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 WITHDRAWN AND REPLACED — the entry was wrong, and a corrected version of it appears in the entries below.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 An entry we have WITHDRAWN is removed from this page and kept in the record, with its reason.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.| second reading | alternatives | an independent re-reading of a facet, recorded whether or not it agrees |
| 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; none 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 | the contribution of each individual input pixel to one non-linear classifier's decision on one image 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 | how to explain why a non-linear image classifier reached a particular decision, at the resolution of single pixels 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 | layer-wise relevance propagation - a heatmapping concept defined as a set of constraints rather than an algorithm - together with a Taylor-type alternative, both applicable to pre-trained Bag-of-Words and neural classifiers 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 | 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 | classifier opacity: a non-linear model gives a decision without saying what in the input produced it 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 | system-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 | method | the paper's words | |
| mechanisms | the relevance held by a unit is redistributed onto the units that fed it, and the total is preserved from one layer to the next, so the prediction survives intact all the way down to the pixels 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 | relevance is computed one layer at a time rather than globally, which is cheap but can strand relevance in a lower layer where it is then distributed randomly Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: greedy layer-at-a-time propagation | mechanisms[1] | 0.95 | the tagger's words |
| mechanisms | the gradient at the prediction point points toward the nearest local optimum, which may carry the SAME SIGN as the prediction - so it does not point at the boundary the explanation is relative to Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | mechanisms[2] | 0.95 | the tagger's words |
| mechanisms | a root is found by taking any candidate with the opposite prediction sign and searching the line between them - the segment must cross zero, so interval intersection locates 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 | the root point is specified by CONSTRAINTS rather than by a formula - it must be a root and must lie near the data point, with the rest deferred 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 |
| mechanisms | the two approaches differ in what they conserve: the earlier work rectifies activations to keep feature maps non-negative, this one uses SIGNED activations to conserve the relevance quantity across layers Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. about this quote: THE QUOTE'S SUBJECT IS A CITATION THE TEXT EXTRACTION DROPPED: the paper's sentence opens with a reference to earlier work, so what 'uses rectified linear units' is that work, which the paragraph compares with this paper's approach - not this paper. | mechanisms[5] | 0.95 | the tagger's words |
| limitations | the propagation is greedy - computed one layer at a time - and some relevance may hit a dead end in the lower layers and be distributed randomly 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 proposed propagation rules are heuristic: whether relevance proportional to weighted neuron activations can be analytically justified is open 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 | there is no way to evaluate the quality of a heatmap beyond looking at it 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 | no universal metric for quantifying heatmap quality exists; the paper defers it to future work 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 | a decomposition satisfying the conservation equation is neither unique nor guaranteed to be meaningful - the constraint set does not pin down an answer 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 Taylor approach needs a second point besides the input, and finding it is called a technical difficulty in the paper's own words 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 |
| limitations | where several minimal-norm roots exist the method must average or integrate over them rather than pick one Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | limitations[6] | 0.9 | the tagger's words |
| limitations | a competing method is specific to convolutional architectures, which the paper contrasts with its own range of applicability Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | limitations[7] | 0.9 | the tagger's words |
| transfers | the conservation law, taken from physics and imposed on relevance flowing between network layers Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | transfers[0] | 0.85 | the tagger's words |
| controls | a quantitative test that can separate two heatmaps which look equally good to a human Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. eliminates: two heatmapping methods being ranked on how good they look to a human, which is the judgement the paper exists to replace · outcome: partial | controls[0] | 0.95 | the tagger's words |
| controls | a counterexample testing whether the conservation constraint alone yields a meaningful decomposition Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. eliminates: the conservation constraint being credited with producing a meaningful decomposition when it constrains only the total · outcome: failed | controls[1] | 0.95 | the tagger's words |
| controls | application to a classifier the authors did not train, to show no retraining is needed Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. eliminates: a heatmapping result that depends on the authors having trained the classifier themselves · outcome: held | controls[2] | 0.95 | the tagger's words |
| concepts | pixel-wise decomposition Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: pixel-wise decomposition | concepts[0] | 0.95 | the paper's words |
| concepts | layer-wise relevance propagation Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: layer-wise relevance propagation | concepts[1] | 0.95 | the paper's words |
| concepts | relevance Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: relevance | concepts[2] | 0.95 | the paper's words |
| concepts | heatmap Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: heatmap | concepts[3] | 0.95 | the paper's words |
| concepts | conservation law Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: conservation law | concepts[4] | 0.95 | the paper's words |
| concepts | black box Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: black box | concepts[5] | 0.95 | the paper's words |
| concepts | pixel-flipping Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: pixel-flipping | concepts[6] | 0.95 | the paper's words |
| concepts | segmentation Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: segmentation | concepts[7] | 0.95 | the paper's words |
| concepts | pre-trained classifier Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: pre-trained classifier | concepts[8] | 0.95 | the paper's words |
| concepts | non-linearity Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: non-linearity | concepts[9] | 0.95 | the paper's words |
| concepts | Taylor reference point Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: Taylor reference point | concepts[10] | 0.85 | the paper's words |
| concepts | Taylor-type decomposition Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: Taylor-type decomposition | concepts[11] | 0.95 | the paper's words |
| concepts | root point Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: root point | concepts[12] | 0.95 | the paper's words |
| concepts | sensitivity maps Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: sensitivity maps | concepts[13] | 0.95 | the paper's words |
