Kun Gai, Huan Yang, Bo Zhao, Wei Ji, Yihang Liu, Chenfeng Zhang
9 of 10 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; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 7 failures of our instrument; 1 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/2603.18488.json · badge: /api/ran/2603.18488.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 |
|---|---|---|
| KlingAIResearch/TexEditor | canonical (classifier label) classifier basis: census |
9 ran · 1 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| b64_to_pil | Ran ran, honoured the contract we drafted |
KlingAIResearch/TexEditor/flow_grpo/reward_edge_loss.py code served (permissive licence) · get_code("4b30f1ddbab556db") 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.
|
| get_image_transform | Ran ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT) |
KlingAIResearch/TexEditor/flow_grpo/clip_scorer.py code served (permissive licence) · get_code("1d0c29e5ba66b093") 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 Compose. 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.
|
| get_size | Ran ran, honoured the contract we drafted |
KlingAIResearch/TexEditor/flow_grpo/clip_scorer.py code served (permissive licence) · get_code("b4ae73baea6f9f47") 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, 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.
|
| image_transform_tensor | Ran ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT) |
KlingAIResearch/TexEditor/flow_grpo/hpsv2_scorer.py code served (permissive licence) · get_code("e75cc96a39865389") 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 Compose. 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.
|
| parse_eval_output | Ran ran; our contract draft was wrong, not the code |
KlingAIResearch/TexEditor/flow_grpo/reward_edge_loss.py code served (permissive licence) · get_code("3150b5d693a52ec3") 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 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.
|
| pil2b64 | Ran ran; our contract draft was wrong, not the code |
KlingAIResearch/TexEditor/flow_grpo/reward_edge_loss.py code served (permissive licence) · get_code("90e613f6eda68cc0") 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 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.
|
| pil_image_to_base64 | Ran ran; our contract draft was wrong, not the code |
KlingAIResearch/TexEditor/flow_grpo/unifiedreward_scorer.py code served (permissive licence) · get_code("679c61d741aabb1d") 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 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.
|
| to_3d | Ran ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT) |
KlingAIResearch/TexEditor/model/sauge_vitb.py pointer only (licence: Apache-2.0); the stored copy get_code serves, from gladzhang/Xformer, is pointer only (licence: NONE) · get_code("82a15cc1e46f7e4d") 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 gladzhang/Xformer, 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. |
| to_4d | Ran ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT) |
KlingAIResearch/TexEditor/model/sauge_vitb.py pointer only (licence: Apache-2.0); the stored copy get_code serves, from gladzhang/Xformer, is pointer only (licence: NONE) · get_code("b20f2a5df739a59e") 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 gladzhang/Xformer, 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. |
| get_config | Not yet run unverified (harvested, no recorded run) |
KlingAIResearch/TexEditor/config/texeditor_infer.py code served (permissive licence) · get_code("b6e22297f43ef430") How it ranno invocation recorded. |
Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 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, 4 later) and 4 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 |
|---|---|---|---|
| to_3d | 80 other papers 77 dated earlier, 3 later · 18 only as an assembly brick |
2003.06792 (2020-03) Learning Enriched Features for Real Image Restoration and Enhancement |
2102.02808 (2021-02) Multi-Stage Progressive Image Restoration 2111.09881 (2021-11) Restormer: Efficient Transformer for High-Resolution Image Restoration and 77 more not named here |
| to_4d | 79 other papers 76 dated earlier, 3 later · 18 only as an assembly brick |
2003.06792 (2020-03) Learning Enriched Features for Real Image Restoration and Enhancement |
2102.02808 (2021-02) Multi-Stage Progressive Image Restoration 2111.09881 (2021-11) Restormer: Efficient Transformer for High-Resolution Image Restoration and 76 more not named here |
| get_config | 6 other papers 6 dated earlier |
2305.13301 (2023-05) Training Diffusion Models with Reinforcement Learning |
2310.10639 (2023-10) Zero-Shot Robotic Manipulation with Pretrained Image-Editing Diffusion Models 2402.08552 (2024-02) Confronting Reward Overoptimization for Diffusion Models: A Perspective of Inductive and Primacy Biases and 3 more not named here |
| get_image_transform | 3 other papers 2 dated earlier, 1 later |
2505.05470 (2025-05) Flow-GRPO: Training Flow Matching Models via Online RL |
2602.22809 (2026-02) PhotoAgent: Exploratory Visual Aesthetic Planning with Large Vision Models 2605.07950 (2026-05) Slowly Annealed Langevin Dynamics: Theory and Applications to Training-Free Guided Generation |
| get_size | 3 other papers 2 dated earlier, 1 later |
2505.05470 (2025-05) Flow-GRPO: Training Flow Matching Models via Online RL |
2602.22809 (2026-02) PhotoAgent: Exploratory Visual Aesthetic Planning with Large Vision Models 2605.07950 (2026-05) Slowly Annealed Langevin Dynamics: Theory and Applications to Training-Free Guided Generation |
| pil_image_to_base64 | 2 other papers 2 dated earlier |
2505.05470 (2025-05) Flow-GRPO: Training Flow Matching Models via Online RL |
2509.25050 (2025-09) Advantage Weighted Matching: Aligning RL with Pretraining in Diffusion Models |
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.
Text-guided texture editing aims to modify object appearance while preserving the underlying geometric structure. However, our empirical analysis reveals that even SOTA editing models frequently struggle to maintain structural consistency during texture editing, despite the intended changes being purely appearance-related. Motivated by this observation, we jointly enhance structure preservation from both data and training perspectives, and build TexEditor, a dedicated texture editing model based on Qwen-Image-Edit-2509. Firstly, we construct TexBlender, a high-quality SFT dataset generated with Blender, which provides strong structural priors for a cold start. Secondly, we introduce StructureNFT, a RL-based approach that integrates structure-preserving losses to transfer the structural priors learned during SFT to real-world scenes. Moreover, due to the limited realism and evaluation coverage of existing benchmarks, we introduce TexBench, a general-purpose real-world benchmark for text-guided texture editing. Extensive experiments on existing Blenderbased texture benchmarks and our TexBench show that TexEditor consistently outperforms strong baselines such as Nano Banana Pro. In addition, we assess TexEditor on the generalpurpose benchmark ImgEdit to validate its generalization. Our code and data are available at https://github.com/KlingAIResearch/TexEditor.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2603.18488")
get_code_for_paper("2603.18488")
have("2603.18488")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2603.18488.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2603.18488)
Connect an agent — have() is free.