17 of 27 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; 0 honoured the contract we drafted, 0 violated it and 8 have no contract verdict; 9 failures of our instrument; 10 no recorded run), measured 2026-11-21; 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/1908.10357.json · badge: /api/ran/1908.10357.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 |
|---|---|---|
| HRNet/Higher-HRNet-Human-Pose-Estimation | canonical (classifier label) classifier basis not recorded on the link |
2 ran · 3 no recorded run |
| LiuShenLan/HRNet | canonical (classifier label) classifier basis: classifier_2025 |
0 ran · 1 no recorded run |
| abhi1kumar/hrnet_pose_single_gpu | community (classifier label) classifier basis: plan_row |
6 ran · 2 no recorded run |
| xn1997/HigherHRnet | community (classifier label) classifier basis not recorded on the link |
4 ran · 2 no recorded run |
| anshky/HR-NET | community (classifier label) classifier basis: plan_row |
2 ran · 1 no recorded run |
| ducongju/HRNet | community (classifier label) classifier basis not recorded on the link |
2 ran · 1 no recorded run |
| Darius-Liesis/HRNet-works | community (classifier label) classifier basis: plan_row |
1 ran · 0 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| aggregate_results | Ran ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT) |
HRNet/Higher-HRNet-Human-Pose-Estimation/lib/core/inference.py code served (permissive licence) · get_code("b2deafbfd7c1f3fc") 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.
|
| box_to_center_scale | Ran ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT) |
anshky/HR-NET/demo/inference.py code served (permissive licence) · get_code("192666724266ef19") 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 2, 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.
|
| calc_dists | Ran ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT) |
abhi1kumar/hrnet_pose_single_gpu/lib/core/evaluate.py code served (permissive licence) · get_code("b91b38261b03587d") 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 ndarray, ndim 2, dtype family float, shape (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.
|
| conv3x3 | Ran ran; our contract draft was wrong, not the code |
Darius-Liesis/HRNet-works/lib/models/pose_higher_hrnet.py pointer only (licence: MIT); the stored copy get_code serves, from lixiaotong97/DSU, is pointer only (licence: NONE) · get_code("fac5364e2f53c6db") 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 lixiaotong97/DSU, 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. |
| cpu_nms_wrapper | Ran ran on a synthesized input |
abhi1kumar/hrnet_pose_single_gpu/lib/nms/nms.py code served (permissive licence) · get_code("0bdca114d99f4177") 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 function. 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.
|
| dist_acc | Ran ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT) |
abhi1kumar/hrnet_pose_single_gpu/lib/core/evaluate.py code served (permissive licence) · get_code("1c2da88027e6e151") 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 float64, 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.
|
| get_max_preds | Ran ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT) |
abhi1kumar/hrnet_pose_single_gpu/lib/core/inference.py code served (permissive licence) · get_code("55c58ef5f795e3d1") 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.
|
| get_max_preds | Ran ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT) |
ducongju/HRNet/lib/core/inference.py code served (permissive licence) · get_code("cc7c8978e2671688") 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.
|
| get_outputs | Ran ran on a synthesized input |
xn1997/HigherHRnet/lib/core/inference.py code served (permissive licence) · get_code("9cf201ffe0770f4a") 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.
|
| get_person_detection_boxes | Ran ran; our contract draft was wrong, not the code |
anshky/HR-NET/demo/inference.py code served (permissive licence) · get_code("74bb768e238398b0") 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, ndim 3, dtype family float; no output shape is stated. 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 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.
|
| get_person_detection_boxes | Ran ran on a synthesized input |
ducongju/HRNet/demo/inference.py code served (permissive licence) · get_code("74695a514c70d509") 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, ndim 3, 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.
|
| gpu_nms_wrapper | Ran ran on a synthesized input |
abhi1kumar/hrnet_pose_single_gpu/lib/nms/nms.py code served (permissive licence) · get_code("167b862a31de0adf") 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 function. 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.
|
| make_input | Ran ran; our contract draft was wrong, not the code |
HRNet/Higher-HRNet-Human-Pose-Estimation/lib/core/loss.py pointer only (licence: MIT); the stored copy get_code serves, from ayh015-dev/da-llpose, is pointer only (licence: NONE) · get_code("cdea90667046c71c") 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 ayh015-dev/da-llpose, 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. |
| py_nms_wrapper | Ran ran on a synthesized input |
abhi1kumar/hrnet_pose_single_gpu/lib/nms/nms.py code served (permissive licence) · get_code("8551f210abffd79e") 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 function. 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.
|
| read_image | Ran ran on a synthesized input |
xn1997/HigherHRnet/datasets/bases.py code served (permissive licence) · get_code("d9cb02ac7b2cd953") 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.
|
| train_collate_fn | Ran ran on a synthesized input |
xn1997/HigherHRnet/datasets/make_dataloader.py code served (permissive licence) · get_code("84d4b3637b0b4b2d") 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.
