phenomenon · claim-type · cross-domain-transfer · mechanism · claim-relation · replication-status · limitation — grounded in the full text| phenomenon | fairness in classification— “In this work, we study fairness in classification.” | |
| claim-type | method— “The main conceptual contribution of this paper is a framework for fair classification comprising (1) a (hypothetical) task-specific metric for determining the degree to which individuals are similar with respect to the classification task at hand; (2) an algorithm for maximizing utility subject to the fairness constraint, that similar… | |
| method — evidence | — “Our framework permits us to formulate the question as an optimization problem that can be solved by a linear program.” | |
| transfer | from computer science (differential privacy) / mathematics: differential-privacy tools and a Lipschitz metric formalism applied to define and enforce fairness in classification— “how tools developed in the context of differential privacy may be applied to fairness” | transfers[0] |
| mechanism | 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— “We formalize this guiding principle as a Lipschitz condition on the classifier” | mechanisms[0] |
| contradicts | statistical parity as a notion of fairness— “which statistical parity is maintained, but from the point of view of an individual, the outcome is blatantly unfair. While statistical parity (or group fairness) is insufficient by itself, we investigate conditions under which our notion of fairness implies statistical parity.” | claim_relations[0] |
| builds-on | differential privacy (tools applied to fairness)— “tools developed in the context of differential privacy may be applied to fairness” | claim_relations[1] |
| extends | differential privacy [Dwo06, DMNS06]— “We observe that our definition of fairness is a generalization of the notion of differential privacy [Dwo06, DMNS06].” | claim_relations[2] |
| builds-on | the exponential mechanism [MT07]— “Our mechanism is based on the exponential mechanism [MT07], first considered in the context of differential privacy.” | claim_relations[3] |
| builds-on | the Earthmover relaxation for metric labeling and 0-extension [KT02, CKNZ04]— “The approach is inspired by the use of the Earthmover relaxation in the context of metric labeling and 0-extension [KT02, CKNZ04].” | claim_relations[4] |
| sense | 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— “Statistical parity speaks to group fairness rather than individual fairness, and appears desirable, as it equalizes outcomes across protected and non-protected groups” | senses[0] |
| sense | 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— “When ground truth is unavailable, the metric may reflect the “best” available approximation as agreed upon by society. Following established tradition [Raw01], the metric is assumed to be public and open to discussion and continual refinement” | senses[1] |
| sense | 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— “We capture fairness by the principle that any two individuals who are similar with respect to a particular task should be classified similarly” | senses[2] |
| edge | statistical parity —same-as→ group fairness— “Statistical parity speaks to group fairness rather than individual fairness, and appears desirable, as it equalizes outcomes across protected and non-protected groups” | concept_edges[0] |
| holds when | Lipschitz condition —causes→ statistical parity — only when the Earthmover distance between the two groups is small— “we show that the Lipschitz condition implies statistical parity between two groups if and only if the Earthmover distance between the two groups is small”— “if and only if the Earthmover distance between the two groups is small” | concept_edges[1] |
| for which use | limitation — every guarantee the framework offers: it assumes A TASK-SPECIFIC SIMILARITY METRIC DESCRIBING THE EXTENT TO WHICH PAIRS OF INDIVIDUALS SHOULD BE REGARDED AS SIMILAR - supplied from outside the definition— “a task-specific similarity metric describing the extent to which pairs of individuals should be regarded as similar” | limitations[0] |
| for which use | limitation — 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]— “Justifying the availability of or access to the distance metric in various settings is one of the most challenging aspects of our framework, and in reality the metric used will most likely only be society’s current best approximation to the truth.” | limitations[1] |
| for which use | limitation — the loss claim for the general fairness LP: THE RESULT HOWEVER DOES NOT GIVE A CONCRETE QUANTITATIVE BOUND ON THE RESULTING LOSS— “The result however does not give a concrete quantitative bound on the resulting loss.” | limitations[2] |
| for which use | limitation — 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— “Thus, 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] |
| for which use | limitation — the Earthmover characterisation: for biasD-infinity WE DO NOT GET A TIGHT CHARACTERIZATION— “The situation for biasD∞, d is somewhat more complicated and we do not get a tight characterization in terms of an Earthmover distance.” | limitations[4] |
| for which use | limitation — 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— “Further research into the feasibility of this approach is needed, in particular, our discussion throughout this paper has assumed that a single metric is used across the board.” | limitations[5] |
| for which use | limitation — 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— “This work could serve as a starting point in the fairness setting, although it does not (yet?) provide the distance metric that our approach requires.” | limitations[6] |
| for which use | limitation — 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— “However, we demonstrate its inadequacy as a notion of fairness through several examples in which statistical parity is maintained, but from the point of view of an individual, the outcome is blatantly unfair” | limitations[7] |
