Prune Truong, Van Gool, Yu Luc, Martin Fisher
13 of 15 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 6 have no contract verdict; 6 failures of our instrument; 2 no recorded run), measured 2026-11-22; 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/2203.04279.json · badge: /api/ran/2203.04279.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 |
|---|---|---|
| PruneTruong/DenseMatching | marked official in Papers with Code Papers with Code archive |
13 ran · 2 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| BinaryCrossEntropy | Ran ran on a synthesized input · constructed an object; no result was computed |
PruneTruong/DenseMatching/training/losses/probabilistic_warp_consistency_losses.py pointer only (licence: LGPL-2.1) · get_code("02a0560c27387518") How it ranThe body of this sample is withheld: LGPL-2.1, as GitHub detects it on this paper's repository, PruneTruong/DenseMatching, 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. |
| Correlation | Ran ran on a synthesized input |
PruneTruong/DenseMatching/training/losses/probabilistic_warp_consistency_losses.py pointer only (licence: LGPL-2.1) · get_code("2beec2454ea2317c") How it ranThe body of this sample is withheld: LGPL-2.1, as GitHub detects it on this paper's repository, PruneTruong/DenseMatching, 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. |
| Norm | Ran ran on a synthesized input |
PruneTruong/DenseMatching/training/losses/probabilistic_warp_consistency_losses.py pointer only (licence: LGPL-2.1) · get_code("5a05b45173a6074c") How it ranThe body of this sample is withheld: LGPL-2.1, as GitHub detects it on this paper's repository, PruneTruong/DenseMatching, 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. |
| OneHotBinaryCrossEntropy | Ran ran on a synthesized input |
PruneTruong/DenseMatching/training/losses/probabilistic_warp_consistency_losses.py pointer only (licence: LGPL-2.1) · get_code("6e57a2cc4025f5f1") How it ranThe body of this sample is withheld: LGPL-2.1, as GitHub detects it on this paper's repository, PruneTruong/DenseMatching, 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. |
| OneHotCrossEntropy | Ran ran on a synthesized input |
PruneTruong/DenseMatching/training/losses/probabilistic_warp_consistency_losses.py pointer only (licence: LGPL-2.1) · get_code("270e207c18ad6449") How it ranThe body of this sample is withheld: LGPL-2.1, as GitHub detects it on this paper's repository, PruneTruong/DenseMatching, 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. |
| SmoothCrossEntropy | Ran ran on a synthesized input |
PruneTruong/DenseMatching/training/losses/probabilistic_warp_consistency_losses.py pointer only (licence: LGPL-2.1) · get_code("8324e64c71eefb52") How it ranThe body of this sample is withheld: LGPL-2.1, as GitHub detects it on this paper's repository, PruneTruong/DenseMatching, 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. |
| compute_global_correlation | Ran ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT) |
PruneTruong/DenseMatching/training/losses/probabilistic_warp_consistency_losses.py pointer only (licence: LGPL-2.1) · get_code("beec515814429501") How it ranThe body of this sample is withheld: LGPL-2.1, as GitHub detects it on this paper's repository, PruneTruong/DenseMatching, 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. |
| convert_flow_to_mapping | Ran ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT) |
PruneTruong/DenseMatching/training/losses/probabilistic_warp_consistency_losses.py pointer only (licence: LGPL-2.1) · get_code("a733bcc981152875") How it ranThe body of this sample is withheld: LGPL-2.1, as GitHub detects it on this paper's repository, PruneTruong/DenseMatching, 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. |
| cost_volume_to_probabilistic_mapping | Ran ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT) |
PruneTruong/DenseMatching/training/losses/probabilistic_warp_consistency_losses.py pointer only (licence: LGPL-2.1) · get_code("ff06c3e066c36e85") How it ranThe body of this sample is withheld: LGPL-2.1, as GitHub detects it on this paper's repository, PruneTruong/DenseMatching, 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. |
| featureL2Norm | Ran ran; our contract draft was wrong, not the code |
PruneTruong/DenseMatching/training/losses/probabilistic_warp_consistency_losses.py pointer only (licence: LGPL-2.1) · get_code("8aa4dc35337276eb") How it ranThe body of this sample is withheld: LGPL-2.1, as GitHub detects it on this paper's repository, PruneTruong/DenseMatching, 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. |
