SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2409.00147 · 2024

MultiMath: Bridging Visual and Mathematical Reasoning for Large Language Models

arXiv · PDF · Open in the Atlas

Code that ran

17 of 18 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 4 violated it and 0 have no contract verdict; 13 failures of our instrument; 1 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2409.00147.json · badge: /api/ran/2409.00147.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
pengshuai-rin/multimath canonical (classifier label)
classifier basis: census
17 ran · 1 no recorded run
FunctionStatusWhere it lives
create_one_query Ran
ran; our contract draft was wrong, not the code
pengshuai-rin/multimath/eval_mathvista/build_query.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from lupantech/MathVista, is pointer only (licence: CC-BY-SA-4.0) · get_code("ecc1e50a10f04fa0")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from lupantech/MathVista, and CC-BY-SA-4.0, as GitHub detects it on that repository, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

evaluate_code Ran
ran; our contract draft was wrong, not the code
pengshuai-rin/multimath/eval_mathvista/response.py
code served (permissive licence) · get_code("6a7cafccc873c34d")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned tuple, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import sys
import io

torch.manual_seed(0)

# The function evaluate_code takes a code_string parameter
# It executes that string and captures stdout and any exceptions
# We need to provide a valid code string that can be executed

code_string = """
x = 5
y = 10
print(x + y)
"""

ARGS = {
    "code_string": code_string
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
extract_boxed_content Ran
ran; our contract draft was wrong, not the code
pengshuai-rin/multimath/eval_mathverse/infer.py
code served (permissive licence) · get_code("8c9945b50705931d")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import re

def extract_boxed_content(text):
    pattern = '\\\\boxed\\{(.*?)\\}'
    match_list = re.findall(pattern, text)
    if match_list == []:
        return None
    else:
        return match_list[-1]

# Setup code to construct valid arguments
text_with_boxed = r"The answer is \boxed{42} and another \boxed{final answer}"

ARGS = {
    "text": text_with_boxed
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_chunk Ran
ran; our contract draft was wrong, not the code
pengshuai-rin/multimath/eval_mathverse/infer.py
code served (permissive licence) · get_code("42a46570620cd9fa")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned list, ndim 1, dtype family int; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import math

def split_list(lst, n):
    """Split a list into n (roughly) equal-sized chunks"""
    chunk_size = math.ceil(len(lst) / n)
    return [lst[i:i + chunk_size] for i in range(0, len(lst), chunk_size)]

def get_chunk(lst, n, k):
    chunks = split_list(lst, n)
    return chunks[k]

# Setup code
lst = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
n = 3
k = 1

ARGS = {
    "lst": lst,
    "n": n,
    "k": k
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family int — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_most_similar Ran
ran; our contract draft was wrong, not the code
pengshuai-rin/multimath/eval_mathvista/calculate_score.py
code served (permissive licence) · get_code("c28eb86a8d14e4ed")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

from Levenshtein import distance

def get_most_similar(prediction, choices):
    """
    Use the Levenshtein distance (or edit distance) to determine which of the choices is most similar to the given prediction
    """
    distances = [distance(prediction, choice) for choice in choices]
    ind = distances.index(min(distances))
    return choices[ind]


ARGS = {
    "prediction": "kitten",
    "choices": ["sitting", "kitten", "kitchen", "mitten"]
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
Levenshtein — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
is_number Ran
ran, violated the contract we drafted
pengshuai-rin/multimath/eval_mathverse/utils.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from RikVN/AMR, is pointer only (licence: NONE) · get_code("e18607dae38b30e2")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from RikVN/AMR, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

load_jsonl Ran
ran; our contract draft was wrong, not the code
pengshuai-rin/multimath/eval_mathverse/utils.py
code served (permissive licence) · get_code("17081a7b73a41850")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import json
import tempfile
import os

# Create a temporary JSONL file with valid JSON lines
temp_dir = tempfile.mkdtemp()
temp_file = os.path.join(temp_dir, "test.jsonl")

with open(temp_file, 'w', encoding='utf-8') as f:
    f.write(json.dumps({"key": "value1"}) + "\n")
    f.write(json.dumps({"key": "value2"}) + "\n")
    f.write(json.dumps({"key": "value3"}) + "\n")

