Datasets:
id stringlengths 32 32 ⌀ | instruction_seed stringlengths 34 28.7k | output stringlengths 1.96k 81k ⌀ | source stringclasses 10
values | license stringclasses 4
values | dataset stringclasses 4
values | split stringclasses 4
values | difficulty int64 6 10 | solution stringlengths 8 12k ⌀ | index stringclasses 555
values | _source stringclasses 2
values | difficulty_reasoning stringlengths 189 958 | __original_row_idx int64 0 459k | ms_id int64 0 38.4k | generated_text stringlengths 1.55k 1.84M | conversations listlengths 2 2 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
839e9414076426ea98e166278c495f2d | "Cold winter evenings in Tomsk are very boring — nobody wants be on the streets at such a time. Re(...TRUNCATED) | "<think>\nOkay, let's see. I need to compute the expected number of minutes the game will last when (...TRUNCATED) | codeforces | cc-by-4.0 | code_contests | train | 8 | "import sys\nfrom functools import lru_cache\n\ndef main():\n sys.setrecursionlimit(1 << 25)\n (...TRUNCATED) | null | nvidia/OpenCodeReasoning | "The problem requires a sophisticated understanding of probability and combinatorial optimization to(...TRUNCATED) | 76,549 | 276 | "<think>\nOkay, let's try to figure out how to solve this problem. So, the problem is about a game c(...TRUNCATED) | [{"from":"human","value":"Cold winter evenings in Tomsk are very boring — nobody wants be on the s(...TRUNCATED) |
b1092142ac236eea9f72313b637fc12e | "As you know, the game of \"Nim\" is played with n piles of stones, where the i-th pile initially co(...TRUNCATED) | "<think>\nOkay, let's see. We need to find the probability that Petya wins the Gambling Nim game giv(...TRUNCATED) | codeforces | cc-by-4.0 | code_contests | train | 8 | "import sys\nfrom math import gcd\n\ndef main():\n n = int(sys.stdin.readline())\n initial_xor(...TRUNCATED) | null | nvidia/OpenCodeReasoning | "The problem combines elements of game theory with a probabilistic approach to determine the outcome(...TRUNCATED) | 43,419 | 277 | "<think>\nOkay, let's try to figure out how to solve this Gambling Nim problem. \n\nSo, the problem (...TRUNCATED) | [{"from":"human","value":"As you know, the game of \"Nim\" is played with n piles of stones, where t(...TRUNCATED) |
null | "sandbox (deleted) \nLets define a matrix of 9s as:\n$$ N = \\begin{bmatrix} 9&9&9\\\\9&9&9\\\\9&9&9(...TRUNCATED) | null | null | null | null | null | 8 | null | null | stackexchange_codegolf | "The problem involves manipulating a matrix based on defined rules which requires a combination of a(...TRUNCATED) | 38,595 | 278 | "<think>\nOkay, let's see. I need to solve this problem where I have to explode numbers in a matrix (...TRUNCATED) | [{"from":"human","value":"sandbox (deleted) \nLets define a matrix of 9s as:\n$$ N = \\begin{bmatrix(...TRUNCATED) |
d182f81c365a9f472a80d4247178edbc | "A point belongs to a triangle if it lies inside the triangle or on one of its sides. Two triangles (...TRUNCATED) | "<think>\nOkay, let's try to solve this problem. Hmm, the task is to find the number of pairs of dis(...TRUNCATED) | codeforces | cc-by-4.0 | code_contests | train | 8 | "import sys\nfrom itertools import combinations\n\ndef main():\n n = int(sys.stdin.readline())\n (...TRUNCATED) | null | nvidia/OpenCodeReasoning | "The problem requires deep mathematical insights and involves complex algorithmic implementations, p(...TRUNCATED) | 55,227 | 279 | "<think>\nOkay, I need to solve this problem where I have to find the number of ways to choose two d(...TRUNCATED) | [{"from":"human","value":"A point belongs to a triangle if it lies inside the triangle or on one of (...TRUNCATED) |
66f23b18404ff661d1b59d50f8024fee | "* This story is fiction and has nothing to do with real people or groups.\n\nSocial games have beco(...TRUNCATED) | "<think>\nOkay, I need to solve this programming problem. Let's read the problem carefully.\n\nThe p(...TRUNCATED) | aizu | cc-by-4.0 | code_contests | train | 8 | "import math\n\nn = int(input())\np = [float(input()) for _ in range(n)]\nsqrt_p = [math.sqrt(pi) fo(...TRUNCATED) | null | nvidia/OpenCodeReasoning | "The problem requires deep mathematical insights combined with complex algorithmic implementations, (...TRUNCATED) | 6,521 | 280 | "<think>\nOkay, let's try to figure out how to solve this problem. \n\nSo the problem is about minim(...TRUNCATED) | [{"from":"human","value":"* This story is fiction and has nothing to do with real people or groups.\(...TRUNCATED) |