| gaussian2d | Ran ran, honoured the contract we drafted |
PruneTruong/DenseMatching/training/losses/probabilistic_warp_consistency_losses.py pointer only (licence: LGPL-2.1) · get_code("cce902f0bf3d2e38") How it ranThe body of this sample is withheld: LGPL-2.1, as GitHub detects it on this paper's repository, PruneTruong/DenseMatching, 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. |
| getBlurredGT_multiple_kp | Ran ran; our contract draft was wrong, not the code |
PruneTruong/DenseMatching/training/losses/probabilistic_warp_consistency_losses.py pointer only (licence: LGPL-2.1) · get_code("10c460b3e318cb5c") How it ranThe body of this sample is withheld: LGPL-2.1, as GitHub detects it on this paper's repository, PruneTruong/DenseMatching, 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. |
| get_gt_correspondence_mask | Ran ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT) |
PruneTruong/DenseMatching/training/losses/probabilistic_warp_consistency_losses.py pointer only (licence: LGPL-2.1) · get_code("62ec77ea92e938ca") How it ranThe body of this sample is withheld: LGPL-2.1, as GitHub detects it on this paper's repository, PruneTruong/DenseMatching, 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. |
| ProbabilisticWarpConsistencyForGlobalCorr | Not yet run unverified (harvested, no recorded run) |
PruneTruong/DenseMatching/training/losses/probabilistic_warp_consistency_losses.py pointer only (licence: LGPL-2.1) · get_code("75412cba570e9371") How it ranThe body of this sample is withheld: LGPL-2.1, as GitHub detects it on this paper's repository, PruneTruong/DenseMatching, 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. No invocation recorded. |
| apply_gaussian_kernel | Not yet run unverified (harvested, no recorded run) |
PruneTruong/DenseMatching/training/losses/probabilistic_warp_consistency_losses.py pointer only (licence: LGPL-2.1) · get_code("8f15d60047a7169a") How it ranThe body of this sample is withheld: LGPL-2.1, as GitHub detects it on this paper's repository, PruneTruong/DenseMatching, 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. No invocation recorded. |
Of 15 samples lifted from this paper's linked repositories, 15 carry a function identity and 0 do not. Of the 15 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 0 later) and 13 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 |
|---|---|---|---|
| convert_flow_to_mapping brick of this paper's assembly: helper |
1 other paper 1 dated earlier · 1 only as an assembly brick |
2104.03308 (2021-04) Warp Consistency for Unsupervised Learning of Dense Correspondences |
|
| get_gt_correspondence_mask brick of this paper's assembly: helper |
1 other paper 1 dated earlier · 1 only as an assembly brick |
2104.03308 (2021-04) Warp Consistency for Unsupervised Learning of Dense Correspondences |
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.
We propose Probabilistic Warp Consistency, a weaklysupervised learning objective for semantic matching. Our approach directly supervises the dense matching scores predicted by the network, encoded as a conditional probability distribution. We first construct an image triplet by applying a known warp to one of the images in a pair depicting different instances of the same object class. Our probabilistic learning objectives are then derived using the constraints arising from the resulting image triplet. We further account for occlusion and background clutter present in real image pairs by extending our probabilistic output space with a learnable unmatched state. To supervise it, we design an objective between image pairs depicting different object classes. We validate our method by applying it to four recent semantic matching architectures. Our weakly-supervised approach sets a new state-of-the-art on four challenging semantic matching benchmarks. Lastly, we demonstrate that our objective also brings substantial improvements in the strongly-supervised regime, when combined with keypoint annotations. Unmatched state prediction Known warping distribution Estimated probabilistic mapping Known probabilistic mapping Direct Composition w. marginalization Known non-matching distribution Matching images (same object class) Non-matching images (different object classes)
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2203.04279")
get_code_for_paper("2203.04279")
have("2203.04279")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2203.04279.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2203.04279)
Connect an agent — have() is free.