Dataset Viewer
Auto-converted to Parquet
row_uuid
string
dataset_uuid
string
dataset_name
string
dataset_description
string
keywords
list
preferred_score
string
metrics
list
question_template
string
question_template_input
string
answer
string
compute_function
string
image
image
401d4e49-afb8-4fad-b0b6-1a55c9da1a53-multimodal-grid10-15
401d4e49-afb8-4fad-b0b6-1a55c9da1a53-multimodal-grid10
diffusion_path_multimodal_grid10
Find shortest path on a 10x10 grid (multimodal version).
[ "computer science", "pathfinding", "BFS", "grid", "algorithmic reasoning", "materials science", "diffusion", "multimodal" ]
exact_str_match
[ "exact_str_match" ]
The image {{entry1}} shows a grid representing a crystal surface where 0 is a walkable site and 1 is an impassable defect. An atom must move from the start coordinate {{start}} to the end coordinate {{end}}. What is the length of the shortest possible path? Movement is restricted to up, down, left, or right steps. If no path exists, the answer is -1.
{"grid": [[1, 1, 0, 1, 0, 0, 0, 0, 0, 0], [0, 0, 0, 0, 1, 1, 0, 1, 0, 1], [0, 1, 0, 0, 0, 0, 0, 1, 0, 1], [0, 1, 0, 1, 0, 0, 1, 0, 0, 0], [0, 0, 1, 0, 0, 1, 1, 0, 0, 0], [0, 1, 0, 0, 0, 0, 0, 0, 1, 0], [0, 1, 0, 1, 1, 1, 0, 1, 0, 0], [0, 0, 0, 0, 1, 0, 0, 0, 0, 0], [1, 1, 0, 1, 0, 0, 0, 0, 0, 0], [0, 1, 0, 0, 0, 0, 1, 0, 0, 1]], "start": [6, 8], "end": [3, 5]}
10
import collections def calculate_solution(template_input: dict) -> str: """ Finds the length of the shortest path in a grid from start to end using the Breadth-First Search (BFS) algorithm. """ grid = template_input['grid'] start = tuple(template_input['start']) end = tuple(template_input['end']) rows, cols = len(grid), len(grid[0]) # Check if start or end are on an obstacle if grid[start[0]][start[1]] == 1 or grid[end[0]][end[1]] == 1: return "-1" # Queue for BFS: (row, col, distance) queue = collections.deque([(start[0], start[1], 0)]) # Set to keep track of visited cells visited = {start} while queue: r, c, dist = queue.popleft() # If we reached the end, return the distance if (r, c) == end: return str(dist) # Explore neighbors (up, down, left, right) for dr, dc in [(0, 1), (0, -1), (1, 0), (-1, 0)]: nr, nc = r + dr, c + dc # Check for valid next step if (0 <= nr < rows and 0 <= nc < cols and grid[nr][nc] == 0 and (nr, nc) not in visited): visited.add((nr, nc)) queue.append((nr, nc, dist + 1)) # If the queue empties and we haven't found the end, it's unreachable return "-1"
401d4e49-afb8-4fad-b0b6-1a55c9da1a53-multimodal-grid10-9
401d4e49-afb8-4fad-b0b6-1a55c9da1a53-multimodal-grid10
diffusion_path_multimodal_grid10
Find shortest path on a 10x10 grid (multimodal version).
[ "computer science", "pathfinding", "BFS", "grid", "algorithmic reasoning", "materials science", "diffusion", "multimodal" ]
exact_str_match
[ "exact_str_match" ]
The image {{entry1}} shows a grid representing a crystal surface where 0 is a walkable site and 1 is an impassable defect. An atom must move from the start coordinate {{start}} to the end coordinate {{end}}. What is the length of the shortest possible path? Movement is restricted to up, down, left, or right steps. If no path exists, the answer is -1.
{"grid": [[1, 0, 0, 0, 0, 0, 0, 0, 1, 1], [0, 0, 0, 0, 1, 0, 1, 0, 0, 1], [0, 0, 0, 0, 1, 0, 1, 0, 0, 1], [1, 1, 0, 0, 1, 0, 0, 1, 0, 0], [0, 0, 0, 1, 0, 1, 0, 0, 0, 1], [0, 1, 1, 0, 0, 1, 0, 0, 1, 0], [0, 0, 0, 0, 0, 0, 0, 0, 0, 0], [0, 0, 0, 0, 0, 1, 0, 1, 0, 0], [0, 1, 0, 0, 1, 0, 0, 0, 0, 1], [0, 1, 1, 0, 1, 0, 1, 0, 1, 0]], "start": [6, 6], "end": [0, 2]}
10
import collections def calculate_solution(template_input: dict) -> str: """ Finds the length of the shortest path in a grid from start to end using the Breadth-First Search (BFS) algorithm. """ grid = template_input['grid'] start = tuple(template_input['start']) end = tuple(template_input['end']) rows, cols = len(grid), len(grid[0]) # Check if start or end are on an obstacle if grid[start[0]][start[1]] == 1 or grid[end[0]][end[1]] == 1: return "-1" # Queue for BFS: (row, col, distance) queue = collections.deque([(start[0], start[1], 0)]) # Set to keep track of visited cells visited = {start} while queue: r, c, dist = queue.popleft() # If we reached the end, return the distance if (r, c) == end: return str(dist) # Explore neighbors (up, down, left, right) for dr, dc in [(0, 1), (0, -1), (1, 0), (-1, 0)]: nr, nc = r + dr, c + dc # Check for valid next step if (0 <= nr < rows and 0 <= nc < cols and grid[nr][nc] == 0 and (nr, nc) not in visited): visited.add((nr, nc)) queue.append((nr, nc, dist + 1)) # If the queue empties and we haven't found the end, it's unreachable return "-1"
401d4e49-afb8-4fad-b0b6-1a55c9da1a53-multimodal-grid10-14
401d4e49-afb8-4fad-b0b6-1a55c9da1a53-multimodal-grid10
diffusion_path_multimodal_grid10
Find shortest path on a 10x10 grid (multimodal version).
[ "computer science", "pathfinding", "BFS", "grid", "algorithmic reasoning", "materials science", "diffusion", "multimodal" ]
exact_str_match
[ "exact_str_match" ]
The image {{entry1}} shows a grid representing a crystal surface where 0 is a walkable site and 1 is an impassable defect. An atom must move from the start coordinate {{start}} to the end coordinate {{end}}. What is the length of the shortest possible path? Movement is restricted to up, down, left, or right steps. If no path exists, the answer is -1.
{"grid": [[1, 1, 0, 1, 1, 0, 0, 0, 1, 0], [0, 0, 0, 1, 0, 1, 0, 0, 1, 0], [0, 0, 0, 0, 1, 0, 0, 0, 1, 0], [0, 0, 1, 1, 0, 0, 1, 0, 0, 0], [0, 1, 0, 0, 0, 1, 0, 0, 0, 0], [0, 0, 0, 0, 0, 0, 1, 0, 0, 1], [0, 0, 0, 1, 1, 0, 1, 0, 0, 0], [0, 0, 1, 1, 0, 1, 0, 0, 0, 0], [1, 0, 0, 0, 0, 1, 1, 0, 0, 0], [0, 0, 1, 0, 0, 1, 0, 1, 0, 1]], "start": [3, 5], "end": [7, 6]}
9
import collections def calculate_solution(template_input: dict) -> str: """ Finds the length of the shortest path in a grid from start to end using the Breadth-First Search (BFS) algorithm. """ grid = template_input['grid'] start = tuple(template_input['start']) end = tuple(template_input['end']) rows, cols = len(grid), len(grid[0]) # Check if start or end are on an obstacle if grid[start[0]][start[1]] == 1 or grid[end[0]][end[1]] == 1: return "-1" # Queue for BFS: (row, col, distance) queue = collections.deque([(start[0], start[1], 0)]) # Set to keep track of visited cells visited = {start} while queue: r, c, dist = queue.popleft() # If we reached the end, return the distance if (r, c) == end: return str(dist) # Explore neighbors (up, down, left, right) for dr, dc in [(0, 1), (0, -1), (1, 0), (-1, 0)]: nr, nc = r + dr, c + dc # Check for valid next step if (0 <= nr < rows and 0 <= nc < cols and grid[nr][nc] == 0 and (nr, nc) not in visited): visited.add((nr, nc)) queue.append((nr, nc, dist + 1)) # If the queue empties and we haven't found the end, it's unreachable return "-1"
