Paper Citation Record · LEDGER

CodeShrink: Adaptive Visual Compression for Efficient Multimodal Code Understanding

As of 10 August 2026, this Paper Citation Record lists 40 of 40 outbound references and 0 inbound Pith citation observations for arXiv:2607.29637.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2607.29637 v1

Coverage vector

measured 40 of 40 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-03T03:05:15.273347Z

measured 40 of 40 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

40 of 40 outbound references displayed

verified exact2
verified fuzzy0
unresolved38
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation b39f6440-da18-4e90-b5fb-5634d922bb04 · outbound

This paper cites CodeOCR: On the Effectiveness of Vision Language Models in Code Understanding.

CodeShrink: Adaptive Visual Compression for Efficient Multimodal Code Understanding CodeOCR: On the Effectiveness of Vision Language Models in Code Understanding

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-03T03:05:14.533134Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0adaf043-849c-4845-a665-cb869d86ccfc · outbound

This paper cites Longcodebench: Evaluating coding llms at 1m context windows,.

CodeShrink: Adaptive Visual Compression for Efficient Multimodal Code Understanding Longcodebench: Evaluating coding llms at 1m context windows,

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-03T03:05:14.599501Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9435618-9838-44b1-a6bd-049ab67f2c9f · outbound

This paper cites Gptclonebench: A comprehensive benchmark of semantic clones and cross-language clones using gpt-3 model and semanticclonebench,.

CodeShrink: Adaptive Visual Compression for Efficient Multimodal Code Understanding Gptclonebench: A comprehensive benchmark of semantic clones and cross-language clones using gpt-3 model and semanticclonebench,

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-03T03:05:14.695422Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ccd73bfc-e865-4896-8283-ecf8bb82b2c7 · outbound

This paper cites Longcoder: A long- range pre-trained language model for code completion,.

CodeShrink: Adaptive Visual Compression for Efficient Multimodal Code Understanding Longcoder: A long- range pre-trained language model for code completion,

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-03T03:05:14.790813Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3897d13d-3741-47e1-91d6-f7cc7695e324 · outbound

This paper cites Codereval: A benchmark of pragmatic code generation with generative pre-trained models,.

CodeShrink: Adaptive Visual Compression for Efficient Multimodal Code Understanding Codereval: A benchmark of pragmatic code generation with generative pre-trained models,

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-03T03:05:14.797509Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d29e2412-f420-497d-b5ec-e9374ab699b1 · outbound

This paper cites Repogenix: Dual context-aided repository-level code completion with language models,.

CodeShrink: Adaptive Visual Compression for Efficient Multimodal Code Understanding Repogenix: Dual context-aided repository-level code completion with language models,

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-03T03:05:15.066816Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4833491c-982d-4746-9cbc-0fb7f0b0d35c · outbound

This paper cites A 3a3-codgen: A repository-level code generation framework for code reuse with local-aware, global-aware, and third-party-library- aware,.

CodeShrink: Adaptive Visual Compression for Efficient Multimodal Code Understanding A 3a3-codgen: A repository-level code generation framework for code reuse with local-aware, global-aware, and third-party-library- aware,

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-03T03:05:15.075724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d9481eca-c300-4df2-9e36-8188b216b8dc · outbound

This paper cites VisualRepair: Dynamic Tool Calling and Region Focusing for Visual Software Issue Repair.

CodeShrink: Adaptive Visual Compression for Efficient Multimodal Code Understanding VisualRepair: Dynamic Tool Calling and Region Focusing for Visual Software Issue Repair

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-03T03:05:15.141509Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1451fe86-d4e0-4fc5-bdbb-7981c875a341 · outbound

This paper cites Natural is the best: Model-agnostic code simplification for pre-trained large language models,.

CodeShrink: Adaptive Visual Compression for Efficient Multimodal Code Understanding Natural is the best: Model-agnostic code simplification for pre-trained large language models,

Reference 9

Resolution: verified exact; doi, observed 2026-08-03T03:09:21.261810Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 1861d7a7-50cb-4b2d-8bd8-b9e6613ed5cc · outbound

This paper cites Diet code is healthy: simplifying programs for pre-trained models of code,.

CodeShrink: Adaptive Visual Compression for Efficient Multimodal Code Understanding Diet code is healthy: simplifying programs for pre-trained models of code,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-03T03:05:15.185880Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6afacb9-005c-4d7c-942e-ab3b5ac24c08 · outbound

This paper cites Llmlingua: Com- pressing prompts for accelerated inference of large language models,.

CodeShrink: Adaptive Visual Compression for Efficient Multimodal Code Understanding Llmlingua: Com- pressing prompts for accelerated inference of large language models,

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-03T03:05:15.189176Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5a9320a-4db5-4bee-b1aa-1675c5bf5ba6 · outbound

This paper cites Longllmlingua: Accelerating and enhancing llms in long context sce- narios via prompt compression,.

