Papers › Intersectional Unfairness Discovery
Intersectional Unfairness Discovery
Gezheng Xu, Qi Chen, Charles Ling, Boyu Wang, Changjian Shui
AI systems have been shown to produce unfair results for certain subgroups of population, highlighting the need to understand bias on certain sensitive attributes. Current research often falls short, primarily focusing on the subgroups characterized by a single sensitive attribute, while neglecting the nature of intersectional fairness of multiple sensitive attributes. This paper focuses on its one fundamental aspect by discovering diverse high-bias subgroups under intersectional sensitive attributes. Specifically, we propose a Bias-Guided Generative Network (BGGN). By treating each bias value as a reward, BGGN efficiently generates high-bias intersectional sensitive attributes. Experiments on real-world text and image datasets demonstrate a diverse and efficient discovery of BGGN. To further evaluate the generated unseen but possible unfair intersectional sensitive attributes, we formulate them as prompts and use modern generative AI to produce new texts and images. The results of frequently generating biased data provides new insights of discovering potential unfairness in popular modern generative AI systems. Warning: This paper contains generative examples that are offensive in nature.
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="2405.20790")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="2405.20790", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2405.20790")
Code
Syntology 36 code samples harvested from 1 repository linked to this paper: 24 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 6 honoured, 1 violated, 0 with no contract checked; 17 where Syntology's instrument failed) · 12 unverified. Where Syntology's instrument failed: 10 where our contract draft was wrong; 7 where the contract check could not run; failures of Syntology's instrument, not of the code.
By repository: official repository: 36 samples from 1 repository, 24 ran (7 with no instrument failure; 17 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
36 samples harvested: 24 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 6 honoured, 1 violated, 0 with no contract checked; 17 where Syntology's instrument failed) · 12 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: 36 of the 36 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 xugezheng/bggn. “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”. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.
57d865bf1a287ccb · report
fixture: signature evluation_dicts:dict/0/? · returned tuple · level recorded 2026-09-22 064fdf4c7a190f52 · report
fixture: signature gen_A_sorted_listTuple:tuple/1/NoneType, gen_X_sorted_listTuple:tuple/1/NoneType, dataset_AX_sorted_tupleList:list/1/tuple, bias_ratio:float/0/float · returned dict · level recorded 2026-09-22 a9bc3a5a4b2bffd2 · report
fixture: signature baseline_dict:dict/0/?, cur_dict:dict/0/?, print_flag:bool/0/bool · returned bool · level recorded 2026-09-22 census: 5 implementations from 5 papers, 5 distinct outputs across 4 buckets, one shared input per bucket this sample: bucket 4 of 4, arg 1: rank 3, kind float, dtype float32 engine/engine_vae_bias.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only ·
42b500b9cf00fc46 · report
fixture: signature vector:Tensor/3/float, normal:bool/0/bool, mask:NoneType/0/? · returned Tensor · level recorded 2026-09-22 effd9564d57e6ae2 · report
fixture: signature vector_proba:Tensor/3/float, vector_true:Tensor/3/float, normal:bool/0/bool · returned Tensor · level recorded 2026-09-22 84c19af3b81754ad · report
fixture: signature list_true:list/1/tuple, list_pred:list/1/list, k:int/0/int, gains:str/0/str · returned float64 · level recorded 2026-09-22 c97352ec4c132013 · report
fixture: signature df_dict:dict/0/?, target_id:int/0/int, sens_attr_ids:list/1/int · returned dict · level recorded 2026-09-22 f2891755fbef7181 · report
fixture: signature df_dict:dict/0/?, sens_attr_ids:list/1/int · returned dict · level recorded 2026-09-22 1c47e9bdf6cab4a1 · report
fixture: signature dict_dataset_AX_sorted_tupleList:dict/0/?, bias_ratio:float/0/float · returned dict · level recorded 2026-09-22 0cba59ac8e11f912 · report
fixture: signature gen_A_sorted_listTuple:tuple/1/ndarray, gen_X_sorted_listTuple:tuple/1/str · returned dict · level recorded 2026-09-22 1b9aa87cee22fb7a · report
fixture: signature a_generated_all:ndarray/2/float, b_all:ndarray/1/float, a_dicts:dict/0/? · returned dict · level recorded 2026-09-22 8598d814f1813079 · report
fixture: signature a_batch:Tensor/3/float, pred:callable/0/?, a_bank:Tensor/2/int, a_fea_bank:Tensor/2/float, gp_bias_bank:Tensor/1/float, args:Args/0/? · returned Tensor · level recorded 2026-09-22 census: 9 implementations from 10 papers, 9 distinct outputs across 7 buckets, one shared input per bucket engine/engine_vae_bias.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant no licence file found · pointer only ·
2d1680fb0c695a56 · report
fixture: signature b:Tensor/2/float, args:Args/0/?, mask_type:str/0/str, dis_x:Tensor/2/float, a_bank:Tensor/2/int · returned Tensor · level recorded 2026-09-22 f03d0c3b5c8756be · report
