.</p>",
"datasets": [
{
"name": "Multi-path logic puzzles scored on path coverage",
"link": "#"
}
]
},
{
"id": "iterative_cot",
"name": "Iterative Chain-of-Thought",
"score": 0.89,
"content": "<p>Refining reasoning through successive revisions of partial solutions.</p>",
"datasets": [
{
"name": "Self-reflective CoT evaluation protocols",
"link": "https://www.emergentmind.com/topics/gsm8k-verification"
}
]
}
]
},
{
"id": "multimodal_reasoning_integration",
"name": "3.2 Multi-Modal Reasoning Integration",
"score": 0.85,
"content": "<p>Combining visual, embodied, and linguistic reasoning modes.</p>",
"datasets": [
{
"name": "Vision-language CoT tasks; embodied simulation benchmarks",
"link": "https://arxiv.org/abs/2305.05308"
}
],
"children": [
{
"id": "visual_cot",
"name": "Visual Chain-of-Thought",
"score": 0.86,
"content": "<p>Integrating visual interpretations into step-by-step reasoning.</p>",
"datasets": [
{
"name": "Visual-CoT datasets (e.g., MME-CoT)",
"link": "https://arxiv.org/abs/2405.14341"
}
]
},
{
"id": "embodied_cot",
"name": "Embodied Chain-of-Thought",
"score": 0.84,
"content": "<p>Simulating physical interactions in reasoning chains.</p>",
"datasets": [
{
"name": "Robotics CoT tasks",
"link": "#"
}
]
}
]
},
{
"id": "meta_reasoning_tasks",
"name": "3.3 Meta-Reasoning Tasks",
"score": 0.87,
"content": "<p>Monitoring and controlling one’s own chain-of-thought processes.</p>",
"datasets": [
{
"name": "Meta-Reasoning protocols with feeling-of-rightness ratings",
"link": "https://dacemirror.sci-hub.se/journal-article/c2286260f7ebbc44e1d06675e66fc87d/ackerman2017.pdf"
}
],
"children": [
{
"id": "strategy_selection",
"name": "Strategy Selection Tasks",
"score": 0.88,
"content": "<p>Choosing among alternative reasoning strategies based on task demands.</p>",
"datasets": [
{
"name": "Strategy-selection experiments with process tracing",
"link": "#"
}
]
},
{
"id": "process_monitoring",
"name": "Process Monitoring Tasks",
"score": 0.86,
"content": "<p>Tracking intermediate confidence and detecting errors.</p>",
"datasets": [
{
"name": "Feeling-of-error paradigms",
"link": "https://dacemirror.sci-hub.se/journal-article/c2286260f7ebbc44e1d06675e66fc87d/ackerman2017.pdf"
}
]
}
]
}
]
},
{
"id": "level4",
"name": "1.4 Level 4: Domain-Specific Reasoning",
"score": null,
"content": "<p>This level addresses reasoning that relies on specialized knowledge and principles from distinct academic or professional domains. Datasets test not only logical processes but also the correct application of domain-specific content.</p>",
"children": [
{
"id": "mathematical_reasoning",
"name": "4.1 Mathematical Reasoning",
"score": 0.92,
"content": "<p>Applying numerical, algebraic, and geometric principles in proofs and problem-solving.</p>",
"datasets": [
{
"name": "Math CoT benchmarks (GSM8K-Verification); standardized math tests (TIMSS)",
"link": "https://www.emergentmind.com/topics/gsm8k-verification"
}
],
"children": [
{
"id": "arithmetic_reasoning",
"name": "Arithmetic Reasoning",
"score": 0.9,
"content": "<p>Multi-step numerical calculations and unit reasoning.</p>",
"datasets": [
{
"name": "GSM8K arithmetic problems",
"link": "https://github.com/openai/grade-school-math"
}
]
},
{
"id": "algebraic_reasoning",
"name": "Algebraic Reasoning",
"score": 0.92,
"content": "<p>Symbolic manipulation and equation solving.</p>",
"datasets": [
{
"name": "Algebraic proof rubrics",
"link": "#"
}
]
},
{
"id": "geometric_reasoning",
"name": "Geometric Reasoning",
"score": 0.95,
"content": "<p>Spatial deduction, proof construction.</p>",
"datasets": [
{
"name": "Geometry proof assessments",
"link": "#"
}
]
}
]
},
{
"id": "scientific_reasoning",
"name": "4.2 Scientific Reasoning",
"score": 0.89,
"content": "<p>Designing experiments, analyzing data, inferring causality.</p>",
"datasets": [
{
"name": "Experimental design tasks; PISA science frameworks",
