Papers › Fairness and Unfairness in Binary and Multiclass Classification: Quantifying,...

Fairness and Unfairness in Binary and Multiclass Classification: Quantifying, Calculating, and Bounding

7 Jun 2022arXiv:2206.03234archive 2025-07-28

Sivan Sabato, Eran Treister, Elad Yom-Tov

We propose a new interpretable measure of unfairness, that allows providing a quantitative analysis of classifier fairness, beyond a dichotomous fair/unfair distinction. We show how this measure can be calculated when the classifier's conditional confusion matrices are known. We further propose methods for auditing classifiers for their fairness when the confusion matrices cannot be obtained or even estimated. Our approach lower-bounds the unfairness of a classifier based only on aggregate statistics, which may be provided by the owner of the classifier or collected from freely available data. We use the equalized odds criterion, which we generalize to the multiclass case. We report experiments on data sets representing diverse applications, which demonstrate the effectiveness and the wide range of possible uses of the proposed methodology. An implementation of the procedures proposed in this paper and as the code for running the experiments are provided in https://github.com/sivansabato/unfairness.

PaperPDFCodeCode Syntology ranMethod as code

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):

Code

Syntology 31 code samples harvested from 2 repositories linked to this paper: 24 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 5 honoured, 2 violated, 0 with no contract checked; 17 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 9 where our contract draft was wrong; 8 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 18 samples from 1 repository, 15 ran (2 with no instrument failure; 13 where Syntology's instrument failed); found in paper text by Syntology: 13 samples from 1 repository, 9 ran (5 with no instrument failure; 4 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 between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 3 of the 24 samples that ran have no recorded date.

sivansabato/unfairness officialmentioned in paperSyntology: 18 samples, 15 ran (13 instrument-failed) · 3 unverified report

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

31 samples harvested: 24 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 5 honoured, 2 violated, 0 with no contract checked; 17 where Syntology's instrument failed) · 7 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.

5ran · honoured contract
2ran · violated contract
9ran · our draft was wrong
8ran; the contract check could not run
7unverified

Licence: 31 of the 31 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 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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.

