(cid:NN). The PDF this text was extracted from encodes 1 character 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.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 WITHDRAWN AND REPLACED — the entry was wrong, and a corrected version of it appears in the entries below.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 An entry we have WITHDRAWN is removed from this page and kept in the record, with its reason.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.| 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 |
| contribution | contribution | what the paper claims to add |
| control | controls | an experiment run to eliminate a rival explanation |
| 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 |
| object of study | object_of_study | what the paper is about — the thing it investigates |
| phenomenon | phenomenon | the effect or regularity under study |
| research question | research_question | the question the paper sets itself |
| 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 |
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; 2 of 2 relations here carry that mark. The rest are the tagger’s reading of the sentence quoted beside them.
| facet | tag | field | conf. | whose words |
|---|---|---|---|---|
| object_of_study | when a classifier trained on one distribution can be expected to work on another, and how to weight source against target data when a little labelled target data exists Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | object_of_study | the paper's words | |
| research_question | what quantity, estimable from unlabeled samples, bounds the target error of a source-trained classifier Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | research_question | the paper's words | |
| contribution | a classifier-induced divergence that can be estimated from finite unlabeled samples, and a bound in which the target error is the source error plus that divergence plus the error of the ideal joint hypothesis Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | contribution | the paper's words | |
| claim_type | mechanism 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 | domain adaptation - training where the labels are and deploying where they are not, with a theory whose usable half is the half that can be computed without labels 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 | mathematical-proof Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: mathematical-proof | method | the paper's words | |
| mechanisms | the L1 divergence takes a supremum over all measurable subsets and is rejected as unestimable and over-strict; the H-divergence takes it over the hypothesis class. So the distance between two FIXED distributions is a function of H - a richer class sees the domains as further apart, and the bound loosens because the model got more expressive rather than because the data moved Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | mechanisms[0] | 0.95 | the tagger's words |
| mechanisms | label every unlabeled source instance 0 and every unlabeled target instance 1, train a classifier to tell them apart, and read the divergence off its error. If the domains are indistinguishable to H the divergence is zero. The measurement IS the adversary, which is why the whole domain-adversarial literature follows from this paragraph Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | mechanisms[1] | 0.95 | the tagger's words |
| mechanisms | target error is bounded by source error plus divergence plus lambda. The first two come from unlabeled data. Lambda is the error of the best joint hypothesis and needs labelled target data to evaluate - the thing the setting is defined by not having. THE BOUND IS USABLE EXACTLY WHEN ITS UNCHECKABLE TERM IS SMALL Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: the third term is the assumption | mechanisms[2] | 0.95 | the tagger's words |
| mechanisms | two domains can differ in their labeling functions as well as in their input distributions. One clause - `since we expect the labeling function difference to be small in practice` - removes the first from the theory. Everything downstream measures distributional shift and inherits the assumption without restating it Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | mechanisms[3] | 0.95 | the tagger's words |
| mechanisms | computing the H-divergence needs the minimum-error hypothesis for the source-versus-target problem, which is intractable for most classes. What is used instead is the error of a hypothesis minimising a convex upper bound - so the reported divergence is an approximation of an approximation, and the paper says so Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | mechanisms[4] | 0.95 | the tagger's words |
| limitations | the bound is only useful when the ideal joint hypothesis has small error, and that error cannot be estimated without labelled target data Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | limitations[0] | 0.95 | the tagger's words |
| limitations | the difference between the two domains' labeling functions is assumed small rather than measured Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | limitations[1] | 0.95 | the tagger's words |
| limitations | minimising error to compute the H-divergence is computationally intractable for most hypothesis classes, so a convex surrogate is used Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | limitations[2] | 0.95 | the tagger's words |
| limitations | common divergences such as L1 and Kullback-Leibler cannot be accurately estimated from finite samples in a distribution-free setting Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | limitations[3] | 0.95 | the tagger's words |
