Xiaoyi Dong, Dongdong Chen, Weiming Zhang, Nenghai Yu, Hang Zhou, Qidong Huang
16 of 19 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; 12 failures of our instrument; 3 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, 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/2203.04041.json · badge: /api/ran/2203.04041.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 |
|---|---|---|
| shikiw/SI-Adv | canonical (classifier label) classifier basis not recorded on the link |
16 ran · 3 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| index_points | Ran ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT) |
shikiw/SI-Adv/model_utils/pct_util.py code served (permissive licence) · get_code("449a0265144f6530") How it ranRan in Syntology's jail on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Tensor, ndim 3, dtype family float, shape (2, 4, 3) as a later run recorded it. The image it ran in was not recorded. The comparison behind this sample's level is a different run: the peer-agreement lane ran it again on the host, not in the jail (report dated 2026-09-04T23:32:40Z). 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.
|
| cal_loss | Ran ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT) |
shikiw/SI-Adv/model_utils/pct_util.py code served (permissive licence) · get_code("c6c2758c0c2fa756") 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 Tensor, ndim 0, dtype family float, 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.
|
| closest_pool | Ran ran; our contract draft was wrong, not the code |
shikiw/SI-Adv/model_utils/kpconv_util.py code served (permissive licence) · get_code("728888ce9772c062") 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 2, dtype family float, shape (3, 4) 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.
|
| farthest_point_sample | Ran ran; our contract draft was wrong, not the code |
shikiw/SI-Adv/data_utils/ModelNetDataLoader.py pointer only (licence: MIT); the stored copy get_code serves, from Yuzhe-Fu/FlashFPS, is pointer only (licence: NOASSERTION) · get_code("f80066a00e7156a2") 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 Yuzhe-Fu/FlashFPS, and GitHub could not classify the licence of that repository (NOASSERTION). 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. |
| gather | Ran ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT) |
shikiw/SI-Adv/model_utils/kpconv_util.py code served (permissive licence) · get_code("06eb9b038422a6ef") 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 4, dtype family float, shape (2, 3, 4, 3) 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_scorenet_input | Ran ran; our contract draft was wrong, not the code |
shikiw/SI-Adv/model_utils/paconv_util.py pointer only (licence: MIT); the stored copy get_code serves, from yossilevii100/refocusing, is pointer only (licence: NONE) · get_code("d77f00230e16006d") 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 yossilevii100/refocusing, 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. |
| index_points | Ran ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT) |
shikiw/SI-Adv/model_utils/pointconv_util.py code served (permissive licence) · get_code("573cb024ea47999f") 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 Tensor, ndim 3, dtype family float, shape (2, 2, 3) 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.
|
| knn | Ran ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT) |
shikiw/SI-Adv/model_utils/curvenet_util.py code served (permissive licence) · get_code("fd43b3106ac73716") 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 3, dtype family int, shape (2, 3, 3) 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.
|
| knn | Ran ran; our contract draft was wrong, not the code |
shikiw/SI-Adv/model_utils/paconv_util.py pointer only (licence: MIT); the stored copy get_code serves, from yossilevii100/refocusing, is pointer only (licence: NONE) · get_code("69845e3c207ea9e7") 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 yossilevii100/refocusing, 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. |
| normal_knn | Ran ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT) |
shikiw/SI-Adv/model_utils/curvenet_util.py code served (permissive licence) · get_code("1979f86a5b2b0446") 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 3, dtype family int, shape (2, 3, 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.
|
| pc_normalize | Ran ran, honoured the contract we drafted |
shikiw/SI-Adv/data_utils/ModelNetDataLoader.py pointer only (licence: MIT); the stored copy get_code serves, from ajhamdi/MVTN, is pointer only (licence: NONE) · get_code("4783fbece52f500e") 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 ajhamdi/MVTN, 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. |
| pc_normalize | Ran ran, honoured the contract we drafted |
shikiw/SI-Adv/model_utils/curvenet_util.py pointer only (licence: MIT); the stored copy get_code serves, from aboulch/ConvPoint, is pointer only (licence: NOASSERTION) · get_code("ec413739d406e611") 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 aboulch/ConvPoint, and GitHub could not classify the licence of that repository (NOASSERTION). 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. |
| radius_gaussian | Ran ran, violated the contract we drafted |
shikiw/SI-Adv/model_utils/kpconv_util.py code served (permissive licence) · get_code("42f2cd40ba483d3b") 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 3, dtype family float, shape (2, 3, 4) 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.