401d4e49-afb8-4fad-b0b6-1a55c9da1a53-multimodal-grid10-7
401d4e49-afb8-4fad-b0b6-1a55c9da1a53-multimodal-grid10
diffusion_path_multimodal_grid10
Find shortest path on a 10x10 grid (multimodal version).
[ "computer science", "pathfinding", "BFS", "grid", "algorithmic reasoning", "materials science", "diffusion", "multimodal" ]
exact_str_match
[ "exact_str_match" ]
The image {{entry1}} shows a grid representing a crystal surface where 0 is a walkable site and 1 is an impassable defect. An atom must move from the start coordinate {{start}} to the end coordinate {{end}}. What is the length of the shortest possible path? Movement is restricted to up, down, left, or right steps. If no path exists, the answer is -1.
{"grid": [[0, 0, 0, 0, 1, 0, 0, 0, 0, 0], [0, 1, 1, 0, 0, 0, 0, 0, 0, 0], [1, 1, 1, 0, 0, 0, 1, 1, 1, 0], [0, 1, 1, 1, 1, 0, 1, 0, 1, 0], [0, 1, 0, 1, 0, 0, 0, 0, 0, 1], [0, 0, 0, 0, 1, 0, 0, 0, 0, 0], [0, 1, 0, 0, 1, 0, 0, 0, 1, 1], [0, 0, 0, 0, 0, 0, 0, 0, 0, 1], [0, 0, 1, 0, 1, 0, 0, 0, 0, 1], [0, 0, 1, 0, 0, 0, 1, 0, 0, 1]], "start": [6, 3], "end": [6, 6]}
5
import collections def calculate_solution(template_input: dict) -> str: """ Finds the length of the shortest path in a grid from start to end using the Breadth-First Search (BFS) algorithm. """ grid = template_input['grid'] start = tuple(template_input['start']) end = tuple(template_input['end']) rows, cols = len(grid), len(grid[0]) # Check if start or end are on an obstacle if grid[start[0]][start[1]] == 1 or grid[end[0]][end[1]] == 1: return "-1" # Queue for BFS: (row, col, distance) queue = collections.deque([(start[0], start[1], 0)]) # Set to keep track of visited cells visited = {start} while queue: r, c, dist = queue.popleft() # If we reached the end, return the distance if (r, c) == end: return str(dist) # Explore neighbors (up, down, left, right) for dr, dc in [(0, 1), (0, -1), (1, 0), (-1, 0)]: nr, nc = r + dr, c + dc # Check for valid next step if (0 <= nr < rows and 0 <= nc < cols and grid[nr][nc] == 0 and (nr, nc) not in visited): visited.add((nr, nc)) queue.append((nr, nc, dist + 1)) # If the queue empties and we haven't found the end, it's unreachable return "-1"
401d4e49-afb8-4fad-b0b6-1a55c9da1a53-multimodal-grid10-12
401d4e49-afb8-4fad-b0b6-1a55c9da1a53-multimodal-grid10
diffusion_path_multimodal_grid10
Find shortest path on a 10x10 grid (multimodal version).
[ "computer science", "pathfinding", "BFS", "grid", "algorithmic reasoning", "materials science", "diffusion", "multimodal" ]
exact_str_match
[ "exact_str_match" ]
The image {{entry1}} shows a grid representing a crystal surface where 0 is a walkable site and 1 is an impassable defect. An atom must move from the start coordinate {{start}} to the end coordinate {{end}}. What is the length of the shortest possible path? Movement is restricted to up, down, left, or right steps. If no path exists, the answer is -1.
{"grid": [[0, 0, 0, 1, 0, 0, 0, 0, 0, 0], [0, 1, 0, 0, 0, 1, 0, 0, 0, 0], [0, 1, 1, 0, 0, 0, 0, 1, 0, 0], [0, 0, 0, 0, 0, 0, 0, 0, 0, 0], [0, 1, 0, 1, 1, 0, 1, 0, 1, 0], [0, 1, 0, 0, 1, 0, 0, 0, 1, 1], [1, 0, 1, 0, 0, 0, 1, 1, 0, 1], [1, 0, 0, 0, 1, 1, 0, 1, 1, 0], [0, 0, 0, 0, 0, 1, 0, 0, 1, 0], [0, 1, 0, 1, 0, 0, 0, 1, 0, 0]], "start": [7, 3], "end": [0, 7]}
11
import collections def calculate_solution(template_input: dict) -> str: """ Finds the length of the shortest path in a grid from start to end using the Breadth-First Search (BFS) algorithm. """ grid = template_input['grid'] start = tuple(template_input['start']) end = tuple(template_input['end']) rows, cols = len(grid), len(grid[0]) # Check if start or end are on an obstacle if grid[start[0]][start[1]] == 1 or grid[end[0]][end[1]] == 1: return "-1" # Queue for BFS: (row, col, distance) queue = collections.deque([(start[0], start[1], 0)]) # Set to keep track of visited cells visited = {start} while queue: r, c, dist = queue.popleft() # If we reached the end, return the distance if (r, c) == end: return str(dist) # Explore neighbors (up, down, left, right) for dr, dc in [(0, 1), (0, -1), (1, 0), (-1, 0)]: nr, nc = r + dr, c + dc # Check for valid next step if (0 <= nr < rows and 0 <= nc < cols and grid[nr][nc] == 0 and (nr, nc) not in visited): visited.add((nr, nc)) queue.append((nr, nc, dist + 1)) # If the queue empties and we haven't found the end, it's unreachable return "-1"
401d4e49-afb8-4fad-b0b6-1a55c9da1a53-multimodal-grid10-10
401d4e49-afb8-4fad-b0b6-1a55c9da1a53-multimodal-grid10
diffusion_path_multimodal_grid10
Find shortest path on a 10x10 grid (multimodal version).
[ "computer science", "pathfinding", "BFS", "grid", "algorithmic reasoning", "materials science", "diffusion", "multimodal" ]
exact_str_match
[ "exact_str_match" ]
The image {{entry1}} shows a grid representing a crystal surface where 0 is a walkable site and 1 is an impassable defect. An atom must move from the start coordinate {{start}} to the end coordinate {{end}}. What is the length of the shortest possible path? Movement is restricted to up, down, left, or right steps. If no path exists, the answer is -1.
{"grid": [[0, 0, 1, 1, 1, 0, 1, 0, 0, 1], [0, 0, 0, 0, 0, 0, 0, 1, 0, 0], [0, 0, 0, 1, 0, 0, 0, 1, 1, 0], [1, 0, 0, 0, 0, 1, 1, 0, 0, 0], [1, 0, 1, 0, 1, 0, 0, 0, 1, 0], [0, 1, 0, 0, 1, 0, 0, 0, 0, 0], [0, 1, 1, 1, 0, 0, 0, 1, 1, 0], [0, 1, 0, 0, 0, 0, 0, 0, 1, 0], [0, 0, 1, 1, 0, 0, 0, 1, 1, 0], [1, 0, 0, 0, 0, 0, 0, 0, 0, 0]], "start": [1, 0], "end": [2, 2]}
3
import collections def calculate_solution(template_input: dict) -> str: """ Finds the length of the shortest path in a grid from start to end using the Breadth-First Search (BFS) algorithm. """ grid = template_input['grid'] start = tuple(template_input['start']) end = tuple(template_input['end']) rows, cols = len(grid), len(grid[0]) # Check if start or end are on an obstacle if grid[start[0]][start[1]] == 1 or grid[end[0]][end[1]] == 1: return "-1" # Queue for BFS: (row, col, distance) queue = collections.deque([(start[0], start[1], 0)]) # Set to keep track of visited cells visited = {start} while queue: r, c, dist = queue.popleft() # If we reached the end, return the distance if (r, c) == end: return str(dist) # Explore neighbors (up, down, left, right) for dr, dc in [(0, 1), (0, -1), (1, 0), (-1, 0)]: nr, nc = r + dr, c + dc # Check for valid next step if (0 <= nr < rows and 0 <= nc < cols and grid[nr][nc] == 0 and (nr, nc) not in visited): visited.add((nr, nc)) queue.append((nr, nc, dist + 1)) # If the queue empties and we haven't found the end, it's unreachable return "-1"