| limitations | with enough labelled target data the source data is never preferred, no matter how much of it there is - the method's value is bounded by target-label scarcity Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | limitations[4] | 0.95 | the tagger's words |
| limitations | the practical recommendation holds only given a reasonable measure of complexity Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | limitations[5] | 0.95 | the tagger's words |
| transfers | a divergence built for change detection in data streams, taken into statistical learning theory as the domain-distance term of a generalisation bound Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | transfers[0] | 0.95 | the tagger's words |
| transfers | binary classification itself used as a measuring instrument - a discriminator trained to separate two unlabeled samples, with its error read as a distance Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | transfers[1] | 0.95 | the tagger's words |
| controls | the H-divergence checked against the L1 divergence on both counts that matter - estimability from finite samples and tightness of the resulting bound Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. eliminates: a new measure adopted for convenience - it is shown never to be larger than the one it replaces, so the bound cannot have been loosened to make it work · outcome: held | controls[0] | 0.95 | the tagger's words |
| controls | the bound's behaviour examined at both extremes of lambda rather than only where it is convenient Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. eliminates: a bound that is quietly vacuous when adaptation is impossible - the paper states plainly that a large lambda means no classifier serves both domains · outcome: held | controls[1] | 0.95 | the tagger's words |
| controls | the intractability of computing the H-divergence stated, with the convex surrogate named as an approximation rather than presented as the quantity Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. eliminates: a reported divergence being read as the defined one - the gap between them is declared at the point the substitution is made · outcome: held | controls[2] | 0.95 | the tagger's words |
| controls | source domains at varying distance compared against target-only training as labelled target data increases Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. eliminates: the claim that source data always helps - with enough target labels it never does, whatever its volume · outcome: failed | controls[3] | 0.95 | the tagger's words |
| controls | the relation to Crammer et al. (2008) worked out, with the conditions under which the two measures coincide Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. eliminates: that the two divergence measures differ in the cases that matter - the conditions under which they coincide are what would settle it · outcome (stated by the tagger, no quotation): absent-stated-about-other | controls[4] | 0.95 | the tagger's words |
| concepts | H-divergence Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: H-divergence | concepts[0] | 0.95 | the paper's words |
| concepts | L1 divergence Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: L1 divergence | concepts[1] | 0.95 | the paper's words |
| concepts | ideal joint hypothesis Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: ideal joint hypothesis | concepts[2] | 0.95 | the paper's words |
| concepts | adaptability Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: adaptability | concepts[3] | 0.95 | the paper's words |
| concepts | labeling function Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: labeling function | concepts[4] | 0.95 | the paper's words |
| concepts | distribution divergence Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: distribution divergence | concepts[5] | 0.95 | the paper's words |
| concepts | VC dimension Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: VC dimension | concepts[6] | 0.95 | the paper's words |
| concepts | source domain Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: source domain | concepts[7] | 0.95 | the paper's words |
| concepts | target domain Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: target domain | concepts[8] | 0.95 | the paper's words |
| concepts | hypothesis classes Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: hypothesis classes | concepts[9] | 0.95 | the paper's words |
| senses | divergence between domains - AS L1: a supremum over all measurable subsets, which cannot be accurately estimated from finite samples and unnecessarily inflates the bound Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | senses[0] | 0.95 | the tagger's words |
| senses | divergence between domains - AS H-DIVERGENCE: a supremum over the hypothesis class only, estimable from finite unlabeled samples and never larger than L1 Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | senses[1] | 0.95 | the tagger's words |
| senses | the domain difference - THE PART MEASURED: the divergence between the two marginal distributions Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | senses[2] | 0.95 | the tagger's words |
| senses | the domain difference - THE PART ASSUMED AWAY: the difference between the two labeling functions, expected to be small in practice and not measured Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | senses[3] | 0.95 | the tagger's words |
| senses | lambda - AS A TERM IN THE BOUND: the combined error of the hypothesis that minimises source plus target error Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | senses[4] | 0.95 | the tagger's words |
| senses | lambda - AS AN ASSUMPTION: adaptability itself. If it is large there is no classifier good on both domains and no hope from source training; if small, the H-divergence carries the bound - and which of the two holds cannot be checked without labelled target data Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | senses[5] | 0.95 | the tagger's words |
