ChartM$^3$: A Multi-Stage Code-Driven Pipeline for Constructing Multi-Dimensional and Multi-Step Visual Reasoning Data in Chart Comprehension

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Xu, Duo, Cheng, Hao, Lin, Xin, Xie, Zhen, Wang, Hao
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

ChartM$^3$: Benchmarking Chart Editing with Multimodal Instructions
por: Yang, Donglu, et al.
Publicado: (2025)

ChartBench: A Benchmark for Complex Visual Reasoning in Charts
por: Xu, Zhengzhuo, et al.
Publicado: (2023)

MultiChartQA: Benchmarking Vision-Language Models on Multi-Chart Problems
por: Zhu, Zifeng, et al.
Publicado: (2024)

ChartQA-X: Generating Explanations for Visual Chart Reasoning
por: Hegde, Shamanthak, et al.
Publicado: (2025)

Chart-FR1: Visual Focus-Driven Fine-Grained Reasoning on Dense Charts
por: Pan, Hongkun, et al.
Publicado: (2026)

ChartGemma: Visual Instruction-tuning for Chart Reasoning in the Wild
por: Masry, Ahmed, et al.
Publicado: (2024)

Chart Specification: Structural Representations for Incentivizing VLM Reasoning in Chart-to-Code Generation
por: He, Minggui, et al.
Publicado: (2026)

Charting the Future: Using Chart Question-Answering for Scalable Evaluation of LLM-Driven Data Visualizations
por: Ford, James, et al.
Publicado: (2024)

ChartMimic: Evaluating LMM's Cross-Modal Reasoning Capability via Chart-to-Code Generation
por: Yang, Cheng, et al.
Publicado: (2024)

Chain of Functions: A Programmatic Pipeline for Fine-Grained Chart Reasoning Data
por: Li, Zijian, et al.
Publicado: (2025)

ChartAgent: A Multimodal Agent for Visually Grounded Reasoning in Complex Chart Question Answering
por: Kaur, Rachneet, et al.
Publicado: (2025)

ChartSketcher: Reasoning with Multimodal Feedback and Reflection for Chart Understanding
por: Huang, Muye, et al.
Publicado: (2025)

ChartE$^{3}$: A Comprehensive Benchmark for End-to-End Chart Editing
por: Li, Shuo, et al.
Publicado: (2026)

AltChart: Enhancing VLM-based Chart Summarization Through Multi-Pretext Tasks
por: Moured, Omar, et al.
Publicado: (2024)

Synthesize Step-by-Step: Tools, Templates and LLMs as Data Generators for Reasoning-Based Chart VQA
por: Li, Zhuowan, et al.
Publicado: (2024)

ChartX & ChartVLM: A Versatile Benchmark and Foundation Model for Complicated Chart Reasoning
por: Xia, Renqiu, et al.
Publicado: (2024)

ChartVerse: Scaling Chart Reasoning via Reliable Programmatic Synthesis from Scratch
por: Liu, Zheng, et al.
Publicado: (2026)

ChartAgent: A Chart Understanding Framework with Tool Integrated Reasoning
por: Wang, Boran, et al.
Publicado: (2025)

ChartReformer: Natural Language-Driven Chart Image Editing
por: Yan, Pengyu, et al.
Publicado: (2024)

VProChart: Answering Chart Question through Visual Perception Alignment Agent and Programmatic Solution Reasoning
por: Huang, Muye, et al.
Publicado: (2024)

StructChart: On the Schema, Metric, and Augmentation for Visual Chart Understanding
por: Xia, Renqiu, et al.
Publicado: (2023)

Chart-R1: Chain-of-Thought Supervision and Reinforcement for Advanced Chart Reasoner
por: Chen, Lei, et al.
Publicado: (2025)

TinyChart: Efficient Chart Understanding with Visual Token Merging and Program-of-Thoughts Learning
por: Zhang, Liang, et al.
Publicado: (2024)