sivansabato/unfairness official repository 18 samples, 15 ran (13 instrument-failed) · 3 unverified
FairObjLarge solve_large.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · 5b15f0c7d44b4f68 · report fixture: signature alpha:ndarray/1/float, B:ndarray/3/float, wy:ndarray/1/float, beta_param:float/0/float · returned tuple · level recorded 2026-09-22
FairObjSmall solve_large.py ran · honoured contract fingerprinted no licence file found · pointer only · a810da487b9d6a25 · report fixture: signature alpha:float/0/float, w:ndarray/1/float, B:ndarray/2/float · returned tuple · level recorded 2026-09-22
Linesearch solve_large.py ran · our draft was wrong no licence file found · pointer only · 0797d51ac434feea · report fixture: signature f:callable/0/?, param:dict/0/?, x_k:Tensor/1/float, e:Tensor/1/float, f_prev:Tensor/0/float, lr0:float/0/float, beta:float/0/float, num_ls:int/0/int · returned tuple · level recorded 2026-09-22
combineComponentsIntoIterate solve_large.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 9ce71c0ff5a39821 · report fixture: signature alpha:ndarray/2/float, B:ndarray/3/float, c:ndarray/2/float, nz:int/0/int, ng:int/0/int · returned ndarray · level recorded 2026-09-22
etta solve_large.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · 573158668f667055 · report fixture: signature a:Tensor/2/float, b:Tensor/2/float, type:int/0/int · returned Tensor · level recorded 2026-09-22
etta_a_deriv solve_large.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · 07453f31330f3cad · report fixture: signature a:Tensor/2/float, b:Tensor/2/float, type:int/0/int · returned Tensor · level recorded 2026-09-22
etta_approx solve_large.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · b8b0905adeaba5ff · report fixture: signature a:Tensor/2/float, b:Tensor/2/float, type:int/0/int · returned tuple · level recorded 2026-09-22
etta_b_deriv solve_large.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · d9d0f36151228572 · report fixture: signature a:Tensor/2/float, b:Tensor/2/float, type:int/0/int · returned Tensor · level recorded 2026-09-22
f_linesearch solve_large.py ran · our draft was wrong no licence file found · pointer only · 54d8f2bfc48c3357 · report fixture: signature x:ndarray/1/float, param:Param/0/? · returned tuple · level recorded 2026-09-22
getBoundsLarge solve_large.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 9b75fdb8486bf5e9 · report fixture: signature nz:int/0/int, ng:int/0/int, eps:float/0/float, max_step:float/0/float, alphak:ndarray/2/float, Bk:ndarray/3/float, ck:ndarray/2/float · returned list · level recorded 2026-09-22
getBoundsLargeV0 solve_large.py ran · honoured contract fingerprinted no licence file found · pointer only · 31dcf9843a2d001e · report fixture: signature nz:int/0/int, ng:int/0/int, eps:float/0/float · returned list · level recorded 2026-09-22
getEqualityConstraintsLarge solve_large.py ran · our draft was wrong fingerprinted no licence file found · pointer only · c021d021cff53be6 · report fixture: signature nz:int/0/int, ng:int/0/int, Pi:ndarray/2/float, P:ndarray/2/float · returned tuple · level recorded 2026-09-22
getFairnessApproxSmall solve_large.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · 991b1926a41dde2f · report fixture: signature alpha:float/0/float, B:ndarray/2/float, type:int/0/int · returned tuple · level recorded 2026-09-22
getLPComponents solve_large.py ran · our draft was wrong no licence file found · pointer only · 49f95e8302398d5b · report fixture: signature nz:int/0/int, ng:int/0/int, param:Param/0/? · returned tuple · level recorded 2026-09-22
seperateIterateIntoComponents solve_large.py ran · our draft was wrong no licence file found · pointer only · c800d35508a5bd1c · report fixture: signature x:ndarray/1/float, nz:int/0/int, ng:int/0/int · returned tuple · level recorded 2026-09-22
getFairnessApproxLargeV0 solve_large.py unverified no licence file found · pointer only · a6d27ebb3c5d09f1 · report
getFairnessApproxLargeV2 solve_large.py unverified no licence file found · pointer only · 0ae9efb2697817b0 · report
solveFairness solve_large.py unverified no licence file found · pointer only · e40e0031507290d2 · report
sivansabato/DCPmulticlass found in paper text by Syntology 13 samples, 9 ran (4 instrument-failed) · 4 unverified
FairObj localmin.py ran · honoured contract fingerprinted no licence file found · pointer only · b9fe921e99d1294c · report fixture: signature alpha:float/0/float, w:ndarray/1/float, B:ndarray/2/float · returned tuple · level recorded 2026-09-22
calc_eta runexps.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant no licence file found · pointer only · 16b9a6aae0cf7761 · report fixture: signature _a:ndarray/1/float, _b:ndarray/1/float · returned ndarray · level recorded, date not recorded
etta localmin.py ran · violated contract fingerprinted no licence file found · pointer only · 820a4aab8fb1e7f2 · report fixture: signature a:Tensor/2/float, b:Tensor/2/float · returned Tensor · level recorded 2026-09-22
etta_a_deriv localmin.py ran · honoured contract fingerprinted no licence file found · pointer only · 23d8ef11f17e93d2 · report fixture: signature a:Tensor/2/float, b:Tensor/2/float · returned Tensor · level recorded 2026-09-24
etta_approx localmin.py ran · honoured contract fingerprinted no licence file found · pointer only · 9945e0a1733ccc0c · report fixture: signature a:Tensor/2/float, b:Tensor/2/float · returned tuple · level recorded 2026-09-22
getFairnessApprox localmin.py ran · our draft was wrong no licence file found · pointer only · 1d5927318b309d1f · report fixture: signature alpha:float/0/float, B:ndarray/2/float · returned tuple · level recorded 2026-09-24
is_neg_zero runexps.py ran · violated contract fingerprinted no licence file found · pointer only · e42ae7e825c1a0f7 · report fixture: signature x:float/0/float · returned bool · level recorded, date not recorded
solveFairness localmin.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · c0a2f988d70ba66d · report fixture: signature alpha_0:ndarray/1/float, B:ndarray/2/float, w:ndarray/1/float, tol:float/0/float · returned tuple · level recorded 2026-09-22
table_latex_str runexps.py ran · our draft was wrong no licence file found · pointer only · c6c392494c81e533 · report fixture: signature x:list/1/list · returned str · level recorded, date not recorded
Linesearch localmin.py unverified no licence file found · pointer only · a3c97a8bb5ee16a2 · report
etta localmin.py unverified no licence file found · pointer only · a48f41425b57fdab · report
etta_a_deriv localmin.py unverified no licence file found · pointer only · 639e2c42726aa4b2 · report
getFairnessProblem localmin.py unverified no licence file found · pointer only · 948ea61cfe14ef84 · 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. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

