Papers › ShortcutProbe: Probing Prediction Shortcuts for Learning Robust Models
ShortcutProbe: Probing Prediction Shortcuts for Learning Robust Models
Guangtao Zheng, Wenqian Ye, Aidong Zhang
Deep learning models often achieve high performance by inadvertently learning spurious correlations between targets and non-essential features. For example, an image classifier may identify an object via its background that spuriously correlates with it. This prediction behavior, known as spurious bias, severely degrades model performance on data that lacks the learned spurious correlations. Existing methods on spurious bias mitigation typically require a variety of data groups with spurious correlation annotations called group labels. However, group labels require costly human annotations and often fail to capture subtle spurious biases such as relying on specific pixels for predictions. In this paper, we propose a novel post hoc spurious bias mitigation framework without requiring group labels. Our framework, termed ShortcutProbe, identifies prediction shortcuts that reflect potential non-robustness in predictions in a given model's latent space. The model is then retrained to be invariant to the identified prediction shortcuts for improved robustness. We theoretically analyze the effectiveness of the framework and empirically demonstrate that it is an efficient and practical tool for improving a model's robustness to spurious bias on diverse datasets.
In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.
Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
For agents, on Syntology's MCP service (how to connect):
get_harvested_code_for_paper(arxiv_id="2505.13910")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="2505.13910", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2505.13910")
Code
Syntology 27 code samples harvested from 1 repository linked to this paper: 21 ran (of which 12 constructed an object rather than computing a result; 15 with no instrument failure: 1 honoured, 0 violated, 14 with no contract checked; 6 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 6 where our contract draft was wrong; failures of Syntology's instrument, not of the code.
By repository: official repository: 27 samples from 1 repository, 21 ran (15 with no instrument failure; 6 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.
Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
27 samples harvested: 21 ran (of which 12 constructed an object rather than computing a result; 15 with no instrument failure: 1 honoured, 0 violated, 14 with no contract checked; 6 where Syntology's instrument failed) · 6 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.
Licence: 27 of the 27 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.
Harvested from gtzheng/shortcutprobe. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 1 sample that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.
Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.
Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.
A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.
6e663667ba7ed3f2 · report
fixture: returned ClassBalancedSampler · level recorded 2026-09-22 a87713c5b6ae5b15 · report
fixture: returned EmbedDataset · level recorded 2026-09-22 c468389298284a04 · report
fixture: returned GroupBalancedSampler · level recorded 2026-09-22 4711b44eb7381e64 · report
fixture: signature idx:int/0/int · returned tuple · level recorded 2026-09-22 fa1c55aa70701d1e · report
fixture: returned JointDataset · level recorded 2026-09-22 a5207b840e3096a2 · report
fixture: returned JointRandomSampler · level recorded 2026-09-22 52fb87f5341104be · report
fixture: returned MisDataset · level recorded 2026-09-22 2ee64f5afd17a5a3 · report
fixture: returned PredDataset · level recorded 2026-09-22 36087249bd727695 · report
fixture: returned RandomSampler · level recorded 2026-09-22 4a0b5cf2bf60d9e7 · report
fixture: returned RunningVariance · level recorded 2026-09-22 f6cdc99333d7ac0c · report
fixture: returned ShortcutSampler · level recorded 2026-09-22 b3e59759edda6308 · report
fixture: returned SpuriousVectors · level recorded 2026-09-22 3be6f85f9a2c50c3 · report
fixture: returned SubsetDataset · level recorded 2026-09-22 abb051ad54c04456 · report
fixture: signature model:callable/0/?, lr:float/0/float, weight_decay:float/0/float · returned AdamW · level recorded 2026-09-22 227d71f4a9526c48 · report
fixture: signature embedding_dir:str/0/str, split:str/0/str, keep_ndims:int/0/int · returned ndarray · level recorded 2026-09-22 ffd024417d2e0ee9 · report
fixture: signature model:callable/0/?, loader:SimpleLoader/0/?, embedding_dir:str/0/str, split:str/0/str, threshold:int/0/int, keep_ndims:int/0/int, device:str/0/str · returned tuple · level recorded 2026-09-22 24df1f39ca418afa · report
fixture: signature dataset:SimpleDataset/0/?, ratio:float/0/float · returned tuple · level recorded 2026-09-22 ad87b4581c72eb68 · report
fixture: signature model:callable/0/?, opt_name:str/0/str, kwargs:dict/0/? · returned AdamW · level recorded 2026-09-22 97a6fbbb8298e7a0 · report
fixture: signature optimizer:SGD/0/?, scheduler_name:str/0/str, kwargs:dict/0/? · returned CosineAnnealingLR · level recorded 2026-09-22 2a04614f7104524c · report
fixture: signature path:str/0/str, split:str/0/str, keep_ndims:int/0/int · returned tuple · level recorded 2026-09-22 6f906e5668960d23 · report
fixture: signature name:str/0/str · returned function · level recorded 2026-09-22 9c581ceeab1e7194 · report
aa528f9aa86d7413 · report
6a3dd1d39f936e97 · report
3db8286f1e2584d6 · report
0d22a2219be7c189 · report
d99a2ddd28ee9061 · report
Method as code Syntology
What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.