ARGS = {
    "path": temp_file
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
normalize_extracted_answer Ran
ran; our contract draft was wrong, not the code
pengshuai-rin/multimath/eval_mathvista/calculate_score.py
code served (permissive licence) · get_code("ff5aa85ec44db5ee")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import re
from Levenshtein import distance

def get_most_similar(prediction, choices):
    """
    Use the Levenshtein distance (or edit distance) to determine which of the choices is most similar to the given prediction
    """
    distances = [distance(prediction, choice) for choice in choices]
    ind = distances.index(min(distances))
    return choices[ind]

def normalize_extracted_answer(extraction, choices, question_type, answer_type, precision):
    """
    Normalize the extracted answer to match the answer type
    """
    if question_type == 'multi_choice':
        if isinstance(extraction, str):
            extraction = extraction.strip()
        else:
            try:
                extraction = str(extraction)
            except:
                extraction = ''
        letter = re.findall('\\(([a-zA-Z])\\)', extraction)
        if len(letter) > 0:
            extraction = letter[0].upper()
        options = [chr(ord('A') + i) for i in range(len(choices))]
        if extraction in options:
            ind = options.index(extraction)
            extraction = choices[ind]
        else:
            extraction = get_most_similar(extraction, choices)
        assert extraction in choices
    elif answer_type == 'integer':
        try:
            extraction = str(int(float(extraction)))
        except:
            extraction = None
    elif answer_type == 'float':
        try:
            extraction = str(round(float(extraction), precision))
        except:
            extraction = None
    elif answer_type == 'list':
        try:
            extraction = str(extraction)
        except:
            extraction = None
    return extraction

ARGS = {
    'extraction': '(A) apple',
    'choices': ['apple', 'banana', 'cherry'],
    'question_type': 'multi_choice',
    'answer_type': 'string',
    'precision': 2
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
Levenshtein — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
read_csv Ran
ran; our contract draft was wrong, not the code
pengshuai-rin/multimath/eval_mathvista/utilities.py
code served (permissive licence) · get_code("1694e6d4f46ff13e")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import tempfile
import os

# Create a temporary CSV file
temp_fd, temp_file_path = tempfile.mkstemp(suffix='.csv', text=True)
try:
    with os.fdopen(temp_fd, 'w') as f:
        f.write("name,age,city\n")
        f.write("Alice,30,New York\n")
        f.write("Bob,25,Los Angeles\n")
        f.write("Charlie,35,Chicago\n")
finally:
    pass

ARGS = {
    "file": temp_file_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
read_json Ran
ran; our contract draft was wrong, not the code
pengshuai-rin/multimath/eval_mathvista/utilities.py
code served (permissive licence) · get_code("9ffa907555068ff3")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import json
import tempfile
import os

# Create a temporary JSON file with valid content
temp_dir = tempfile.mkdtemp()
temp_file = os.path.join(temp_dir, "test.json")

test_data = {
    "key1": "value1",
    "key2": [1, 2, 3],
    "key3": {"nested": "object"}
}

with open(temp_file, 'w', encoding='utf-8') as f:
    json.dump(test_data, f)

ARGS = {
    "path": temp_file
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
read_pandas_csv Ran
ran; our contract draft was wrong, not the code
pengshuai-rin/multimath/eval_mathvista/utilities.py
code served (permissive licence) · get_code("32ae2fb99638aba7")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned DataFrame. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import pandas as pd
import tempfile
import os

# Create a temporary CSV file for testing
temp_dir = tempfile.mkdtemp()
csv_path = os.path.join(temp_dir, "test_data.csv")

# Write a simple CSV file
df_test = pd.DataFrame({
    'col1': [1, 2, 3],
    'col2': ['a', 'b', 'c'],
    'col3': [1.5, 2.5, 3.5]
})
df_test.to_csv(csv_path, index=False)

ARGS = {
    'csv_path': csv_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
pandas — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type DataFrame — a DataFrame output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DataFrame output the recorded ndim 2 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
refine_caption Ran
ran; our contract draft was wrong, not the code
pengshuai-rin/multimath/eval_mathvista/build_query.py
code served (permissive licence) · get_code("d027e6e473c9fcd4")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

# Analyze the function: refine_caption takes a single parameter 'caption'
# The function checks if caption is a string, and if so, removes various nonsense phrases
# If caption is not a string, it returns an empty string

# Test case 1: caption is a string with nonsense phrases
caption_with_nonsense = "Sure. This is a great image. I hope this helps!"

