Yan Wang, Liangqiong Qu, Yuyin Zhou, Wei Shao, Zhiheng Cheng, Qingyue Wei, Hongru Zhu
9 of 12 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (3 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 2 violated it and 3 have no contract verdict; 3 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/2403.18271.json · badge: /api/ran/2403.18271.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 |
|---|---|---|
| cccccczh404/h-sam | canonical (classifier label) classifier basis: census |
6 ran · 3 no recorded run |
| Cccccczh404/H-SAM | community Papers with Code archive |
3 ran · 0 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| Attention | Ran ran on a synthesized input · constructed an object; no result was computed |
Cccccczh404/H-SAM/segment_anything/modeling/mask_decoder_224.py code served (permissive licence) · get_code("284d02bbefb07995") 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 an instance of its own class, Attention: the run constructed the object and did not call it, so no result was computed. 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.
|
| MLPBlock | Ran ran on a synthesized input · constructed an object; no result was computed |
Cccccczh404/H-SAM/segment_anything/modeling/mask_decoder_224.py code served (permissive licence) · get_code("51c9cfbbea25d855") 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 an instance of its own class, MLPBlock: the run constructed the object and did not call it, so no result was computed. 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.
|
| MaskDecoder2_224 | Ran ran on a synthesized input · constructed an object; no result was computed |
Cccccczh404/H-SAM/segment_anything/modeling/mask_decoder_224.py code served (permissive licence) · get_code("a1ef1a16dd1da406") 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 an instance of its own class, MaskDecoder2_224: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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.
|
| calc_loss | Ran ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT) |
cccccczh404/h-sam/trainer.py code served (permissive licence) · get_code("ad5471db7ab93cbf") 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 float; 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.
|
| mask_latent_code_spatial_wise | Ran ran; our contract draft was wrong, not the code |
cccccczh404/h-sam/utils.py code served (permissive licence) · get_code("f7b26aed76a9fab8") 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.
|
| random_crop | Ran ran, honoured the contract we drafted |
cccccczh404/h-sam/datasets/dataset_synapse.py code served (permissive licence) · get_code("3b50ddb9ad3810af") 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 3, 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.
|
| random_rot_flip | Ran ran, violated the contract we drafted |
cccccczh404/h-sam/datasets/dataset_synapse.py pointer only (licence: MIT); the stored copy get_code serves, from jefferyjiang-yf/m4oe, is pointer only (licence: NONE) · get_code("960b785e65a00358") How it ranThe body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from jefferyjiang-yf/m4oe, 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. |
| random_rotate | Ran ran, violated the contract we drafted |
cccccczh404/h-sam/datasets/dataset_synapse.py pointer only (licence: MIT); the stored copy get_code serves, from jefferyjiang-yf/m4oe, is pointer only (licence: NONE) · get_code("43fa66325ce3cafd") How it ranThe body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from jefferyjiang-yf/m4oe, 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. |
| torch2D_Hausdorff_distance | Ran ran; our contract draft was wrong, not the code |
cccccczh404/h-sam/trainer.py code served (permissive licence) · get_code("9fc81019a0d23d94") 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 Tensor, ndim 1, dtype family float, shape (2,) 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.