fixture: signature one_hot_batch:ndarray/2/float, output_dim:int/0/int, class_dim:int/0/int · returned ndarray · level recorded 2026-09-22 4800aa7f52553655 · report
fixture: signature list_pred:list/1/NoneType, k:int/0/int, vae_eval_bias_thresh:float/0/float · returned float · level recorded 2026-09-22 9b9c19ba2a0d261c · report
fixture: signature d:dict/0/? · returned str · level recorded 2026-09-22 1a4c35f9017f9cb5 · report
fixture: signature list_true:list/1/tuple, list_pred:list/1/str, k:int/0/int, vae_eval_bias_thresh:float/0/float · returned float64 · level recorded 2026-09-22 005cd4db1e67853f · report
fixture: signature a_dicts:dict/0/? · returned dict · level recorded 2026-09-22 127d7012d2754445 · report
fixture: signature mu:Tensor/2/float, logvar:Tensor/2/float, args:Args/0/? · returned Tensor · level recorded 2026-09-22 1755b6f77dcb9a2f · report
fixture: signature re_dict:dict/0/?, epo:int/0/int, type:str/0/str · returned tuple · level recorded 2026-09-22 b7baf45d83666191 · report
fixture: signature list_true:list/1/tuple, list_pred:tuple/1/str · returned tuple · level recorded 2026-09-22 ca065ddc9e07d6be · report
fixture: signature list_true:tuple/1/list, list_pred:tuple/1/list, k:int/0/int · returned tuple · level recorded 2026-09-22 da444d5c027e40ef · report
fixture: signature vector:Tensor/3/float, class_dim:int/0/int, normal:bool/0/bool, one_hot:bool/0/bool · returned Tensor · level recorded 2026-09-22 609ab87b158974d0 · report
fixture: signature vector:Tensor/2/float, attr_dim:int/0/int, attri_range:int/0/int · returned Tensor · level recorded 2026-09-22 c9f1553e541bc459 · report
6d82d74e0c0e698d · report
2b3859b1137b90e6 · report
9f22a7e05edf9c71 · report
3dad36b11b014f06 · report
b4e424706d6e8d17 · report
01a0d1b74cde1693 · report
e378aa7295e2b34d · report
9c79e5b3c213e90f · report
16ed4d14f65e60df · report
3f062da62d5063c8 · report
2283d3d11eb6c162 · 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 Bias-Guided Generative Network (BGGN) (graph method: Bias-Guided Generative Network (BGGN)). 36 bricks; individually on a fixture: 24 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 6 honoured, 1 violated, 0 with no contract checked; 17 where Syntology's instrument failed) · 12 unverified. The assembly has not been run end-to-end.
- bias_vae_train entry · level 0 · unverified ·
c9f1553e541bc459 - compare_evaluations helper · level 1 · ran · violated contract ·
a9bc3a5a4b2bffd2 - df_2_lists helper · level 1 · ran; the contract check could not run (RAISES) ·
f2891755fbef7181 - evaluate_genModel_multi_round helper · level 0 · unverified ·
2b3859b1137b90e6 - get_trA_based_loss loss · level 0 · unverified ·
3dad36b11b014f06 - get_z_based_loss loss · level 0 · unverified ·
b4e424706d6e8d17 - grad_activate helper · level 0 · unverified ·
01a0d1b74cde1693 - grad_freeze helper · level 0 · unverified ·
e378aa7295e2b34d - save_dset_dict_2_df helper · level 0 · unverified ·
3f062da62d5063c8 - ten2vec helper · level 1 · ran · our draft was wrong ·
609ab87b158974d0 - avg_evaluations helper · level 1 · ran · our draft was wrong ·
57d865bf1a287ccb - evaluate_genModel helper · level 0 · unverified ·
6d82d74e0c0e698d - result_dict_2_list helper · level 1 · ran · our draft was wrong ·
1755b6f77dcb9a2f - save_train_test_dict_2_df helper · level 0 · unverified ·
2283d3d11eb6c162 - compute_entropy loss · level 1 · ran; the contract check could not run (RAISES) ·
42b500b9cf00fc46 - compute_log_softmax_distribution loss · level 1 · ran; the contract check could not run (RAISES) ·
effd9564d57e6ae2 - get_mask helper · level 1 · ran; the contract check could not run (RAISES) ·
2d1680fb0c695a56 - reparameterize_latent sampler · level 1 · ran · honoured contract ·
127d7012d2754445 - sample_from_multi_softmax_distribution sampler · level 1 · ran; the contract check could not run (RAISES) ·
da444d5c027e40ef - get_bias helper · level 1 · ran · our draft was wrong ·
8598d814f1813079 - print_dict helper · level 1 · ran · our draft was wrong ·
9b9c19ba2a0d261c - df_2_dict helper · level 1 · ran; the contract check could not run (RAISES) ·
c97352ec4c132013 - evaluate_dataset helper · level 1 · ran · our draft was wrong ·
1c47e9bdf6cab4a1 - evaluate_seen helper · level 0 · unverified ·
9f22a7e05edf9c71 - evaluate_unseen helper · level 1 · ran · our draft was wrong ·
0cba59ac8e11f912 - filter_and_regroup_genA helper · level 1 · ran; the contract check could not run (RAISES) ·
1b9aa87cee22fb7a - log_evaluation_dict helper · level 0 · unverified ·
9c79e5b3c213e90f - regroup_dataset helper · level 1 · ran · our draft was wrong ·
005cd4db1e67853f - sampling_for_evaluation helper · level 0 · unverified ·
16ed4d14f65e60df - bias_num_ratio helper · level 1 · ran · our draft was wrong ·
064fdf4c7a190f52 - dcg_at_k helper · level 1 · ran · honoured contract ·
84c19af3b81754ad - precision_at_k helper · level 1 · ran · honoured contract ·
4800aa7f52553655 - recall_at_k helper · level 1 · ran · honoured contract ·
1a4c35f9017f9cb5 - rr helper · level 1 · ran · honoured contract ·
b7baf45d83666191 - rr_at_k helper · level 1 · ran · honoured contract ·
ca065ddc9e07d6be - onehot2vec helper · level 1 · ran · our draft was wrong ·
f03d0c3b5c8756be
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="2405.20790") 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.
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