| concepts | Taylor residuum Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: Taylor residuum | concepts[14] | 0.9 | the paper's words |
| concepts | locally linear Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: locally linear | concepts[15] | 0.9 | the paper's words |
| senses | layer-wise relevance propagation = whatever satisfies the constraints; several different algorithms qualify 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 | R_d < 0 = evidence AGAINST the structure being present; R_d > 0 = evidence FOR it 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 | relevance at the output layer = the prediction f(x) itself 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 | heatmap = relevances mapped to a colour space - named, then explicitly put out of scope 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 | 'admissible' = satisfying the constraints, which is weaker than 'correct' and the paper says so Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | senses[4] | 0.85 | the tagger's words |
| alternatives | claim_type: method Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. a second reading reaching the same value. Recorded: method — note: A BLIND second reading by the project on 2026-08-25: the record's own claim type/method/phenomenon were not looked at until every value here was written and substring-verified. Not applied - a person decides. Sampling frame: the 504 staged records carrying no alternatives block, so this never re-measures the 202. All 11 records with 130+ tags were taken as a census and 19 more spread one per discipline across 22 disciplines - the dense non-neuroscience cell is the one the 202 do not contain (inside them, 94-100% of the densest bands are neuroscience; among these 11, one is)., | alternatives.claim_type | 0.9 | the tagger's words |
| alternatives | method: system-or-tool-building Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. a second reading DIFFERING from the recorded value. Recorded: system-or-tool-building — note: A BLIND second reading by the project on 2026-08-25: the record's own claim type/method/phenomenon were not looked at until every value here was written and substring-verified. Not applied - a person decides. Sampling frame: the 504 staged records carrying no alternatives block, so this never re-measures the 202. All 11 records with 130+ tags were taken as a census and 19 more spread one per discipline across 22 disciplines - the dense non-neuroscience cell is the one the 202 do not contain (inside them, 94-100% of the densest bands are neuroscience; among these 11, one is)., | alternatives.method | 0.8 | the tagger's words |
| alternatives | phenomenon: which parts of an input image drive a nonlinear classifier's decision Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. a second reading DIFFERING from the recorded value. Recorded: classifier opacity: a non-linear model gives a decision without saying what in the input produced it — note: A BLIND second reading by the project on 2026-08-25: the record's own claim type/method/phenomenon were not looked at until every value here was written and substring-verified. Not applied - a person decides. Sampling frame: the 504 staged records carrying no alternatives block, so this never re-measures the 202. All 11 records with 130+ tags were taken as a census and 19 more spread one per discipline across 22 disciplines - the dense non-neuroscience cell is the one the 202 do not contain (inside them, 94-100% of the densest bands are neuroscience; among these 11, one is)., | alternatives.phenomenon | 0.85 | the tagger's words |
| claim_relations | distinguishes-from → the standard task of optimising a classifier for accuracy and generalisation Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. note: the paper's framing move: explaining one decision is ORTHOGONAL to training a good classifier, so a better classifier does not make a better explanation | claim_relations[0] | the tagger's words | |
| claim_relations | critiques → the claim that non-linear models' success justifies their opacity Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. note: highly successful AND prevented from contributing understanding - the paper puts those in one sentence | claim_relations[1] | the tagger's words | |
| concept_edges | non-linearity —causes→ black box Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. direction on the measure: increases · strength of the relation: 0.95 · direction on the measure (stated by the tagger, no quotation): increases
Audit 2026-09-28: DOUBTFUL - read against its full span and kept, but endpoint by anaphora: 'This lack of interpretability' = the classifier acting as a black box (previous sentence). also in: non-linearity · black box | concept_edges[1] | the tagger's words | |
| concept_edges | relevance —part-of→ conservation law Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. strength of the relation: 0.85 · note: the conservation law is a property required OF relevance, which is why it constrains rather than computes it
Audit 2026-09-28: DOUBTFUL - read against its span and kept, but the formula is read as a conservation law for relevance; part-of is loose. also in: relevance · conservation law | concept_edges[2] | the tagger's words | |
| content_tags | a decomposition satisfying the layer-wise equation is neither unique nor necessarily meaningful 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 | a trivially valid decomposition makes every input point the same way as the prediction, which is not a realistic interpretation 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 method was applied to a third-party pre-trained ImageNet network without retraining. 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 | Further specification of the relevance propagation rule is deferred to the user or to future work. 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 | there is no direct relationship between a classifier's value at a point and its derivative at the same point, which is the first reason a gradient map is not an explanation 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 | Derivatives at the prediction point are not useful for the paper's aim. 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 | layer-wise relevance propagation needs no second reference point at all, which is the practical advantage claimed over Taylor decomposition 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 | In the example, the local-gradient explanation gives too large a contribution to an irrelevant direction. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | content_tags.findings[7] | 0.9 | the tagger's words |
| content_tags | pixel-wise decomposition Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: pixel-wise decomposition | content_tags.definitions[0] | 0.95 | the tagger's words |
| content_tags | layer-wise relevance propagation Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: layer-wise relevance propagation | content_tags.definitions[1] | 0.95 | the tagger's words |
| content_tags | relevance Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: relevance | content_tags.definitions[2] | 0.95 | the tagger's words |
| content_tags | heatmap Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: heatmap | content_tags.definitions[3] | 0.95 | the tagger's words |
| content_tags | pixel-flipping Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: pixel-flipping | content_tags.definitions[4] | 0.95 | the tagger's words |
| content_tags | the sign convention that makes a root the state of maximal uncertainty - positive means presence, negative means absence Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: state of maximal uncertainty | content_tags.definitions[5] | 0.95 | the tagger's words |
| content_tags | conservation of total relevance across layers Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | content_tags.statistics[0] | 0.95 | the tagger's words |
| content_tags | relevance Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: relevance | content_tags.variables[0] | 0.95 | the tagger's words |
| content_tags | prediction Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: prediction | 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.