feat: Expose equation exports (#869)

* pin new docling-core and exploit it via assembler changes

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* update test results

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* update with docling-core release

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

---------

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

docling/utils/glm_utils.py

@@ -307,6 +307,10 @@ def to_docling_document(doc_glm, update_name_label=False) -> DoclingDocument:
                 current_list = None
 
                 doc.add_code(text=text, prov=prov)
+            elif label == DocItemLabel.FORMULA:
+                current_list = None
+
+                doc.add_text(label=DocItemLabel.FORMULA, text="", orig=text, prov=prov)
             else:
                 current_list = None
 

poetry.lock

@@ -182,8 +182,8 @@ files = [
 lazy-object-proxy = ">=1.4.0"
 typing-extensions = {version = ">=4.0.0", markers = "python_version < \"3.11\""}
 wrapt = [
-    {version = ">=1.14,<2", markers = "python_version >= \"3.11\""},
     {version = ">=1.11,<2", markers = "python_version < \"3.11\""},
+    {version = ">=1.14,<2", markers = "python_version >= \"3.11\""},
 ]
 
 [[package]]
@@ -861,18 +861,19 @@ files = [
 
 [[package]]
 name = "docling-core"
-version = "2.16.1"
+version = "2.17.0"
 description = "A python library to define and validate data types in Docling."
 optional = false
 python-versions = "<4.0,>=3.9"
 files = [
-    {file = "docling_core-2.16.1-py3-none-any.whl", hash = "sha256:d26af2f49e9f1f65ae5dfca972e206860339c1f91adfe427fa67d1cf95cce241"},
-    {file = "docling_core-2.16.1.tar.gz", hash = "sha256:676f51fa5797c91a86ccbc1fdaa020effcde4cc86aa9b094a0d5d775636871ba"},
+    {file = "docling_core-2.17.0-py3-none-any.whl", hash = "sha256:5c3015e0eed8e939069bdfd566761dc9f39239647893ae42c53d1333dd0a4749"},
+    {file = "docling_core-2.17.0.tar.gz", hash = "sha256:cfcba8d173730baf244f279369f68e3cb5ddc7680769841afd254b61e432133e"},
 ]
 
 [package.dependencies]
 jsonref = ">=1.1.0,<2.0.0"
 jsonschema = ">=4.16.0,<5.0.0"
+latex2mathml = ">=3.77.0,<4.0.0"
 pandas = ">=2.1.4,<3.0.0"
 pillow = ">=10.3.0,<11.0.0"
 pydantic = ">=2.6.0,<2.10.0 || >2.10.0,<2.10.1 || >2.10.1,<2.10.2 || >2.10.2,<3.0.0"
@@ -2167,6 +2168,17 @@ requests-toolbelt = ">=1.0.0,<2.0.0"
 [package.extras]
 langsmith-pyo3 = ["langsmith-pyo3 (>=0.1.0rc2,<0.2.0)"]
 
+[[package]]
+name = "latex2mathml"
+version = "3.77.0"
+description = "Pure Python library for LaTeX to MathML conversion"
+optional = false
+python-versions = ">=3.8.1,<4.0.0"
+files = [
+    {file = "latex2mathml-3.77.0-py3-none-any.whl", hash = "sha256:5531e18a2a9eae7c24e257118b6a444cbba253cd27ff3e81f1bd6c41e88e786e"},
+    {file = "latex2mathml-3.77.0.tar.gz", hash = "sha256:e2f501d1878f2e489c3f6f12786bef74c62f712d2770f7f3c837eb20a55d0a1e"},
+]
+
 [[package]]
 name = "lazy-loader"
 version = "0.4"
@@ -2817,8 +2829,8 @@ files = [
 
