Equality of Opportunity in Supervised Learning

Moritz Hardt, Eric Price, Nathan Srebro · NeurIPS / arXiv · 2016 · law · record hardt2016-equality-opportunity
tag layer · index · concepts · authors · עברית
Where this record's text came from. faceted 2026-08 by reading the locally held text (pdftext); every evidence string verified as an exact substring of that text before merging. The paper is primarily a definitional and theoretical contribution (proofs of Bayes optimality, near-optimality, and unidentifiability) plus an empirical case study on 301,536 TransUnion TransRisk FICO scores; the controlled method vocabulary has no 'theory' value, so system-or-tool-building was chosen for the post-processing construction. The FICO study is an illustrative case study, not a hypothesis test, so replication status is untested. 2026-08-14, 2026-08-15 and 2026-08-17 schema-0.3 passes: every quote verified as an exact substring of the staged text and anchored at merge time; concept terms verified present; every edge endpoint an existing node.
Some quotes on this page contain (cid:NN). The PDF this text was extracted from encodes 17 characters in a way that names no letter, so the extractor could not say what they were. The quotes keep them because a quote is reproduced exactly or it proves nothing — the marks are the source’s, not the tagging’s.
How to read this page. The article itself is not reproduced here — this paper is not cleared for redistribution, so what follows is the tag layer alone. The evidence sentences are withheld with the article. The table at the foot lists every tag the record carries; each row names the facet it belongs to, and the whose words column says whether the tag records the paper's own wording or the tagger's sentence about the paper. Every tag links to each other paper in the corpus carrying it. The machine-readable edition of the same thing is the TEI file beside this one, where the tags live in standOff, and the article is at its publisher via the link below. When we have changed our mind. Some entries in the table begin with a word in capitals and the reason for it. EVIDENCE CORRECTED — the finding still stands, but we had quoted the wrong sentence from the paper, and the quotation has been replaced with the right one. RETRACTED — the entry itself was wrong; it stays on the page, marked, with the reason, rather than being deleted. WITHDRAWN AND REPLACED — the entry was wrong, and a corrected version of it appears in the entries below. Each mark carries its own reason, in brackets, because the reasons differ from one entry to the next. An entry we have WITHDRAWN is removed from this page and kept in the record, with its reason. A line reading Audit and a date is a later re-reading of the entry against its whole sentence: DOUBTFUL means it was kept, and the reason says what is loose about it. Quotation marks inside the tagger's sentence. Where a tag is the tagger's own sentence, a phrase in quotation marks inside it is borrowed from the paper — the tagger's wording around it is not. The paper's own sentence is the evidence quote for that row; on this page it is withheld with the article, and the article is at its publisher. Nothing inside quotation marks anywhere on this page is ours: if it is quoted, it is the paper's. Whose words a concept carries. A concept entry records a term the paper itself uses, so the term, the sense given for it, and its evidence are the paper's own words, quoted where the paper fixes them. This is the opposite of a sense entry in the tag table, which is the tagger's sentence about how the paper uses a term. Where a concept entry could not be grounded in the paper's words, the entry says so on its own row.
Other fields define these differently the same word, defined another way in another discipline
supervised learning 3 fields · discrimination 2 fields · classification 2 fields · fairness 2 fields