CodeShrink: Adaptive Visual Compression for Efficient Multimodal Code Understanding Longllmlingua: Accelerating and enhancing llms in long context sce- narios via prompt compression,

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-03T03:05:15.192112Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4a19edb-9a02-4c02-9536-eeef2dbd66d8 · outbound

This paper cites Llmlingua-2: Data distillation for efficient and faithful task-agnostic prompt compression,.

CodeShrink: Adaptive Visual Compression for Efficient Multimodal Code Understanding Llmlingua-2: Data distillation for efficient and faithful task-agnostic prompt compression,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-03T03:05:15.194936Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df7f7240-7b12-483f-bbd9-a115755f5d58 · outbound

This paper cites DeepSeek-OCR: Contexts Optical Compression.

CodeShrink: Adaptive Visual Compression for Efficient Multimodal Code Understanding DeepSeek-OCR: Contexts Optical Compression

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-03T03:05:15.200256Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2bf5e77-d154-4b81-a506-81277564af97 · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

CodeShrink: Adaptive Visual Compression for Efficient Multimodal Code Understanding DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-03T03:05:15.203222Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2f2500e-7767-45a2-a005-b565e3f96fed · outbound

This paper cites Visionzip: Longer is better but not necessary in vision language models,.

CodeShrink: Adaptive Visual Compression for Efficient Multimodal Code Understanding Visionzip: Longer is better but not necessary in vision language models,

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-03T03:05:15.206532Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5b6ebb2-2b29-42b1-aa67-3f31a1278b2b · outbound

This paper cites An image is worth 1/2 tokens after layer 2: Plug-and-play inference acceleration for large vision-language models,.

CodeShrink: Adaptive Visual Compression for Efficient Multimodal Code Understanding An image is worth 1/2 tokens after layer 2: Plug-and-play inference acceleration for large vision-language models,

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-03T03:05:15.209384Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0643c3a1-6df4-469f-affc-f27c7da63a74 · outbound

This paper cites Qwen3.5-Omni Technical Report.

CodeShrink: Adaptive Visual Compression for Efficient Multimodal Code Understanding Qwen3.5-Omni Technical Report

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-03T03:05:15.212064Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1dcd1fa7-f960-4897-aadb-68d29d7a4afb · outbound

This paper cites Lora: Low-rank adaptation of large language models.

CodeShrink: Adaptive Visual Compression for Efficient Multimodal Code Understanding Lora: Low-rank adaptation of large language models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-03T03:05:15.215403Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57fb9599-2e51-47d1-81c6-876cc4654207 · outbound

This paper cites Qwen3 Technical Report.

CodeShrink: Adaptive Visual Compression for Efficient Multimodal Code Understanding Qwen3 Technical Report

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-03T03:05:15.218781Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2630c2f2-3f9d-439b-b337-4614f903aa8a · outbound

This paper cites Gpt-5-mini model documentation,.

CodeShrink: Adaptive Visual Compression for Efficient Multimodal Code Understanding Gpt-5-mini model documentation,

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-03T03:05:15.222944Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e82c3c1b-71a3-4a8a-8679-abbec0865bf6 · outbound

This paper cites Gemini 3 flash model card,.

CodeShrink: Adaptive Visual Compression for Efficient Multimodal Code Understanding Gemini 3 flash model card,

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-03T03:05:15.226145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa5a471f-944c-453f-bdf5-ee2f1a8fe4ec · outbound

This paper cites SlideCoder: Layout- aware RAG-enhanced hierarchical slide generation from design,.

CodeShrink: Adaptive Visual Compression for Efficient Multimodal Code Understanding SlideCoder: Layout- aware RAG-enhanced hierarchical slide generation from design,

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-03T03:05:15.228734Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0215458-174c-4cbc-8f6e-6c7c7ac754a9 · outbound

This paper cites Mmcode: Bench- marking multimodal large language models for code generation with visually rich programming problems,.

CodeShrink: Adaptive Visual Compression for Efficient Multimodal Code Understanding Mmcode: Bench- marking multimodal large language models for code generation with visually rich programming problems,

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-03T03:05:15.231573Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7cc60637-7190-4551-a31a-950500ad92bc · outbound

This paper cites Humaneval-v: Systematic evaluation of visual reasoning in large multimodal models for code generation,.

CodeShrink: Adaptive Visual Compression for Efficient Multimodal Code Understanding Humaneval-v: Systematic evaluation of visual reasoning in large multimodal models for code generation,

Reference 26

Resolution: verified exact; doi, observed 2026-08-03T03:09:21.101585Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 622174ea-a30a-41c8-9cef-6a7fd9c7cac2 · outbound

This paper cites Efficientpostergen: Semantic-aware efficient poster generation via token compression and accurate violation detection,.

CodeShrink: Adaptive Visual Compression for Efficient Multimodal Code Understanding Efficientpostergen: Semantic-aware efficient poster generation via token compression and accurate violation detection,

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-03T03:05:15.237118Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bcf80207-ceac-4e78-a437-dff3dc538637 · outbound

This paper cites Envisioning future interactive web development: Editing webpage with natural language,.