|
| val_collate_fn | Ran ran on a synthesized input |
xn1997/HigherHRnet/datasets/make_dataloader.py code served (permissive licence) · get_code("236a60a4db5abeb0") 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.
|
| build_dataset | Not yet run unverified (harvested, no recorded run) |
HRNet/Higher-HRNet-Human-Pose-Estimation/lib/dataset/build.py code served (permissive licence) · get_code("0ff31375e05cb70d") How it ranno invocation recorded. |
| get_multi_stage_outputs | Not yet run unverified (harvested, no recorded run) |
xn1997/HigherHRnet/lib/core/inference.py code served (permissive licence) · get_code("cbb539b2a4e3ea1a") How it ranno invocation recorded. |
| get_multi_stage_outputs111 | Not yet run unverified (harvested, no recorded run) |
xn1997/HigherHRnet/lib/core/inference.py code served (permissive licence) · get_code("7d41c67f85ba1f2c") How it ranno invocation recorded. |
| get_pose_net | Not yet run unverified (harvested, no recorded run) |
anshky/HR-NET/lib/models/pose_hrnet.py code served (permissive licence) · get_code("2534c81208f21998") How it ranno invocation recorded. |
| get_pose_net | Not yet run unverified (harvested, no recorded run) |
abhi1kumar/hrnet_pose_single_gpu/lib/models/pose_hrnet.py code served (permissive licence) · get_code("78015ae361e585ca") How it ranno invocation recorded. |
| get_pose_net | Not yet run unverified (harvested, no recorded run) |
LiuShenLan/HRNet/lib/models/pose_higher_hrnet.py code served (permissive licence) · get_code("b1587fcc78f6fa72") How it ranno invocation recorded. |
| get_pose_net | Not yet run unverified (harvested, no recorded run) |
abhi1kumar/hrnet_pose_single_gpu/lib/models/pose_resnet.py code served (permissive licence) · get_code("179c4caeed1a0d16") How it ranno invocation recorded. |
| get_pose_net | Not yet run unverified (harvested, no recorded run) |
ducongju/HRNet/lib/models/pose_hrnet.py code served (permissive licence) · get_code("92f669c4ac6961d1") How it ranno invocation recorded. |
| make_dataloader | Not yet run unverified (harvested, no recorded run) |
HRNet/Higher-HRNet-Human-Pose-Estimation/lib/dataset/build.py code served (permissive licence) · get_code("df9c22deab975625") How it ranno invocation recorded. |
| make_test_dataloader | Not yet run unverified (harvested, no recorded run) |
HRNet/Higher-HRNet-Human-Pose-Estimation/lib/dataset/build.py code served (permissive licence) · get_code("a4025bf00b852a33") How it ranno invocation recorded. |
Of 27 samples lifted from this paper's linked repositories, 27 carry a function identity and 0 do not. Of the 25 distinct functions with an identity, 20 are also present in other papers whose code we hold (11 with at least one paper dated earlier, 9 the same month, 15 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 |
|---|---|---|---|
| conv3x3 | 686 other papers 143 dated earlier, 10 the same month, 533 later · 31 only as an assembly brick |
1406.2661 (2014-06) Generative Adversarial Networks |
1409.0575 (2014-09) ImageNet Large Scale Visual Recognition Challenge 1412.6572 (2014-12) Explaining and Harnessing Adversarial Examples and 683 more not named here |
| get_max_preds | 6 other papers 1 dated earlier, 1 the same month, 4 later |
1902.09212 (2019-02) Deep High-Resolution Representation Learning for Human Pose Estimation |
1908.11542 (2019-08) Satellite Pose Estimation with Deep Landmark Regression and Nonlinear Pose Refinement 1910.06278 (2019-10) Distribution-Aware Coordinate Representation for Human Pose Estimation and 3 more not named here |
| calc_dists | 5 other papers 1 dated earlier, 1 the same month, 3 later |
1902.09212 (2019-02) Deep High-Resolution Representation Learning for Human Pose Estimation |
1908.11542 (2019-08) Satellite Pose Estimation with Deep Landmark Regression and Nonlinear Pose Refinement 1910.06278 (2019-10) Distribution-Aware Coordinate Representation for Human Pose Estimation and 2 more not named here |
| dist_acc | 5 other papers 1 dated earlier, 1 the same month, 3 later |
1902.09212 (2019-02) Deep High-Resolution Representation Learning for Human Pose Estimation |
1908.11542 (2019-08) Satellite Pose Estimation with Deep Landmark Regression and Nonlinear Pose Refinement 1910.06278 (2019-10) Distribution-Aware Coordinate Representation for Human Pose Estimation and 2 more not named here |
| get_pose_net | 5 other papers 2 dated earlier, 1 the same month, 2 later |
1902.09212 (2019-02) Deep High-Resolution Representation Learning for Human Pose Estimation |
1904.04514 (2019-04) High-Resolution Representations for Labeling Pixels and Regions 1908.11542 (2019-08) Satellite Pose Estimation with Deep Landmark Regression and Nonlinear Pose Refinement and 2 more not named here |
