Fairness Through Awareness

Cynthia Dwork, Moritz Hardt, Toniann Pitassi, Omer Reingold, Richard Zemel · ITCS / arXiv · 2012 · law · 10.1145/2090236.2090255 · record dwork2012-fairness
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. method is not in the suggested vocabulary: the paper is definitional and theoretical (definitions, LP formulations, theorems and lower bounds, no experiments, no implementation), hence 'formal-framework'. A major element of the paper is its argument that statistical parity is inadequate as a fairness notion ('Quotation withheld.'), which would read as a 'contradicts' relation; it is deliberately NOT recorded in claim relations because the paper attaches no citation or named prior work to statistical parity, and rule 7 forbids inferring the target. Replication status 'untested' - the paper reports no empirical evaluation and no prior or subsequent confirmation of its results. 2026-08-14 schema-0.3 pass: 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.

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 WITHDRAWN AND REPLACED — the entry was wrong, and a corrected version of it appears in the entries below.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
discrimination 2 fields · statistical-significance 2 fields · algorithmic fairness 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.

algorithmic fairness individual fairness discrimination classification statistical parity group fairness Lipschitz condition Earthmover distance fairness through blindness fairness as treat similar individuals similarly, formalized as a Lipschitz condition on the classifier w.r.t. a task-specific similarity metric, maximizing utility subject to that constraint fairness individuals similar metric utility parity fairness constraint Lipschitz condition on the classifier task-specific metric statistical-significance formal-model

Method, as described: formal-framework

Legend

relation to other work	`claim_relations`	how this paper stands to another: agrees, contradicts, extends, qualifies
claim type	`claim_type`	the shape of the claim: existence, mechanism, method, critique, prediction, null
concept edge	`concept_edges`	an asserted relation between two concepts, with the sentence asserting it
concept	`concepts`	an idea the paper works with, quoted where the paper uses it
content tag	`content_tags`	a finding, definition, quantity, statistic or variable named in the paper
limitation	`limitations`	what the paper says its evidence cannot support
mechanism	`mechanisms`	how the reported effect is said to come about
method	`method`	how the paper produced its evidence
phenomenon	`phenomenon`	the effect or regularity under study
sense	`senses`	a distinct use of a term, quoted where the paper fixes it
transfer	`transfers`	a method or concept carried in from another field

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://doi.org/10.1145/2090236.2090255. The reading view exists for the papers whose licence permits it.

Every tag on this page

claim_relations 5 · claim_type 1 · concept_edges 2 · concepts 5 · content_tags 9 · limitations 11 · mechanisms 1 · method 1 · phenomenon 1 · senses 3 · transfers 1

Relations on this page carry a quotation for the claim. Where a relation was separately evidenced — and so tested against the vocabulary for its type — the row says so; none of 2 relations here carry that mark. The rest are the tagger’s reading of the sentence quoted beside them.

