phenomenon · claim-type · cross-domain-transfer · mechanism · claim-relation · replication-status · limitation — grounded in the full text| phenomenon | human trust in individual predictions of black-box classifiers— “Understanding the reasons behind predictions is, however, quite important in assessing trust, which is fundamental if one plans to take action based on a prediction, or when choosing whether to deploy a new model.” | |
| claim-type | method— “In this work, we propose LIME, a novel explanation technique that explains the predictions of any classifier in an interpretable and faithful manner, by learning an interpretable model locally around the prediction.” | |
| method — evidence | — “We proposed LIME, a modular and extensible approach to faithfully explain the predictions of any model in an interpretable manner.” | |
| mechanism | THE EXPLANATION'S VOCABULARY IS NOT THE MODEL'S: an interpretable representation is defined separately from the features the classifier actually uses - presence or absence of a word, or of a contiguous patch of similar pixels - while the model may work over embeddings or a three-channel tensor— “Before we present the explanation system, it is important to distinguish between features and interpretable data representations. As mentioned before, interpretable explanations need to use a representation that is understandable to humans, regardless of the actual features used by the model. For example, a possible interpretable… | mechanisms[0] |
| mechanism | INTERPRETABILITY IS DEFINED AS AUDIENCE-RELATIVE, not as a property of the model class: the authors state that a linear model, a gradient vector or an additive model MAY OR MAY NOT be interpretable, because the criterion has to take the user's limitations into account— “An essential criterion for explanations is that they must be interpretable, i.e., provide qualitative understanding between the input variables and the response. We note that interpretability must take into account the user’s limitations. Thus, a linear model [24], a gradient vector [2] or an additive model [6] may or may not be… | mechanisms[1] |
| mechanism | and the audience-relativity is made concrete rather than left as a caveat: practitioners may be able to read a small Bayesian network where laymen are better served by a few weighted features— “Finally, we note that the notion of interpretability also depends on the target audience. Machine learning practitioners may be able to interpret small Bayesian networks, but laymen may be more comfortable with a small number of weighted features as an explanation.” | mechanisms[2] |
| mechanism | THE IMPOSSIBILITY IS STATED BEFORE THE CRITERION IS WEAKENED: an explanation cannot be completely faithful unless it IS the complete description of the model, so the requirement imposed instead is that it be faithful in the vicinity of the instance being explained— “Although it is often impossible for an explanation to be completely faithful unless it is the complete description of the model itself, for an explanation to be meaningful it must at least be locally faithful, i.e. it must correspond to how the model behaves in the vicinity of the instance being predicted.” | mechanisms[3] |
| mechanism | AND THE IMPLICATION IS STATED TO RUN ONE WAY ONLY: local fidelity does not imply global fidelity - a feature that matters globally may not matter locally, and the reverse - while global fidelity would imply local, and globally faithful interpretable explanations are said to remain a challenge— “We note that local fidelity does not imply global fidelity: features that are globally important may not be important in the local context, and vice versa. While global fidelity would imply local fidelity, identifying globally faithful explanations that are interpretable remains a challenge for complex models.” | mechanisms[4] |
| mechanism | the explainer is required to treat the model as a BLACK BOX, and the reason given is not only that current classifiers are uninterpretable but that model-agnosticism buys the ability to explain classifiers that do not exist yet Quotation withheld — our stored copy of this sentence carries a text-extraction fault (two words run together), so it is not what the paper says. The tag itself stands; the sentence is being re-fetched. | mechanisms[5] |
| mechanism | THE TRADE-OFF IS PUT IN THE OBJECTIVE RATHER THAN LEFT TO JUDGEMENT: unfaithfulness in the neighbourhood is minimised while a separate measure of the explanation's own complexity is held low enough for a human to read, and the authors note the same formulation admits different explanation families, fidelity functions and complexity measures— “In order to ensure both interpretability and local fidelity, we must minimize L(f, g, πx) while having Ω(g) be low enough to be interpretable by humans. The explanation produced by LIME is obtained by the following: ξ(x) = argmin L(f, g, πx) + Ω(g) (1) g∈G This formulation can be used with different explanation families” | mechanisms[6] |
| mechanism | the neighbourhood is explored BY SAMPLING rather than by assumption, precisely to keep the method model-agnostic: no assumption is made about the model, and the local loss is approximated by drawing samples weighted by proximity to the instance— “We want to minimize the locality-aware loss L(f, g, πx) without making any assumptions about f , since we want the explainer to be model-agnostic. Thus, in order to learn the local behavior of f as the interpretable inputs vary, we approximate L(f, g, πx) by drawing samples, weighted by πx.” | mechanisms[7] |