ARGS = {
    "caption": caption_with_nonsense
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
refine_ocr Ran
ran; our contract draft was wrong, not the code
pengshuai-rin/multimath/eval_mathvista/build_query.py
code served (permissive licence) · get_code("bfd184123c9012c3")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

# Construct valid OCR data as a string representation
# The function expects a string that can be eval'd into a list of tuples
# Each tuple contains: (bounding_box, text, confidence_score)
ocr_data = str([
    (
        [[161, 39], [766, 39], [766, 120], [161, 120]], 
        'The spring force does', 
        0.912845069753024
    ),
    (
        [[200, 150], [500, 150], [500, 200], [200, 200]], 
        'Another text line', 
        0.95
    )
])

ARGS = {
    'ocr': ocr_data
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
safe_equal Ran
ran, violated the contract we drafted
pengshuai-rin/multimath/eval_mathvista/calculate_score.py
code served (permissive licence) · get_code("e7a23ea3695f6437")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned bool, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)

# The function safe_equal simply compares two values for equality
# It handles exceptions that might arise from the comparison
# We need to provide two arguments: prediction and answer

# Test case 1: Simple scalar values
prediction_1 = 42
answer_1 = 42

# Test case 2: Different types but comparable
prediction_2 = torch.tensor([1.0, 2.0, 3.0])
answer_2 = torch.tensor([1.0, 2.0, 3.0])

# Test case 3: Strings
prediction_3 = "hello"
answer_3 = "hello"

# Test case 4: Lists
prediction_4 = [1, 2, 3]
answer_4 = [1, 2, 3]

# Use the first test case as the primary arguments
ARGS = {
    "prediction": prediction_1,
    "answer": answer_1
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type bool, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
split_list Ran
ran; our contract draft was wrong, not the code
pengshuai-rin/multimath/eval_mathverse/infer.py
code served (permissive licence) · get_code("076c252c52cbb161")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned list. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import math

def split_list(lst, n):
    """Split a list into n (roughly) equal-sized chunks"""
    chunk_size = math.ceil(len(lst) / n)
    return [lst[i:i + chunk_size] for i in range(0, len(lst), chunk_size)]

# Setup code
lst = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
n = 3

ARGS = {
    "lst": lst,
    "n": n
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list — a list output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
verify_extraction Ran
ran, violated the contract we drafted
pengshuai-rin/multimath/eval_mathvista/extract_answer.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from rucaibox/virgo, is pointer only (licence: NONE) · get_code("350d0bc5afcc4922")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from rucaibox/virgo, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

verify_response Ran
ran, violated the contract we drafted
pengshuai-rin/multimath/eval_mathvista/response.py
code served (permissive licence) · get_code("d6259b0d9750cac7")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned bool, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)

# The function verify_response takes a single parameter 'response'
# It checks if response is a string, strips it, and validates it
# against empty strings, None, and 'Response Error' substring

# Test case 1: Valid non-empty string response
response_valid = "This is a valid response"

ARGS = {
    "response": response_valid
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type bool, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
extract_boxed_content Not yet run
unverified (harvested, no recorded run)
pengshuai-rin/multimath/eval_mathvista/response.py
code served (permissive licence) · get_code("a820443033d63826")
How it ran

no invocation recorded.

