Jingrui He, Wenxuan Bao, Yanjun Zhao, Xiyuan Yang
4 of 6 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 3 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/2604.21728.json · badge: /api/ran/2604.21728.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 |
|---|---|---|
| baowenxuan/Ramen | canonical (classifier label) classifier basis: census |
4 ran · 2 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| get_optimizer_class | Ran ran; our contract draft was wrong, not the code |
baowenxuan/Ramen/src/models/optimizer.py pointer only (licence: NONE) · get_code("c3c0cd93c993b4f0") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, baowenxuan/Ramen 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. |
| make_custom_dataset | Ran ran; our contract draft was wrong, not the code |
baowenxuan/Ramen/src/datasets/utils.py pointer only (licence: NONE) · get_code("c62c4350be9aa59f") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, baowenxuan/Ramen 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. |
| pil_loader | Ran ran, honoured the contract we drafted |
baowenxuan/Ramen/src/datasets/utils.py pointer only (licence: NONE) · get_code("f321f54723433661") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, baowenxuan/Ramen 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. |
| softmax_entropy | Ran ran; our contract draft was wrong, not the code |
baowenxuan/Ramen/src/methods/losses.py pointer only (licence: NONE) · get_code("4a0cb945bd6d86fa") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, baowenxuan/Ramen 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. |
| accimage_loader | Not yet run unverified (harvested, no recorded run) |
baowenxuan/Ramen/src/datasets/utils.py pointer only (licence: NONE); the stored copy get_code serves, from RobustBench/robustbench, is pointer only (licence: NOASSERTION) · get_code("404fb2b2daa1ae78") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, baowenxuan/Ramen 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. |
| get_domainbed_dataset_class | Not yet run unverified (harvested, no recorded run) |
baowenxuan/Ramen/src/datasets/domainbed.py pointer only (licence: NONE) · get_code("0c30987079844922") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, baowenxuan/Ramen 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 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 2 the same month, 2 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 |
|---|---|---|---|
| pil_loader | 66 other papers 64 dated earlier, 1 the same month, 1 later |
1502.03044 (2015-02) Show, Attend and Tell: Neural Image Caption Generation with Visual Attention |
1710.10196 (2017-10) Progressive Growing of GANs for Improved Quality, Stability, and Variation 1711.02512 (2017-11) Fine-tuning CNN Image Retrieval with No Human Annotation and 63 more not named here |
| accimage_loader | 39 other papers 37 dated earlier, 1 the same month, 1 later |
1702.00758 (2017-02) HashNet: Deep Learning to Hash by Continuation |
1711.02512 (2017-11) Fine-tuning CNN Image Retrieval with No Human Annotation 1805.00907 (2018-05) Glow: Graph Lowering Compiler Techniques for Neural Networks and 36 more not named here |
| make_custom_dataset | 1 other paper 1 dated earlier |
2510.22127 (2025-10) Mint: A Simple Test-Time Adaptation of Vision-Language Models against Common Corruptions |
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.
Pretrained vision-language models such as CLIP exhibit strong zero-shot generalization but remain sensitive to distribution shifts. Test-time adaptation adapts models during inference without access to source data or target labels, offering a practical way to handle such shifts. However, existing methods typically assume that test samples come from a single, consistent domain, while in practice, test data often include samples from mixed domains with distinct characteristics. Consequently, their performance degrades under mixed-domain settings. To address this, we present Ramen, a framework for robust test-time adaptation through active sample selection. For each incoming test sample, Ramen retrieves a customized batch of relevant samples from previously seen data based on two criteria: domain consistency, which ensures that adaptation focuses on data from similar domains, and prediction balance, which mitigates adaptation bias caused by skewed predictions. To improve efficiency, Ramen employs an embedding-gradient cache that stores the embeddings and sample-level gradients of past test images. The stored embeddings are used to retrieve relevant samples, and the corresponding gradients are aggregated for model updates, eliminating the need for any additional forward or backward passes. Our theoretical analysis provides insight into why the proposed adaptation mechanism is effective under mixed-domain shifts. Experiments on multiple image corruption and domain-shift benchmarks demonstrate that Ramen achieves strong and consistent performance, offering robust and efficient adaptation in complex mixed-domain scenarios. Our code is available at https://github.com/baowenxuan/Ramen.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2604.21728")
get_code_for_paper("2604.21728")
have("2604.21728")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2604.21728.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2604.21728)
Connect an agent — have() is free.