2 assemblies on this paper: 2 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

2 sibling assemblies for Disparate Conditional Prediction (DCP) for multiclass classifiers (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for Disparate Conditional Prediction (DCP) for multiclass classifiers (graph method: Disparate Conditional Prediction (DCP) for multiclass classifiers). 18 bricks; individually on a fixture: 15 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 13 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. solveFairness entry · level 0 · unverified · e40e0031507290d2
  2. FairObjLarge loss · level 1 · ran; the contract check could not run (RAISES) · 5b15f0c7d44b4f68
  3. Linesearch update_rule · level 1 · ran · our draft was wrong · 0797d51ac434feea
  4. combineComponentsIntoIterate helper · level 1 · ran · our draft was wrong · 9ce71c0ff5a39821
  5. f_linesearch helper · level 1 · ran · our draft was wrong · 54d8f2bfc48c3357
  6. getBoundsLarge helper · level 1 · ran · our draft was wrong · 9b75fdb8486bf5e9
  7. getBoundsLargeV0 helper · level 1 · ran · honoured contract · 31dcf9843a2d001e
  8. getEqualityConstraintsLarge helper · level 1 · ran · our draft was wrong · c021d021cff53be6
  9. getFairnessApproxLargeV2 helper · level 0 · unverified · 0ae9efb2697817b0
  10. getLPComponents helper · level 1 · ran · our draft was wrong · 49f95e8302398d5b
  11. seperateIterateIntoComponents helper · level 1 · ran · our draft was wrong · c800d35508a5bd1c
  12. FairObjSmall helper · level 1 · ran · honoured contract · a810da487b9d6a25
  13. getFairnessApproxLargeV0 helper · level 0 · unverified · a6d27ebb3c5d09f1
  14. etta helper · level 1 · ran; the contract check could not run (RAISES) · 573158668f667055
  15. getFairnessApproxSmall helper · level 1 · ran; the contract check could not run (RAISES) · 991b1926a41dde2f
  16. etta_approx helper · level 1 · ran; the contract check could not run (RAISES) · b8b0905adeaba5ff
  17. etta_a_deriv helper · level 1 · ran; the contract check could not run (RAISES) · 07453f31330f3cad
  18. etta_b_deriv helper · level 1 · ran; the contract check could not run (RAISES) · d9d0f36151228572

harvested Assembly for Disparate Conditional Prediction (DCP) for multiclass classifiers (graph method: Disparate Conditional Prediction (DCP) for multiclass classifiers). 7 bricks; individually on a fixture: 6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. solveFairness entry · level 1 · ran; the contract check could not run (RAISES) · c0a2f988d70ba66d
  2. FairObj loss · level 1 · ran · honoured contract · b9fe921e99d1294c
  3. Linesearch update_rule · level 0 · unverified · a3c97a8bb5ee16a2
  4. getFairnessApprox helper · level 1 · ran · our draft was wrong · 1d5927318b309d1f
  5. etta helper · level 1 · ran · violated contract · 820a4aab8fb1e7f2
  6. etta_approx helper · level 1 · ran · honoured contract · 9945e0a1733ccc0c
  7. etta_a_deriv helper · level 1 · ran · honoured contract · 23d8ef11f17e93d2

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="2206.03234") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Fairness

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