 [package.dependencies]
 multiprocess = [
-    {version = ">=0.70.15", optional = true, markers = "python_version >= \"3.11\" and extra == \"dill\""},
     {version = "*", optional = true, markers = "python_version < \"3.11\" and extra == \"dill\""},
+    {version = ">=0.70.15", optional = true, markers = "python_version >= \"3.11\" and extra == \"dill\""},
 ]
 pygments = ">=2.0"
 pywin32 = {version = ">=301", markers = "platform_system == \"Windows\""}
@@ -3833,10 +3845,10 @@ files = [
 
 [package.dependencies]
 numpy = [
-    {version = ">=1.26.0", markers = "python_version >= \"3.12\""},
-    {version = ">=1.23.5", markers = "python_version >= \"3.11\" and python_version < \"3.12\""},
     {version = ">=1.21.4", markers = "python_version >= \"3.10\" and platform_system == \"Darwin\" and python_version < \"3.11\""},
     {version = ">=1.21.2", markers = "platform_system != \"Darwin\" and python_version >= \"3.10\" and python_version < \"3.11\""},
+    {version = ">=1.23.5", markers = "python_version >= \"3.11\" and python_version < \"3.12\""},
+    {version = ">=1.26.0", markers = "python_version >= \"3.12\""},
     {version = ">=1.21.0", markers = "python_version == \"3.9\" and platform_system == \"Darwin\" and platform_machine == \"arm64\""},
     {version = ">=1.19.3", markers = "platform_system == \"Linux\" and platform_machine == \"aarch64\" and python_version >= \"3.8\" and python_version < \"3.10\" or python_version > \"3.9\" and python_version < \"3.10\" or python_version >= \"3.9\" and platform_system != \"Darwin\" and python_version < \"3.10\" or python_version >= \"3.9\" and platform_machine != \"arm64\" and python_version < \"3.10\""},
 ]
@@ -3859,10 +3871,10 @@ files = [
 
 [package.dependencies]
 numpy = [
-    {version = ">=1.26.0", markers = "python_version >= \"3.12\""},
-    {version = ">=1.23.5", markers = "python_version >= \"3.11\" and python_version < \"3.12\""},
     {version = ">=1.21.4", markers = "python_version >= \"3.10\" and platform_system == \"Darwin\" and python_version < \"3.11\""},
     {version = ">=1.21.2", markers = "platform_system != \"Darwin\" and python_version >= \"3.10\" and python_version < \"3.11\""},
+    {version = ">=1.23.5", markers = "python_version >= \"3.11\" and python_version < \"3.12\""},
+    {version = ">=1.26.0", markers = "python_version >= \"3.12\""},
     {version = ">=1.21.0", markers = "python_version == \"3.9\" and platform_system == \"Darwin\" and platform_machine == \"arm64\""},
     {version = ">=1.19.3", markers = "platform_system == \"Linux\" and platform_machine == \"aarch64\" and python_version >= \"3.8\" and python_version < \"3.10\" or python_version > \"3.9\" and python_version < \"3.10\" or python_version >= \"3.9\" and platform_system != \"Darwin\" and python_version < \"3.10\" or python_version >= \"3.9\" and platform_machine != \"arm64\" and python_version < \"3.10\""},
 ]
@@ -4048,9 +4060,9 @@ files = [
 
 [package.dependencies]
 numpy = [
-    {version = ">=1.26.0", markers = "python_version >= \"3.12\""},
-    {version = ">=1.23.2", markers = "python_version == \"3.11\""},
     {version = ">=1.22.4", markers = "python_version < \"3.11\""},
+    {version = ">=1.23.2", markers = "python_version == \"3.11\""},
+    {version = ">=1.26.0", markers = "python_version >= \"3.12\""},
 ]
 python-dateutil = ">=2.8.2"
 pytz = ">=2020.1"
@@ -4814,8 +4826,8 @@ files = [
 astroid = ">=2.15.8,<=2.17.0-dev0"
 colorama = {version = ">=0.4.5", markers = "sys_platform == \"win32\""}
 dill = [
-    {version = ">=0.3.6", markers = "python_version >= \"3.11\""},
     {version = ">=0.2", markers = "python_version < \"3.11\""},
+    {version = ">=0.3.6", markers = "python_version >= \"3.11\""},
 ]
 isort = ">=4.2.5,<6"
 mccabe = ">=0.6,<0.8"
@@ -7825,4 +7837,4 @@ tesserocr = ["tesserocr"]
 [metadata]
 lock-version = "2.0"
 python-versions = "^3.9"
-content-hash = "336970505f4bae6b21f4cf358ebf6b5ef4fa42a4980358297e63bfea381b350a"
+content-hash = "907c7cef6722358ac30193f07f9cc15684daf1b75b6c400104e87f3b22137632"

