SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2410.18798 · 2024

Distill Visual Chart Reasoning Ability from LLMs to MLLMs

arXiv · PDF · Open in the Atlas

Code that ran

10 of 13 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; 4 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 6 failures of our instrument; 3 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/2410.18798.json · badge: /api/ran/2410.18798.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
hewei2001/reachqa canonical (classifier label)
classifier basis: census
10 ran · 3 no recorded run
FunctionStatusWhere it lives
create_chat_response Ran
ran; our contract draft was wrong, not the code
hewei2001/reachqa/utils/openai_utils.py
pointer only (licence: NONE) · get_code("af6a0fc9903f51d4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hewei2001/reachqa 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.

create_chat_response_by_messages Ran
ran; our contract draft was wrong, not the code
hewei2001/reachqa/utils/openai_utils.py
pointer only (licence: NONE) · get_code("965a7683faa03bf9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hewei2001/reachqa 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.

create_json_mode_chat_response_by_messages Ran
ran; our contract draft was wrong, not the code
hewei2001/reachqa/utils/openai_utils.py
pointer only (licence: NONE) · get_code("c4113cface723033")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hewei2001/reachqa 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.

extract_decision Ran
ran, honoured the contract we drafted
hewei2001/reachqa/batch_filter_QA.py
pointer only (licence: NONE) · get_code("7cd243b2d264c131")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hewei2001/reachqa 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.

extract_python_code_block Ran
ran, honoured the contract we drafted
hewei2001/reachqa/openai_generate_code.py
pointer only (licence: NONE) · get_code("7c45fbb8ee3f6b2b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hewei2001/reachqa 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.

extract_rating Ran
ran, honoured the contract we drafted
hewei2001/reachqa/batch_filter_image.py
pointer only (licence: NONE) · get_code("9dad39546954330c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hewei2001/reachqa 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.

get_chart_note Ran
ran; our contract draft was wrong, not the code
hewei2001/reachqa/utils/chart_notes.py
pointer only (licence: NONE) · get_code("51a34bdea2f554b0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hewei2001/reachqa 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_swift_outputs Ran
ran; our contract draft was wrong, not the code
hewei2001/reachqa/openai_llm_evaluation.py
pointer only (licence: NONE) · get_code("f1d27a598bf0c523")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hewei2001/reachqa 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.

post_process_model_response Ran
ran, honoured the contract we drafted
hewei2001/reachqa/openai_llm_evaluation.py
pointer only (licence: NONE) · get_code("4d1a3a68e63960b3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hewei2001/reachqa 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.

simulate_code Ran
ran; our contract draft was wrong, not the code
hewei2001/reachqa/openai_generate_code.py
pointer only (licence: NONE) · get_code("4e745eb2738b7b9d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hewei2001/reachqa 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_datasets Not yet run
unverified (harvested, no recorded run)
hewei2001/reachqa/swift_infer_dataset.py
pointer only (licence: NONE) · get_code("93aa2fdc7356d575")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hewei2001/reachqa 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. No invocation recorded.

load_vlmevalkit_outputs Not yet run
unverified (harvested, no recorded run)
hewei2001/reachqa/openai_llm_evaluation.py
pointer only (licence: NONE) · get_code("94874ae0d42c0dd1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hewei2001/reachqa 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. No invocation recorded.

post_process_model_response Not yet run
unverified (harvested, no recorded run)
hewei2001/reachqa/openai_generate_code.py
pointer only (licence: NONE) · get_code("a4d5ecf8ca46fdf1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hewei2001/reachqa 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. No invocation recorded.

Also present in other papers' code

Of 13 samples lifted from this paper's linked repositories, 13 carry a function identity and 0 do not. Of the 13 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 13 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.

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

Solving complex chart Q&A tasks requires advanced visual reasoning abilities in multimodal large language models (MLLMs), including recognizing key information from visual inputs and conducting reasoning over it. While fine-tuning MLLMs for reasoning is critical, collecting and annotating charts and questions is expensive, hard to scale, and often results in low-quality annotations. To address this, we propose Code-as-Intermediary Translation (CIT), a cost-effective, efficient and scalable data synthesis method for distilling visual reasoning abilities from LLMs to MLLMs. The code serves as an intermediary that translates visual chart representations into textual representations, enabling language models to understand cross-modal information and generate reasoning chains accordingly. In this way, we can employ text-based synthesizing techniques to expand chart-plotting code and generate high-quality Q&A pairs for training models. This produces ReachQA, a dataset containing 3k reasoning-intensive charts and 20k Q&A pairs to enhance both recognition and reasoning abilities of MLLMs. Experiments show that models fine-tuned with ReachQA not only perform well on chart-related tasks but also show performance gains on general reasoning benchmarks. The code and dataset are publicly available at https://github.com/hewei2001/ReachQA.

For agents

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

get_harvested_code_for_paper("2410.18798")
get_code_for_paper("2410.18798")
have("2410.18798")

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

curl https://syntology.ai/api/ran/2410.18798.json

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

[![Syntology run record](https://syntology.ai/api/ran/2410.18798.svg)](https://syntology.ai/paper/2410.18798)

Connect an agent — have() is free.