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

facet	tag	field	conf.	whose words
claim_type	method Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`claim_type`		the paper's words
phenomenon	fairness in classification Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`phenomenon`		the paper's words
method	formal-model Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: formal-model	`method`		the paper's words
mechanisms	mechanisms Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: fairness as treat similar individuals similarly, formalized as a Lipschitz condition on the classifier w.r.t. a task-specific similarity metric, maximizing utility subject to that constraint	`mechanisms[0]`		the tagger's words
limitations	the approach assumes a task-specific similarity metric, which is hard to define Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: every guarantee the framework offers: it assumes Quotation withheld - supplied from outside the definition	`limitations[0]`		the tagger's words
limitations	Obtaining or justifying the task-specific similarity metric the framework depends on is the hardest part, and any real metric will be an approximation. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: the practical applicability of the whole approach: JUSTIFYING THE AVAILABILITY OF OR ACCESS TO THE DISTANCE METRIC ... IS ONE OF THE MOST CHALLENGING ASPECTS OF OUR FRAMEWORK, AND IN REALITY THE METRIC USED WIL[l be imperfect]	`limitations[1]`		the tagger's words
limitations	The general fairness LP gives no quantitative bound on the loss it incurs. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: the loss claim for the general fairness LP: THE RESULT HOWEVER DOES NOT GIVE A CONCRETE QUANTITATIVE BOUND ON THE RESULTING LOSS	`limitations[2]`		the tagger's words
limitations	When the protected set is far from the rest of the population under the metric, satisfying the Lipschitz condition can still leave unfair practices unchecked. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: the protection guarantee for a distant protected set: IF MEMBERS OF S ARE RELATIVELY FAR FROM THE MEMBERS OF T ACCORDING TO THE DISTANCE METRIC, THEN SATISFYING THE LIPSCHITZ CONDITION MAY FAIL TO PREVENT SOME OF THE UNFAIR PRACTICES	`limitations[3]`		the tagger's words
limitations	No tight Earthmover characterisation is obtained for the relative-infinity distance version of the bias. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: the Earthmover characterisation: for biasD-infinity WE DO NOT GET A TIGHT CHARACTERIZATION	`limitations[4]`		the tagger's words
limitations	The whole treatment assumes one metric applied uniformly to everyone; per-user or plural metrics are untested. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: the scope of every result in the paper: OUR DISCUSSION THROUGHOUT THIS PAPER HAS ASSUMED THAT A SINGLE METRIC IS USED ACROSS THE BOARD - per-user or plural metrics are untested	`limitations[5]`		the tagger's words
limitations	The nearest existing similarity system the authors point to (AALIM, health care) does not supply the kind of distance metric the framework needs. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: the claim that a metric could be obtained in practice: the nearest existing system DOES NOT (YET?) PROVIDE THE DISTANCE METRIC THAT OUR APPROACH REQUIRES	`limitations[6]`		the tagger's words
limitations	A widely used fairness criterion can hold while the outcome is, in the authors' words, blatantly unfair to an individual. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: statistical parity used as evidence that a classifier is fair: the authors give examples in which statistical parity is maintained while the outcome from an individual's point of view is blatantly unfair	`limitations[7]`	1.0	the tagger's words
limitations	The metric the formal guarantee consumes is a social agreement that is expected to change. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: any fairness guarantee obtained in this framework: when ground truth is unavailable the metric may reflect the best available approximation as agreed upon by society, and is assumed to be public and open to continual refinement	`limitations[8]`	1.0	the tagger's words
limitations	The bridge from individual fairness to group fairness holds only under a stated distance condition. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: the claim that individual fairness delivers group fairness: it holds Quotation withheld	`limitations[9]`	1.0	the tagger's words
limitations	The population the metric is defined over is a modelling choice the authors flag. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: the scope of the fairness guarantee proved here: the authors state they have assumed the set is that of real individuals rather than all possible encodings of individuals	`limitations[10]`	1.0	the tagger's words
transfers	differential-privacy tools and a Lipschitz metric formalism applied to define and enforce fairness in classification Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`transfers[0]`		the tagger's words
concepts	statistical parity Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: statistical parity	`concepts[4]`		the paper's words
concepts	group fairness Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: group fairness	`concepts[5]`		the paper's words
concepts	Lipschitz condition Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: Lipschitz condition	`concepts[6]`		the paper's words
concepts	Earthmover distance Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: Earthmover distance	`concepts[7]`		the paper's words
concepts	fairness through blindness Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: fairness through blindness	`concepts[8]`		the paper's words
senses	fairness - INDIVIDUAL VERSUS GROUP, AND THE SECOND CAN HOLD WHILE THE FIRST FAILS: individual fairness is the principle that two people similar for a task be classified similarly, statistical parity is a property of demographics in aggregate, and the paper's examples keep the second while the first is blatantly violated Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[0]`	1.0	the tagger's words
senses	the similarity metric - AS SOCIETY'S CURRENT BEST APPROXIMATION: where no ground truth exists the metric stands in for one by agreement, is meant to be public and revisable, and is the input on which every formal result in the paper depends Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[1]`	1.0	the tagger's words
senses	fairness as a principle - TREAT SIMILAR INDIVIDUALS SIMILARLY: the paper's whole notion is one sentence, and everything formal in it is machinery for making 'similar' precise, which is why the metric carries the weight rather than the definition Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[2]`	1.0	the tagger's words
claim_relations	contradicts → statistical parity as a notion of fairness 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_relations	builds-on → differential privacy (tools applied to fairness) 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_relations	extends → differential privacy [Dwo06, DMNS06] 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_relations	builds-on → the exponential mechanism [MT07] Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`claim_relations[3]`		the tagger's words
claim_relations	builds-on → the Earthmover relaxation for metric labeling and 0-extension [KT02, CKNZ04] Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`claim_relations[4]`		the tagger's words
concept_edges	statistical parity —same-as→ group fairness Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. strength of the relation: 1 also in: statistical parity · group fairness	`concept_edges[0]`		the tagger's words
concept_edges	Lipschitz condition —causes→ statistical parity Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. holds when: only when the Earthmover distance between the two groups is small · strength of the relation: 1 also in: Lipschitz condition · statistical parity	`concept_edges[1]`		the tagger's words
content_tags	An algorithm maximizes utility subject to the fairness constraint that similar individuals are treated similarly. 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_tags	An adaptation guarantees statistical parity: the demographics of those receiving any classification match the demographics of the underlying population. 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_tags	task-specific metric Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: task-specific metric	`content_tags.variables[0]`		the tagger's words
content_tags	fairness constraint Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: fairness constraint	`content_tags.variables[2]`		the tagger's words
content_tags	utility Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: utility	`content_tags.variables[3]`		the tagger's words
content_tags	fairness constraint Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: fairness constraint	`content_tags.definitions[0]`		the tagger's words
content_tags	statistical parity Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: statistical parity	`content_tags.definitions[1]`		the tagger's words
content_tags	Lipschitz condition on the classifier Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: Lipschitz condition on the classifier	`content_tags.definitions[2]`		the tagger's words
content_tags	statistical-significance Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: statistical-significance	`content_tags.statistics[1]`		the tagger's words

Interpretive choices

Tags that could not be placed in the text:

none — every tag was located 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.