Hye Chung, Hongsin Lee, Chen Rebuffi, Bartoldson Gowal
8 of 10 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 0 have no contract verdict; 8 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/2605.21999.json · badge: /api/ran/2605.21999.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 |
|---|---|---|
| HongsinLee/why-robust-teachers-fail | canonical (classifier label) classifier basis: census |
8 ran · 2 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| PGD | Ran ran; our contract draft was wrong, not the code |
HongsinLee/why-robust-teachers-fail/real_exp/attacks.py pointer only (licence: NONE) · get_code("a648902a7268d3fd") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, HongsinLee/why-robust-teachers-fail 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. |
| TRADES | Ran ran; our contract draft was wrong, not the code |
HongsinLee/why-robust-teachers-fail/real_exp/attacks.py pointer only (licence: NONE) · get_code("1de719bcbbc0bd3c") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, HongsinLee/why-robust-teachers-fail 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. |
| pResNet18 | Ran ran; our contract draft was wrong, not the code |
HongsinLee/why-robust-teachers-fail/real_exp/cifar100_models/preresnet.py pointer only (licence: NONE) · get_code("f5088fe40e624080") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, HongsinLee/why-robust-teachers-fail 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. |
| pResNet34 | Ran ran; our contract draft was wrong, not the code |
HongsinLee/why-robust-teachers-fail/real_exp/cifar100_models/preresnet.py pointer only (licence: NONE) · get_code("fd5e91ae30144db3") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, HongsinLee/why-robust-teachers-fail 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. |
| pResNet50 | Ran ran; our contract draft was wrong, not the code |
HongsinLee/why-robust-teachers-fail/real_exp/cifar100_models/preresnet.py pointer only (licence: NONE) · get_code("c26044835e29342e") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, HongsinLee/why-robust-teachers-fail 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. |
| resnet18 | Ran ran; our contract draft was wrong, not the code |
HongsinLee/why-robust-teachers-fail/real_exp/cifar100_models/resnet.py pointer only (licence: NONE) · get_code("804dc4361a30432d") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, HongsinLee/why-robust-teachers-fail 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. |
| rslad_inner_loss | Ran ran; our contract draft was wrong, not the code |
HongsinLee/why-robust-teachers-fail/real_exp/attacks.py pointer only (licence: NONE) · get_code("47e8b2f8a9d376b2") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, HongsinLee/why-robust-teachers-fail 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. |
| wideresnet | Ran ran; our contract draft was wrong, not the code |
HongsinLee/why-robust-teachers-fail/real_exp/cifar10_models/wideresnet.py pointer only (licence: NONE) · get_code("95a525f1ac88c43c") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, HongsinLee/why-robust-teachers-fail 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. |
| svhn_wideresnetwithswish | Not yet run unverified (harvested, no recorded run) |
HongsinLee/why-robust-teachers-fail/real_exp/cifar100_models/wideresnetswish_svhn.py pointer only (licence: NONE) · get_code("6e78bd6eb54f58a0") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, HongsinLee/why-robust-teachers-fail 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. |
| ti_wideresnetwithswish | Not yet run unverified (harvested, no recorded run) |
HongsinLee/why-robust-teachers-fail/real_exp/cifar100_models/wideresnetswish.py pointer only (licence: NONE) · get_code("414b9f77b95e1b72") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, HongsinLee/why-robust-teachers-fail 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 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 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 4 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 |
|---|---|---|---|
| resnet18 | 2 other papers 2 dated earlier |
2405.01460 (2024-05) Purify Unlearnable Examples via Rate-Constrained Variational Autoencoders |
2512.10275 (2025-12) Sample-wise Adaptive Weighting for Transfer Consistency in Adversarial Distillation |
| pResNet18 | 1 other paper 1 dated earlier |
2512.10275 (2025-12) Sample-wise Adaptive Weighting for Transfer Consistency in Adversarial Distillation |
|
| pResNet34 | 1 other paper 1 dated earlier |
2512.10275 (2025-12) Sample-wise Adaptive Weighting for Transfer Consistency in Adversarial Distillation |
|
| pResNet50 | 1 other paper 1 dated earlier |
2512.10275 (2025-12) Sample-wise Adaptive Weighting for Transfer Consistency in Adversarial Distillation |
|
| svhn_wideresnetwithswish | 1 other paper 1 dated earlier |
2512.10275 (2025-12) Sample-wise Adaptive Weighting for Transfer Consistency in Adversarial Distillation |
|
| ti_wideresnetwithswish | 1 other paper 1 dated earlier |
2512.10275 (2025-12) Sample-wise Adaptive Weighting for Transfer Consistency in Adversarial Distillation |
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.
Adversarial Distillation aims to enhance student robustness by guiding the student with a robust teacher's soft labels within the min-max adversarial training framework, yet its success is notoriously inconsistent: a more robust teacher often fails to improve, or even harms, the student's robust generalization. In this paper, we identify a key mechanism of this teacher dependency: the misalignment between the teacher's supervisory confidence and the student's representational limitations on a consistent subset of training data-the Robustly Unlearnable Set. We present a theoretical framework analyzing the feature learning dynamics of a two-layer neural network, demonstrating that this mismatch creates a dichotomy in distillation outcomes. We prove that when a teacher provides confident supervision on unlearnable samples, it compels the student to memorize spurious noise patterns that eventually overpower the learned robust signal, thereby driving robust overfitting. Conversely, a teacher that exhibits high uncertainty on these samples effectively suppresses noise memorization, allowing the student to rely solely on the learnable signal for robust generalization. We empirically validate our theory across both synthetic simulations and real-image classification datasets, confirming that robust overfitting is driven by the teacher's interaction with unlearnable samples. Finally, we demonstrate that a teacher's predictive entropy on unlearnable samples serves as a strong indicator of student robustness, validating our theoretical framework and offering a principled guideline for robust teacher selection.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2605.21999")
get_code_for_paper("2605.21999")
have("2605.21999")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2605.21999.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2605.21999)
Connect an agent — have() is free.