Tags on this paper

Every tag the record carries, each linking to every other paper in the corpus that carries it. A tag appears here whether or not its words occur in the article — the spans below are only the ones a sentence in this paper licenses. Of the 9 concept tags on this paper, 5 are grounded in a quoted sentence.
fairness equalized odds discrimination supervised learning protected attribute equal opportunity demographic parity oblivious fairness through unawareness A NAMED APPROACH IS SHOWN NOT TO DO WHAT ITS NAME PROMISES: `fairness through unawareness` - simply ignoring the protected attributes - is called INEFFECTIVE, because redundant encodings let the protected attribute be predicted from other features anyway. Removing the variable does not remove the information AN ESTABLISHED CRITERION IS SATISFIED BY EXACTLY THE BEHAVIOUR IT WAS MEANT TO FORBID: demographic parity PERMITS accepting qualified applicants in one group and UNQUALIFIED individuals in the other, so long as the acceptance percentages match - and the authors add that this can arise NATURALLY when one group has little or no training data. The criterion is not merely weak; it is passed by the discrimination it names A CRITERION IS SHOWN TO FORBID THE GROUND TRUTH: demographic parity would not allow the ideal predictor that simply equals the true outcome - which, the authors say, CAN HARDLY BE CONSIDERED DISCRIMINATORY as it represents the actual outcome. The case arises whenever the target is correlated with the protected attribute THE NEW CRITERION IS ENGINEERED SO THE PERFECT PREDICTOR ALWAYS PASSES, AND SO THAT IT GETS EASIER AS ACCURACY RISES: the authors state that unlike demographic parity theirs always allows the perfectly accurate solution, and that the criterion is easier to achieve the more accurate the predictor is - explicitly ALIGNING fairness with the existing objective of supervised learning rather than trading against it THE CRITERION PERMITS ONE ROUTE AND PROHIBITS ANOTHER BETWEEN THE SAME TWO VARIABLES: the prediction may depend on the protected attribute but ONLY THROUGH the target, so the definition ENCOURAGES features that predict the target directly and PROHIBITS abusing the protected attribute as a proxy for it. What the definition constrains is the PATH the dependence takes A PROPERTY IS DEFINED FOR PROPERTIES, NOT FOR PREDICTORS: `oblivious` is given a formal definition one level up - a PROPERTY of a predictor or score is oblivious if it depends only on the joint distribution of outcome, protected attribute and prediction. The definition's subject is other definitions THE CRITERION IS RESTRICTED TO WHAT IS OBSERVABLE, AND THE RESTRICTION IS JUSTIFIED BY OBSERVABILITY RATHER THAN BY CORRECTNESS: in many cases only oblivious analysis is POSSIBLE, because the functional form of the score and the training data are not public - and going beyond it would require SUBJECTIVE INTERPRETATION or, as the paper prints it, `casual` assumptions about specific features (causal is meant), WHICH THE AUTHORS AIM TO AVOID. The definition is cut to fit what can be seen A WEAKER CRITERION IS OBTAINED BY RESTRICTING THE STRONGER ONE TO ONE OUTCOME, AND WHICH OUTCOME IS AN INTERPRETIVE CHOICE: the authors say they OFTEN THINK OF one value as the ADVANTAGED outcome, then relax the requirement to hold only within that group, WITHOUT SPECIFYING ANY REQUIREMENT for those who will ultimately default - and name the result `equal opportunity`. The asymmetry that makes the weaker notion weaker is supplied by the reading of the outcome, not by the mathematics THE CRITERION IS PRESENTED IN TERMS OF WHERE IT PUTS THE COST: it is described as SHIFTING THE BURDEN OF UNCERTAINTY from the protected class to the decision maker, and thereby INCENTIVISING the collection of better features - ones depending more directly on the target than on the protected attribute - and of data allowing better prediction for all groups THE PAPER PROVES THE LIMIT OF ITS OWN ENTIRE FAMILY OF DEFINITIONS: a NON-IDENTIFIABILITY result shows that different dependency structures, WITH POSSIBLY DIFFERENT INTUITIVE NOTIONS OF FAIRNESS, cannot be separated by ANY oblivious notion or test - not merely by theirs. The contribution is a proof about what the class of measures cannot see TWO SITUATIONS THAT DIFFER IN EXACTLY THE WAY THE CONCEPT IS SUPPOSED TO TRACK ARE SHOWN TO BE INDISTINGUISHABLE: the authors construct two dependency structures which can have FUNDAMENTALLY DIFFERENT INTERPRETATIONS FROM THE POINT OF VIEW OF FAIRNESS and yet be indistinguishable from their joint distribution - so no oblivious test can resolve which applies ACCESS TO THE FEATURES DOES NOT RESCUE IT - THE PAPER CLOSES ITS OWN LOOP: without ATTACHING MEANING to the features or making CAUSAL ASSUMPTIONS about them, no further insight into the two scores is gained. Subjective interpretation was excluded in order to make the criterion objective, and here the authors state that without it nothing more can be learned A PROPERTY IS NAMED, GIVEN A USEFUL MEANING, AND THEN SHOWN NOT TO MEAN WHAT IT SOUNDS LIKE: having MATCHING conditional ROC curves does correspond to being deterministically correctable to non-discrimination - but the authors state plainly that it DOES NOT AT ALL mean the score is itself non-discriminatory, since it can be biased according to the protected attribute and need correcting A PROPERTY OFFERED AS A FAIRNESS MEASURE IS EQUIVALENT TO THE SCORE USING EVERYTHING THE PROTECTED ATTRIBUTE OFFERS: matching conditional frequencies means the score includes ALL POSSIBLE INFORMATION the protected attribute can provide about the target, so the score is IN A SENSE OPTIMALLY DEPENDENT on that attribute predictor equality of opportunity sensitive attribute classification oblivious notion equal opportunity by design protected attribute A target Y features X Bayesian system-or-tool-building

