Zijie Wang, Wei He, Xiao An, Jiepan Li, Chen Zhong, Guangyi Yang
8 of 8 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; 3 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 4 failures of our instrument; 0 no recorded run), measured 2026-11-22; 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/2608.04496.json · badge: /api/ran/2608.04496.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.
| Repository | Role | Ran |
|---|---|---|
| Zhong-Chenchen/DIVE | canonical (classifier label) classifier basis: census |
8 ran · 0 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| collate_fn | Ran ran; our contract draft was wrong, not the code |
Zhong-Chenchen/DIVE/llava/eval/model_vqa_loader.py code served (permissive licence) · get_code("20e4f665698a3d18") How it ranRan 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 tuple. 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.
|
| compute_keep_count | Ran ran, honoured the contract we drafted |
Zhong-Chenchen/DIVE/llava/model/language_model/dive/utils.py code served (permissive licence) · get_code("a5f4ad234532da9c") How it ranRan 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 int, ndim 0, dtype family int, 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.
|
| compute_token_topk | Ran ran, honoured the contract we drafted |
Zhong-Chenchen/DIVE/llava/model/language_model/dive/utils.py code served (permissive licence) · get_code("8920b1b0aa6951fe") How it ranRan 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 int, ndim 0, dtype family int, 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.
|
| get_chunk | Ran ran; our contract draft was wrong, not the code |
Zhong-Chenchen/DIVE/llava/eval/model_vqa.py code served (permissive licence) · get_code("42a46570620cd9fa") How it ranRan 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.
|
| is_none | Ran ran, violated the contract we drafted |
Zhong-Chenchen/DIVE/llava/eval/model_vqa_mmbench.py pointer only (licence: Apache-2.0); the stored copy get_code serves, from ASTRAL-Group/ASTRA, is pointer only (licence: NONE) · get_code("bae18947b56f2be1") How it ranThe 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 ASTRAL-Group/ASTRA, 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_image | Ran ran, honoured the contract we drafted |
Zhong-Chenchen/DIVE/predict.py code served (permissive licence) · get_code("9b3c1cb391672ccb") How it ranRan 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 Image. 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.
|
| split_list | Ran ran; our contract draft was wrong, not the code |
Zhong-Chenchen/DIVE/llava/eval/model_vqa.py code served (permissive licence) · get_code("076c252c52cbb161") How it ranRan 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.
|
| split_list | Ran ran; our contract draft was wrong, not the code |
Zhong-Chenchen/DIVE/llava/eval/model_vqa_ocrbench.py code served (permissive licence) · get_code("cb9eaee96a223830") How it ranRan 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. 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.
|
Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 6 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 0 the same month, 5 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.
| Function | Also present in | Earliest-dated | Others named |
|---|---|---|---|
| split_list | 197 other papers 195 dated earlier, 1 later, 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 188 dated earlier, 1 later |
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 |
| load_image | 85 other papers 84 dated earlier, 1 later |
2112.05682 (2021-12) Self-attention Does Not Need $O(n^2)$ Memory |
2305.10973 (2023-05) Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold 2307.10490 (2023-07) Abusing Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMs and 82 more not named here |
| is_none | 83 other papers 82 dated earlier, 1 later |
2112.05682 (2021-12) Self-attention Does Not Need $O(n^2)$ Memory |
2308.10253 (2023-08) StableLLaVA: Enhanced Visual Instruction Tuning with Synthesized Image-Dialogue Data 2308.13566 (2023-08) MLLM-DataEngine: An Iterative Refinement Approach for MLLM and 80 more not named here |
| collate_fn | 54 other papers 53 dated earlier, 1 later |
2308.13566 (2023-08) MLLM-DataEngine: An Iterative Refinement Approach for MLLM |
2310.08588 (2023-10) Octopus: Embodied Vision-Language Programmer from Environmental Feedback 2311.07362 (2023-11) Volcano: Mitigating Multimodal Hallucination through Self-Feedback Guided Revision and 51 more not named here |
| split_list | 1 other paper 1 dated earlier |
2501.00321 (2025-01) OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning |
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.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Visual inputs in vision-language models (VLMs) are often encoded into substantially longer token sequences than text, making visual tokens a major bottleneck for efficient inference. Abundant recent methods address this bottleneck by scoring token importance and pruning low-scoring tokens in a single pass. However, one-shot scoring is insufficient because a token's prompt-relevant usefulness depends on the evidence already retained. Motivated by this insight, we introduce DIVE (Dynamic Iterative Visual Evidence Construction), a trainingfree framework that recasts visual-token pruning as dynamic evidence construction. DIVE repeatedly selects the remaining token with the highest residual-conditioned score, updates the visual and prompt residuals to discount the evidence already explained, and re-evaluates the remaining tokens. This selectupdate-re-evaluate process builds a retained set of complementary, prompt-relevant evidence. Experiments across eight image-understanding benchmarks show that DIVE consistently preserves performance across token budgets. With an 88.9% reduction in visual tokens, DIVE retains 98.2% of the uncompressed model's average performance. Code is available at https://github.com/Zhong-Chenchen/DIVE.git.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2608.04496")
get_code_for_paper("2608.04496")
have("2608.04496")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2608.04496.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2608.04496)
Connect an agent — have() is free.