| mechanism | samples are drawn both near the instance and FAR from it, weighted by proximity - which is what lets a globally complex model still be approximated locally, and what the authors say makes the method fairly robust to sampling noise— “The primary intuition behind LIME is presented in Figure 3, where we sample instances both in the vicinity of x (which have a high weight due to πx) and far away from x (low weight from πx). Even though the original model may be too complex to explain globally, LIME presents an explanation that is locally faithful (linear in this case), where… | mechanisms[8] |
| mechanism | A CLASSIFIER AT 94% HELD-OUT ACCURACY IS SHOWN TO BE UNTRUSTWORTHY BY ITS EXPLANATIONS: the words it relies on are said to have no connection to either class, and one of them appears in 22% of training examples with 99% of those in a single class - and removing the headers only substitutes the names of prolific posters, which would not generalise either— “Although this classifier achieves 94% held-out accuracy, and one would be tempted to trust it based on this, the explanation for an instance shows that predictions are made for quite arbitrary reasons (words “Posting”, “Host”, and “Re” have no connection to either Christianity or Atheism). The word “Posting” appears in 22% of examples in the… | mechanisms[9] |
| builds-on | model-agnostic explanation by learning an interpretable model on the original model's predictions [2, 7, 22]— “A common approach to model-agnostic explanation is learning a potentially interpretable model on the predictions of the original model [2, 7, 22].” | claim_relations[0] |
| extends | prior perturbation-based explanation work [24]— “The idea of perturbing inputs for explanations has been explored before [24], where the authors focus on learning a specific contribution model, as opposed to our general framework.” | claim_relations[1] |
| builds-on | the 1-1/e greedy approximation guarantee for submodular coverage maximisation [15]— “Due to submodularity, a greedy algorithm that iteratively adds the instance with the highest marginal coverage gain to the solution offers a constant-factor approximation guarantee of 1−1/e to the optimum [15].” | claim_relations[2] |
| sense | trust - SENSE 1, IN A PREDICTION: whether a user is willing to act on one individual output, which is the question an explanation of a single prediction addresses— “It is important to differentiate between two different (but related) definitions of trust: (1) trusting a prediction” | senses[0] |
| sense | interpretability - AUDIENCE-RELATIVE: it depends on the target audience, so practitioners may read a small Bayesian network while laymen need a few weighted features, and the same artefact is interpretable for one and not the other— “Finally, we note that the notion of interpretability also depends on the target audience. Machine learning practitioners may be able to interpret small Bayesian networks, but laymen may be more comfortable with a small number of weighted features as an explanation” | senses[1] |
| sense | fidelity - LOCAL AND GLOBAL, AND THE IMPLICATION RUNS ONE WAY ONLY: local fidelity does not give global fidelity, and features that matter globally may not matter locally— “We note that local fidelity does not imply global fidelity: features that are globally important may not be important in the local context” | senses[2] |
| control | the explanation-based trust assessment checked against human experts — held — rules out an explanation that satisfies a metric without helping a person - the human check is the only thing that can test a claim about trust— “These results demonstrate that the trust assessments provided by SP-selected LIME explanations are good indicators of generalization, which we validate with human experiments in the next section.” | controls[0] |
| edge | local fidelity —distinct-from→ global fidelity— “We note that local fidelity does not imply global fidelity: features that are globally important may not be important in the local context” | concept_edges[0] |
| outcome (stated by the tagger, no quotation) | control — held | controls[0] |
| for which use | limitation — the reach of any explanation the method produces: it works BY LEARNING AN INTERPRETABLE MODEL LOCALLY AROUND THE PREDICTION, so faithfulness is local and not global— “by learning an interpretable model locally around the prediction” | limitations[0] |
| for which use | limitation — the choice of interpretable representation: CERTAIN INTERPRETABLE REPRESENTATIONS WILL NOT BE POWERFUL ENOUGH TO EXPLAIN CERTAIN BEHAVIORS— “First, while the underlying model can be treated as a black-box, certain interpretable representations will not be powerful enough to explain certain… | limitations[1] |
| for which use | limitation — any guarantee that an explanation exists at all: IF THE UNDERLYING MODEL IS HIGHLY NON-LINEAR EVEN IN THE LOCALITY OF THE PREDICTION, THERE MAY NOT BE A FAITHFUL EXPLANATION | limitations[2] |
| for which use | limitation — image applications of the global pick step: HOW TO PERFORM THE PICK STEP FOR IMAGES ... WE WOULD LIKE TO ADDRESS THIS LIMITATION IN THE FUTURE | limitations[3] |
| for which use | limitation — the husky-versus-wolf human-subject result: ALTHOUGH OUR SAMPLE SIZE IS SMALL 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. | limitations[4] |
| for which use | limitation — any claim that a method produces interpretable explanations: interpretability is stated to depend on the user's limitations, so a linear model, a gradient vector or an additive model may or may not be interpretable depending on the audience 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. | limitations[5] |