Legend

relation to other workclaim_relationshow this paper stands to another: agrees, contradicts, extends, qualifies
claim typeclaim_typethe shape of the claim: existence, mechanism, method, critique, prediction, null
conceptconceptsan idea the paper works with, quoted where the paper uses it
content tagcontent_tagsa finding, definition, quantity, statistic or variable named in the paper
limitationlimitationswhat the paper says its evidence cannot support
mechanismmechanismshow the reported effect is said to come about
methodmethodhow the paper produced its evidence
phenomenonphenomenonthe effect or regularity under study
sensesensesa distinct use of a term, quoted where the paper fixes it

The paper

The full text is not reproduced here. This article is not cleared for redistribution, so the page carries the tag layer only. Its evidence sentences are withheld; the grounding status remains with each tag, and the article itself is at https://arxiv.org/abs/1610.02413. The reading view exists for the papers whose licence permits it.

Every tag on this page

claim_relations 4 · claim_type 1 · concepts 5 · content_tags 15 · limitations 8 · mechanisms 14 · method 1 · phenomenon 1 · senses 3

This record holds no relations between concepts or controls. A layer is empty when the tagger recorded nothing in it — which is not the same as the paper having nothing to record.

facettagfieldconf.whose words
claim_typemethod
Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.
claim_typethe paper's words
phenomenondiscrimination against protected attributes in supervised learning
Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.
phenomenonthe paper's words
methodsystem-or-tool-building
Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.
also in: system-or-tool-building
methodthe paper's words
mechanismsmechanisms
Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.
also in: A NAMED APPROACH IS SHOWN NOT TO DO WHAT ITS NAME PROMISES: `fairness through unawareness` - simply ignoring the protected attributes - is called INEFFECTIVE, because redundant encodings let the protected attribute be predicted from other features anyway. Removing the variable does not remove the information
mechanisms[0]0.95the tagger's words
mechanismsmechanisms
Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.
also in: AN ESTABLISHED CRITERION IS SATISFIED BY EXACTLY THE BEHAVIOUR IT WAS MEANT TO FORBID: demographic parity PERMITS accepting qualified applicants in one group and UNQUALIFIED individuals in the other, so long as the acceptance percentages match - and the authors add that this can arise NATURALLY when one group has little or no training data. The criterion is not merely weak; it is passed by the discrimination it names
mechanisms[1]0.95the tagger's words
mechanismsmechanisms
Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.
about this quote: The span contains '(cid:98)Y', which is Y-hat - the circumflex accent failed to map and the extraction emitted a glyph code. 367 of these are in this file and almost all are this same hat. The quote is an exact substring and anchors correctly; the mathematics is unreadable in it. Damage shape 6. Unavoidable here: the sentence's subject IS the predictor.
also in: A CRITERION IS SHOWN TO FORBID THE GROUND TRUTH: demographic parity would not allow the ideal predictor that simply equals the true outcome - which, the authors say, CAN HARDLY BE CONSIDERED DISCRIMINATORY as it represents the actual outcome. The case arises whenever the target is correlated with the protected attribute
mechanisms[2]0.85the tagger's words
mechanismsmechanisms
Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.
about this quote: The span contains '(cid:98)Y', which is Y-hat - the circumflex accent failed to map and the extraction emitted a glyph code. 367 of these are in this file and almost all are this same hat. The quote is an exact substring and anchors correctly; the mathematics is unreadable in it. Damage shape 6. Unavoidable here: the sentence's subject IS the predictor.
also in: THE NEW CRITERION IS ENGINEERED SO THE PERFECT PREDICTOR ALWAYS PASSES, AND SO THAT IT GETS EASIER AS ACCURACY RISES: the authors state that unlike demographic parity theirs always allows the perfectly accurate solution, and that the criterion is easier to achieve the more accurate the predictor is - explicitly ALIGNING fairness with the existing objective of supervised learning rather than trading against it
mechanisms[3]0.95the tagger's words
mechanismsmechanisms
Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.
about this quote: The span contains '(cid:98)Y', which is Y-hat - the circumflex accent failed to map and the extraction emitted a glyph code. 367 of these are in this file and almost all are this same hat. The quote is an exact substring and anchors correctly; the mathematics is unreadable in it. Damage shape 6. Unavoidable here: the sentence's subject IS the predictor.