pyproject.toml

@@ -26,7 +26,7 @@ packages = [{include = "docling"}]
 ######################
 python = "^3.9"
 pydantic = "^2.0.0"
-docling-core = {version = "^2.16.1", extras = ["chunking"]}
+docling-core = {extras = ["chunking"], version = "^2.17.0"}
 docling-ibm-models = "^3.3.0"
 deepsearch-glm = "^1.0.0"
 docling-parse = "^3.1.0"

tests/data/groundtruth/docling_v2/2203.01017v2.doctags.txt

@@ -106,12 +106,12 @@
 <text><location><page_6><loc_8><loc_70><loc_47><loc_80></location>The output features for each table cell are then fed into the feed-forward network (FFN). The FFN consists of a Multi-Layer Perceptron (3 layers with ReLU activation function) that predicts the normalized coordinates for the bounding box of each table cell. Finally, the predicted bounding boxes are classified based on whether they are empty or not using a linear layer.</text>
 <text><location><page_6><loc_8><loc_44><loc_47><loc_69></location>Loss Functions. We formulate a multi-task loss Eq. 2 to train our network. The Cross-Entropy loss (denoted as l$_{s}$ ) is used to train the Structure Decoder which predicts the structure tokens. As for the Cell BBox Decoder it is trained with a combination of losses denoted as l$_{box}$ . l$_{box}$ consists of the generally used l$_{1}$ loss for object detection and the IoU loss ( l$_{iou}$ ) to be scale invariant as explained in [25]. In comparison to DETR, we do not use the Hungarian algorithm [15] to match the predicted bounding boxes with the ground-truth boxes, as we have already achieved a one-toone match through two steps: 1) Our token input sequence is naturally ordered, therefore the hidden states of the table data cells are also in order when they are provided as input to the Cell BBox Decoder , and 2) Our bounding boxes generation mechanism (see Sec. 3) ensures a one-to-one mapping between the cell content and its bounding box for all post-processed datasets.</text>
 <text><location><page_6><loc_8><loc_41><loc_47><loc_43></location>The loss used to train the TableFormer can be defined as following:</text>
-<formula><location><page_6><loc_20><loc_35><loc_47><loc_38></location>l$_{box}$ = λ$_{iou}$l$_{iou}$ + λ$_{l}$$_{1}$ l = λl$_{s}$ + (1 - λ ) l$_{box}$ (1)</formula>
+<formula><location><page_6><loc_20><loc_35><loc_47><loc_38></location></formula>
 <text><location><page_6><loc_8><loc_32><loc_46><loc_33></location>where λ ∈ [0, 1], and λ$_{iou}$, λ$_{l}$$_{1}$ ∈$_{R}$ are hyper-parameters.</text>
 <section_header_level_1><location><page_6><loc_8><loc_28><loc_28><loc_30></location>5. Experimental Results</section_header_level_1>
 <section_header_level_1><location><page_6><loc_8><loc_26><loc_29><loc_27></location>5.1. Implementation Details</section_header_level_1>
 <text><location><page_6><loc_8><loc_19><loc_47><loc_25></location>TableFormer uses ResNet-18 as the CNN Backbone Network . The input images are resized to 448*448 pixels and the feature map has a dimension of 28*28. Additionally, we enforce the following input constraints:</text>
-<formula><location><page_6><loc_15><loc_14><loc_47><loc_17></location>Image width and height ≤ 1024 pixels Structural tags length ≤ 512 tokens. (2)</formula>
+<formula><location><page_6><loc_15><loc_14><loc_47><loc_17></location></formula>
 <text><location><page_6><loc_8><loc_10><loc_47><loc_13></location>Although input constraints are used also by other methods, such as EDD, ours are less restrictive due to the improved</text>
 <text><location><page_6><loc_50><loc_86><loc_89><loc_91></location>runtime performance and lower memory footprint of TableFormer. This allows to utilize input samples with longer sequences and images with larger dimensions.</text>