| for which use | limitation — 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— “When ground truth is unavailable, the metric may reflect the “best” available approximation as agreed upon by society. Following established tradition [Raw01], the metric is assumed to be public and open to discussion and continual refinement” | limitations[8] |
| for which use | limitation — the claim that individual fairness delivers group fairness: it holds if and only if the Earthmover distance between the two groups is small— “we show that the Lipschitz condition implies statistical parity between two groups if and only if the Earthmover distance between the two groups is small” | limitations[9] |
| for which use | limitation — 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— “When dealing with the set V, we have assumed that V is the set of real individuals (rather than the potentially huge set of all possible encodings of individuals).” | limitations[10] |
| replication | untested | |
| limitation | the approach assumes a task-specific similarity metric, which is hard to define— “a task-specific similarity metric describing the extent to which pairs of individuals should be regarded as similar” | limitations[0] |
| limitation | Obtaining or justifying the task-specific similarity metric the framework depends on is the hardest part, and any real metric will be an approximation.— “Justifying the availability of or access to the distance metric in various settings is one of the most challenging aspects of our framework, and in reality the metric used will most likely only be society’s current best approximation to the truth.” | limitations[1] |
| limitation | The general fairness LP gives no quantitative bound on the loss it incurs.— “The result however does not give a concrete quantitative bound on the resulting loss.” | limitations[2] |
| limitation | 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.— “Thus, 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] |
| limitation | No tight Earthmover characterisation is obtained for the relative-infinity distance version of the bias.— “The situation for biasD∞, d is somewhat more complicated and we do not get a tight characterization in terms of an Earthmover distance.” | limitations[4] |
| limitation | The whole treatment assumes one metric applied uniformly to everyone; per-user or plural metrics are untested.— “Further research into the feasibility of this approach is needed, in particular, our discussion throughout this paper has assumed that a single metric is used across the board.” | limitations[5] |
| limitation | The nearest existing similarity system the authors point to (AALIM, health care) does not supply the kind of distance metric the framework needs.— “This work could serve as a starting point in the fairness setting, although it does not (yet?) provide the distance metric that our approach requires.” | limitations[6] |
| limitation | A widely used fairness criterion can hold while the outcome is, in the authors' words, blatantly unfair to an individual.— “However, we demonstrate its inadequacy as a notion of fairness through several examples in which statistical parity is maintained, but from the point of view of an individual, the outcome is blatantly unfair” | limitations[7] |
| limitation | The metric the formal guarantee consumes is a social agreement that is expected to change. | limitations[8] |
| limitation | The bridge from individual fairness to group fairness holds only under a stated distance condition. | limitations[9] |
| limitation | The population the metric is defined over is a modelling choice the authors flag. | limitations[10] |
finding · quantity · variable · definition · key-term — grounded in the full text| finding | An algorithm maximizes utility subject to the fairness constraint that similar individuals are treated similarly. | content_tags.findings[0] |
| finding | An adaptation guarantees statistical parity: the demographics of those receiving any classification match the demographics of the underlying population. | content_tags.findings[1] |
| variable | task-specific metric (independent) Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.variables[0] |
| variable | fairness constraint (dependent) Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.variables[2] |
| variable | utility (dependent) Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.variables[3] |
| definition | fairness constraint Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.definitions[0] |
| definition | statistical parity Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.definitions[1] |
| definition | Lipschitz condition on the classifier Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.definitions[2] |
| key-terms | fairness, classification, individuals, similar, metric, utility, discrimination, parity |
| concept | statistical parity Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | concepts[4] |
| concept | group fairness Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | concepts[5] |
| concept | Lipschitz condition Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | concepts[6] |
| concept | Earthmover distance Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | concepts[7] |
| concept | fairness through blindness Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | concepts[8] |
| statistical-significance | as written: significantly Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.statistics[1] |
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.
Tag layer © the Meta-Tagging Project, CC BY 4.0. The paper text is © its authors/publisher
and is linked, not reproduced. Excerpts shown are short quotations for identification and verification.
· back to index
· concepts · authors
· עברית
© 2026 Shir Sivroni · ORCID 0009-0000-2597-2824