| get_pose_net | 5 other papers 2 dated earlier, 1 the same month, 2 later |
1902.09212 (2019-02) Deep High-Resolution Representation Learning for Human Pose Estimation |
1904.04514 (2019-04) High-Resolution Representations for Labeling Pixels and Regions 1908.07919 (2019-08) Deep High-Resolution Representation Learning for Visual Recognition and 2 more not named here |
| box_to_center_scale | 2 other papers 2 later |
2105.06152 (2021-05) When Human Pose Estimation Meets Robustness: Adversarial Algorithms and Benchmarks |
2602.03157 (2026-02) Human-in-the-loop adaptation in group activity feature learning for team sports video retrieval |
| cpu_nms_wrapper | 2 other papers 1 dated earlier, 1 the same month |
1902.09212 (2019-02) Deep High-Resolution Representation Learning for Human Pose Estimation |
1908.11542 (2019-08) Satellite Pose Estimation with Deep Landmark Regression and Nonlinear Pose Refinement |
| gpu_nms_wrapper | 2 other papers 1 dated earlier, 1 the same month |
1902.09212 (2019-02) Deep High-Resolution Representation Learning for Human Pose Estimation |
1908.11542 (2019-08) Satellite Pose Estimation with Deep Landmark Regression and Nonlinear Pose Refinement |
| make_input | 2 other papers 2 later |
2105.06152 (2021-05) When Human Pose Estimation Meets Robustness: Adversarial Algorithms and Benchmarks |
2407.15451 (2024-07) Domain-Adaptive 2D Human Pose Estimation via Dual Teachers in Extremely Low-Light Conditions |
| py_nms_wrapper | 2 other papers 1 dated earlier, 1 the same month |
1902.09212 (2019-02) Deep High-Resolution Representation Learning for Human Pose Estimation |
1908.11542 (2019-08) Satellite Pose Estimation with Deep Landmark Regression and Nonlinear Pose Refinement |
| aggregate_results | 1 other paper 1 later |
2105.06152 (2021-05) When Human Pose Estimation Meets Robustness: Adversarial Algorithms and Benchmarks |
|
| build_dataset | 1 other paper 1 later |
2105.06152 (2021-05) When Human Pose Estimation Meets Robustness: Adversarial Algorithms and Benchmarks |
|
| get_person_detection_boxes | 1 other paper 1 later |
2105.06152 (2021-05) When Human Pose Estimation Meets Robustness: Adversarial Algorithms and Benchmarks |
|
| get_pose_net | 1 other paper 1 later |
2105.06152 (2021-05) When Human Pose Estimation Meets Robustness: Adversarial Algorithms and Benchmarks |
|
| get_pose_net | 1 other paper 1 later |
1910.06278 (2019-10) Distribution-Aware Coordinate Representation for Human Pose Estimation |
|
| make_dataloader | 1 other paper 1 later |
2105.06152 (2021-05) When Human Pose Estimation Meets Robustness: Adversarial Algorithms and Benchmarks |
|
| make_test_dataloader | 1 other paper 1 later |
2105.06152 (2021-05) When Human Pose Estimation Meets Robustness: Adversarial Algorithms and Benchmarks |
|
| train_collate_fn | 1 other paper 1 dated earlier |
1903.07071 (2019-03) Bag of Tricks and A Strong Baseline for Deep Person Re-identification |
|
| val_collate_fn | 1 other paper 1 dated earlier |
1903.07071 (2019-03) Bag of Tricks and A Strong Baseline for Deep Person Re-identification |
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 2026-11-21.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Bottom-up human pose estimation methods have difficulties in predicting the correct pose for small persons due to challenges in scale variation. In this paper, we present HigherHRNet: a novel bottom-up human pose estimation method for learning scale-aware representations using high-resolution feature pyramids. Equipped with multi-resolution supervision for training and multi-resolution aggregation for inference, the proposed approach is able to solve the scale variation challenge in bottom-up multi-person pose estimation and localize keypoints more precisely, especially for small person. The feature pyramid in HigherHRNet consists of feature map outputs from HRNet and upsampled higher-resolution outputs through a transposed convolution. HigherHRNet outperforms the previous best bottom-up method by 2.5% AP for medium person on COCO test-dev, showing its effectiveness in handling scale variation. Furthermore, HigherHRNet achieves new state-of-the-art result on COCO test-dev (70.5% AP) without using refinement or other post-processing techniques, surpassing all existing bottom-up methods. HigherHRNet even surpasses all top-down methods on CrowdPose test (67.6% AP), suggesting its robustness in crowded scene. The code and models are available at https://github.com/HRNet/Higher-HRNet-Human-Pose-Estimation.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("1908.10357")
get_code_for_paper("1908.10357")
have("1908.10357")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/1908.10357.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/1908.10357)
Connect an agent — have() is free.