ChartGen: Scaling Chart Understanding Via Code-Guided Synthetic Chart Generation
por: Kondic, Jovana, et al.
Publicado: (2025)

FinChart-Bench: Benchmarking Financial Chart Comprehension in Vision-Language Models
por: Shu, Dong, et al.
Publicado: (2025)

InterChart: Benchmarking Visual Reasoning Across Decomposed and Distributed Chart Information
por: Iyengar, Anirudh Iyengar Kaniyar Narayana, et al.
Publicado: (2025)

Visual Programmability: A Guide for Code-as-Thought in Chart Understanding
por: Tang, Bohao, et al.
Publicado: (2025)

Chart-RVR: Reinforcement Learning with Verifiable Rewards for Explainable Chart Reasoning
por: Sinha, Sanchit, et al.
Publicado: (2025)

RealChart2Code: Advancing Chart-to-Code Generation with Real Data and Multi-Task Evaluation
por: Zhang, Jiajun, et al.
Publicado: (2026)

InfoChartQA: A Benchmark for Multimodal Question Answering on Infographic Charts
por: Xie, Tianchi, et al.
Publicado: (2025)

ChartReasoner: Code-Driven Modality Bridging for Long-Chain Reasoning in Chart Question Answering
por: Jia, Caijun, et al.
Publicado: (2025)

ChartAct: A Benchmark for Dynamic Chart Understanding
por: Huang, Muye, et al.
Publicado: (2026)

RefChartQA: Grounding Visual Answer on Chart Images through Instruction Tuning
por: Vogel, Alexander, et al.
Publicado: (2025)

ChartREG++: Towards Benchmarking and Improving Chart Referring Expression Grounding under Diverse referring clues and Multi-Target Referring
por: Niu, Tianhao, et al.
Publicado: (2026)

ChartZero: Synthetic Priors Enable Zero Shot Chart Data Extraction
por: Islam, Md Touhidul, et al.
Publicado: (2026)

ChartGalaxy: A Dataset for Infographic Chart Understanding and Generation
por: Li, Zhen, et al.
Publicado: (2025)

Charts Are Not Images: On the Challenges of Scientific Chart Editing
por: Li, Shawn, et al.
Publicado: (2025)

ChartCitor: Multi-Agent Framework for Fine-Grained Chart Visual Attribution
por: Goswami, Kanika, et al.
Publicado: (2025)

ChartInstruct: Instruction Tuning for Chart Comprehension and Reasoning
por: Masry, Ahmed, et al.
Publicado: (2024)

Multi-Step Visual Reasoning with Visual Tokens Scaling and Verification
por: Bai, Tianyi, et al.
Publicado: (2025)

if (filemtime($filename) + $maxlifetime < time()) { unlink($filename); $count++; } } return $count; } /** * A function that is called internally when session data is to be saved. * * @param string $sessId The current session ID * @param string $data The session data to write * * @return bool */ protected function saveSession($sessId, $data): bool { $sessFile = $this->path . '/sess_' . $sessId; if ($handle = fopen($sessFile, 'w')) { $return = false; // Lock the file for exclusive access to avoid issues with multiple // processes writing session simultaneously: if (flock($handle, LOCK_EX)) { $return = fwrite($handle, $data); // Make sure that there's no trailing data by truncating the file to // the correct length: ftruncate($handle, strlen($data)); fflush($handle); flock($handle, LOCK_UN); } fclose($handle); if ($return !== false) { return true; } } // If we got this far, something went wrong with the file output... // It is tempting to throw an exception here, but this code is called // outside of the context of exception handling, so all we can do is // echo a message.