"link": "https://www.oecd.org/pisa/pisaproducts/pisa-2025-science-framework.pdf"
}
],
"children": [
{
"id": "experimental_design",
"name": "Experimental Design Reasoning",
"score": 0.88,
"content": "<p>Formulating hypotheses, controls, and valid protocols.</p>",
"datasets": [
{
"name": "Science inquiry rubrics",
"link": "#"
}
]
},
{
"id": "data_analysis",
"name": "Data Analysis Reasoning",
"score": 0.9,
"content": "<p>Interpreting charts, statistical inference.</p>",
"datasets": [
{
"name": "Data-analysis problem sets",
"link": "#"
}
]
}
]
},
{
"id": "logical_formal_reasoning",
"name": "4.3 Logical and Formal Reasoning",
"score": 0.85,
"content": "<p>Applying formal symbolic logic and proof systems.</p>",
"datasets": [
{
"name": "Propositional/predicate logic exams",
"link": "#"
}
],
"children": [
{
"id": "propositional_logic",
"name": "Propositional Logic Tasks",
"score": 0.84,
"content": "<p>Truth-table analysis, logical equivalences.</p>",
"datasets": [
{
"name": "Logic course assessments",
"link": "#"
}
]
},
{
"id": "predicate_logic",
"name": "Predicate Logic Tasks",
"score": 0.86,
"content": "<p>Quantifier manipulation, formal derivations.</p>",
"datasets": [
{
"name": "Predicate calculus assignments",
"link": "#"
}
]
}
]
},
{
"id": "commonsense_reasoning",
"name": "4.4 Commonsense Reasoning",
"score": 0.8,
"content": "<p>Everyday causal and situational inference.</p>",
"datasets": [
{
"name": "Winograd Schema Challenge",
"link": "https://winogrande.allenai.org/"
}
],
"children": [
{
"id": "everyday_reasoning",
"name": "Everyday Reasoning Tasks",
"score": 0.78,
"content": "<p>Inferences about routine causal chains.</p>",
"datasets": [
{
"name": "Commonsense QA datasets",
"link": "https://www.tau-nlp.sites.tau.ac.il/commonsenseqa"
}
]
},
{
"id": "causal_reasoning",
"name": "Causal Reasoning Tasks",
"score": 0.82,
"content": "<p>Inferring cause-effect relationships from scenarios.</p>",
"datasets": [
{
"name": "Causal reasoning benchmarks",
"link": "#"
}
]
}
]
}
]
},
{
"id": "level5",
"name": "1.5 Level 5: Metacognitive Reasoning",
"score": null,
"content": "<p>This level focuses on the higher-order processes of self-reflection and self-regulation, where the reasoner actively monitors, controls, and evaluates their own cognitive processes.</p>",
"children": [
{
"id": "self_monitoring_tasks",
"name": "Self-Monitoring Tasks",
"score": 0.88,
"content": "<p>Reflecting on one’s own knowledge state and identifying gaps.</p>",
"datasets": [
{
"name": "Metacognitive awareness inventories",
"link": "https://services.viu.ca/sites/default/files/metacognitive-awareness-inventory.pdf"
}
]
},
{
"id": "confidence_calibration",
"name": "Confidence Calibration",
"score": 0.87,
"content": "<p>Aligning confidence ratings with actual accuracy.</p>",
"datasets": [
{
"name": "Calibration curves in decision tasks",
"link": "https://scikit-learn.org/stable/modules/calibration.html"
}
]
},
{
"id": "progress_tracking",
"name": "Progress Tracking",
"score": 0.85,
"content": "<p>Monitoring advancement toward solution goals.</p>",
"datasets": [
{
"name": "Self-report logs in problem-solving studies",
"link": "#"
}
]
},
{
"id": "self_regulation_tasks",
"name": "Self-Regulation Tasks",
"score": 0.86,
"content": "<p>Adjusting strategies dynamically to meet task demands.</p>",
"datasets": [
{
"name": "Study-strategy intervention assessments",
"link": "#"
}
]
},
{
"id": "strategy_adaptation",
"name": "Strategy Adaptation",
"score": 0.88,
"content": "<p>Switching reasoning approaches based on performance feedback.</p>",
"datasets": [
{
"name": "Adaptive problem-solving paradigms",
"link": "#"
}
]
},
{
"id": "error_correction",
"name": "Error Correction",
"score": 0.89,
"content": "<p>Detecting and revising faulty inferences in reasoning chains.</p>",
"datasets": [
{
"name": "Think-aloud error-detection tasks",
