Bin Wang, Chunxiao Liu, Peng Zhang, Zhendong Mao, Yongdong Zhang, Xi Zhu
7 of 8 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (3 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 5 have no contract verdict; 2 failures of our instrument; 1 no recorded run), measured 2026-11-21; 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/2012.11528.json · badge: /api/ran/2012.11528.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 |
|---|---|---|
| CrossmodalGroup/SSL-VQA | marked official in Papers with Code Papers with Code archive |
7 ran · 1 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| Att_3 | Ran ran on a synthesized input · constructed an object; no result was computed |
CrossmodalGroup/SSL-VQA/base_model.py pointer only (licence: NONE) · get_code("2b0829c0325ec336") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, CrossmodalGroup/SSL-VQA 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. |
| FCNet | Ran ran on a synthesized input |
CrossmodalGroup/SSL-VQA/base_model.py pointer only (licence: NONE) · get_code("c0aedef157f0caf4") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, CrossmodalGroup/SSL-VQA 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. |
| QuestionEmbedding | Ran ran on a synthesized input · constructed an object; no result was computed |
CrossmodalGroup/SSL-VQA/base_model.py pointer only (licence: NONE) · get_code("b97bebdb4ff97926") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, CrossmodalGroup/SSL-VQA 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. |
| SimpleClassifier | Ran ran on a synthesized input |
CrossmodalGroup/SSL-VQA/base_model.py pointer only (licence: NONE) · get_code("78c2b60a61a6f6f3") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, CrossmodalGroup/SSL-VQA 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. |
| WordEmbedding | Ran ran on a synthesized input · constructed an object; no result was computed |
CrossmodalGroup/SSL-VQA/base_model.py pointer only (licence: NONE) · get_code("d5f763946d9d924d") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, CrossmodalGroup/SSL-VQA 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. |
| get_act | Ran ran; our contract draft was wrong, not the code |
CrossmodalGroup/SSL-VQA/base_model.py pointer only (licence: NONE) · get_code("c213b477dc6eef52") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, CrossmodalGroup/SSL-VQA 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. |
| get_norm | Ran ran; our contract draft was wrong, not the code |
CrossmodalGroup/SSL-VQA/base_model.py pointer only (licence: NONE) · get_code("26077f523336af12") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, CrossmodalGroup/SSL-VQA 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. |
| Model | Not yet run unverified (harvested, no recorded run) |
CrossmodalGroup/SSL-VQA/base_model.py pointer only (licence: NONE) · get_code("3c1f5fcc89b26ec8") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, CrossmodalGroup/SSL-VQA 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 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 8 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.
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 2026-11-21.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Most Visual Question Answering (VQA) models suffer from the language prior problem, which is caused by inherent data biases. Specifically, VQA models tend to answer questions (e.g., what color is the banana?) based on the high-frequency answers (e.g., yellow) ignoring image contents. Existing approaches tackle this problem by creating delicate models or introducing additional visual annotations to reduce question dependency and strengthen image dependency. However, they are still subject to the language prior problem since the data biases have not been fundamentally addressed. In this paper, we introduce a self-supervised learning framework to solve this problem. Concretely, we first automatically generate labeled data to balance the biased data, and then propose a self-supervised auxiliary task to utilize the balanced data to assist the VQA model to overcome language priors. Our method can compensate for the data biases by generating balanced data without introducing external annotations. Experimental results show that our method achieves state-of-the-art performance, improving the overall accuracy from 49.50% to 57.59% on the most commonly used benchmark VQA-CP v2. In other words, we can increase the performance of annotation-based methods by 16% without using external annotations. Our code is available on GitHub 1 .
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2012.11528")
get_code_for_paper("2012.11528")
have("2012.11528")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2012.11528.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2012.11528)
Connect an agent — have() is free.