Datasets:
messages listlengths 2 2 |
|---|
[
{
"role": "user",
"content": "What are the implications of the Eocene-Oligocene transition's increased sedimentation rates in the Olympic Peninsula's sedimentary basins on the regional paleogeography and the subsequent development of the Cascadia subduction zone's forearc geometry?"
},
{
"role": "as... |
[
{
"role": "user",
"content": "What are the optimal conditions for using microbial-induced calcite precipitation as a sustainable method for self-healing concrete, specifically in terms of bacterial strain selection, nutrient supplementation, and environmental factors, to improve durability and reduce mainte... |
[
{
"role": "user",
"content": "What is the optimal ratio of polylactic acid (PLA) to polyhydroxyalkanoates (PHA) in a biodegradable plastic blend to achieve a degradation rate of 50% within 6 months in a marine environment with average temperatures ranging from 15°C to 25°C and pH levels between 7.5 and 8.5?... |
[
{
"role": "user",
"content": "How can a polycentric urban structure, with multiple secondary cities and a range of small to medium-sized towns, be effectively integrated into a regional transportation network to promote more equitable economic growth and reduce peripherality, particularly in a region with a... |
[
{
"role": "user",
"content": "How can I effectively integrate the concept of intersectionality into my lesson plans on the Civil Rights Movement, specifically when teaching about the roles of women and LGBTQ+ individuals in the movement, while also addressing the potential skepticism or pushback from some s... |
[
{
"role": "user",
"content": "How can the supervaluationist approach to vagueness be reconciled with the Sorites paradox, particularly in cases where the penumbral connections between adjacent degrees of a soritical series are context-dependent and subject to semantic holism, thereby threatening to undermin... |
[
{
"role": "user",
"content": "What are the specific parameters and G-code settings required to optimize the performance of a Haas VF-2 CNC milling machine when machining a complex aluminum alloy part with a combination of 3D curved surfaces and high-aspect-ratio features, while maintaining a surface finish ... |
[
{
"role": "user",
"content": "What are the implications of the recent discovery of the SARS-CoV-2 N-protein's ability to inhibit the activity of the host cell's autophagy-related gene 5 (ATG5) on the development of COVID-19 vaccines that target the nucleocapsid protein, and how might this impact the efficac... |
[
{
"role": "user",
"content": "How might the distinction between 'jurisgenesis' and 'jurispathy' in Robert Cover's theory of constitutionalism inform an analysis of the Supreme Court's role in shaping the meaning of 'commerce' in the Commerce Clause, particularly in light of the tension between the Court's t... |
[
{
"role": "user",
"content": "How can I effectively adapt the Feynman diagram representation of particle scattering processes to illustrate the concept of time reversal symmetry to students who have only recently been introduced to special relativity and may not have a strong background in group theory?"
... |
[
{
"role": "user",
"content": "What specific modifications would be required to adapt the Corliss valve gear system, as used in the 1876 Corliss steam engine, to operate efficiently with a more modern, high-pressure boiler system, such as those used in the early 20th-century power plants, while still maintai... |
[
{
"role": "user",
"content": "How can I effectively demonstrate the concept of broken color to my students, specifically in relation to Claude Monet's use of optical mixing in his series of water lily paintings, while also taking into account the challenges of translating this technique from oil paint to wa... |
[
{
"role": "user",
"content": "How do the variations in sinuosity and meandering wavelength of a river, such as the Amazon River, impact the distribution and morphology of its anabranching and distributary channels, and what are the implications for sedimentation patterns and deltaic landform development in ... |
[
{
"role": "user",
"content": "How do the differences in the historical development of the concept of Rechtsdogmatik in German civil law and legal formalism in American common law influence the way each tradition approaches the relationship between jurisprudence, legislation, and judicial decision-making, pa... |
[
{
"role": "user",
"content": "What is the historical and sociological significance of the 1966 Mississippi Freedom Summer Project's emphasis on voter registration drives and community organizing in predominantly African-American counties, and how did this specific approach influence the subsequent developme... |
[
{
"role": "user",
"content": "How can I effectively integrate project-based learning into my kindergarten classroom's literacy block, while still meeting the phonics and phonemic awareness requirements of our state's early childhood education standards, and what types of scaffolding techniques can I use to ... |
[
{
"role": "user",
"content": "How does the portrayal of female spiritual ecstasy in the works of 19th-century American women writers such as Emily Dickinson and Harriet Beecher Stowe intersect with or subvert the patriarchal ideologies of their time, and what implications do these representations hold for c... |
[
{
"role": "user",
"content": "How can I effectively use gel electrophoresis to separate and identify the different types of biomolecules, specifically proteins and DNA, in a sample of E. coli cells that have been exposed to varying concentrations of antibiotics, in order to determine the impact of antibioti... |
[
{
"role": "user",
"content": "How can I adapt the 'Number Lines' math concept to create a differentiated instruction activity that addresses the varying learning needs of my third-grade students, specifically those who struggle with visual-spatial awareness, and integrate it with a literacy component by hav... |
[
{
"role": "user",