 <text><location><page_6><loc_50><loc_59><loc_89><loc_85></location>The Transformer Encoder consists of two "Transformer Encoder Layers", with an input feature size of 512, feed forward network of 1024, and 4 attention heads. As for the Transformer Decoder it is composed of four "Transformer Decoder Layers" with similar input and output dimensions as the "Transformer Encoder Layers". Even though our model uses fewer layers and heads than the default implementation parameters, our extensive experimentation has proved this setup to be more suitable for table images. We attribute this finding to the inherent design of table images, which contain mostly lines and text, unlike the more elaborate content present in other scopes (e.g. the COCO dataset). Moreover, we have added ResNet blocks to the inputs of the Structure Decoder and Cell BBox Decoder. This prevents a decoder having a stronger influence over the learned weights which would damage the other prediction task (structure vs bounding boxes), but learn task specific weights instead. Lastly our dropout layers are set to 0.5.</text>
@@ -122,7 +122,7 @@
 <text><location><page_6><loc_50><loc_10><loc_89><loc_14></location>We also share our baseline results on the challenging SynthTabNet dataset. Throughout our experiments, the same parameters stated in Sec. 5.1 are utilized.</text>
 <section_header_level_1><location><page_7><loc_8><loc_89><loc_27><loc_91></location>5.3. Datasets and Metrics</section_header_level_1>
 <text><location><page_7><loc_8><loc_83><loc_47><loc_88></location>The Tree-Edit-Distance-Based Similarity (TEDS) metric was introduced in [37]. It represents the prediction, and ground-truth as a tree structure of HTML tags. This similarity is calculated as:</text>
-<formula><location><page_7><loc_14><loc_78><loc_47><loc_81></location>TEDS ( T$_{a}$, T$_{b}$ ) = 1 - EditDist ( T$_{a}$, T$_{b}$ ) max ( | T$_{a}$ | , | T$_{b}$ | ) (3)</formula>
+<formula><location><page_7><loc_14><loc_78><loc_47><loc_81></location></formula>
 <text><location><page_7><loc_8><loc_73><loc_47><loc_77></location>where T$_{a}$ and T$_{b}$ represent tables in tree structure HTML format. EditDist denotes the tree-edit distance, and | T | represents the number of nodes in T .</text>
 <section_header_level_1><location><page_7><loc_8><loc_70><loc_28><loc_72></location>5.4. Quantitative Analysis</section_header_level_1>
 <text><location><page_7><loc_8><loc_50><loc_47><loc_69></location>Structure. As shown in Tab. 2, TableFormer outperforms all SOTA methods across different datasets by a large margin for predicting the table structure from an image. All the more, our model outperforms pre-trained methods. During the evaluation we do not apply any table filtering. We also provide our baseline results on the SynthTabNet dataset. It has been observed that large tables (e.g. tables that occupy half of the page or more) yield poor predictions. We attribute this issue to the image resizing during the preprocessing step, that produces downsampled images with indistinguishable features. This problem can be addressed by treating such big tables with a separate model which accepts a large input image size.</text>
@@ -304,7 +304,7 @@
 <list_item><location><page_12><loc_8><loc_29><loc_47><loc_33></location>3.a. If all IOU scores in a column are below the threshold, discard all predictions (structure and bounding boxes) for that column.</list_item>
 <list_item><location><page_12><loc_8><loc_24><loc_47><loc_28></location>4. Find the best-fitting content alignment for the predicted cells with good IOU per each column. The alignment of the column can be identified by the following formula:</list_item>
 </unordered_list>
-<formula><location><page_12><loc_18><loc_17><loc_47><loc_21></location>alignment = arg min c { D$_{c}$ } D$_{c}$ = max { x$_{c}$ } - min { x$_{c}$ } (4)</formula>
+<formula><location><page_12><loc_18><loc_17><loc_47><loc_21></location></formula>
 <text><location><page_12><loc_8><loc_13><loc_47><loc_16></location>where c is one of { left, centroid, right } and x$_{c}$ is the xcoordinate for the corresponding point.</text>
 <unordered_list>
 <list_item><location><page_12><loc_8><loc_10><loc_47><loc_13></location>5. Use the alignment computed in step 4, to compute the median x -coordinate for all table columns and the me-</list_item>