|
| square_distance | Ran ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT) |
shikiw/SI-Adv/model_utils/pct_util.py code served (permissive licence) · get_code("3bfe172e686075cd") 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 Tensor, ndim 3, dtype family float, shape (2, 3, 5) 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.
|
| square_distance | Ran ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT) |
shikiw/SI-Adv/model_utils/pointconv_util.py code served (permissive licence) · get_code("580dee6761649b29") 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 Tensor, ndim 3, dtype family float, shape (2, 4, 5) 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.
|
| timeit | Ran ran, honoured the contract we drafted |
shikiw/SI-Adv/model_utils/pointconv_util.py pointer only (licence: MIT); the stored copy get_code serves, from duasoi/Mind2Cloud, is pointer only (licence: NONE) · get_code("b1227ddb721e2999") 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 duasoi/Mind2Cloud, 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. |
| assign_score_withk | Not yet run unverified (harvested, no recorded run) |
shikiw/SI-Adv/cuda_lib/functional.py pointer only (licence: MIT); the stored copy get_code serves, from yossilevii100/critical_points2, is pointer only (licence: NONE) · get_code("72e38b49e5bad8ba") 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 yossilevii100/critical_points2, 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. No invocation recorded. |
| assign_score_withk_halfkernel | Not yet run unverified (harvested, no recorded run) |
shikiw/SI-Adv/cuda_lib/functional.py pointer only (licence: MIT); the stored copy get_code serves, from yossilevii100/critical_points2, is pointer only (licence: NONE) · get_code("f6e6c6c45d23680a") 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 yossilevii100/critical_points2, 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. No invocation recorded. |
| feat_trans_dgcnn | Not yet run unverified (harvested, no recorded run) |
shikiw/SI-Adv/model_utils/paconv_util.py pointer only (licence: MIT); the stored copy get_code serves, from yossilevii100/refocusing, is pointer only (licence: NONE) · get_code("5fb9a68241c62149") 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 yossilevii100/refocusing, 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. No invocation recorded. |
Of 19 samples lifted from this paper's linked repositories, 19 carry a function identity and 0 do not. Of the 17 distinct functions with an identity, 17 are also present in other papers whose code we hold (12 with at least one paper dated earlier, 6 the same month, 17 later) and 0 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 |
|---|---|---|---|
| square_distance | 75 other papers 13 dated earlier, 1 the same month, 60 later, 1 same year, order not determinable · 9 only as an assembly brick |
1706.02413 (2017-06) PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space |
1811.07246 (2018-11) PointConv: Deep Convolutional Networks on 3D Point Clouds 2003.00410 (2020-03) PF-Net: Point Fractal Network for 3D Point Cloud Completion and 72 more not named here |
| pc_normalize | 47 other papers 8 dated earlier, 3 the same month, 36 later |
1811.07246 (2018-11) PointConv: Deep Convolutional Networks on 3D Point Clouds |
1912.12098 (2019-12) Quaternion Equivariant Capsule Networks for 3D Point Clouds 2003.00492 (2020-03) PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Sampling and 44 more not named here |
| farthest_point_sample | 43 other papers 5 dated earlier, 3 the same month, 35 later |
1811.07246 (2018-11) PointConv: Deep Convolutional Networks on 3D Point Clouds |
2003.00492 (2020-03) PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Sampling 2010.05272 (2020-10) IF-Defense: 3D Adversarial Point Cloud Defense via Implicit Function based Restoration and 40 more not named here |
| index_points | 42 other papers 10 dated earlier, 2 the same month, 30 later · 6 only as an assembly brick |
1706.02413 (2017-06) PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space |
1811.07246 (2018-11) PointConv: Deep Convolutional Networks on 3D Point Clouds 2003.13479 (2020-03) RPM-Net: Robust Point Matching using Learned Features and 39 more not named here |
| pc_normalize | 36 other papers 12 dated earlier, 1 the same month, 23 later |
1803.05827 (2018-03) Local Spectral Graph Convolution for Point Set Feature Learning |
1904.02375 (2019-04) ConvPoint: Continuous Convolutions for Point Cloud Processing 1904.10014 (2019-04) Linked Dynamic Graph CNN: Learning on Point Cloud via Linking Hierarchical Features and 33 more not named here |
| timeit | 33 other papers 5 dated earlier, 1 the same month, 27 later |
1811.07246 (2018-11) PointConv: Deep Convolutional Networks on 3D Point Clouds |