also in: THE CRITERION PERMITS ONE ROUTE AND PROHIBITS ANOTHER BETWEEN THE SAME TWO VARIABLES: the prediction may depend on the protected attribute but ONLY THROUGH the target, so the definition ENCOURAGES features that predict the target directly and PROHIBITS abusing the protected attribute as a proxy for it. What the definition constrains is the PATH the dependence takes
mechanisms[4]0.85the tagger's words
mechanismsmechanisms
Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.
about this quote: The span contains '(cid:98)Y', which is Y-hat - the circumflex accent failed to map and the extraction emitted a glyph code. 367 of these are in this file and almost all are this same hat. The quote is an exact substring and anchors correctly; the mathematics is unreadable in it. Damage shape 6. Unavoidable here: the sentence's subject IS the predictor.
also in: A PROPERTY IS DEFINED FOR PROPERTIES, NOT FOR PREDICTORS: `oblivious` is given a formal definition one level up - a PROPERTY of a predictor or score is oblivious if it depends only on the joint distribution of outcome, protected attribute and prediction. The definition's subject is other definitions
mechanisms[5]0.85the tagger's words
mechanismsmechanisms
Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.
also in: THE CRITERION IS RESTRICTED TO WHAT IS OBSERVABLE, AND THE RESTRICTION IS JUSTIFIED BY OBSERVABILITY RATHER THAN BY CORRECTNESS: in many cases only oblivious analysis is POSSIBLE, because the functional form of the score and the training data are not public - and going beyond it would require SUBJECTIVE INTERPRETATION or, as the paper prints it, `casual` assumptions about specific features (causal is meant), WHICH THE AUTHORS AIM TO AVOID. The definition is cut to fit what can be seen
mechanisms[6]0.85the tagger's words
mechanismsmechanisms
Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.
also in: A WEAKER CRITERION IS OBTAINED BY RESTRICTING THE STRONGER ONE TO ONE OUTCOME, AND WHICH OUTCOME IS AN INTERPRETIVE CHOICE: the authors say they OFTEN THINK OF one value as the ADVANTAGED outcome, then relax the requirement to hold only within that group, WITHOUT SPECIFYING ANY REQUIREMENT for those who will ultimately default - and name the result `equal opportunity`. The asymmetry that makes the weaker notion weaker is supplied by the reading of the outcome, not by the mathematics
mechanisms[7]0.95the tagger's words
mechanismsmechanisms
Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.
also in: THE CRITERION IS PRESENTED IN TERMS OF WHERE IT PUTS THE COST: it is described as SHIFTING THE BURDEN OF UNCERTAINTY from the protected class to the decision maker, and thereby INCENTIVISING the collection of better features - ones depending more directly on the target than on the protected attribute - and of data allowing better prediction for all groups
mechanisms[8]0.85the tagger's words
mechanismsmechanisms
Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.
also in: THE PAPER PROVES THE LIMIT OF ITS OWN ENTIRE FAMILY OF DEFINITIONS: a NON-IDENTIFIABILITY result shows that different dependency structures, WITH POSSIBLY DIFFERENT INTUITIVE NOTIONS OF FAIRNESS, cannot be separated by ANY oblivious notion or test - not merely by theirs. The contribution is a proof about what the class of measures cannot see
mechanisms[9]0.95the tagger's words
mechanismsmechanisms
Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.
also in: TWO SITUATIONS THAT DIFFER IN EXACTLY THE WAY THE CONCEPT IS SUPPOSED TO TRACK ARE SHOWN TO BE INDISTINGUISHABLE: the authors construct two dependency structures which can have FUNDAMENTALLY DIFFERENT INTERPRETATIONS FROM THE POINT OF VIEW OF FAIRNESS and yet be indistinguishable from their joint distribution - so no oblivious test can resolve which applies
mechanisms[10]0.95the tagger's words
mechanismsmechanisms
Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.
about this quote: RE-SLICED. My first cut ran straight through a WORD-ORDER SCRAMBLE (damage shape 5): the staged text reads "since the distributions , (cid:101)R) agree ... The over (Y , A, R features are correlated", with two clauses interleaved and a superscript hoisted. It would have been perfectly verbatim and unreadable. The span now keeps only the closing sentence, which carries the claim and is clean.
also in: ACCESS TO THE FEATURES DOES NOT RESCUE IT - THE PAPER CLOSES ITS OWN LOOP: without ATTACHING MEANING to the features or making CAUSAL ASSUMPTIONS about them, no further insight into the two scores is gained. Subjective interpretation was excluded in order to make the criterion objective, and here the authors state that without it nothing more can be learned
mechanisms[11]0.85the tagger's words
mechanismsmechanisms
Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.