tests/data/groundtruth/docling_v2/2203.01017v2.md

@@ -52,11 +52,11 @@ To meet the design criteria listed above, we developed a new model called TableF
 
 The paper is structured as follows. In Sec. 2, we give a brief overview of the current state-of-the-art. In Sec. 3, we describe the datasets on which we train. In Sec. 4, we introduce the TableFormer model-architecture and describe
 
-its results & performance in Sec. 5. As a conclusion, we describe how this new model-architecture can be re-purposed for other tasks in the computer-vision community.
+its results & performance in Sec. 5. As a conclusion, we describe how this new model-architecture can be re-purposed for other tasks in the computer-vision community.
 
 ## 2. Previous work and State of the Art
 
-Identifying the structure of a table has been an outstanding problem in the document-parsing community, that motivates many organised public challenges [6, 4, 14]. The difficulty of the problem can be attributed to a number of factors. First, there is a large variety in the shapes and sizes of tables. Such large variety requires a flexible method. This is especially true for complex column- and row headers, which can be extremely intricate and demanding. A second factor of complexity is the lack of data with regard to table-structure. Until the publication of PubTabNet [37], there were no large datasets (i.e. > 100 K tables) that provided structure information. This happens primarily due to the fact that tables are notoriously time-consuming to annotate by hand. However, this has definitely changed in recent years with the deliverance of PubTabNet [37], FinTabNet [36], TableBank [17] etc.
+Identifying the structure of a table has been an outstanding problem in the document-parsing community, that motivates many organised public challenges [6, 4, 14]. The difficulty of the problem can be attributed to a number of factors. First, there is a large variety in the shapes and sizes of tables. Such large variety requires a flexible method. This is especially true for complex column- and row headers, which can be extremely intricate and demanding. A second factor of complexity is the lack of data with regard to table-structure. Until the publication of PubTabNet [37], there were no large datasets (i.e. > 100 K tables) that provided structure information. This happens primarily due to the fact that tables are notoriously time-consuming to annotate by hand. However, this has definitely changed in recent years with the deliverance of PubTabNet [37], FinTabNet [36], TableBank [17] etc.
 
 Before the rising popularity of deep neural networks, the community relied heavily on heuristic and/or statistical methods to do table structure identification [3, 7, 11, 5, 13, 28]. Although such methods work well on constrained tables [12], a more data-driven approach can be applied due to the advent of convolutional neural networks (CNNs) and the availability of large datasets. To the best-of-our knowledge, there are currently two different types of network architecture that are being pursued for state-of-the-art tablestructure identification.
 