Also present in other papers' code

Of 18 samples lifted from this paper's linked repositories, 18 carry a function identity and 0 do not. Of the 18 distinct functions with an identity, 16 are also present in other papers whose code we hold (13 with at least one paper dated earlier, 6 the same month, 15 later) and 2 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
split_list 197 other papers
92 dated earlier, 16 the same month, 82 later, 6 same year, order not determinable, 1 undated
2112.05682 (2021-12)
Self-attention Does Not Need $O(n^2)$ Memory
2306.17107 (2023-06)
LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding
2307.10490 (2023-07)
Abusing Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMs
and 194 more not named here
get_chunk 189 other papers
88 dated earlier, 15 the same month, 80 later, 6 same year, order not determinable
2112.05682 (2021-12)
Self-attention Does Not Need $O(n^2)$ Memory
2306.17107 (2023-06)
LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding
2307.10490 (2023-07)
Abusing Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMs
and 186 more not named here
is_number 13 other papers
9 dated earlier, 1 the same month, 2 later, 1 undated
1202.3665 (2012-02)
emcee: The MCMC Hammer
1705.09980 (2017-05)
Neural Semantic Parsing by Character-based Translation: Experiments with Abstract Meaning Representations
2003.05855 (2020-03)
End-to-End Learning Local Multi-view Descriptors for 3D Point Clouds
and 10 more not named here
get_most_similar 7 other papers
3 dated earlier, 1 the same month, 3 later
2403.03003 (2024-03)
Feast Your Eyes: Mixture-of-Resolution Adaptation for Multimodal Large Language Models
2405.05949 (2024-05)
CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-Experts
2405.15574 (2024-05)
Meteor: Mamba-based Traversal of Rationale for Large Language and Vision Models
and 4 more not named here
load_jsonl 6 other papers
2 dated earlier, 1 the same month, 3 later
2310.03731 (2023-10)
MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning
2407.00782 (2024-07)
Step-Controlled DPO: Leveraging Stepwise Error for Enhanced Mathematical Reasoning
2409.02834 (2024-09)
CMM-Math: A Chinese Multimodal Math Dataset To Evaluate and Enhance the Mathematics Reasoning of Large Multimodal Models
and 3 more not named here
read_json 6 other papers
2 dated earlier, 4 later
2402.16379 (2024-02)
TEaR: Improving LLM-based Machine Translation with Systematic Self-Refinement
2405.05949 (2024-05)
CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-Experts
2410.17885 (2024-10)
Theorem-Validated Reverse Chain-of-Thought Problem Generation for Geometric Reasoning
and 3 more not named here
safe_equal 6 other papers
2 dated earlier, 1 the same month, 3 later
2403.03003 (2024-03)
Feast Your Eyes: Mixture-of-Resolution Adaptation for Multimodal Large Language Models
2405.15574 (2024-05)
Meteor: Mamba-based Traversal of Rationale for Large Language and Vision Models
2409.14713 (2024-09)
Phantom of Latent for Large Language and Vision Models
and 3 more not named here
refine_caption 4 other papers
1 dated earlier, 3 later
2310.02255 (2023-10)
MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts
2410.17885 (2024-10)
Theorem-Validated Reverse Chain-of-Thought Problem Generation for Geometric Reasoning
Guo_Integrating_Visual_Interpretation_and_Linguistic_Reasoning_for_Geometric_Problem_Solving_ICCV_2025_paper (2025 (year only))
Integrating Visual Interpretation and Linguistic Reasoning for Geometric Problem Solving
and 1 more not named here
refine_ocr 4 other papers
1 dated earlier, 3 later
2310.02255 (2023-10)
MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts
2410.17885 (2024-10)
Theorem-Validated Reverse Chain-of-Thought Problem Generation for Geometric Reasoning
Guo_Integrating_Visual_Interpretation_and_Linguistic_Reasoning_for_Geometric_Problem_Solving_ICCV_2025_paper (2025 (year only))
Integrating Visual Interpretation and Linguistic Reasoning for Geometric Problem Solving
and 1 more not named here
verify_response 4 other papers
2 dated earlier, 2 later
2403.03003 (2024-03)
Feast Your Eyes: Mixture-of-Resolution Adaptation for Multimodal Large Language Models