|
| build_sam_vit_b | Not yet run unverified (harvested, no recorded run) |
cccccczh404/h-sam/segment_anything/build_sam.py code served (permissive licence) · get_code("9f4a1072f21a09c1") How it ranno invocation recorded. |
| build_sam_vit_h | Not yet run unverified (harvested, no recorded run) |
cccccczh404/h-sam/segment_anything/build_sam.py code served (permissive licence) · get_code("e4133f792f260d92") How it ranno invocation recorded. |
| build_sam_vit_l | Not yet run unverified (harvested, no recorded run) |
cccccczh404/h-sam/segment_anything/build_sam.py code served (permissive licence) · get_code("c97d7adfb4b0a020") How it ranno invocation recorded. |
Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 7 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 0 the same month, 3 later) and 5 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 |
|---|---|---|---|
| random_rotate | 10 other papers 6 dated earlier, 4 later |
2111.04734 (2021-11) Mixed Transformer U-Net For Medical Image Segmentation |
2304.13785 (2023-04) Customized Segment Anything Model for Medical Image Segmentation 2306.12737 (2023-06) Ladder Fine-tuning approach for SAM integrating complementary network and 7 more not named here |
| random_rot_flip | 9 other papers 6 dated earlier, 3 later |
2111.04734 (2021-11) Mixed Transformer U-Net For Medical Image Segmentation |
2304.13785 (2023-04) Customized Segment Anything Model for Medical Image Segmentation 2306.12737 (2023-06) Ladder Fine-tuning approach for SAM integrating complementary network and 6 more not named here |
| calc_loss | 5 other papers 5 dated earlier |
2304.13785 (2023-04) Customized Segment Anything Model for Medical Image Segmentation |
2306.12737 (2023-06) Ladder Fine-tuning approach for SAM integrating complementary network 2309.08842 (2023-09) MA-SAM: Modality-agnostic SAM Adaptation for 3D Medical Image Segmentation and 2 more not named here |
| build_sam_vit_b | 4 other papers 4 dated earlier |
2304.13785 (2023-04) Customized Segment Anything Model for Medical Image Segmentation |
2306.12737 (2023-06) Ladder Fine-tuning approach for SAM integrating complementary network 2309.08842 (2023-09) MA-SAM: Modality-agnostic SAM Adaptation for 3D Medical Image Segmentation and 1 more not named here |
| build_sam_vit_h | 4 other papers 4 dated earlier |
2304.13785 (2023-04) Customized Segment Anything Model for Medical Image Segmentation |
2306.12737 (2023-06) Ladder Fine-tuning approach for SAM integrating complementary network 2309.08842 (2023-09) MA-SAM: Modality-agnostic SAM Adaptation for 3D Medical Image Segmentation and 1 more not named here |
| build_sam_vit_l | 4 other papers 4 dated earlier |
2304.13785 (2023-04) Customized Segment Anything Model for Medical Image Segmentation |
2306.12737 (2023-06) Ladder Fine-tuning approach for SAM integrating complementary network 2309.08842 (2023-09) MA-SAM: Modality-agnostic SAM Adaptation for 3D Medical Image Segmentation and 1 more not named here |
| Attention brick of this paper's assembly: helper |
1 other paper 1 later |
2503.06683 (2025-03) Dynamic Dictionary Learning for Remote Sensing Image Segmentation |
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.
The Segment Anything Model (SAM) has garnered significant attention for its versatile segmentation abilities and intuitive prompt-based interface. However, its application in medical imaging presents challenges, requiring either substantial training costs and extensive medical datasets for full model fine-tuning or high-quality prompts for optimal performance. This paper introduces H-SAM: a prompt-free adaptation of SAM tailored for efficient fine-tuning of medical images via a two-stage hierarchical decoding procedure. In the initial stage, H-SAM employs SAM's original decoder to generate a prior probabilistic mask, guiding a more intricate decoding process in the second stage. Specifically, we propose two key designs: 1) A class-balanced, mask-guided self-attention mechanism addressing the unbalanced label distribution, enhancing image embedding; 2) A learnable mask cross-attention mechanism spatially modulating the interplay among different image regions based on the prior mask. Moreover, the inclusion of a hierarchical pixel decoder in H-SAM enhances its proficiency in capturing fine-grained and localized details. This approach enables SAM to effectively integrate learned medical priors, facilitating enhanced adaptation for medical image segmentation with limited samples. Our H-SAM demonstrates a 4.78% improvement in average Dice compared to existing prompt-free SAM variants for multi-organ segmentation using only 10% of 2D slices. Notably, without using any unlabeled data, H-SAM even outperforms state-of-the-art semisupervised models relying on extensive unlabeled training data across various medical datasets. Our code is available at https://github.com/Cccccczh404/H-SAM . Recently, Segment Anything Model (SAM) [37], trained with over a billion masks from diverse natural images, demonstrates remarkable zero-shot learning capabilities. This breakthrough presents an avenue for significant advancements in medical image segmentation, especially considering the limited availability of extensive datasets in the medical realm. However, SAM's performance on medical This CVPR paper is the Open Access version, provided by the Computer Vision Foundation. Except for this watermark, it is identical to the accepted version; the final published version of the proceedings is available on IEEE Xplore.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2403.18271")
get_code_for_paper("2403.18271")
have("2403.18271")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2403.18271.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2403.18271)
Connect an agent — have() is free.