@@ -115,7 +115,7 @@ Given the image of a table, TableFormer is able to predict: 1) a sequence of tok
 
 ## 4.1. Model architecture.
 
-We now describe in detail the proposed method, which is composed of three main components, see Fig. 4. Our CNN Backbone Network encodes the input as a feature vector of predefined length. The input feature vector of the encoded image is passed to the Structure Decoder to produce a sequence of HTML tags that represent the structure of the table. With each prediction of an HTML standard data cell (' < td > ') the hidden state of that cell is passed to the Cell BBox Decoder. As for spanning cells, such as row or column span, the tag is broken down to ' < ', 'rowspan=' or 'colspan=', with the number of spanning cells (attribute), and ' > '. The hidden state attached to ' < ' is passed to the Cell BBox Decoder. A shared feed forward network (FFN) receives the hidden states from the Structure Decoder, to provide the final detection predictions of the bounding box coordinates and their classification.
+We now describe in detail the proposed method, which is composed of three main components, see Fig. 4. Our CNN Backbone Network encodes the input as a feature vector of predefined length. The input feature vector of the encoded image is passed to the Structure Decoder to produce a sequence of HTML tags that represent the structure of the table. With each prediction of an HTML standard data cell (' &lt; td &gt; ') the hidden state of that cell is passed to the Cell BBox Decoder. As for spanning cells, such as row or column span, the tag is broken down to ' &lt; ', 'rowspan=' or 'colspan=', with the number of spanning cells (attribute), and ' &gt; '. The hidden state attached to ' &lt; ' is passed to the Cell BBox Decoder. A shared feed forward network (FFN) receives the hidden states from the Structure Decoder, to provide the final detection predictions of the bounding box coordinates and their classification.
 
 CNN Backbone Network. A ResNet-18 CNN is the backbone that receives the table image and encodes it as a vector of predefined length. The network has been modified by removing the linear and pooling layer, as we are not per-
 
@@ -123,7 +123,7 @@ Figure 3: TableFormer takes in an image of the PDF and creates bounding box and
 
 <!-- image -->
 
-Figure 4: Given an input image of a table, the Encoder produces fixed-length features that represent the input image. The features are then passed to both the Structure Decoder and Cell BBox Decoder . During training, the Structure Decoder receives 'tokenized tags' of the HTML code that represent the table structure. Afterwards, a transformer encoder and decoder architecture is employed to produce features that are received by a linear layer, and the Cell BBox Decoder. The linear layer is applied to the features to predict the tags. Simultaneously, the Cell BBox Decoder selects features referring to the data cells (' < td > ', ' < ') and passes them through an attention network, an MLP, and a linear layer to predict the bounding boxes.
+Figure 4: Given an input image of a table, the Encoder produces fixed-length features that represent the input image. The features are then passed to both the Structure Decoder and Cell BBox Decoder . During training, the Structure Decoder receives 'tokenized tags' of the HTML code that represent the table structure. Afterwards, a transformer encoder and decoder architecture is employed to produce features that are received by a linear layer, and the Cell BBox Decoder. The linear layer is applied to the features to predict the tags. Simultaneously, the Cell BBox Decoder selects features referring to the data cells (' &lt; td &gt; ', ' &lt; ') and passes them through an attention network, an MLP, and a linear layer to predict the bounding boxes.
 
 <!-- image -->
 
@@ -133,7 +133,7 @@ Structure Decoder. The transformer architecture of this component is based on th
 
 The transformer encoder receives an encoded image from the CNN Backbone Network and refines it through a multi-head dot-product attention layer, followed by a Feed Forward Network. During training, the transformer decoder receives as input the output feature produced by the transformer encoder, and the tokenized input of the HTML ground-truth tags. Using a stack of multi-head attention layers, different aspects of the tag sequence could be inferred. This is achieved by each attention head on a layer operating in a different subspace, and then combining altogether their attention score.
 
