Kijung Shin, Sunwoo Kim, Hyunjin Hwang
4 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, 1 violated it and 0 have no contract verdict; 3 failures of our instrument; 3 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/2510.18360.json · badge: /api/ran/2510.18360.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 |
|---|---|---|
| y0ngjaenius/CVPR2024_FLOWERFormer | canonical (classifier label) classifier basis: census |
3 ran · 3 no recorded run |
| kswoo97/FGPAnom | community Papers with Code archive |
1 ran · 0 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| FGP | Ran ran; our contract draft was wrong, not the code |
kswoo97/FGPAnom/src.py pointer only (licence: NONE) · get_code("8c985e59de33f035") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, kswoo97/FGPAnom 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. |
| collate_edge_masks | Ran ran, violated the contract we drafted |
y0ngjaenius/CVPR2024_FLOWERFormer/utils.py pointer only (licence: NONE) · get_code("070985961091da7c") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, y0ngjaenius/CVPR2024_FLOWERFormer 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. |
| collate_fn | Ran ran; our contract draft was wrong, not the code |
y0ngjaenius/CVPR2024_FLOWERFormer/utils.py pointer only (licence: NONE) · get_code("1466d657fc2b6567") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, y0ngjaenius/CVPR2024_FLOWERFormer 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. |
| evaluation | Ran ran; our contract draft was wrong, not the code |
y0ngjaenius/CVPR2024_FLOWERFormer/utils.py pointer only (licence: NONE) · get_code("fa3c832aaf87cffc") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, y0ngjaenius/CVPR2024_FLOWERFormer 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. |
| GNNPreMP | Not yet run unverified (harvested, no recorded run) |
y0ngjaenius/CVPR2024_FLOWERFormer/two_cell/flowerformer_2cell.py pointer only (licence: NONE) · get_code("df948b1cb9d89d1f") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, y0ngjaenius/CVPR2024_FLOWERFormer 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. |
| train_1cell | Not yet run unverified (harvested, no recorded run) |
y0ngjaenius/CVPR2024_FLOWERFormer/train_utils.py pointer only (licence: NONE) · get_code("1e1562902342884c") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, y0ngjaenius/CVPR2024_FLOWERFormer 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. |
| train_2cell | Not yet run unverified (harvested, no recorded run) |
y0ngjaenius/CVPR2024_FLOWERFormer/train_utils.py pointer only (licence: NONE) · get_code("cfbe6c5308631b07") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, y0ngjaenius/CVPR2024_FLOWERFormer 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 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, 6 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 0 the same month, 0 later) and 1 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 |
|---|---|---|---|
| GNNPreMP | 1 other paper 1 dated earlier |
2403.12821 (2024-03) FlowerFormer: Empowering Neural Architecture Encoding using a Flow-aware Graph Transformer |
|
| collate_edge_masks | 1 other paper 1 dated earlier |
2403.12821 (2024-03) FlowerFormer: Empowering Neural Architecture Encoding using a Flow-aware Graph Transformer |
|
| collate_fn | 1 other paper 1 dated earlier |
2403.12821 (2024-03) FlowerFormer: Empowering Neural Architecture Encoding using a Flow-aware Graph Transformer |
|
| evaluation | 1 other paper 1 dated earlier |
2403.12821 (2024-03) FlowerFormer: Empowering Neural Architecture Encoding using a Flow-aware Graph Transformer |
|
| train_1cell | 1 other paper 1 dated earlier |
2403.12821 (2024-03) FlowerFormer: Empowering Neural Architecture Encoding using a Flow-aware Graph Transformer |
|
| train_2cell | 1 other paper 1 dated earlier |
2403.12821 (2024-03) FlowerFormer: Empowering Neural Architecture Encoding using a Flow-aware Graph Transformer |
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.
The performance of a deep learning model on a specific task and dataset depends heavily on its neural architecture, motivating considerable efforts to rapidly and accurately identify architectures suited to the target task and dataset. To achieve this, researchers use machine learning models-typically neural architecture encoders-to predict the performance of a neural architecture. Many state-of-the-art encoders aim to capture information flow within a neural architecture, which reflects how information moves through the forward pass and backpropagation, via a specialized model structure. However, due to their complicated structures, these flow-based encoders are significantly slower to process neural architectures compared to simpler encoders, presenting a notable practical challenge. To address this, we propose FGP, a novel pre-training method for neural architecture encoding that trains an encoder to capture the information flow without requiring specialized model structures. FGP trains an encoder to reconstruct a flow surrogate, our proposed representation of the neural architecture's information flow. Our experiments show that FGP boosts encoder performance by up to 106% in Precision@1%, compared to the same encoder trained solely with supervised learning. Performance prediction task results (metric: Kendall's tau, higher the better) Neural architecture processing time (sec.) -14% x57 -5% x43 NAS-Bench-101 dataset NAS-Bench-201 dataset Flow-based encoder (FlowerFormer) Non-flow-based encoder (ResGatedGCN) (a) The total processing time of FlowerFormer [15] and ResGatedGCN [3] for the 14K and 15K architectures in Nas-Bench-10 and NAS-Bench-201, respectively. H O ? O O H out in 1x1 3x3 3x3 mp ? Generative pretext task on a molecule Generative pretext task on a neural architecture (b) Example generative pretext tasks: deep learning models are trained to predict the masked atoms or operations (colored in gray).
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2510.18360")
get_code_for_paper("2510.18360")
have("2510.18360")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2510.18360.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2510.18360)
Connect an agent — have() is free.