| claim_relations | critiques → the use of L1 and Kullback-Leibler divergence in domain adaptation, on the grounds that neither can be accurately estimated from finite samples in a distribution-free setting Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | claim_relations[0] | 0.95 | the tagger's words |
| claim_relations | extends → Kifer et al. 2004's divergence for change detection, carried into a learning bound Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | claim_relations[1] | 0.95 | the tagger's words |
| claim_relations | distinguishes-from → Crammer et al. 2008, whose bound is less general and does not handle positive H-delta-H divergence or non-uniform weighting Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | claim_relations[2] | 0.95 | the tagger's words |
| claim_relations | qualifies → its own bound, by stating that it is informative only when the ideal joint hypothesis has small error - a quantity the setting cannot supply Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | claim_relations[3] | 0.95 | the tagger's words |
| concept_edges | H-divergence —distinct-from→ L1 divergence Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. differs in: what set the supremum runs over, and therefore whether the distance can be estimated · the relation itself is separately evidenced · strength of the relation: 0.95 · differs in (stated by the tagger, no quotation): what set the supremum runs over, and therefore whether the distance can be estimated · the relation stated: the H-divergence is estimable from finite samples for classes of finite VC dimension and is never larger than the L1 divergence, because its supremum runs over the hypothesis class rather than over all measurable subsets also in: H-divergence · L1 divergence | concept_edges[0] | 0.95 | the tagger's words |
| concept_edges | labeling function —distinct-from→ distribution divergence Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. differs in: which of the two ways a domain can shift the theory actually measures · the relation itself is separately evidenced · strength of the relation: 0.95 · differs in (stated by the tagger, no quotation): which of the two ways a domain can shift the theory actually measures · the relation stated: two domains can differ in their labeling functions or in their distributions; the labeling difference is expected to be small in practice and the paper measures the other one
Audit 2026-09-28: DOUBTFUL - read against its full span and kept, but the span sets the labeling-function difference aside to focus on distribution divergence; distinct-from is loose. also in: labeling function · distribution divergence | concept_edges[2] | 0.95 | the tagger's words |
| content_tags | A classifier-induced divergence estimable from unlabeled samples, with the empirical source error, characterizes a source-trained classifier's target error, assuming some hypothesis performs well in both domains. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | content_tags.findings[0] | 0.95 | the tagger's words |
| content_tags | when the ideal joint hypothesis has large error, no classifier performs well on both domains and source training cannot help Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | content_tags.findings[1] | 0.95 | the tagger's words |
| content_tags | the H-divergence is computed by training a classifier to distinguish source from target instances and reading it off the error Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | content_tags.findings[2] | 0.95 | the tagger's words |
| content_tags | the H-divergence is never larger than the L1 divergence and is generally smaller when H has finite VC dimension Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | content_tags.findings[3] | 0.95 | the tagger's words |
| content_tags | the difference between the two domains' labeling functions is assumed small rather than measured Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | content_tags.findings[4] | 0.95 | the tagger's words |
| content_tags | computing the H-divergence exactly is intractable for most hypothesis classes; convex surrogates are used to approximate it Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | content_tags.findings[5] | 0.95 | the tagger's words |
| content_tags | with enough labelled target data, target-only training is always preferred no matter how much source data is available Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | content_tags.findings[6] | 0.95 | the tagger's words |
| content_tags | a divergence whose supremum runs over the hypothesis class rather than over all measurable subsets - estimable from finite unlabeled samples when H has finite VC dimension, and never larger than L1 Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: H-divergence | content_tags.definitions[0] | 0.95 | the tagger's words |
| content_tags | what the ideal joint hypothesis embodies - whether any single classifier can perform well on both domains at once Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: adaptability | content_tags.definitions[1] | 0.95 | the tagger's words |
| content_tags | VC dimension Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: VC dimension | content_tags.statistics[0] | 0.95 | the tagger's words |
| content_tags | distribution divergence Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: distribution divergence | content_tags.variables[0] | 0.95 | the tagger's words |
| content_tags | labeling function Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: labeling function | content_tags.variables[1] | 0.95 | the tagger's words |
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.