2003.00410 (2020-03) PF-Net: Point Fractal Network for 3D Point Cloud Completion 2003.04618 (2020-03) Convolutional Occupancy Networks and 30 more not named here |
| gather | 8 other papers 3 dated earlier, 5 later |
1904.08889 (2019-04) KPConv: Flexible and Deformable Convolution for Point Clouds |
2007.12668 (2020-07) KPRNet: Improving projection-based LiDAR semantic segmentation 2111.12591 (2021-11) Lepard: Learning partial point cloud matching in rigid and deformable scenes and 5 more not named here |
| radius_gaussian | 8 other papers 3 dated earlier, 5 later |
1904.08889 (2019-04) KPConv: Flexible and Deformable Convolution for Point Clouds |
2007.12668 (2020-07) KPRNet: Improving projection-based LiDAR semantic segmentation 2111.12591 (2021-11) Lepard: Learning partial point cloud matching in rigid and deformable scenes and 5 more not named here |
| cal_loss | 7 other papers 3 dated earlier, 4 later |
1911.00195 (2019-11) Rotation Invariant Point Cloud Classification: Where Local Geometry Meets Global Topology |
2101.01461 (2021-01) PointCutMix: Regularization Strategy for Point Cloud Classification 2201.12296 (2022-01) Benchmarking Robustness of 3D Point Cloud Recognition Against Common Corruptions and 4 more not named here |
| closest_pool | 6 other papers 3 dated earlier, 3 later |
1904.08889 (2019-04) KPConv: Flexible and Deformable Convolution for Point Clouds |
2007.12668 (2020-07) KPRNet: Improving projection-based LiDAR semantic segmentation 2111.12591 (2021-11) Lepard: Learning partial point cloud matching in rigid and deformable scenes and 3 more not named here |
| knn | 3 other papers 1 dated earlier, 2 later |
2201.12296 (2022-01) Benchmarking Robustness of 3D Point Cloud Recognition Against Common Corruptions |
2308.05525 (2023-08) Robustifying Point Cloud Networks by Refocusing 2410.03644 (2024-10) Unlearnable 3D Point Clouds: Class-wise Transformation Is All You Need |
| normal_knn | 3 other papers 1 dated earlier, 2 later |
2201.12296 (2022-01) Benchmarking Robustness of 3D Point Cloud Recognition Against Common Corruptions |
2308.05525 (2023-08) Robustifying Point Cloud Networks by Refocusing 2410.03644 (2024-10) Unlearnable 3D Point Clouds: Class-wise Transformation Is All You Need |
| assign_score_withk | 1 other paper 1 later |
2308.05525 (2023-08) Robustifying Point Cloud Networks by Refocusing |
|
| assign_score_withk_halfkernel | 1 other paper 1 later |
2308.05525 (2023-08) Robustifying Point Cloud Networks by Refocusing |
|
| feat_trans_dgcnn | 1 other paper 1 later |
2308.05525 (2023-08) Robustifying Point Cloud Networks by Refocusing |
|
| get_scorenet_input | 1 other paper 1 later |
2308.05525 (2023-08) Robustifying Point Cloud Networks by Refocusing |
|
| knn | 1 other paper 1 later |
2308.05525 (2023-08) Robustifying Point Cloud Networks by Refocusing |
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.
Adversary and invisibility are two fundamental but conflict characters of adversarial perturbations. Previous adversarial attacks on 3D point cloud recognition have often been criticized for their noticeable point outliers, since they just involve an "implicit constrain" like global distance loss in the time-consuming optimization to limit the generated noise. While point cloud is a highly structured data format, it is hard to constrain its perturbation with a simple loss or metric properly. In this paper, we propose a novel Point-Cloud Sensitivity Map to boost both the efficiency and imperceptibility of point perturbations. This map reveals the vulnerability of point cloud recognition models when encountering shape-invariant adversarial noises. These noises are designed along the shape surface with an "explicit constrain" instead of extra distance loss. Specifically, we first apply a reversible coordinate transformation on each point of the point cloud input, to reduce one degree of point freedom and limit its movement on the tangent plane. Then we calculate the best attacking direction with the gradients of the transformed point cloud obtained on the white-box model. Finally we assign each point with a non-negative score to construct the sensitivity map, which benefits both white-box adversarial invisibility and blackbox query-efficiency extended in our work. Extensive evaluations prove that our method can achieve the superior performance on various point cloud recognition models, with its satisfying adversarial imperceptibility and strong resistance to different point cloud defense settings. Our code is available at: https://github.com/shikiw/SI-Adv.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2203.04041")
get_code_for_paper("2203.04041")
have("2203.04041")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2203.04041.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2203.04041)
Connect an agent — have() is free.