"content": "How can I effectively leverage spatial analysis and geographic information systems (GIS) to identify and characterize COVID-19 hotspots in urban areas with high concentrations of marginalized populations, while controlling for the effects of socioeconomic factors, housing densi... |
[
{
"role": "user",
"content": "How do the linguistic and narrative structures employed by Maori writers such as Patricia Grace and Keri Hulme in their representations of whakapapa (genealogy) and whanau (family) relationships subvert or reinforce the dominant Pakeha notions of history, identity, and belongin... |
[
{
"role": "user",
"content": "What is the most effective way to clinically distinguish between a pronator teres syndrome and a median nerve entrapment at the level of the ligament of Struthers, considering the variability in anatomical relationships between the median nerve and the pronator teres muscle in ... |
[
{
"role": "user",
"content": "How can I effectively incorporate loose parts materials, such as rocks, sticks, and fabric scraps, into my preschool classroom's outdoor play area to encourage open-ended exploration, creative problem-solving, and STEM concept development in children aged 4-5, while also ensuri... |
[
{
"role": "user",
"content": "How can I optimize the convergence of the PML (Perfectly Matched Layer) boundary conditions in my Ansys HFSS simulations of a microstrip patch antenna array to accurately capture the effects of mutual coupling on the S-parameters, while minimizing the computational resources re... |
[
{
"role": "user",
"content": "What was the extent to which the Indian National Congress's adoption of Gandhian non-violent resistance in the 1920s was influenced by the party's internal debates and criticisms, particularly from figures like Subhas Chandra Bose and Jawaharlal Nehru, who were known to have re... |
End of preview. Expand in Data Studio
enPurified Collection
Dataset Overview
This dataset is a pruned version of https://huggingface.co/datasets/glaiveai/reasoning-v1-20m
The enPurified collection represents a rigorous effort to distill existing high-value datasets into their purest English prose form. While the open-source community provides excellent resources for code (e.g., StackV2) and mathematics (e.g., OpenMath), high-quality, noise-free English prose often remains buried under multimodal debris.
The purpose of this collection is to apply a strict series of heuristic tests to remove coding languages, mathematical notation, foreign languages, and low-quality web text. The result is a corpus dedicated exclusively to high-quality reasoning and storytelling, formatted in the standard OpenAI messages schema for immediate use in training or fine-tuning.
For source datasets containing large contiguous strings (such as novels or long-form articles), a preprocessing step utilizes LangChain to chunk text into paragraphs while preserving context, ensuring the output remains compatible with the message format.
This heuristic pruning process reduced the dataset from 22,199,375 rows to 14,270,411 rows of high-quality English prose.
Pruning Pipeline
The dataset generation process employs a multi-stage strict filtering pipeline designed to aggressively cull low-quality or out-of-domain data. The pipeline is implemented via the following heuristics:
1. Normalization & Pre-Processing
- Format Standardization: All data is converted to the OpenAI messages format (
{"messages": [...]}). - Tag Normalization: Specialized tokens (e.g., solution blocks) are stripped, and reasoning tags (like
<|thought|>) are standardized to<think>/</think>. - Short Response Cull: Assistant responses under 350 characters are immediately discarded to ensure only substantial reasoning or prose remains.
2. The "No-Code / No-Math" Gate
- Symbol Density Check: Any text where code-like symbols (
{,},[,],;, etc.) constitute more than 2.5% of the character count is rejected. - Code Line Detection: If more than 15% of the lines end in code-syntax markers (
;,{,}), the sample is dropped. - Keyword Ban List: Documents containing specific programming keywords (e.g.,
def main():,import torch,std::,console.log) are filtered out. - Math Gate: Text containing LaTeX delimiters (
$$,\[,\begin{equation}) or excessive backslashes is removed to ensure the dataset focuses purely on natural language.
3. Structural Integrity & Syntax
- Strict Syntax: Documents are filtered for length (100 - 400k characters) and checked for broken HTML or forbidden DOM tags.
- Quiz/MCQ Filter: Heuristics detect and remove multiple-choice questions (e.g., distinct patterns of "Option A", "Option B") to prevent data contamination from simple evaluation benchmarks.
- Line Quality: Texts where over 60% of lines are extremely short (<20 chars) are discarded to remove list-heavy or chat-log style data.
4. Literary Quality & Prose Identification
- Lexical Diversity (MTLD): The pipeline calculates the Measure of Textual Lexical Diversity (MTLD). Only documents with a score ≥ 80.0 are retained, ensuring a vocabulary richness comparable to academic writing or high-quality novels.
- English Prose Verification:
- Stopword Density: The text must have a stopword density (words like "the", "is", "of") greater than 27%. This effectively filters out "keyword soup," log files, or non-standard English that lacks grammatical structure.
- ASCII Purity: 95% of characters must be standard ASCII.
- Word Complexity: The mean word length must fall between 4.25 and 11 characters, filtering out overly simplistic text or garbage data strings.
5. Safety & Repetition
- Repetition Check: An N-gram analysis ensures unique trigrams constitute at least 50% of the text, removing repetitive loops common in generated data.
- Toxicity Filter: A keyword-based safety check removes content containing explicit NSFW terms.
License
This dataset is a filtered derivative of existing open-source datasets. Users should refer to the license of the original source dataset (specified in the repository metadata or original card) to determine usage rights and attribution requirements.
- Downloads last month
- 167