401d4e49-afb8-4fad-b0b6-1a55c9da1a53-multimodal-grid10-6
401d4e49-afb8-4fad-b0b6-1a55c9da1a53-multimodal-grid10
diffusion_path_multimodal_grid10
Find shortest path on a 10x10 grid (multimodal version).
[ "computer science", "pathfinding", "BFS", "grid", "algorithmic reasoning", "materials science", "diffusion", "multimodal" ]
exact_str_match
[ "exact_str_match" ]
The image {{entry1}} shows a grid representing a crystal surface where 0 is a walkable site and 1 is an impassable defect. An atom must move from the start coordinate {{start}} to the end coordinate {{end}}. What is the length of the shortest possible path? Movement is restricted to up, down, left, or right steps. If no path exists, the answer is -1.
{"grid": [[0, 0, 1, 1, 0, 0, 0, 0, 1, 0], [0, 0, 0, 1, 1, 1, 0, 0, 0, 0], [1, 1, 0, 1, 0, 0, 0, 1, 0, 0], [0, 1, 0, 0, 1, 0, 1, 0, 0, 0], [1, 0, 0, 0, 0, 0, 0, 0, 0, 0], [0, 0, 0, 0, 0, 0, 1, 0, 0, 0], [0, 0, 1, 1, 0, 0, 1, 1, 1, 1], [1, 0, 0, 0, 1, 0, 1, 0, 0, 0], [1, 0, 1, 1, 0, 0, 0, 0, 0, 0], [1, 0, 0, 0, 1, 1, 0, 0, 0, 0]], "start": [8, 6], "end": [4, 5]}
5
import collections def calculate_solution(template_input: dict) -> str: """ Finds the length of the shortest path in a grid from start to end using the Breadth-First Search (BFS) algorithm. """ grid = template_input['grid'] start = tuple(template_input['start']) end = tuple(template_input['end']) rows, cols = len(grid), len(grid[0]) # Check if start or end are on an obstacle if grid[start[0]][start[1]] == 1 or grid[end[0]][end[1]] == 1: return "-1" # Queue for BFS: (row, col, distance) queue = collections.deque([(start[0], start[1], 0)]) # Set to keep track of visited cells visited = {start} while queue: r, c, dist = queue.popleft() # If we reached the end, return the distance if (r, c) == end: return str(dist) # Explore neighbors (up, down, left, right) for dr, dc in [(0, 1), (0, -1), (1, 0), (-1, 0)]: nr, nc = r + dr, c + dc # Check for valid next step if (0 <= nr < rows and 0 <= nc < cols and grid[nr][nc] == 0 and (nr, nc) not in visited): visited.add((nr, nc)) queue.append((nr, nc, dist + 1)) # If the queue empties and we haven't found the end, it's unreachable return "-1"
401d4e49-afb8-4fad-b0b6-1a55c9da1a53-multimodal-grid10-19
401d4e49-afb8-4fad-b0b6-1a55c9da1a53-multimodal-grid10
diffusion_path_multimodal_grid10
Find shortest path on a 10x10 grid (multimodal version).
[ "computer science", "pathfinding", "BFS", "grid", "algorithmic reasoning", "materials science", "diffusion", "multimodal" ]
exact_str_match
[ "exact_str_match" ]
The image {{entry1}} shows a grid representing a crystal surface where 0 is a walkable site and 1 is an impassable defect. An atom must move from the start coordinate {{start}} to the end coordinate {{end}}. What is the length of the shortest possible path? Movement is restricted to up, down, left, or right steps. If no path exists, the answer is -1.
{"grid": [[0, 1, 0, 0, 1, 1, 0, 0, 0, 1], [1, 0, 1, 1, 0, 0, 0, 1, 0, 0], [1, 0, 0, 1, 1, 0, 0, 0, 0, 0], [0, 1, 0, 0, 0, 0, 0, 1, 0, 0], [0, 0, 1, 0, 1, 1, 0, 1, 1, 0], [0, 0, 0, 0, 0, 1, 0, 1, 0, 0], [1, 0, 0, 0, 0, 1, 0, 0, 1, 0], [0, 0, 0, 0, 1, 0, 0, 1, 0, 0], [0, 0, 1, 0, 0, 0, 1, 0, 0, 0], [1, 0, 1, 0, 0, 0, 1, 0, 0, 0]], "start": [9, 8], "end": [0, 7]}
12
import collections def calculate_solution(template_input: dict) -> str: """ Finds the length of the shortest path in a grid from start to end using the Breadth-First Search (BFS) algorithm. """ grid = template_input['grid'] start = tuple(template_input['start']) end = tuple(template_input['end']) rows, cols = len(grid), len(grid[0]) # Check if start or end are on an obstacle if grid[start[0]][start[1]] == 1 or grid[end[0]][end[1]] == 1: return "-1" # Queue for BFS: (row, col, distance) queue = collections.deque([(start[0], start[1], 0)]) # Set to keep track of visited cells visited = {start} while queue: r, c, dist = queue.popleft() # If we reached the end, return the distance if (r, c) == end: return str(dist) # Explore neighbors (up, down, left, right) for dr, dc in [(0, 1), (0, -1), (1, 0), (-1, 0)]: nr, nc = r + dr, c + dc # Check for valid next step if (0 <= nr < rows and 0 <= nc < cols and grid[nr][nc] == 0 and (nr, nc) not in visited): visited.add((nr, nc)) queue.append((nr, nc, dist + 1)) # If the queue empties and we haven't found the end, it's unreachable return "-1"
401d4e49-afb8-4fad-b0b6-1a55c9da1a53-multimodal-grid10-3
401d4e49-afb8-4fad-b0b6-1a55c9da1a53-multimodal-grid10
diffusion_path_multimodal_grid10
Find shortest path on a 10x10 grid (multimodal version).
[ "computer science", "pathfinding", "BFS", "grid", "algorithmic reasoning", "materials science", "diffusion", "multimodal" ]
exact_str_match
[ "exact_str_match" ]
The image {{entry1}} shows a grid representing a crystal surface where 0 is a walkable site and 1 is an impassable defect. An atom must move from the start coordinate {{start}} to the end coordinate {{end}}. What is the length of the shortest possible path? Movement is restricted to up, down, left, or right steps. If no path exists, the answer is -1.
{"grid": [[1, 0, 0, 0, 1, 0, 0, 1, 1, 0], [1, 0, 0, 0, 0, 1, 0, 0, 0, 0], [1, 0, 0, 1, 0, 0, 0, 0, 0, 0], [0, 1, 0, 0, 0, 1, 0, 1, 0, 0], [1, 0, 1, 1, 0, 0, 0, 0, 0, 0], [0, 1, 0, 0, 1, 1, 0, 0, 1, 0], [1, 0, 1, 0, 0, 0, 0, 0, 0, 0], [0, 1, 0, 0, 0, 0, 1, 0, 0, 1], [0, 0, 0, 0, 1, 0, 0, 0, 0, 0], [0, 0, 1, 1, 1, 0, 1, 1, 0, 1]], "start": [1, 1], "end": [9, 1]}
18
import collections def calculate_solution(template_input: dict) -> str: """ Finds the length of the shortest path in a grid from start to end using the Breadth-First Search (BFS) algorithm. """ grid = template_input['grid'] start = tuple(template_input['start']) end = tuple(template_input['end']) rows, cols = len(grid), len(grid[0]) # Check if start or end are on an obstacle if grid[start[0]][start[1]] == 1 or grid[end[0]][end[1]] == 1: return "-1" # Queue for BFS: (row, col, distance) queue = collections.deque([(start[0], start[1], 0)]) # Set to keep track of visited cells visited = {start} while queue: r, c, dist = queue.popleft() # If we reached the end, return the distance if (r, c) == end: return str(dist) # Explore neighbors (up, down, left, right) for dr, dc in [(0, 1), (0, -1), (1, 0), (-1, 0)]: nr, nc = r + dr, c + dc # Check for valid next step if (0 <= nr < rows and 0 <= nc < cols and grid[nr][nc] == 0 and (nr, nc) not in visited): visited.add((nr, nc)) queue.append((nr, nc, dist + 1)) # If the queue empties and we haven't found the end, it's unreachable return "-1"