also in: A PROPERTY IS NAMED, GIVEN A USEFUL MEANING, AND THEN SHOWN NOT TO MEAN WHAT IT SOUNDS LIKE: having MATCHING conditional ROC curves does correspond to being deterministically correctable to non-discrimination - but the authors state plainly that it DOES NOT AT ALL mean the score is itself non-discriminatory, since it can be biased according to the protected attribute and need correcting
mechanisms[12]0.95the tagger's words
mechanismsmechanisms
Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.
also in: A PROPERTY OFFERED AS A FAIRNESS MEASURE IS EQUIVALENT TO THE SCORE USING EVERYTHING THE PROTECTED ATTRIBUTE OFFERS: matching conditional frequencies means the score includes ALL POSSIBLE INFORMATION the protected attribute can provide about the target, so the score is IN A SENSE OPTIMALLY DEPENDENT on that attribute
mechanisms[13]0.85the tagger's words
limitationsthe criterion is oblivious - it uses only joint statistics, not the interpretation of individual features
Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.
what this limits: everything the criterion can detect: Quotation withheld
limitations[0]the tagger's words
limitationsSatisfying the proposed oblivious criterion is not a proof of fairness (nor is violating it a proof of unfairness).
Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.
what this limits: any use of the criterion as a fairness certificate: SATISFYING OUR NOTION (OR ANY OTHER OBLIVIOUS MEASURE) SHOULD NOT BE CONSIDERED A CONCLUSIVE PROOF OF FAIRNESS
limitations[1]the tagger's words
limitationsThe criterion requires reliable observed outcome labels, which are not always available and may themselves be biased.
Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.
what this limits: every application of the method: HAVING ACCESS TO RELIABLE LABELED DATA IS NOT ALWAYS POSSIBLE, and the labels may themselves carry the bias being measured
limitations[2]the tagger's words
limitationsThe near-optimality guarantee is relative to other constrained predictors only; the derived predictor need not be good in absolute terms.
Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.
what this limits: the optimality claim: THIS DOES NOT MEAN THAT THE PREDICTOR IS NECESSARILY GOOD IN AN ABSOLUTE SENSE - near-optimality is relative to other constrained predictors
limitations[3]the tagger's words
limitationsNo test of this kind can tell two situations apart, and the authors prove it about their own class of test.
Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.
what this limits: a verdict of non-discrimination obtained from this criterion: the authors show no oblivious test can resolve which of two dependency structures applies, so two scenarios with different intuitive fairness are indistinguishable to it
limitations[4]1.0the tagger's words
limitationsAccess to the features does not rescue the test, without assumptions the authors decline to make.
Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.
what this limits: the suggestion that inspecting the model's features would settle what this test cannot: the authors state that without attaching meaning to the features or making causal assumptions about them, no further insight is gained
limitations[5]1.0the tagger's words
limitationsMeeting the criterion can require deciding individual cases partly at random.
Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.
what this limits: the deployment of this criterion on individual decisions: achieving it cannot be done with a single threshold per group and requires randomization
limitations[6]1.0the tagger's words
limitationsWho pays for the fairness is a property of the design, and the authors name the payer.
Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.
what this limits: the incidence of the utility cost reported here: the authors state the cost is borne by the company using the classifier, which can invest in better classification, rather than by the classified group, which cannot
limitations[7]1.0the tagger's words
conceptsequalized odds
Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.
about this quote: DAMAGED GLYPHS IN THIS QUOTE: (cid:98). These are raw PDF font glyph indices that leaked out in place of the characters they stand for - usually a mathematical operator. The quote is verbatim to the staged text and its anchor is sound; the STAGED TEXT is what is damaged. NOT repaired: the cid-to-character mapping is defined by the font embedded in that particular PDF, so guessing it would produce a clean and unverifiable quote. Repair needs the source PDF and is a re-staging job.
also in: equalized odds
concepts[1]the paper's words
conceptsequal opportunity
Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.
also in: equal opportunity
concepts[5]the paper's words
conceptsdemographic parity
Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.
also in: demographic parity
concepts[6]the paper's words
conceptsoblivious
Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.
also in: oblivious
concepts[7]the paper's words