"link": "https://www.nngroup.com/articles/thinking-aloud/"
}
]
},
{
"id": "reflection_evaluation",
"name": "Reflection and Evaluation",
"score": 0.87,
"content": "<p>Critically appraising one’s solution and reasoning process.</p>",
"datasets": [
{
"name": "Post-task reflection protocols",
"link": "#"
}
]
},
{
"id": "solution_evaluation_tasks",
"name": "Solution Evaluation Tasks",
"score": 0.86,
"content": "<p>Judging the adequacy and efficiency of proposed solutions.</p>",
"datasets": [
{
"name": "Rubric-scored solution critiques",
"link": "#"
}
]
},
{
"id": "learning_transfer_tasks",
"name": "Learning Transfer Tasks",
"score": 0.88,
"content": "<p>Applying previously learned reasoning patterns to new domains.</p>",
"datasets": [
{
"name": "Far-transfer problem sets",
"link": "#"
}
]
}
]
},
{
"id": "level6",
"name": "1.6 Level 6: Task Complexity Modulation",
"score": null,
"content": "<p>This level addresses how the inherent characteristics of a task—its information load, length, and degree of ambiguity—can be modulated to create different levels of reasoning challenge.</p>",
"children": [
{
"id": "info_processing_load",
"name": "6.1 Information Processing Load",
"score": 0.8,
"content": "<p>Managing working memory demands and information flow.</p>",
"datasets": [
{
"name": "NASA-TLX mental-load ratings",
"link": "https://humansystems.arc.nasa.gov/groups/tlx/"
}
],
"children": [
{
"id": "low_cog_load",
"name": "Low Cognitive Load Tasks",
"score": 0.75,
"content": "<p>Simple information presentation, minimal splits of attention.</p>",
"datasets": [
{
"name": "Cognitive load experiments with eye-tracking",
"link": "#"
}
]
},
{
"id": "medium_cog_load",
"name": "Medium Cognitive Load Tasks",
"score": 0.8,
"content": "<p>Moderate multitasking or data integration requirements.</p>",
"datasets": [
{
"name": "CLT manipulation studies",
"link": "#"
}
]
},
{
"id": "high_cog_load",
"name": "High Cognitive Load Tasks",
"score": 0.85,
"content": "<p>Complex information integration under time pressure.</p>",
"datasets": [
{
"name": "High-load dual-task paradigms",
"link": "#"
}
]
}
]
},
{
"id": "reasoning_length_depth",
"name": "6.2 Reasoning Length and Depth",
"score": 0.82,
"content": "<p>Scaling tasks by number of inference steps and conceptual depth.</p>",
"datasets": [
{
"name": "Short vs. long-chain CoT benchmarks",
"link": "https://github.com/openai/grade-school-math"
}
],
"children": [
{
"id": "short_form_reasoning",
"name": "Short-Form Reasoning",
"score": 0.8,
"content": "<p>Few inference steps, limited conceptual jump.</p>",
"datasets": [
{
"name": "Short CoT demonstration tasks",
"link": "#"
}
]
},
{
"id": "medium_form_reasoning",
"name": "Medium-Form Reasoning",
"score": 0.82,
"content": "<p>Moderate chain length, moderate branching.</p>",
"datasets": [
{
"name": "Mid-length reasoning benchmarks",
"link": "#"
}
]
},
{
"id": "long_form_reasoning",
"name": "Long-Form Reasoning",
"score": 0.85,
"content": "<p>Extensive multi-step, multi-branch reasoning.</p>",
"datasets": [
{
"name": "Extended CoT problems on GSM8K-Ver",
"link": "https://www.emergentmind.com/topics/gsm8k-verification"
}
]
}
]
},
{
"id": "uncertainty_ambiguity",
"name": "6.3 Uncertainty and Ambiguity Levels",
"score": 0.78,
"content": "<p>Degree of ill-posedness and multiple valid solution paths.</p>",
"datasets": [
{
"name": "Well-defined vs. open-ended problem inventories",
"link": "#"
}
],
"children": [
{
"id": "well_defined_tasks",
"name": "Well-Defined Tasks",
"score": 0.8,
"content": "<p>Clear goals and solution methods.</p>",
"datasets": [
{
"name": "Structured logic puzzles",
"link": "#"
}
]
},
{
"id": "ill_defined_tasks",
"name": "Ill-Defined Tasks",
"score": 0.75,
"content": "<p>Under-specified goals requiring interpretation.</p>",
"datasets": [
{
"name": "Ill-structured case studies",
"link": "#"
}
]
},
{
"id": "open_ended_tasks",