401d4e49-afb8-4fad-b0b6-1a55c9da1a53-multimodal-grid10-0
401d4e49-afb8-4fad-b0b6-1a55c9da1a53-multimodal-grid10
diffusion_path_multimodal_grid10
Find shortest path on a 10x10 grid (multimodal version).
[ "computer science", "pathfinding", "BFS", "grid", "algorithmic reasoning", "materials science", "diffusion", "multimodal" ]
exact_str_match
[ "exact_str_match" ]
The image {{entry1}} shows a grid representing a crystal surface where 0 is a walkable site and 1 is an impassable defect. An atom must move from the start coordinate {{start}} to the end coordinate {{end}}. What is the length of the shortest possible path? Movement is restricted to up, down, left, or right steps. If no path exists, the answer is -1.
{"grid": [[0, 0, 0, 0, 0, 0, 0, 0, 1, 0], [0, 1, 0, 1, 0, 0, 0, 0, 1, 1], [1, 1, 1, 0, 0, 0, 0, 0, 0, 0], [1, 0, 1, 0, 1, 0, 1, 0, 0, 1], [1, 0, 0, 1, 0, 1, 1, 1, 0, 0], [0, 0, 0, 0, 0, 0, 0, 0, 0, 0], [0, 0, 0, 0, 1, 0, 0, 0, 1, 0], [1, 0, 0, 0, 1, 0, 0, 1, 0, 1], [0, 0, 0, 1, 1, 0, 0, 0, 1, 0], [1, 0, 0, 0, 0, 1, 0, 0, 0, 1]], "start": [8, 6], "end": [2, 3]}
13
import collections def calculate_solution(template_input: dict) -> str: """ Finds the length of the shortest path in a grid from start to end using the Breadth-First Search (BFS) algorithm. """ grid = template_input['grid'] start = tuple(template_input['start']) end = tuple(template_input['end']) rows, cols = len(grid), len(grid[0]) # Check if start or end are on an obstacle if grid[start[0]][start[1]] == 1 or grid[end[0]][end[1]] == 1: return "-1" # Queue for BFS: (row, col, distance) queue = collections.deque([(start[0], start[1], 0)]) # Set to keep track of visited cells visited = {start} while queue: r, c, dist = queue.popleft() # If we reached the end, return the distance if (r, c) == end: return str(dist) # Explore neighbors (up, down, left, right) for dr, dc in [(0, 1), (0, -1), (1, 0), (-1, 0)]: nr, nc = r + dr, c + dc # Check for valid next step if (0 <= nr < rows and 0 <= nc < cols and grid[nr][nc] == 0 and (nr, nc) not in visited): visited.add((nr, nc)) queue.append((nr, nc, dist + 1)) # If the queue empties and we haven't found the end, it's unreachable return "-1"
401d4e49-afb8-4fad-b0b6-1a55c9da1a53-multimodal-grid10-16
401d4e49-afb8-4fad-b0b6-1a55c9da1a53-multimodal-grid10
diffusion_path_multimodal_grid10
Find shortest path on a 10x10 grid (multimodal version).
[ "computer science", "pathfinding", "BFS", "grid", "algorithmic reasoning", "materials science", "diffusion", "multimodal" ]
exact_str_match
[ "exact_str_match" ]
The image {{entry1}} shows a grid representing a crystal surface where 0 is a walkable site and 1 is an impassable defect. An atom must move from the start coordinate {{start}} to the end coordinate {{end}}. What is the length of the shortest possible path? Movement is restricted to up, down, left, or right steps. If no path exists, the answer is -1.
{"grid": [[1, 1, 1, 0, 0, 1, 0, 0, 0, 0], [1, 1, 0, 1, 1, 0, 0, 0, 1, 0], [0, 0, 0, 0, 0, 0, 0, 0, 1, 0], [0, 0, 1, 1, 0, 0, 1, 0, 0, 0], [1, 0, 0, 0, 0, 0, 0, 0, 0, 0], [1, 0, 0, 0, 0, 0, 1, 1, 0, 1], [1, 1, 1, 0, 1, 0, 0, 0, 0, 0], [0, 0, 0, 1, 1, 0, 0, 0, 1, 0], [0, 0, 0, 0, 1, 0, 0, 0, 1, 0], [1, 0, 0, 0, 1, 0, 0, 0, 1, 0]], "start": [6, 9], "end": [9, 7]}
5
import collections def calculate_solution(template_input: dict) -> str: """ Finds the length of the shortest path in a grid from start to end using the Breadth-First Search (BFS) algorithm. """ grid = template_input['grid'] start = tuple(template_input['start']) end = tuple(template_input['end']) rows, cols = len(grid), len(grid[0]) # Check if start or end are on an obstacle if grid[start[0]][start[1]] == 1 or grid[end[0]][end[1]] == 1: return "-1" # Queue for BFS: (row, col, distance) queue = collections.deque([(start[0], start[1], 0)]) # Set to keep track of visited cells visited = {start} while queue: r, c, dist = queue.popleft() # If we reached the end, return the distance if (r, c) == end: return str(dist) # Explore neighbors (up, down, left, right) for dr, dc in [(0, 1), (0, -1), (1, 0), (-1, 0)]: nr, nc = r + dr, c + dc # Check for valid next step if (0 <= nr < rows and 0 <= nc < cols and grid[nr][nc] == 0 and (nr, nc) not in visited): visited.add((nr, nc)) queue.append((nr, nc, dist + 1)) # If the queue empties and we haven't found the end, it's unreachable return "-1"
401d4e49-afb8-4fad-b0b6-1a55c9da1a53-multimodal-grid10-5
401d4e49-afb8-4fad-b0b6-1a55c9da1a53-multimodal-grid10
diffusion_path_multimodal_grid10
Find shortest path on a 10x10 grid (multimodal version).
[ "computer science", "pathfinding", "BFS", "grid", "algorithmic reasoning", "materials science", "diffusion", "multimodal" ]
exact_str_match
[ "exact_str_match" ]
The image {{entry1}} shows a grid representing a crystal surface where 0 is a walkable site and 1 is an impassable defect. An atom must move from the start coordinate {{start}} to the end coordinate {{end}}. What is the length of the shortest possible path? Movement is restricted to up, down, left, or right steps. If no path exists, the answer is -1.
{"grid": [[0, 1, 0, 0, 1, 0, 0, 1, 1, 0], [0, 1, 0, 1, 0, 0, 0, 0, 0, 1], [0, 0, 1, 0, 0, 0, 0, 0, 0, 1], [0, 0, 0, 0, 0, 0, 0, 0, 0, 0], [1, 0, 1, 1, 0, 0, 0, 1, 1, 0], [1, 0, 0, 0, 1, 0, 0, 1, 1, 0], [0, 0, 0, 0, 0, 1, 0, 1, 0, 0], [0, 1, 0, 0, 0, 1, 1, 0, 0, 1], [0, 1, 1, 1, 0, 1, 0, 0, 1, 1], [0, 0, 0, 0, 0, 0, 0, 0, 0, 0]], "start": [3, 1], "end": [6, 2]}
4
import collections def calculate_solution(template_input: dict) -> str: """ Finds the length of the shortest path in a grid from start to end using the Breadth-First Search (BFS) algorithm. """ grid = template_input['grid'] start = tuple(template_input['start']) end = tuple(template_input['end']) rows, cols = len(grid), len(grid[0]) # Check if start or end are on an obstacle if grid[start[0]][start[1]] == 1 or grid[end[0]][end[1]] == 1: return "-1" # Queue for BFS: (row, col, distance) queue = collections.deque([(start[0], start[1], 0)]) # Set to keep track of visited cells visited = {start} while queue: r, c, dist = queue.popleft() # If we reached the end, return the distance if (r, c) == end: return str(dist) # Explore neighbors (up, down, left, right) for dr, dc in [(0, 1), (0, -1), (1, 0), (-1, 0)]: nr, nc = r + dr, c + dc # Check for valid next step if (0 <= nr < rows and 0 <= nc < cols and grid[nr][nc] == 0 and (nr, nc) not in visited): visited.add((nr, nc)) queue.append((nr, nc, dist + 1)) # If the queue empties and we haven't found the end, it's unreachable return "-1"