conceptsfairness through unawareness
Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.
also in: fairness through unawareness
concepts[8]the paper's words
sensesequal opportunity vs equalized odds - TWO CRITERIA, ONE STRICTLY WEAKER, AND THE PAPER PRICES THE GAP: equal opportunity relaxes equalized odds to the advantaged outcome group only, and in the case study equal opportunity keeps 92.8% of maximal profit against equalized odds' 80.2%, so a claim citing 'Hardt et al.' without saying which criterion is a claim about neither
Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.
senses[0]1.0the tagger's words
sensesoblivious - IN A FORMAL SENSE THE PAPER DEFINES: a property is oblivious if it depends only on the joint distribution of target, protected attribute and prediction, which is what makes the criterion checkable from published statistics and also what makes it blind
Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.
senses[1]1.0the tagger's words
sensesdemographic parity - THE CRITERION THIS ONE IS DEFINED AGAINST: it requires the decision to be independent of the protected attribute, which the authors reject because it forbids the perfectly accurate predictor and costs the most utility of the four thresholds they compare
Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.
senses[2]1.0the tagger's words
claim_relationscontradicts → fairness through unawareness (ignoring protected attributes)
Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.
claim_relations[0]the tagger's words
claim_relationsbuilds-on → Dwork et al. [DHP+12], "Fairness through Awareness"
Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.
claim_relations[1]the tagger's words
claim_relationsbuilds-on → Kleinberg, Mullainathan and Raghavan [KMR16] on calibration within groups
Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.
claim_relations[2]the tagger's words
claim_relationscontradicts → demographic parity as a non-discrimination criterion
Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.
differs in: THE AXIS IS THE FAIRNESS CRITERION. 'Quotation withheld' Two criteria, and the disagreement is over which one MEASURES discrimination - not over any fact about a dataset.
claim_relations[3]the tagger's words
content_tags2 — ways demographic parity is flawed
Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.
content_tags.quantities[0]the tagger's words
content_tagsMay 2014 — Obama Big Data report warning on discrimination
Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.
content_tags.quantities[1]the tagger's words
content_tagsdemographic parity is seriously flawed on two counts
Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.
content_tags.findings[0]the tagger's words
content_tagsfairness through unawareness fails because of redundant encodings
Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.
content_tags.findings[1]the tagger's words
content_tagstheir criterion always permits the perfectly accurate predictor
Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.
content_tags.findings[2]the tagger's words
content_tagsthe criterion aligns fairness with predictive accuracy
Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.
content_tags.findings[3]the tagger's words
content_tagsprotected attribute A
Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.
also in: protected attribute A
content_tags.variables[0]the tagger's words
content_tagstarget Y
Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.
also in: target Y
content_tags.variables[1]the tagger's words
content_tagspredictor
Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.
also in: predictor
content_tags.variables[2]the tagger's words
content_tagsfeatures X
Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.
also in: features X
content_tags.variables[3]the tagger's words
content_tagsdemographic parity
Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.
also in: demographic parity
content_tags.definitions[0]the tagger's words
content_tagsfairness through unawareness
Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.
also in: fairness through unawareness
content_tags.definitions[1]the tagger's words
content_tagsoblivious notion
Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.
also in: oblivious notion
content_tags.definitions[2]the tagger's words
content_tagsequal opportunity by design
Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.
also in: equal opportunity by design
content_tags.definitions[3]the tagger's words
content_tagsBayesian
Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.
also in: Bayesian
content_tags.statistics[0]the tagger's words

Interpretive choices

Tags that could not be placed in the text:

What was deliberately not tagged, and why, is recorded per paper by the tagger. Where a paper has no such record, this page says so rather than implying that nothing was declined.

© 2026 Shir Sivroni · ORCID 0009-0000-2597-2824