2406.17294 (2024-06)
Math-LLaVA: Bootstrapping Mathematical Reasoning for Multimodal Large Language Models
2410.17885 (2024-10)
Theorem-Validated Reverse Chain-of-Thought Problem Generation for Geometric Reasoning
and 1 more not named here
create_one_query 3 other papers
1 dated earlier, 2 later
2310.02255 (2023-10)
MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts
2410.17885 (2024-10)
Theorem-Validated Reverse Chain-of-Thought Problem Generation for Geometric Reasoning
Guo_Integrating_Visual_Interpretation_and_Linguistic_Reasoning_for_Geometric_Problem_Solving_ICCV_2025_paper (2025 (year only))
Integrating Visual Interpretation and Linguistic Reasoning for Geometric Problem Solving
evaluate_code 3 other papers
2 dated earlier, 1 later
2403.03003 (2024-03)
Feast Your Eyes: Mixture-of-Resolution Adaptation for Multimodal Large Language Models
2406.17294 (2024-06)
Math-LLaVA: Bootstrapping Mathematical Reasoning for Multimodal Large Language Models
2410.17885 (2024-10)
Theorem-Validated Reverse Chain-of-Thought Problem Generation for Geometric Reasoning
normalize_extracted_answer 3 other papers
3 dated earlier
2403.03003 (2024-03)
Feast Your Eyes: Mixture-of-Resolution Adaptation for Multimodal Large Language Models
2405.05949 (2024-05)
CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-Experts
2405.15574 (2024-05)
Meteor: Mamba-based Traversal of Rationale for Large Language and Vision Models
read_csv 3 other papers
3 later
2410.17885 (2024-10)
Theorem-Validated Reverse Chain-of-Thought Problem Generation for Geometric Reasoning
Guo_Integrating_Visual_Interpretation_and_Linguistic_Reasoning_for_Geometric_Problem_Solving_ICCV_2025_paper (2025 (year only))
Integrating Visual Interpretation and Linguistic Reasoning for Geometric Problem Solving
2509.19003 (2025-09)
Unveiling Chain of Step Reasoning for Vision-Language Models with Fine-grained Rewards
read_pandas_csv 3 other papers
3 later
2410.17885 (2024-10)
Theorem-Validated Reverse Chain-of-Thought Problem Generation for Geometric Reasoning
Guo_Integrating_Visual_Interpretation_and_Linguistic_Reasoning_for_Geometric_Problem_Solving_ICCV_2025_paper (2025 (year only))
Integrating Visual Interpretation and Linguistic Reasoning for Geometric Problem Solving
2509.19003 (2025-09)
Unveiling Chain of Step Reasoning for Vision-Language Models with Fine-grained Rewards
verify_extraction 1 other paper
1 later
2412.09413 (2024-12)
Imitate, Explore, and Self-Improve: A Reproduction Report on Slow-thinking Reasoning Systems

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

The rapid development of large language models (LLMs) has spurred extensive research into their domain-specific capabilities, particularly mathematical reasoning. However, most open-source LLMs focus solely on mathematical reasoning, neglecting the integration with visual injection, despite the fact that many mathematical tasks rely on visual inputs such as geometric diagrams, charts, and function plots. To fill this gap, we introduce \textbf{MultiMath-7B}, a multimodal large language model that bridges the gap between math and vision. \textbf{MultiMath-7B} is trained through a four-stage process, focusing on vision-language alignment, visual and math instruction-tuning, and process-supervised reinforcement learning. We also construct a novel, diverse and comprehensive multimodal mathematical dataset, \textbf{MultiMath-300K}, which spans K-12 levels with image captions and step-wise solutions. MultiMath-7B achieves state-of-the-art (SOTA) performance among open-source models on existing multimodal mathematical benchmarks and also excels on text-only mathematical benchmarks. Our model and dataset are available at {\textcolor{blue}{\url{https://github.com/pengshuai-rin/MultiMath}}}.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2409.00147")
get_code_for_paper("2409.00147")
have("2409.00147")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2409.00147.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2409.00147.svg)](https://syntology.ai/paper/2409.00147)

Connect an agent — have() is free.