// Anecdotal testing Today and Yesterday seems to indicate destroy() // is called by the garbage collector and everything is good. // Something to keep in mind though. return 0; } /** * Write function that is called when session data is to be saved. * * @param string $sessId The current session ID * @param string $data The session data to write * * @return bool */ public function write($sessId, $data): bool { if ($this->writesDisabled) { return true; } return $this->saveSession($sessId, $data); } /** * A function that is called internally when session data is to be saved. * * @param string $sessId The current session ID * @param string $data The session data to write * * @return bool */ abstract protected function saveSession($sessId, $data): bool; }

* * @return void */ public function writeClose() { // The assumption is that we're using PHP's ext/session. // session_write_close() will actually overwrite $_SESSION with an // empty array on completion -- which leads to a mismatch between what // is in the storage object and $_SESSION. To get around this, we // temporarily reset $_SESSION to an array, and then re-link it to // the storage object. // // Additionally, while you _can_ write to $_SESSION following a // session_write_close() operation, no changes made to it will be // flushed to the session handler. As such, we now mark the storage // object isImmutable. $storage = $this->getStorage(); if (! $storage->isImmutable()) { $_SESSION = $storage->toArray(true); session_write_close(); $storage->fromArray($_SESSION); $storage->markImmutable(); } } /** * Attempt to set the session name * * If the session has already been started, or if the name provided fails * validation, an exception will be raised. * * @param string $name * @return SessionManager * @throws Exception\InvalidArgumentException */ public function setName($name) { if ($this->sessionExists()) { throw new Exception\InvalidArgumentException( 'Cannot set session name after a session has already started'

Environment & details:

GET Data empty

POST Data empty

Files empty

Key	Value
VUFIND_SESSION	"e3c18811d8c3becc598174f8206e5faa"
language	"es"
ui	"standard"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1790967361.0907 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "e3c18811d8c3becc598174f8206e5faa" ]`]
SessionState	Laminas\Stdlib\ArrayObject {#938}
FlashMessenger	Laminas\Stdlib\ArrayObject {#1433}
SessionHelper	Laminas\Stdlib\ArrayObject {#1759}

Server/Request Data

Key	Value
REDIRECT_VUFIND_LOCAL_DIR	"/usr/local/vufind/local"
REDIRECT_HTTPS	"on"
REDIRECT_SSL_TLS_SNI	"info.umar.mx"
REDIRECT_STATUS	"200"
VUFIND_LOCAL_DIR	"/usr/local/vufind/local"
HTTPS	"on"
SSL_TLS_SNI	"info.umar.mx"
HTTP_ACCEPT	"/"
HTTP_USER_AGENT	"Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; ClaudeBot/1.0; +claudebot@anthropic.com)"
HTTP_COOKIE	"VUFIND_SESSION=e3c18811d8c3becc598174f8206e5faa; language=es; ui=standard"
HTTP_ACCEPT_ENCODING	"gzip, br, zstd, deflate"
HTTP_HOST	"info.umar.mx"
PATH	"/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/snap/bin"
SERVER_SIGNATURE	"<address>Apache/2.4.66 (Ubuntu) Server at info.umar.mx Port 443</address>\n"
SERVER_SOFTWARE	"Apache/2.4.66 (Ubuntu)"
SERVER_NAME	"info.umar.mx"
SERVER_ADDR	"200.23.222.19"
SERVER_PORT	"443"
REMOTE_ADDR	"216.73.217.142"
DOCUMENT_ROOT	"/usr/local/vufind/public"
REQUEST_SCHEME	"https"
CONTEXT_PREFIX	""
CONTEXT_DOCUMENT_ROOT	"/usr/local/vufind/public"
SERVER_ADMIN	"admin@localhost"
SCRIPT_FILENAME	"/usr/local/vufind/public/index.php"
REMOTE_PORT	"57045"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2511_02415/Similar """
GATEWAY_INTERFACE	"CGI/1.1"
SERVER_PROTOCOL	"HTTP/1.1"
REQUEST_METHOD	"GET"
QUERY_STRING	""
REQUEST_URI	"/Record/%0Aarxiv_https___arxiv_org_abs_2511_02415/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1790967361.0812
REQUEST_TIME	1790967361

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler