(cid:NN). The PDF this text was extracted from encodes 4 characters 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.phenomenon · claim-type · cross-domain-transfer · mechanism · claim-relation · replication-status · limitation — grounded in the full text| phenomenon | pneumonia detection on chest radiographs— “However, detecting pneumonia in chest X-rays is a challenging task that relies on the availability of expert radiologists.” | |
| claim-type | method— “We develop an algorithm that can detect pneumonia from chest X-rays at a level exceeding practicing radiologists.” | |
| method — evidence | — “CheXNet is a 121-layer Dense Convolutional Network (DenseNet) (Huang et al., 2016) trained on the ChestX-ray 14 dataset.” | |
| transfer | from artificial intelligence (deep learning / computer vision): a deep convolutional network (DenseNet) applied to detect disease from chest X-rays at radiologist level— “a 121-layer convolutional neural network trained on ChestX-ray14” | transfers[0] |
| mechanism | the binary cross entropy is weighted by the prevalence of the OPPOSITE class - w+ is the negative share and w- the positive share - so the rarer label carries the larger weight— “For a single example in the training set, we optimize the weighted binary cross entropy loss L(X, y) = −w+ · y log p(Y = 1|X) −w− · (1 − y) log p(Y = 0|X), where p(Y = i|X) is the probability that the network assigns to the label i, w+ = |N |/(|P |+|N |), and w− = |P |/(|P |+|N |) with |P | and |N | the number of positive cases and negative… | mechanisms[0] |
| mechanism | dense connections improve the flow of information and gradients through the network, which is what the paper credits for making the optimization of a very deep network tractable— “DenseNets improve flow of information and gradients through the network, making the optimization of very deep networks tractable.” | mechanisms[1] |
| mechanism | the network is not trained from scratch: the final layer is replaced and the rest starts from ImageNet weights— “We replace the final fully connected layer with one that has a single output, after which we apply a sigmoid nonlinearity. The weights of the network are initialized with weights from a model pretrained on ImageNet” | mechanisms[2] |
| mechanism | the learning rate is cut only when the validation loss stops improving, and the returned model is the best validation checkpoint rather than the last— “We use an initial learning rate of 0.001 that is decayed by a factor of 10 each time the validation loss plateaus after an epoch, and pick the model with the lowest validation loss.” | mechanisms[3] |
| mechanism | each radiologist and the model are scored against the OTHER FOUR radiologists' labels, taken as ground truth, and the reported figure is the mean of those four scores that this makes reader agreement the standard rather than the presence of disease is already recorded on this record as a limitation, not claimed here— “We compute the F1 score for each individual radiologist and for CheXNet against each of the other 4 labels as ground truth. We report the mean of the 4 resulting F1 scores for each radiologist and for CheXNet, along with the average F1 across the radiologists.” | mechanisms[4] |
| mechanism | significance is taken from the DIFFERENCE between the two averages computed on the same bootstrap samples, and read off whether the 95% CI on that difference contains zero | mechanisms[5] |
| mechanism | the heatmap is the weighted sum of the final convolutional feature maps, weighted by the final classification layer's own weights for that pathology, then upscaled and overlaid 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. | mechanisms[6] |
| builds-on | convolutional neural networks (deep learning) 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. | claim_relations[0] |
| builds-on | DenseNet (Huang et al., 2016) 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. | claim_relations[1] |
| builds-on | the ChestX-ray14 dataset of Wang et al. (2017) 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. | claim_relations[2] |
| builds-on | the evaluation protocol of Wang et al. (2017) and Yao et al. (2017) 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. | claim_relations[3] |
| sense | 'exceeding practicing radiologists' - AS AGREEMENT WITH FOUR OF THEM: the F1 for the model and for each radiologist is computed against the other four radiologists' labels, so the claim is about concordance with a particular panel and not about detecting pneumonia in a patient 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. | senses[0] |
| sense | a pathology label - AS A FACT ABOUT A REPORT, NOT AN IMAGE: the fourteen labels are assigned by automatic extraction from radiology reports, so the target the network learns is what a radiologist wrote down, filtered through a text-mining tool 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. | senses[1] |
| sense | 'negative' - AS NOT-LABELLED: every image without pneumonia among its annotated pathologies becomes a negative example, so the class means the extractor found nothing rather than that nothing was there 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. | senses[2] |
| control | four practising academic radiologists annotating the same test set, used as the comparison for the model — held — rules out a number that looks good against no reference - the baseline here is people doing the task on the same 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. | controls[0] |
| audit | pathology labels —operationalised-as→ automatic extraction methods — Audit 2026-09-28: DOUBTFUL - read against its full span and kept, but the span says labels were annotated USING automatic extraction methods; operationalised-as is loose. 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. | concept_edges[1] |
| outcome (stated by the tagger, no quotation) | control — held | controls[0] |
| for which use | limitation — the radiologist comparison, which the authors themselves qualify: WE IDENTIFY THREE LIMITATIONS OF THIS COMPARISON 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] |
| duplicate of | limitation — limitations[0] 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] |
| for which use | limitation — the completeness of that qualification: the paper announces three limitations and prints a FIRST and a THIRD with no SECOND. Verified in the version of record, arXiv 1711.05225v3 (25 Dec 2017), not only in our staged copy - so this is the paper's own text and not a lost sentence in extraction 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] |
| for which use | limitation — the diagnostic setup for both model and radiologists: ONLY FRONTAL RADIOGRAPHS WERE PRESENTED ... BUT IT HAS BEEN SHOWN THAT UP TO 15% OF ACCURATE DIAGNOSES REQUIRE THE LATERAL VIEW 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] |
| for which use | limitation — the comparison against clinical practice: NEITHER THE MODEL NOR THE RADIOLOGISTS WERE ... PERMITTED TO USE PATIENT HISTORY, WHICH HAS BEEN SHOWN TO DECREASE RADIOLOGIST DIAGNOSTIC PERFORMANCE 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] |
| for which use | limitation — the claim that this model exceeds practicing radiologists: the F1 score for each radiologist and for the model is computed against each of the other four radiologists' labels as ground truth, so the comparison is agreement with those four rather than detection of disease 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 — the labels this model was trained on: they were assigned by automatic extraction methods applied to radiology reports, so a label records what a report said rather than what an image shows 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 — the negative class in this task: images are negative when pneumonia is not among the annotated pathologies, so absence of a label is used in place of absence of the 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. | limitations[6] |
| for which use | limitation — the performance figure quoted for this model: the network outputs a vector of binary labels over fourteen pathology classes, while the radiologist comparison concerns the pneumonia task alone 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] |
| evidence status note | mechanism — 2026-08-16: FAILED GLYPH INSIDE THIS QUOTE. The staged text reads "Formally, Mc = (cid:88) k wc,kfk" - (cid:88) is the SUMMATION SIGN, so the formula is Mc = sum over k of w_c,k * f_k, the weighted sum of feature maps the sentence has just described in words. The prose on either side is intact and states the mechanism; only the symbol is lost. The quote is an exact substring of the staged file; the file is incomplete here, not the tag. 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. | mechanisms[6] |
| replication | untested | |
| limitation | the paper identifies three limitations of its radiologist comparison 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 | The paper announces three limitations of the radiologist comparison but enumerates only two (a 'First' and a 'Third'); the second is missing from the text. 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 | Only frontal radiographs were shown to both model and radiologists, although a share of accurate diagnoses requires the lateral view. 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 | Neither model nor radiologists could use patient history, which is known to change radiologist diagnostic performance. 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 standard the model is measured against is the other radiologists' labels, not the presence of disease. 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 | The training labels were produced by text extraction from reports rather than by anyone looking at the 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[5] |
| limitation | Every image the extractor did not mark becomes a negative example. 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 | The model reports fourteen findings while the headline number describes one of them. 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 | EVIDENCE CORRECTED (RE-GROUNDED - THE POINTER WAS WRONG, NOT THE CLAIM) · CheXNet is a 121-layer CNN, trained on the ChestX-ray14 dataset of over 100,000 frontal-view X-rays covering 14 diseases. 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] |
| retracted | finding — RE-GROUNDED - THE POINTER WAS WRONG, NOT THE CLAIM. The old evidence was verbatim, anchored and correctly cut, and it contained NONE of this claim's numbers (121, 14). The paper states the claim in one sentence elsewhere and the tagger did not use it. the project, 2026-08-23: 'WE HAVE SPENT THE DAY VERIFYING THAT QUOTES ARE REAL AND NONE OF IT ASKS WHETHER THEY ARE RELEVANT.' Confirmed by reading the claim, the old span and the candidate together; the candidate carries every number AND the claim's own content words. | content_tags.findings[0] |
| finding | Extended to all 14 thoracic diseases, CheXNet achieves state-of-the-art results on every one. 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] |
| 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[1] |
| quantity | 121 layers — depth of the DenseNet CNN (CheXNet) 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.quantities[0] |
| quantity | 112,120 images — chest X-ray images in the ChestX-ray14 dataset 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.quantities[1] |
| evidence status note | quantity — 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.quantities[1] |
| quantity | 14 diseases — thoracic disease labels detected 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.quantities[2] |
| evidence status note | quantity — 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.quantities[2] |
| quantity | 420 X-rays — size of the radiologist-annotated test set 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.quantities[3] |
| quantity | > 0.05 AUROC — margin over previous state of the art (emphysema) 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.quantities[4] |
| variable | chest X-ray image (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 | F1 metric (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[1] |
| evidence status note | variable — 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.variables[1] |
| definition | CheXNet 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 | ChestX-ray14 dataset 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] |
| evidence status note | definition — QUOTE RECOVERED FROM THE PAPER'S OWN CHARACTERS. The recorded quote was LETTERS-ONLY IDENTICAL to this stretch of the staged text but not an exact substring of it - spaces, hyphens, ligature glyphs or mathematical operators differed, so it could never anchor. This is the file's own text between the same two letters: not produced by a rule about the damage, copied out of the file. Round-trip checked (the recovered span is letters-only equal to the original) and length-checked. The text as originally recorded is kept in evidence as extracted. | content_tags.definitions[1] |
| key-terms | CheXNet, radiologist, pneumonia, X-ray, DenseNet, chest, disease, network, images |
| concept | F1 score 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 | ground truth 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 | pneumonia detection task 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 | pathology labels 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 | automatic extraction methods 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] |
| bootstrap | 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] |
| evidence status note | bootstrap — 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[0] |
| confidence-interval CI | as written: confidence intervals 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] |
| evidence status note | confidence-interval — 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[1] |
| mean μ | as written: mean 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[2] |
| evidence status note | mean — 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[2] |
| standard-deviation SD/σ | 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] |
| statistical-significance | as written: statistically 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[4] |
| evidence status note | statistical-significance — 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] |
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