CodeShrink: Adaptive Visual Compression for Efficient Multimodal Code Understanding Envisioning future interactive web development: Editing webpage with natural language,

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-03T03:05:15.240118Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ae6a85a-75df-4557-a4c0-a6b44071b8e4 · outbound

This paper cites Comuicoder: Component-based reusable ui code generation for complex websites via semantic segmentation and element-wise feedback,.

CodeShrink: Adaptive Visual Compression for Efficient Multimodal Code Understanding Comuicoder: Component-based reusable ui code generation for complex websites via semantic segmentation and element-wise feedback,

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-03T03:05:15.242657Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation caea5b15-91e4-4315-9bb9-1815328ddace · outbound

This paper cites UIBenchKit: A unified toolkit for design-to-code model evaluation.

CodeShrink: Adaptive Visual Compression for Efficient Multimodal Code Understanding UIBenchKit: A unified toolkit for design-to-code model evaluation

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-03T03:05:15.245829Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3e52397-5a6b-49bb-8d74-abd527b33264 · outbound

This paper cites From Runnable to Shippable: Multi-Agent Test-Driven Development for Generating Full-Stack Web Applications from Requirements.

CodeShrink: Adaptive Visual Compression for Efficient Multimodal Code Understanding From Runnable to Shippable: Multi-Agent Test-Driven Development for Generating Full-Stack Web Applications from Requirements

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-03T03:05:15.248609Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f9e1521-e419-4dde-abb0-126750e095e0 · outbound

This paper cites MRWeb: An Exploration of Generating Multi-Page Resource-Aware Web Code from UI Designs.

CodeShrink: Adaptive Visual Compression for Efficient Multimodal Code Understanding MRWeb: An Exploration of Generating Multi-Page Resource-Aware Web Code from UI Designs

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-03T03:05:15.251326Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0512611d-a215-4575-a907-db3d976b1bed · outbound

This paper cites Interaction2code: Benchmarking mllm-based interactive webpage code generation from interactive prototyping,.

CodeShrink: Adaptive Visual Compression for Efficient Multimodal Code Understanding Interaction2code: Benchmarking mllm-based interactive webpage code generation from interactive prototyping,

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-03T03:05:15.253857Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77fa1efd-a13d-4e13-b374-9bd1ebb46ca5 · outbound

This paper cites Designrepair: Dual-stream design guideline-aware frontend repair with large language models,.

CodeShrink: Adaptive Visual Compression for Efficient Multimodal Code Understanding Designrepair: Dual-stream design guideline-aware frontend repair with large language models,

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-03T03:05:15.256882Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de94f7f8-9467-48fd-b5f3-246921939130 · outbound

This paper cites Designbench: A comprehensive benchmark for mllm-based front-end code generation,.

CodeShrink: Adaptive Visual Compression for Efficient Multimodal Code Understanding Designbench: A comprehensive benchmark for mllm-based front-end code generation,

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-03T03:05:15.259931Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98a11707-ffd1-4cb9-8d30-723fe9af9a43 · outbound

This paper cites Empowering agile-based generative software development through human-ai teamwork,.

CodeShrink: Adaptive Visual Compression for Efficient Multimodal Code Understanding Empowering agile-based generative software development through human-ai teamwork,

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-03T03:05:15.262504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28d86365-142f-499a-8a4f-135bf7077587 · outbound

This paper cites Token sugar: Making source code sweeter for llms through token-efficient shorthand,.

CodeShrink: Adaptive Visual Compression for Efficient Multimodal Code Understanding Token sugar: Making source code sweeter for llms through token-efficient shorthand,

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-03T03:05:15.265273Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26f27974-6eac-41d9-bb40-6c6368575d6d · outbound

This paper cites Less is more: Docstring compression in code generation,.

CodeShrink: Adaptive Visual Compression for Efficient Multimodal Code Understanding Less is more: Docstring compression in code generation,

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-03T03:05:15.267816Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6591ea8e-79cc-428c-9645-fd4fa71afbaf · outbound

This paper cites The Hidden Cost of Readability: How Code Formatting Silently Consumes Your LLM Budget.

CodeShrink: Adaptive Visual Compression for Efficient Multimodal Code Understanding The Hidden Cost of Readability: How Code Formatting Silently Consumes Your LLM Budget

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-03T03:05:15.270261Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2c12cb8-ef22-4974-8d83-0f5b6a29c0f8 · outbound

This paper cites Effi- cientuicoder: A bidirectional token compression framework for efficient mllm-based ui code generation,.

CodeShrink: Adaptive Visual Compression for Efficient Multimodal Code Understanding Effi- cientuicoder: A bidirectional token compression framework for efficient mllm-based ui code generation,

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-03T03:05:15.273347Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93d50d47-fa32-46ae-923d-fcd5a2f2602a · outbound

This paper cites Available: https://doi.org/10.1145/3597503.3623316.

CodeShrink: Adaptive Visual Compression for Efficient Multimodal Code Understanding Available: https://doi.org/10.1145/3597503.3623316

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-03T03:05:14.923158Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.