"name": "Open-Ended Tasks",
"score": 0.79,
"content": "<p>Multiple valid solutions, creative reasoning required.</p>",
"datasets": [
{
"name": "Design-thinking challenges",
"link": "#"
}
]
}
]
}
]
}
]
};
const navTreeContainer = document.getElementById('nav-tree');
const contentPane = document.getElementById('content-pane');
let chartInstance = null;
function processData() {
const taxonomyMap = new Map();
function traverse(nodes) {
nodes.forEach(node => {
taxonomyMap.set(node.name, node);
if (!node.prompts) {
node.prompts = [];
}
if (node.children) {
traverse(node.children);
}
});
}
traverse(taxonomyData.children);
const taxonomyNameMapping = {
"Surface-Level Tasks": "Surface-Level Tasks",
"Intermediate-Level Tasks": "Intermediate-Level Tasks",
"Deep-Level Tasks": "Deep-Level Tasks",
"Linear Chain-of-Thought": "Linear Chain-of-Thought",
"Branching Chain-of-Thought": "Branching Chain-of-Thought",
"Iterative Chain-of-Thought": "Iterative Chain-of-Thought",
"Procedural Abstraction": "Procedural Abstraction",
"Conceptual Abstraction": "Conceptual Abstraction",
"Decomposition Tasks": "2.1 Decomposition Tasks",
"Mathematical Reasoning": "4.1 Mathematical Reasoning",
"Data Analysis Reasoning": "Data Analysis Reasoning",
"Algorithm Design Tasks": "Algorithm Design Tasks",
"System Analysis Tasks": "System Analysis Tasks",
"Scientific Reasoning": "4.2 Scientific Reasoning",
"Multithreading": "High Cognitive Load Tasks",
"Algebraic Reasoning": "Algebraic Reasoning",
"Self-Monitoring Tasks": "Self-Monitoring Tasks",
"Error Correction": "Error Correction",
"Visual Chain-of-Thought": "Visual Chain-of-Thought",
"Meta-Reasoning Tasks": "3.3 Meta-Reasoning Tasks",
"Reflection and Evaluation": "Reflection and Evaluation",
"Algorithm Analysis Tasks": "Algorithm Analysis Tasks",
"High Cognitive Load Tasks": "High Cognitive Load Tasks",
"Experimental Design Reasoning": "Experimental Design Reasoning",
"Inductive Reasoning Tasks": "Inductive Reasoning Tasks",
"Structural Pattern Tasks": "Structural Pattern Tasks",
"Big-O analysis problems": "Algorithm Analysis Tasks",
"Graph-pattern matching exercises": "Structural Pattern Tasks",
"Long-Form Reasoning": "Long-Form Reasoning",
"Open-Ended Tasks": "Open-Ended Tasks",
"Logical and Formal Reasoning": "4.3 Logical and Formal Reasoning",
"Self-Regulation Tasks": "Self-Regulation Tasks",
"Solution Evaluation Tasks": "Solution Evaluation Tasks",
"Learning Transfer Tasks": "Learning Transfer Tasks",
"Sequential Pattern Tasks": "Sequential Pattern Tasks"
};
promptsData.forEach(prompt => {
prompt.taxonomies.forEach(tax => {
let targetNodeName = taxonomyNameMapping[tax] || tax;
let node = taxonomyMap.get(targetNodeName);
if (!node) {
for(let [key, value] of taxonomyMap.entries()){
if(key.includes(tax) || tax.includes(key)){
node = value;
break;
}
}
}
if (node) {
node.prompts.push({ text: prompt.prompt, difficulty: prompt.difficulty });
}
});
});
}
function renderNavigation(nodes, parentElement, level = 0) {
const ul = document.createElement('ul');
if (level > 0) {
ul.className = 'pl-4 hidden';
}
nodes.forEach(node => {
const li = document.createElement('li');
const div = document.createElement('div');
div.className = `nav-item flex items-center justify-between p-2 my-1 rounded-md cursor-pointer hover:bg-slate-100 transition-colors`;
div.dataset.id = node.id;
const nameSpan = document.createElement('span');
nameSpan.textContent = node.name;
nameSpan.className = 'flex-grow';
div.appendChild(nameSpan);
if (node.children && node.children.length > 0) {
const chevron = document.createElement('span');
chevron.innerHTML = `&#9656;`; // right-pointing triangle
chevron.className = 'chevron text-xs mr-2 text-slate-400';
div.insertBefore(chevron, nameSpan);
}
li.appendChild(div);
if (node.children && node.children.length > 0) {
const childUl = renderNavigation(node.children, li, level + 1);