401d4e49-afb8-4fad-b0b6-1a55c9da1a53-multimodal-grid10-11
401d4e49-afb8-4fad-b0b6-1a55c9da1a53-multimodal-grid10
diffusion_path_multimodal_grid10
Find shortest path on a 10x10 grid (multimodal version).
[ "computer science", "pathfinding", "BFS", "grid", "algorithmic reasoning", "materials science", "diffusion", "multimodal" ]
exact_str_match
[ "exact_str_match" ]
The image {{entry1}} shows a grid representing a crystal surface where 0 is a walkable site and 1 is an impassable defect. An atom must move from the start coordinate {{start}} to the end coordinate {{end}}. What is the length of the shortest possible path? Movement is restricted to up, down, left, or right steps. If no path exists, the answer is -1.
{"grid": [[0, 0, 0, 0, 0, 1, 0, 0, 0, 0], [0, 1, 1, 0, 0, 0, 0, 1, 0, 1], [0, 0, 0, 0, 0, 0, 0, 0, 1, 0], [0, 1, 1, 0, 0, 1, 1, 0, 0, 0], [0, 0, 0, 0, 0, 0, 0, 0, 0, 1], [0, 1, 0, 0, 1, 0, 0, 1, 1, 0], [1, 1, 0, 0, 1, 0, 1, 1, 0, 0], [1, 1, 0, 0, 0, 1, 0, 0, 0, 1], [0, 0, 0, 1, 0, 0, 0, 1, 0, 1], [0, 1, 0, 0, 0, 0, 0, 0, 1, 1]], "start": [3, 9], "end": [3, 3]}
8
import collections def calculate_solution(template_input: dict) -> str: """ Finds the length of the shortest path in a grid from start to end using the Breadth-First Search (BFS) algorithm. """ grid = template_input['grid'] start = tuple(template_input['start']) end = tuple(template_input['end']) rows, cols = len(grid), len(grid[0]) # Check if start or end are on an obstacle if grid[start[0]][start[1]] == 1 or grid[end[0]][end[1]] == 1: return "-1" # Queue for BFS: (row, col, distance) queue = collections.deque([(start[0], start[1], 0)]) # Set to keep track of visited cells visited = {start} while queue: r, c, dist = queue.popleft() # If we reached the end, return the distance if (r, c) == end: return str(dist) # Explore neighbors (up, down, left, right) for dr, dc in [(0, 1), (0, -1), (1, 0), (-1, 0)]: nr, nc = r + dr, c + dc # Check for valid next step if (0 <= nr < rows and 0 <= nc < cols and grid[nr][nc] == 0 and (nr, nc) not in visited): visited.add((nr, nc)) queue.append((nr, nc, dist + 1)) # If the queue empties and we haven't found the end, it's unreachable return "-1"
401d4e49-afb8-4fad-b0b6-1a55c9da1a53-multimodal-grid10-18
401d4e49-afb8-4fad-b0b6-1a55c9da1a53-multimodal-grid10
diffusion_path_multimodal_grid10
Find shortest path on a 10x10 grid (multimodal version).
[ "computer science", "pathfinding", "BFS", "grid", "algorithmic reasoning", "materials science", "diffusion", "multimodal" ]
exact_str_match
[ "exact_str_match" ]
The image {{entry1}} shows a grid representing a crystal surface where 0 is a walkable site and 1 is an impassable defect. An atom must move from the start coordinate {{start}} to the end coordinate {{end}}. What is the length of the shortest possible path? Movement is restricted to up, down, left, or right steps. If no path exists, the answer is -1.
{"grid": [[0, 1, 1, 0, 0, 1, 1, 0, 0, 0], [0, 1, 1, 0, 1, 0, 1, 1, 0, 0], [0, 1, 0, 0, 0, 0, 1, 0, 1, 0], [1, 0, 0, 0, 0, 0, 0, 1, 0, 0], [0, 0, 0, 0, 1, 0, 0, 0, 0, 1], [1, 0, 1, 1, 0, 0, 0, 0, 0, 1], [0, 0, 1, 0, 0, 0, 0, 1, 1, 1], [0, 0, 1, 0, 0, 0, 0, 0, 0, 0], [1, 0, 0, 0, 0, 0, 0, 0, 0, 0], [0, 0, 0, 1, 0, 0, 1, 0, 1, 1]], "start": [6, 6], "end": [7, 5]}
2
import collections def calculate_solution(template_input: dict) -> str: """ Finds the length of the shortest path in a grid from start to end using the Breadth-First Search (BFS) algorithm. """ grid = template_input['grid'] start = tuple(template_input['start']) end = tuple(template_input['end']) rows, cols = len(grid), len(grid[0]) # Check if start or end are on an obstacle if grid[start[0]][start[1]] == 1 or grid[end[0]][end[1]] == 1: return "-1" # Queue for BFS: (row, col, distance) queue = collections.deque([(start[0], start[1], 0)]) # Set to keep track of visited cells visited = {start} while queue: r, c, dist = queue.popleft() # If we reached the end, return the distance if (r, c) == end: return str(dist) # Explore neighbors (up, down, left, right) for dr, dc in [(0, 1), (0, -1), (1, 0), (-1, 0)]: nr, nc = r + dr, c + dc # Check for valid next step if (0 <= nr < rows and 0 <= nc < cols and grid[nr][nc] == 0 and (nr, nc) not in visited): visited.add((nr, nc)) queue.append((nr, nc, dist + 1)) # If the queue empties and we haven't found the end, it's unreachable return "-1"
401d4e49-afb8-4fad-b0b6-1a55c9da1a53-multimodal-grid10-2
401d4e49-afb8-4fad-b0b6-1a55c9da1a53-multimodal-grid10
diffusion_path_multimodal_grid10
Find shortest path on a 10x10 grid (multimodal version).
[ "computer science", "pathfinding", "BFS", "grid", "algorithmic reasoning", "materials science", "diffusion", "multimodal" ]
exact_str_match
[ "exact_str_match" ]
The image {{entry1}} shows a grid representing a crystal surface where 0 is a walkable site and 1 is an impassable defect. An atom must move from the start coordinate {{start}} to the end coordinate {{end}}. What is the length of the shortest possible path? Movement is restricted to up, down, left, or right steps. If no path exists, the answer is -1.
{"grid": [[0, 0, 0, 0, 0, 0, 0, 0, 1, 0], [1, 0, 0, 1, 0, 0, 0, 0, 0, 0], [0, 0, 0, 0, 0, 1, 0, 0, 0, 0], [0, 0, 1, 0, 1, 1, 0, 0, 1, 0], [0, 1, 1, 0, 1, 0, 0, 0, 0, 0], [0, 0, 0, 1, 1, 0, 0, 0, 0, 0], [0, 0, 1, 0, 0, 1, 0, 0, 0, 0], [1, 1, 0, 1, 1, 0, 0, 0, 1, 1], [1, 1, 0, 1, 0, 1, 0, 0, 0, 0], [0, 1, 1, 0, 1, 0, 0, 1, 0, 1]], "start": [4, 9], "end": [0, 1]}
12
import collections def calculate_solution(template_input: dict) -> str: """ Finds the length of the shortest path in a grid from start to end using the Breadth-First Search (BFS) algorithm. """ grid = template_input['grid'] start = tuple(template_input['start']) end = tuple(template_input['end']) rows, cols = len(grid), len(grid[0]) # Check if start or end are on an obstacle if grid[start[0]][start[1]] == 1 or grid[end[0]][end[1]] == 1: return "-1" # Queue for BFS: (row, col, distance) queue = collections.deque([(start[0], start[1], 0)]) # Set to keep track of visited cells visited = {start} while queue: r, c, dist = queue.popleft() # If we reached the end, return the distance if (r, c) == end: return str(dist) # Explore neighbors (up, down, left, right) for dr, dc in [(0, 1), (0, -1), (1, 0), (-1, 0)]: nr, nc = r + dr, c + dc # Check for valid next step if (0 <= nr < rows and 0 <= nc < cols and grid[nr][nc] == 0 and (nr, nc) not in visited): visited.add((nr, nc)) queue.append((nr, nc, dist + 1)) # If the queue empties and we haven't found the end, it's unreachable return "-1"
    ### Configuration: `particel_energy_2d`

