9 of 11 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 7 have no contract verdict; 2 failures of our instrument; 2 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/2106.14917.json · badge: /api/ran/2106.14917.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 |
|---|---|---|
| PotatoTian/recall-semseg | canonical (classifier label) classifier basis: census |
9 ran · 2 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| RecallCrossEntropy | Ran ran on a synthesized input |
PotatoTian/recall-semseg/ptsemseg/loss/loss.py code served (permissive licence) · get_code("7026f6e0f1e1099b") 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. 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.
|
| RecallPreCrossEntropy | Ran ran on a synthesized input |
PotatoTian/recall-semseg/ptsemseg/loss/loss.py code served (permissive licence) · get_code("4cfe5787eb0e75e1") 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. 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.
|
| alpha_blend | Ran ran on a synthesized input |
PotatoTian/recall-semseg/ptsemseg/utils.py code served (permissive licence) · get_code("3a8e7e1d2e1dc425") 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 3, dtype family float, shape (4, 5, 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.
|
| convert_state_dict | Ran ran on a synthesized input |
PotatoTian/recall-semseg/ptsemseg/utils.py code served (permissive licence) · get_code("ec475f26f39c14b0") 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 OrderedDict. 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.
|
| cross_entropy2d | Ran ran on a synthesized input |
PotatoTian/recall-semseg/ptsemseg/loss/loss.py code served (permissive licence) · get_code("c76dc561618f7c2e") 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 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_interp_size | Ran ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT) |
PotatoTian/recall-semseg/ptsemseg/models/utils.py pointer only (licence: MIT); the stored copy get_code serves, from wty-ustc/hairclip, is pointer only (licence: LGPL-2.1) · get_code("80a82d5149279cdf") 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 wty-ustc/hairclip, and LGPL-2.1, as GitHub detects it on that repository, is not in the permissive set Syntology serves inline. 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. |
| interp | Ran ran on a synthesized input |
PotatoTian/recall-semseg/ptsemseg/models/utils.py code served (permissive licence) · get_code("aed5a907c8821d6d") 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, 4, 6, 8) as a later run recorded it. 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, 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.
|
| lovasz_grad | Ran ran on a synthesized input |
PotatoTian/recall-semseg/ptsemseg/loss/lovasz_loss.py code served (permissive licence) · get_code("4f9d5382c285dae8") 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 (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.
|
| recursive_glob | Ran ran; our contract draft was wrong, not the code |
PotatoTian/recall-semseg/ptsemseg/utils.py pointer only (licence: MIT); the stored copy get_code serves, from axi404/pmt, is pointer only (licence: NONE) · get_code("f1e67bfcea91df50") 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 axi404/pmt, 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_upsampling_weight | Not yet run unverified (harvested, no recorded run) |
PotatoTian/recall-semseg/ptsemseg/models/utils.py pointer only (licence: MIT); the stored copy get_code serves, from jiwei0921/CoNet, is pointer only (licence: NONE) · get_code("68f02849ad3eb678") 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 jiwei0921/CoNet, 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. |
| lovasz_softmax_flat | Not yet run unverified (harvested, no recorded run) |
PotatoTian/recall-semseg/ptsemseg/loss/lovasz_loss.py code served (permissive licence) · get_code("41a1c4fba0ea8662") How it ranno invocation recorded. |
Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 5 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 0 the same month, 3 later) and 6 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 |
|---|---|---|---|
| recursive_glob | 10 other papers 6 dated earlier, 4 later |
1907.07034 (2019-07) Uncertainty-aware Self-ensembling Model for Semi-supervised 3D Left Atrium Segmentation |
1912.13192 (2019-12) PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection 2003.09005 (2020-03) Semi-Supervised Semantic Segmentation with Cross-Consistency Training and 7 more not named here |
| get_upsampling_weight | 9 other papers 4 dated earlier, 4 later, 1 same year, order not determinable |
1807.09856 (2018-07) Where are the Blobs: Counting by Localization with Point Supervision |
1809.00338 (2018-09) Look Across Elapse: Disentangled Representation Learning and Photorealistic Cross-Age Face Synthesis for Age-Invariant Face Recognition 2006.00176 (2020-06) When2com: Multi-Agent Perception via Communication Graph Grouping and 6 more not named here |
| get_interp_size | 3 other papers 1 dated earlier, 2 later |
2006.00176 (2020-06) When2com: Multi-Agent Perception via Communication Graph Grouping |
2112.05142 (2021-12) HairCLIP: Design Your Hair by Text and Reference Image 2112.09130 (2021-12) Ensembling Off-the-shelf Models for GAN Training |
| alpha_blend | 2 other papers 2 dated earlier |
2004.01800 (2020-04) Temporally Distributed Networks for Fast Video Semantic Segmentation |
2006.00176 (2020-06) When2com: Multi-Agent Perception via Communication Graph Grouping |
| interp | 1 other paper 1 dated earlier |
2006.00176 (2020-06) When2com: Multi-Agent Perception via Communication Graph Grouping |
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.
Class imbalance is a fundamental problem in computer vision applications such as semantic segmentation. Specifically, uneven class distributions in a training dataset often result in unsatisfactory performance on under-represented classes. Many works have proposed to weight the standard cross entropy loss function with pre-computed weights based on class statistics, such as the number of samples and class margins. There are two major drawbacks to these methods: 1) constantly up-weighting minority classes can introduce excessive false positives in semantic segmentation; 2) a minority class is not necessarily a hard class. The consequence is low precision due to excessive false positives. In this regard, we propose a hard-class mining loss by reshaping the vanilla cross entropy loss such that it weights the loss for each class dynamically based on instantaneous recall performance. We show that the novel recall loss changes gradually between the standard cross entropy loss and the inverse frequency weighted loss. Recall loss also leads to improved mean accuracy while offering competitive mean Intersection over Union (IoU) performance. On Synthia dataset, recall loss achieves $9\%$ relative improvement on mean accuracy with competitive mean IoU using DeepLab-ResNet18 compared to the cross entropy loss. Code available at https://github.com/PotatoTian/recall-semseg.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2106.14917")
get_code_for_paper("2106.14917")
have("2106.14917")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2106.14917.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2106.14917)
Connect an agent — have() is free.