li.appendChild(childUl);
}
ul.appendChild(li);
});
parentElement.appendChild(ul);
return ul;
}
function renderContent(nodeId) {
function findNode(nodes, id) {
for (const node of nodes) {
if (node.id === id) return node;
if (node.children) {
const found = findNode(node.children, id);
if (found) return found;
}
}
return null;
}
const node = findNode([taxonomyData], nodeId) || findNode(taxonomyData.children, nodeId);
if (node) {
contentPane.innerHTML = ''; // Clear previous content
let scoreHTML = node.score ? `<span class="ml-4 text-sm font-semibold text-teal-700 bg-teal-50 px-2.5 py-1 rounded-full">Score: ${node.score.toFixed(2)}</span>` : '';
let contentHTML = `<div class="content-fade-in"><div class="flex items-center mb-4"><h2 class="text-3xl font-bold text-slate-800">${node.name}</h2>${scoreHTML}</div>`;
if(node.content) {
contentHTML += `<div class="prose max-w-none prose-slate">${node.content}</div>`;
}
if (node.datasets && node.datasets.length > 0) {
contentHTML += `<h3 class="text-xl font-bold text-slate-700 mt-8 mb-4">Key Datasets</h3><div class="grid grid-cols-1 lg:grid-cols-2 gap-4">`;
node.datasets.forEach(dataset => {
contentHTML += `
<div class="bg-slate-50 p-4 rounded-lg border border-slate-200 hover:shadow-sm transition-shadow">
<h4 class="font-bold text-teal-700 hover:text-teal-600">
<a href="${dataset.link}" target="_blank" rel="noopener noreferrer" class="flex items-center">
${dataset.name}
<svg xmlns="http://www.w3.org/2000/svg" width="16" height="16" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="ml-2 shrink-0"><path d="M18 13v6a2 2 0 0 1-2 2H5a2 2 0 0 1-2-2V8a2 2 0 0 1 2-2h6"></path><polyline points="15 3 21 3 21 9"></polyline><line x1="10" y1="14" x2="21" y2="3"></line></svg>
</a>
</h4>
</div>
`;
});
contentHTML += `</div>`;
}
if (node.prompts && node.prompts.length > 0) {
contentHTML += `<h3 class="text-xl font-bold text-slate-700 mt-8 mb-4">Example Prompts</h3><div class="space-y-4">`;
node.prompts.forEach(prompt => {
contentHTML += `
<div class="bg-slate-50 p-4 rounded-lg border border-slate-200 shadow-sm">
<p class="text-slate-800">${prompt.text}</p>
<p class="text-sm text-teal-700 font-semibold mt-2">Difficulty: ${prompt.difficulty}</p>
</div>
`;
});
contentHTML += `</div>`;
}
contentHTML += `</div>`;
contentPane.innerHTML = contentHTML;
if (nodeId === 'intro') {
setTimeout(renderIntroChart, 0);
}
}
}
function renderIntroChart() {
if (chartInstance) {
chartInstance.destroy();
}
const ctx = document.getElementById('datasetChart');
if (!ctx) return;
const data = {
labels: [
'Psychometric Tests',
'Performance Rubrics',
'Large-Scale QA Datasets',
'Simulations & Puzzles',
'Self-Report Inventories',
'Subjective Rating Scales'
],
datasets: [{
label: 'Dataset Categories',
data: [5, 4, 6, 3, 3, 1],
backgroundColor: [
'#0d9488',
'#0f766e',
'#115e59',
'#134e4a',
'#2dd4bf',
'#5eead4'
],
borderColor: '#ffffff',
borderWidth: 2,
hoverOffset: 4
}]
};
chartInstance = new Chart(ctx, {
type: 'doughnut',
data: data,
options: {
responsive: true,
maintainAspectRatio: false,
plugins: {
legend: {
position: 'top',
labels: {
color: '#1e293b'
}
},
title: {
display: false,
text: 'Dataset Category Distribution'
}
}
}
});
}
navTreeContainer.addEventListener('click', function(e) {
const navItem = e.target.closest('.nav-item');
if (navItem) {
const nodeId = navItem.dataset.id;
const childList = navItem.parentElement.querySelector('ul');
if (childList) {
childList.classList.toggle('hidden');
navItem.classList.toggle('open');
}
document.querySelectorAll('.nav-item.active').forEach(item => item.classList.remove('active'));
navItem.classList.add('active');
renderContent(nodeId);
}
});
// Initial render
processData();
renderNavigation(taxonomyData.children, navTreeContainer);
renderContent('intro');
document.querySelector('.nav-item[data-id="intro"]').classList.add('active');
});
</script>
</body>
</html>