702ee32a47350ae3874ae292fc05d3e0 | "Consider the following equation: \n\n<image> where sign [a] represents the integer part of number a(...TRUNCATED) | "<think>\nOkay, let's see. The problem is to find the nth term in the sequence of z values where the(...TRUNCATED) | codeforces | cc-by-4.0 | code_contests | train | 8 | "n = int(input())\nmod = 10**9 + 7\nresult = 1\nfor i in range(1, n + 1):\n result = result * (2 (...TRUNCATED) | null | nvidia/OpenCodeReasoning | "The problem involves understanding the integer part of a mathematical expression and finding specif(...TRUNCATED) | 321,622 | 281 | "<think>\nOkay, let's try to figure out this problem. The task is to find the nth number in a sequen(...TRUNCATED) | [{"from":"human","value":"Consider the following equation: \n\n<image> where sign [a] represents the(...TRUNCATED) |
null | "The task is to count the number of disjoint 11 blocks in a 64-bit word, using the minimum number of(...TRUNCATED) | null | null | null | null | null | 8 | null | null | stackexchange_codegolf | "The problem involves counting disjoint pairs of 1-bits in a 64-bit integer with a minimum instructi(...TRUNCATED) | 51,238 | 282 | "<think>\nOkay, let's see. I need to find the number of non-overlapping neighboring pairs of 1s in a(...TRUNCATED) | [{"from":"human","value":"The task is to count the number of disjoint 11 blocks in a 64-bit word, us(...TRUNCATED) |
null | "Input: a whole positive number greater than 4\nOutput: A whole positive number that describes the h(...TRUNCATED) | null | null | null | null | null | 8 | null | null | stackexchange_codegolf | "This problem combines concepts from cellular automata, specifically involving the behavior of oscil(...TRUNCATED) | 47,760 | 283 | "<think>\nOkay, let's see. The problem is about finding the maximum period of an oscillator in a squ(...TRUNCATED) | [{"from":"human","value":"Input: a whole positive number greater than 4\nOutput: A whole positive nu(...TRUNCATED) |
null | "You are responsible for building a new freeway. However, it leads through\nmountainous lands and th(...TRUNCATED) | null | null | null | null | null | 7 | null | null | stackexchange_codegolf | "The problem involves implementing detailed rules for road construction through a mountainous terrai(...TRUNCATED) | 48,338 | 284 | "<think>\nOkay, let's tackle this problem. Hmm, the task is to build a freeway through a mountainous(...TRUNCATED) | [{"from":"human","value":"You are responsible for building a new freeway. However, it leads through\(...TRUNCATED) |
null | "In my previous challenge, I\ndrew the first diagram mostly by hand (with the help of vim's visual b(...TRUNCATED) | null | null | null | null | null | 7 | null | null | stackexchange_codegolf | "The problem requires advanced algorithmic knowledge to generate a hexagonal grid in ASCII art, whic(...TRUNCATED) | 25,552 | 285 | "<think>\nOkay, I need to create an ASCII hexagonal grid based on given width and height. Let's see.(...TRUNCATED) | [{"from":"human","value":"In my previous challenge, I\ndrew the first diagram mostly by hand (with t(...TRUNCATED) |
End of preview. Expand in Data Studio
Dataset Card for Open-Thoughts-4-30K-Code-Qwen3-32B-Annotated-32768-Tokens
Overview
This dataset is a variant of marin-community/open-thoughts-4-30k-code-qwen3-32b-annotated with an extended maximum sequence length. The responses in the generated_text column were generated with max output tokens = 32768 (instead of 7500 in the original dataset), allowing for longer and more complete chain-of-thought reasoning.
Generation Details
- Model: Qwen/Qwen3-32B
- Temperature: 0.8
- Max Output Tokens: 32768
Dataset Statistics
- Number of Samples: 29,963
- Split: train
Dataset Structure
| Column | Description |
|---|---|
id |
Unique identifier |
instruction_seed |
The original code problem/question text without chat formatting |
output |
Generated output from the original dataset |
source |
Data source |
license |
License information |
dataset |
Original dataset source |
split |
Data split |
difficulty |
Difficulty rating (6-10) |
solution |
Reference solution |
index |
Index reference |
_source |
The origin dataset; tracks data provenance |
difficulty_reasoning |
Explanation of difficulty rating |
__original_row_idx |
The row index from the original source dataset before filtering/processing |
ms_id |
A unique sample identifier |
generated_text |
A response including chain-of-thought with <think> tags, generated by Qwen3-32B |
conversations |
The prompt and response in chat format (list with from and value fields) |
Related Datasets
- open-thoughts-4-30k-code-qwen3-32b-annotated — Same dataset with max_tokens = 7500
- Downloads last month
- 26