| for which use | limitation — an explanation read as a description of what the model computes: the input variables in the explanation may need to differ from the model's features, so the two are stated in different terms by design 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. | limitations[6] |
| for which use | limitation — an explanation offered as an account of the model: the paper states complete faithfulness is often impossible unless the explanation is the complete description of the model, so what is offered instead is local fidelity 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. | limitations[7] |
| replication | untested | |
| limitation | explanations are only locally faithful (learned locally around each prediction) 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. | limitations[0] |
| limitation | Some model behaviours cannot be captured at all by the chosen interpretable representation. 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. | limitations[1] |
| limitation | Sparse linear explanations may be unfaithful where the underlying model is highly non-linear even locally. 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. | limitations[2] |
| limitation | The submodular pick step is not worked out for images. 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. | limitations[3] |
| limitation | The husky-versus-wolf human-subject experiment had a small sample. 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. | limitations[4] |
| limitation | Interpretability is a property of the reader, not of the explanation: the same model may or may not be interpretable depending on who is looking at it. 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. | limitations[5] |
| limitation | The vocabulary of the explanation is deliberately not the vocabulary of the model. 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. | limitations[6] |
| limitation | Complete faithfulness is stated to be impossible short of reproducing the model itself. 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. | limitations[7] |
finding · quantity · variable · definition · key-term — grounded in the full text| finding | LIME explains the predictions of any classifier in an interpretable and faithful way by learning an interpretable model locally around each prediction. 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.findings[0] |
| evidence status note | finding — QUOTE REPAIRED: the extractor split a hyphen-space and the quote was recorded faithfully with the damage in it, which made it unanchorable. The repaired string is an EXACT SUBSTRING of the staged text - that is why it was accepted, not because a rule produced it. The text as originally recorded is kept in evidence as extracted. | content_tags.findings[0] |
| finding | SP-LIME selects a set of representative instances with explanations to address the problem of trusting the model. 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.findings[1] |
| definition | LIME 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] |
| evidence status note | definition — QUOTE REPAIRED: the extractor split a hyphen-space and the quote was recorded faithfully with the damage in it, which made it unanchorable. The repaired string is an EXACT SUBSTRING of the staged text - that is why it was accepted, not because a rule produced it. The text as originally recorded is kept in evidence as extracted. | content_tags.definitions[0] |
| definition | model-agnostic explanation 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] |
| key-terms | explanation, prediction, model, interpretable, classifier, trust, faithful, features, LIME |
| concept | interpretability 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[0] |
| concept | local fidelity 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 | global fidelity 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 | LIME 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 | model-agnostic 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] |
| Bayesian | 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[0] |
| mean μ | as written: average of 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] |
| regression β | as written: logistic regression 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[3] |
| sample-size n/N | 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[4] |
| evidence status note | sample-size — QUOTE REPAIRED: the extractor split a hyphen-space and the quote was recorded faithfully with the damage in it, which made it unanchorable. The repaired string is an EXACT SUBSTRING of the staged text - that is why it was accepted, not because a rule produced it. The text as originally recorded is kept in evidence as extracted. | content_tags.statistics[4] |
| standard-error SE | as written: standard errors 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[5] |
| 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[6] |
| claim type | method — a second reading reaching the same value; recorded: method 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. | alternatives.claim_type |
| method | system-or-tool-building — a second reading reaching the same value; recorded: system-or-tool-building 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. | alternatives.method |
| phenomenon | trust in the predictions of black-box classifiers, and whether a prediction can be understood well enough to act on — a second reading DIFFERING from the recorded value; recorded: human trust in individual predictions of black-box classifiers 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. | alternatives.phenomenon |
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