    This configuration contains text-only problems for calculating the total energy of a 2D particle system.

    **Task Description:**

    Calculate the total energy of a system with 10 particles in a 10x10 Angstrom box. The energy calculation involves:
    1.  **Particle Energy**: The individual energy of each particle.
    2.  **Pairwise Interaction Energy**: For particles within a 5 Angstrom cutoff distance, the interaction energy is `distance * (energy_A + energy_B)`.

    **Data Fields:**
    - `uuid`: A unique identifier for the example.
    - `input`: The question text describing the particle system's coordinates and energies.
    - `target`: The numerical answer for the total energy in eV.
    - ... (and other relevant metadata fields).

    **Usage:**

    ```python
    from datasets import load_dataset

    dataset = load_dataset("n0w0f/scirex-text", name="particel_energy_2d", split="train")
    print(dataset[0])
    

Configuration: particle_energy_2d

Type: Multimodal Examples: 20 Task: Energy computation for 2D particle systems

Description: Calculate the total energy of a system with 10 particles in a 10×10 Angstrom box. The energy calculation involves:

  1. Particle Energy: Individual energy contribution from each particle
  2. Pairwise Interaction Energy: For particles within 5 Angstrom cutoff, interaction energy = distance × (energy_A + energy_B)

Usage:

from datasets import load_dataset

dataset = load_dataset("particle_energy_computation_multimodal", name="particle_energy_2d")
example = dataset['train'][0]
print(example)

Data Fields:

  • uuid: Unique identifier

  • examples: Problem data (JSON string)

  • description: Task description

  • image: Visualization of particle system

  • Other metadata fields

          ---
          ## Configuration: `particle_energy_multimodal_3d_n25`
    
          **Description**: Calculate total energy of 25 3D particles (multimodal version).
    
          **Number of Examples**: 15
    
          **Keywords**: `physics`, `computational chemistry`, `energy`, `particles`, `pairwise-interactions`, `3d-systems`, `numerical-reasoning`, `multimodal`, `visualization`
    
          **Usage:**```python
          from datasets import load_dataset
    
          # Load this specific configuration
          dataset = load_dataset("n0w0f/scirex-image", name="particle_energy_multimodal_3d_n25")
    
          # Access the first example
          example = dataset['train']
          print(example)
          
          ---
          ## Configuration: `particle_energy_multimodal_3d_n5`
    
          **Description**: Calculate total energy of 5 3D particles (multimodal version).
    
          **Number of Examples**: 15
    
          **Keywords**: `physics`, `computational chemistry`, `energy`, `particles`, `pairwise-interactions`, `3d-systems`, `numerical-reasoning`, `multimodal`, `visualization`
    
          **Usage:**```python
          from datasets import load_dataset
    
          # Load this specific configuration
          dataset = load_dataset("n0w0f/scirex-image", name="particle_energy_multimodal_3d_n5")
    
          # Access the first example
          example = dataset['train']
          print(example)
          
          ---
          ## Configuration: `particle_energy_multimodal_2d_n5`
    
          **Description**: Calculate total energy of 5 2D particles (multimodal version).
    
          **Number of Examples**: 15
    
          **Keywords**: `physics`, `computational chemistry`, `energy`, `particles`, `pairwise-interactions`, `2d-systems`, `numerical-reasoning`, `multimodal`, `visualization`
    
          **Usage:**```python
          from datasets import load_dataset
    
          # Load this specific configuration
          dataset = load_dataset("n0w0f/scirex-image", name="particle_energy_multimodal_2d_n5")
    
          # Access the first example
          example = dataset['train']
          print(example)
          
          ---
          ## Configuration: `particle_energy_multimodal_2d_n25`
    
          **Description**: Calculate total energy of 25 2D particles (multimodal version).
    
          **Number of Examples**: 15
    
          **Keywords**: `physics`, `computational chemistry`, `energy`, `particles`, `pairwise-interactions`, `2d-systems`, `numerical-reasoning`, `multimodal`, `visualization`
    
          **Usage:**```python
          from datasets import load_dataset
    
          # Load this specific configuration
          dataset = load_dataset("n0w0f/scirex-image", name="particle_energy_multimodal_2d_n25")
    
          # Access the first example
          example = dataset['train']
          print(example)
          
          ---
          ## Configuration: `particle_energy_multimodal_2d_n10`
    
          **Description**: Calculate total energy of 10 2D particles (multimodal version).
    
          **Number of Examples**: 15
    
          **Keywords**: `physics`, `computational chemistry`, `energy`, `particles`, `pairwise-interactions`, `2d-systems`, `numerical-reasoning`, `multimodal`, `visualization`
    
          **Usage:**```python
          from datasets import load_dataset
    
          # Load this specific configuration
          dataset = load_dataset("n0w0f/scirex-image", name="particle_energy_multimodal_2d_n10")
    
          # Access the first example
          example = dataset['train']
          print(example)
          
          ---
          ## Configuration: `particle_energy_multimodal_2d_n50`
    
          **Description**: Calculate total energy of 50 2D particles (multimodal version).
    
          **Number of Examples**: 15
    
          **Keywords**: `physics`, `computational chemistry`, `energy`, `particles`, `pairwise-interactions`, `2d-systems`, `numerical-reasoning`, `multimodal`, `visualization`
    
          **Usage:**```python
          from datasets import load_dataset
    
          # Load this specific configuration
          dataset = load_dataset("n0w0f/scirex-image", name="particle_energy_multimodal_2d_n50")
    
          # Access the first example
          example = dataset['train']
          print(example)
          
          ---
          ## Configuration: `particle_energy_multimodal_3d_n10`
    
          **Description**: Calculate total energy of 10 3D particles (multimodal version).
    
          **Number of Examples**: 15
    
          **Keywords**: `physics`, `computational chemistry`, `energy`, `particles`, `pairwise-interactions`, `3d-systems`, `numerical-reasoning`, `multimodal`, `visualization`
    
          **Usage:**```python
          from datasets import load_dataset
    
          # Load this specific configuration
          dataset = load_dataset("n0w0f/scirex-image", name="particle_energy_multimodal_3d_n10")
    
          # Access the first example
          example = dataset['train']
          print(example)
          
          ---
          ## Configuration: `particle_energy_multimodal_3d_n50`
    
          **Description**: Calculate total energy of 50 3D particles (multimodal version).
    
          **Number of Examples**: 15
    
          **Keywords**: `physics`, `computational chemistry`, `energy`, `particles`, `pairwise-interactions`, `3d-systems`, `numerical-reasoning`, `multimodal`, `visualization`
    