1 assembly on this paper: 1 harvested, 0 generated.
harvested Assembly for ShortcutProbe (graph method: ShortcutProbe). 27 bricks; individually on a fixture: 21 ran (of which 12 constructed an object rather than computing a result; 15 with no instrument failure: 1 honoured, 0 violated, 14 with no contract checked; 6 where Syntology's instrument failed) · 6 unverified. The assembly has not been run end-to-end.
- shortcutprobe entry · level 0 · unverified ·
d99a2ddd28ee9061 - Algorithm helper · level 0 · unverified ·
9c581ceeab1e7194 - Classifier helper · level 0 · unverified ·
aa528f9aa86d7413 - RunningVariance helper · level 1 · ran ·
4a0b5cf2bf60d9e7 - SpuriousVectors model · level 1 · ran ·
b3e59759edda6308 - init_optimizer helper · level 1 · ran · our draft was wrong ·
ad87b4581c72eb68 - init_scheduler helper · level 1 · ran · our draft was wrong ·
97a6fbbb8298e7a0 - register_algorithm helper · level 1 · ran · our draft was wrong ·
6f906e5668960d23 - ClassBalancedSampler helper · level 1 · ran ·
6e663667ba7ed3f2 - EmbedDataset helper · level 1 · ran ·
a87713c5b6ae5b15 - GroupBalancedSampler helper · level 1 · ran ·
c468389298284a04 - IdxDataset helper · level 1 · ran ·
4711b44eb7381e64 - JointDataset helper · level 1 · ran ·
fa1c55aa70701d1e - JointRandomSampler helper · level 1 · ran ·
a5207b840e3096a2 - MisDataset helper · level 1 · ran ·
52fb87f5341104be - PredDataset helper · level 1 · ran ·
2ee64f5afd17a5a3 - RandomSampler helper · level 1 · ran ·
36087249bd727695 - ShortcutSampler helper · level 1 · ran ·
f6cdc99333d7ac0c - SubsetDataset helper · level 1 · ran ·
3be6f85f9a2c50c3 - extract_feature_info helper · level 1 · ran · our draft was wrong ·
ffd024417d2e0ee9 - prepare_data helper · level 0 · unverified ·
0d22a2219be7c189 - get_backbone helper · level 0 · unverified ·
3db8286f1e2584d6 - bert_adamw_optimizer helper · level 1 · ran · our draft was wrong ·
abb051ad54c04456 - Scaler helper · level 0 · unverified ·
6a3dd1d39f936e97 - disentangle_pca helper · level 1 · ran · honoured contract ·
227d71f4a9526c48 - load_embeddings helper · level 1 · ran · our draft was wrong ·
2a04614f7104524c - get_split_indexes helper · level 1 · ran ·
24df1f39ca418afa
Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2505.13910") returns these assemblies with each brick's role and wiring (how to connect).
Tasks
Results from the paper archive 2025-07-28
No leaderboard rows for this paper in the archive.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections