7 of 7 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 3 have no contract verdict; 4 failures of our instrument; 0 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/1807.08865.json · badge: /api/ran/1807.08865.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 |
|---|---|---|
| meteorshowers/StereoNet | community (classifier label) classifier basis not recorded on the link |
4 ran · 0 no recorded run |
| copy not recorded | community not in the paper's declared repositories |
3 ran · 0 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| compute_volume | Ran ran; our contract draft was wrong, not the code |
this paper's copy was not recorded; identical code first harvested from andrewlstewart/StereoNet_PyTorch pointer only · get_code("4caa20778e7219ba") How it ranThe body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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. |
| convbn | Ran ran on a synthesized input |
meteorshowers/StereoNet/disparity/models/stereonet_disp.py code served (permissive licence) · get_code("aa666386e35d54a5") 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 Sequential. 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.
|
| convbn_3d | Ran ran on a synthesized input |
meteorshowers/StereoNet/disparity/models/stereonet_disp.py code served (permissive licence) · get_code("873f10dc18effe9c") 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 Sequential. 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.
|
| interpolate | Ran ran; our contract draft was wrong, not the code |
meteorshowers/StereoNet/disparity/layers/misc.py pointer only (licence: MIT); the stored copy get_code serves, from KanghoonYoon/torch-rasgg, is pointer only (licence: NONE) · get_code("2902bf4410253ff7") 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 KanghoonYoon/torch-rasgg, 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. |
| project_rect_to_image | Ran ran on a synthesized input |
meteorshowers/StereoNet/disparity/models/stereonet.py code served (permissive licence) · get_code("7ee1a68e85237f6e") 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 (2, 2) 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.
|
| robust_loss | Ran ran; our contract draft was wrong, not the code |
this paper's copy was not recorded; identical code first harvested from andrewlstewart/StereoNet_PyTorch pointer only · get_code("67e14f39a4f3d8e5") How it ranThe body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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. |
| soft_argmin | Ran ran; our contract draft was wrong, not the code |
this paper's copy was not recorded; identical code first harvested from andrewlstewart/StereoNet_PyTorch pointer only · get_code("81c9eec5240c5414") How it ranThe body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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. |
Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 4 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 0 the same month, 1 later) and 3 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 |
|---|---|---|---|
| interpolate | 38 other papers 2 dated earlier, 36 later |
1703.06870 (2017-03) Mask R-CNN |
1803.03243 (2018-03) Domain Adaptive Faster R-CNN for Object Detection in the Wild 1903.00241 (2019-03) Mask Scoring R-CNN and 35 more not named here |
| compute_volume | 1 other paper 1 dated earlier |
1701.03077 (2017-01) A General and Adaptive Robust Loss Function |
|
| robust_loss | 1 other paper 1 dated earlier |
1701.03077 (2017-01) A General and Adaptive Robust Loss Function |
|
| soft_argmin | 1 other paper 1 dated earlier |
1701.03077 (2017-01) A General and Adaptive Robust Loss Function |
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.
This paper presents StereoNet, the first end-to-end deep architecture for real-time stereo matching that runs at 60 fps on an NVidia Titan X, producing high-quality, edge-preserved, quantization-free disparity maps. A key insight of this paper is that the network achieves a sub-pixel matching precision than is a magnitude higher than those of traditional stereo matching approaches. This allows us to achieve real-time performance by using a very low resolution cost volume that encodes all the information needed to achieve high disparity precision. Spatial precision is achieved by employing a learned edge-aware upsampling function. Our model uses a Siamese network to extract features from the left and right image. A first estimate of the disparity is computed in a very low resolution cost volume, then hierarchically the model re-introduces high-frequency details through a learned upsampling function that uses compact pixel-to-pixel refinement networks. Leveraging color input as a guide, this function is capable of producing high-quality edge-aware output. We achieve compelling results on multiple benchmarks, showing how the proposed method offers extreme flexibility at an acceptable computational budget.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("1807.08865")
get_code_for_paper("1807.08865")
have("1807.08865")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/1807.08865.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/1807.08865)
Connect an agent — have() is free.