          **Usage:**```python
          from datasets import load_dataset
    
          # Load this specific configuration
          dataset = load_dataset("n0w0f/scirex-image", name="particle_energy_multimodal_3d_n50")
    
          # Access the first example
          example = dataset['train']
          print(example)
          
          ---
          ## Configuration: `particle_energy_multimodal_3d_n25`
    
          **Description**: Calculate total energy of 25 3D particles (multimodal version).
    
          **Number of Examples**: 15
    
          **Keywords**: `physics`, `computational chemistry`, `energy`, `particles`, `pairwise-interactions`, `3d-systems`, `numerical-reasoning`, `multimodal`, `visualization`
    
          **Usage:**```python
          from datasets import load_dataset
    
          # Load this specific configuration
          dataset = load_dataset("n0w0f/scirex-image", name="particle_energy_multimodal_3d_n25")
    
          # Access the first example
          example = dataset['train']
          print(example)
          
          ---
          ## Configuration: `particle_energy_multimodal_3d_n5`
    
          **Description**: Calculate total energy of 5 3D particles (multimodal version).
    
          **Number of Examples**: 15
    
          **Keywords**: `physics`, `computational chemistry`, `energy`, `particles`, `pairwise-interactions`, `3d-systems`, `numerical-reasoning`, `multimodal`, `visualization`
    
          **Usage:**```python
          from datasets import load_dataset
    
          # Load this specific configuration
          dataset = load_dataset("n0w0f/scirex-image", name="particle_energy_multimodal_3d_n5")
    
          # Access the first example
          example = dataset['train']
          print(example)
          
          ---
          ## Configuration: `particle_energy_multimodal_2d_n5`
    
          **Description**: Calculate total energy of 5 2D particles (multimodal version).
    
          **Number of Examples**: 15
    
          **Keywords**: `physics`, `computational chemistry`, `energy`, `particles`, `pairwise-interactions`, `2d-systems`, `numerical-reasoning`, `multimodal`, `visualization`
    
          **Usage:**```python
          from datasets import load_dataset
    
          # Load this specific configuration
          dataset = load_dataset("n0w0f/scirex-image", name="particle_energy_multimodal_2d_n5")
    
          # Access the first example
          example = dataset['train']
          print(example)
          
          ---
          ## Configuration: `particle_energy_multimodal_2d_n25`
    
          **Description**: Calculate total energy of 25 2D particles (multimodal version).
    
          **Number of Examples**: 15
    
          **Keywords**: `physics`, `computational chemistry`, `energy`, `particles`, `pairwise-interactions`, `2d-systems`, `numerical-reasoning`, `multimodal`, `visualization`
    
          **Usage:**```python
          from datasets import load_dataset
    
          # Load this specific configuration
          dataset = load_dataset("n0w0f/scirex-image", name="particle_energy_multimodal_2d_n25")
    
          # Access the first example
          example = dataset['train']
          print(example)
          
          ---
          ## Configuration: `particle_energy_multimodal_2d_n10`
    
          **Description**: Calculate total energy of 10 2D particles (multimodal version).
    
          **Number of Examples**: 15
    
          **Keywords**: `physics`, `computational chemistry`, `energy`, `particles`, `pairwise-interactions`, `2d-systems`, `numerical-reasoning`, `multimodal`, `visualization`
    
          **Usage:**```python
          from datasets import load_dataset
    
          # Load this specific configuration
          dataset = load_dataset("n0w0f/scirex-image", name="particle_energy_multimodal_2d_n10")
    
          # Access the first example
          example = dataset['train']
          print(example)
          
          ---
          ## Configuration: `particle_energy_multimodal_2d_n50`
    
          **Description**: Calculate total energy of 50 2D particles (multimodal version).
    
          **Number of Examples**: 15
    
          **Keywords**: `physics`, `computational chemistry`, `energy`, `particles`, `pairwise-interactions`, `2d-systems`, `numerical-reasoning`, `multimodal`, `visualization`
    
          **Usage:**```python
          from datasets import load_dataset
    
          # Load this specific configuration
          dataset = load_dataset("n0w0f/scirex-image", name="particle_energy_multimodal_2d_n50")
    
          # Access the first example
          example = dataset['train']
          print(example)
          
          ---
          ## Configuration: `particle_energy_multimodal_3d_n10`
    
          **Description**: Calculate total energy of 10 3D particles (multimodal version).
    
          **Number of Examples**: 15
    
          **Keywords**: `physics`, `computational chemistry`, `energy`, `particles`, `pairwise-interactions`, `3d-systems`, `numerical-reasoning`, `multimodal`, `visualization`
    
          **Usage:**```python
          from datasets import load_dataset
    
          # Load this specific configuration
          dataset = load_dataset("n0w0f/scirex-image", name="particle_energy_multimodal_3d_n10")
    
          # Access the first example
          example = dataset['train']
          print(example)
          
          ---
          ## Configuration: `particle_energy_multimodal_3d_n50`
    
          **Description**: Calculate total energy of 50 3D particles (multimodal version).
    
          **Number of Examples**: 15
    
          **Keywords**: `physics`, `computational chemistry`, `energy`, `particles`, `pairwise-interactions`, `3d-systems`, `numerical-reasoning`, `multimodal`, `visualization`
    
          **Usage:**```python
          from datasets import load_dataset
    
          # Load this specific configuration
          dataset = load_dataset("n0w0f/scirex-image", name="particle_energy_multimodal_3d_n50")
    
          # Access the first example
          example = dataset['train']
          print(example)
          
          ---
          ## Configuration: `peak_sorting_multimodal_n100`
    
          **Description**: Sort a list of 100 spectral peaks by position or intensity (multimodal version).
    
          **Number of Examples**: 15
    
          **Keywords**: `data processing`, `sorting`, `spectroscopy`, `analytical chemistry`, `list manipulation`, `multimodal`
    
          **Usage:**```python
          from datasets import load_dataset
    
          # Load this specific configuration
          dataset = load_dataset("n0w0f/scirex-image", name="peak_sorting_multimodal_n100")
    
          # Access the first example
          example = dataset['train']
          print(example)
          
          ---
          ## Configuration: `peak_sorting_multimodal_n25`
    
          **Description**: Sort a list of 25 spectral peaks by position or intensity (multimodal version).
    
          **Number of Examples**: 15
    
          **Keywords**: `data processing`, `sorting`, `spectroscopy`, `analytical chemistry`, `list manipulation`, `multimodal`
    
          **Usage:**```python
          from datasets import load_dataset
    
          # Load this specific configuration
          dataset = load_dataset("n0w0f/scirex-image", name="peak_sorting_multimodal_n25")
    
          # Access the first example
          example = dataset['train']
          print(example)
          
          ---
          ## Configuration: `peak_sorting_multimodal_n10`
    
          **Description**: Sort a list of 10 spectral peaks by position or intensity (multimodal version).
    
          **Number of Examples**: 15
    
          **Keywords**: `data processing`, `sorting`, `spectroscopy`, `analytical chemistry`, `list manipulation`, `multimodal`
    
          **Usage:**```python
          from datasets import load_dataset
    
          # Load this specific configuration
          dataset = load_dataset("n0w0f/scirex-image", name="peak_sorting_multimodal_n10")
    
          # Access the first example
          example = dataset['train']
          print(example)
          
          ---
          ## Configuration: `peak_sorting_multimodal_n50`
    
          **Description**: Sort a list of 50 spectral peaks by position or intensity (multimodal version).
    
          **Number of Examples**: 15
    
          **Keywords**: `data processing`, `sorting`, `spectroscopy`, `analytical chemistry`, `list manipulation`, `multimodal`
    
          **Usage:**```python
          from datasets import load_dataset
    
          # Load this specific configuration
          dataset = load_dataset("n0w0f/scirex-image", name="peak_sorting_multimodal_n50")
    
          # Access the first example
          example = dataset['train']
          print(example)
          
          ---
          ## Configuration: `peak_sorting_multimodal_n5`
    
          **Description**: Sort a list of 5 spectral peaks by position or intensity (multimodal version).
    
          **Number of Examples**: 15
    
          **Keywords**: `data processing`, `sorting`, `spectroscopy`, `analytical chemistry`, `list manipulation`, `multimodal`
    
          **Usage:**```python
          from datasets import load_dataset
    
          # Load this specific configuration
          dataset = load_dataset("n0w0f/scirex-image", name="peak_sorting_multimodal_n5")
    
          # Access the first example
          example = dataset['train']
          print(example)
          
          ---
          ## Configuration: `diffusion_path_multimodal_grid50`
    
          **Description**: Find shortest path on a 50x50 grid (multimodal version).
    
          **Number of Examples**: 20
    
          **Keywords**: `computer science`, `pathfinding`, `BFS`, `grid`, `algorithmic reasoning`, `materials science`, `diffusion`, `multimodal`
    
          **Usage:**```python
          from datasets import load_dataset
    
          # Load this specific configuration
          dataset = load_dataset("n0w0f/scirex-image", name="diffusion_path_multimodal_grid50")
    
          # Access the first example
          example = dataset['train']
          print(example)
          
          ---
          ## Configuration: `diffusion_path_multimodal_grid10`
    
          **Description**: Find shortest path on a 10x10 grid (multimodal version).
    
          **Number of Examples**: 20
    
          **Keywords**: `computer science`, `pathfinding`, `BFS`, `grid`, `algorithmic reasoning`, `materials science`, `diffusion`, `multimodal`
    
          **Usage:**```python
          from datasets import load_dataset
    
          # Load this specific configuration
          dataset = load_dataset("n0w0f/scirex-image", name="diffusion_path_multimodal_grid10")
    
          # Access the first example
          example = dataset['train']
          print(example)
          
          ---
          ## Configuration: `diffusion_path_multimodal_grid25`
    
          **Description**: Find shortest path on a 25x25 grid (multimodal version).
    
          **Number of Examples**: 20
    
          **Keywords**: `computer science`, `pathfinding`, `BFS`, `grid`, `algorithmic reasoning`, `materials science`, `diffusion`, `multimodal`
    
          **Usage:**```python
          from datasets import load_dataset
    
          # Load this specific configuration
          dataset = load_dataset("n0w0f/scirex-image", name="diffusion_path_multimodal_grid25")
    
          # Access the first example
          example = dataset['train']
          print(example)
          
          ---
          ## Configuration: `diffusion_path_multimodal_grid5`
    
          **Description**: Find shortest path on a 5x5 grid (multimodal version).
    
          **Number of Examples**: 20
    
          **Keywords**: `computer science`, `pathfinding`, `BFS`, `grid`, `algorithmic reasoning`, `materials science`, `diffusion`, `multimodal`
    
          **Usage:**```python
          from datasets import load_dataset
    
          # Load this specific configuration
          dataset = load_dataset("n0w0f/scirex-image", name="diffusion_path_multimodal_grid5")
    
          # Access the first example
          example = dataset['train']
          print(example)
          
          ---
          ## Configuration: `fsm_traversal_multimodal_len5`
    
          **Description**: Traverse a 4-state FSM with an input string of length 5 (multimodal version).
    
          **Number of Examples**: 15
    
          **Keywords**: `computer science`, `FSM`, `finite state machine`, `automata theory`, `algorithmic reasoning`, `rule-following`, `multimodal`
    
          **Usage:**```python
          from datasets import load_dataset
    
          # Load this specific configuration
          dataset = load_dataset("n0w0f/scirex-image", name="fsm_traversal_multimodal_len5")
    
          # Access the first example
          example = dataset['train']
          print(example)
          
          ---
          ## Configuration: `fsm_traversal_multimodal_len25`
    
          **Description**: Traverse a 4-state FSM with an input string of length 25 (multimodal version).
    
          **Number of Examples**: 15
    
          **Keywords**: `computer science`, `FSM`, `finite state machine`, `automata theory`, `algorithmic reasoning`, `rule-following`, `multimodal`
    
          **Usage:**```python
          from datasets import load_dataset
    
          # Load this specific configuration
          dataset = load_dataset("n0w0f/scirex-image", name="fsm_traversal_multimodal_len25")
    
          # Access the first example
          example = dataset['train']
          print(example)
          
          ---
          ## Configuration: `fsm_traversal_multimodal_len10`
    
          **Description**: Traverse a 4-state FSM with an input string of length 10 (multimodal version).
    
          **Number of Examples**: 15
    
          **Keywords**: `computer science`, `FSM`, `finite state machine`, `automata theory`, `algorithmic reasoning`, `rule-following`, `multimodal`
    
          **Usage:**```python
          from datasets import load_dataset
    
          # Load this specific configuration
          dataset = load_dataset("n0w0f/scirex-image", name="fsm_traversal_multimodal_len10")
    
          # Access the first example
          example = dataset['train']
          print(example)
          
          ---
          ## Configuration: `fsm_traversal_multimodal_len50`
    
          **Description**: Traverse a 4-state FSM with an input string of length 50 (multimodal version).
    
          **Number of Examples**: 15
    
          **Keywords**: `computer science`, `FSM`, `finite state machine`, `automata theory`, `algorithmic reasoning`, `rule-following`, `multimodal`
    
          **Usage:**```python
          from datasets import load_dataset
    
          # Load this specific configuration
          dataset = load_dataset("n0w0f/scirex-image", name="fsm_traversal_multimodal_len50")
    
          # Access the first example
          example = dataset['train']
          print(example)
          
          ---
          ## Configuration: `tree_traversal_multimodal_n5`
    
          **Description**: Perform a traversal on a binary tree with 5 nodes (multimodal version).
    
          **Number of Examples**: 15
    
          **Keywords**: `computer science`, `data structures`, `binary tree`, `recursion`, `algorithmic reasoning`, `multimodal`
    
          **Usage:**```python
          from datasets import load_dataset
    
          # Load this specific configuration
          dataset = load_dataset("n0w0f/scirex-image", name="tree_traversal_multimodal_n5")
    
          # Access the first example
          example = dataset['train']
          print(example)
          
          ---
          ## Configuration: `tree_traversal_multimodal_n50`
    
          **Description**: Perform a traversal on a binary tree with 50 nodes (multimodal version).
    
          **Number of Examples**: 15
    
          **Keywords**: `computer science`, `data structures`, `binary tree`, `recursion`, `algorithmic reasoning`, `multimodal`
    
          **Usage:**```python
          from datasets import load_dataset
    
          # Load this specific configuration
          dataset = load_dataset("n0w0f/scirex-image", name="tree_traversal_multimodal_n50")
    
          # Access the first example
          example = dataset['train']
          print(example)
          
          ---
          ## Configuration: `tree_traversal_multimodal_n10`
    
          **Description**: Perform a traversal on a binary tree with 10 nodes (multimodal version).
    
          **Number of Examples**: 15
    
          **Keywords**: `computer science`, `data structures`, `binary tree`, `recursion`, `algorithmic reasoning`, `multimodal`
    
          **Usage:**```python
          from datasets import load_dataset
    
          # Load this specific configuration
          dataset = load_dataset("n0w0f/scirex-image", name="tree_traversal_multimodal_n10")
    
          # Access the first example
          example = dataset['train']
          print(example)
          
          ---
          ## Configuration: `tree_traversal_multimodal_n25`
    
          **Description**: Perform a traversal on a binary tree with 25 nodes (multimodal version).
    
          **Number of Examples**: 15
    
          **Keywords**: `computer science`, `data structures`, `binary tree`, `recursion`, `algorithmic reasoning`, `multimodal`
    
          **Usage:**```python
          from datasets import load_dataset
    
          # Load this specific configuration
          dataset = load_dataset("n0w0f/scirex-image", name="tree_traversal_multimodal_n25")
    
          # Access the first example
          example = dataset['train']
          print(example)
    
Downloads last month
43