-Cell BBox Decoder. Our architecture allows to simultaneously predict HTML tags and bounding boxes for each table cell without the need of a separate object detector end to end. This approach is inspired by DETR [1] which employs a Transformer Encoder, and Decoder that looks for a specific number of object queries (potential object detections). As our model utilizes a transformer architecture, the hidden state of the < td > ' and ' < ' HTML structure tags become the object query.
+Cell BBox Decoder. Our architecture allows to simultaneously predict HTML tags and bounding boxes for each table cell without the need of a separate object detector end to end. This approach is inspired by DETR [1] which employs a Transformer Encoder, and Decoder that looks for a specific number of object queries (potential object detections). As our model utilizes a transformer architecture, the hidden state of the &lt; td &gt; ' and ' &lt; ' HTML structure tags become the object query.
 
 The encoding generated by the CNN Backbone Network along with the features acquired for every data cell from the Transformer Decoder are then passed to the attention network. The attention network takes both inputs and learns to provide an attention weighted encoding. This weighted at-
 
@@ -145,9 +145,9 @@ Loss Functions. We formulate a multi-task loss Eq. 2 to train our network. The C
 
 The loss used to train the TableFormer can be defined as following:
 
-$$l$\_{box}$ = λ$\_{iou}$l$\_{iou}$ + λ$\_{l}$$_{1}$ l = λl$_{s}$ + (1 - λ ) l$_{box}$ (1)$$
+<!-- formula-not-decoded -->
 
-where λ ∈ [0, 1], and λ$\_{iou}$, λ$\_{l}$$_{1}$ ∈$_{R}$ are hyper-parameters.
+where λ ∈ [0, 1], and λ$_{iou}$, λ$_{l}$$\_{1}$ ∈$\_{R}$ are hyper-parameters.
 
 ## 5. Experimental Results
 
@@ -155,7 +155,7 @@ where λ ∈ [0, 1], and λ$\_{iou}$, λ$\_{l}$$_{1}$ ∈$_{R}$ are hyper-parame
 
 TableFormer uses ResNet-18 as the CNN Backbone Network . The input images are resized to 448*448 pixels and the feature map has a dimension of 28*28. Additionally, we enforce the following input constraints:
 
-$$Image width and height ≤ 1024 pixels Structural tags length ≤ 512 tokens. (2)$$
+<!-- formula-not-decoded -->
 
 Although input constraints are used also by other methods, such as EDD, ours are less restrictive due to the improved
 
@@ -177,7 +177,7 @@ We also share our baseline results on the challenging SynthTabNet dataset. Throu
 
 The Tree-Edit-Distance-Based Similarity (TEDS) metric was introduced in [37]. It represents the prediction, and ground-truth as a tree structure of HTML tags. This similarity is calculated as:
 
-$$TEDS ( T$\_{a}$, T$\_{b}$ ) = 1 - EditDist ( T$\_{a}$, T$\_{b}$ ) max ( | T$\_{a}$ | , | T$\_{b}$ | ) (3)$$
+<!-- formula-not-decoded -->
 
 where T$_{a}$ and T$_{b}$ represent tables in tree structure HTML format. EditDist denotes the tree-edit distance, and | T | represents the number of nodes in T .
 
@@ -277,7 +277,7 @@ Figure 6: An example of TableFormer predictions (bounding boxes and structure) f
 
 We showcase several visualizations for the different components of our network on various "complex" tables within datasets presented in this work in Fig. 5 and Fig. 6 As it is shown, our model is able to predict bounding boxes for all table cells, even for the empty ones. Additionally, our post-processing techniques can extract the cell content by matching the predicted bounding boxes to the PDF cells based on their overlap and spatial proximity. The left part of Fig. 5 demonstrates also the adaptability of our method to any language, as it can successfully extract Japanese text, although the training set contains only English content. We provide more visualizations including the intermediate steps in the supplementary material. Overall these illustrations justify the versatility of our method across a diverse range of table appearances and content type.
 
-## 6. Future Work & Conclusion
+## 6. Future Work &amp; Conclusion
 
 In this paper, we presented TableFormer an end-to-end transformer based approach to predict table structures and bounding boxes of cells from an image. This approach enables us to recreate the table structure, and extract the cell content from PDF or OCR by using bounding boxes. Additionally, it provides the versatility required in real-world scenarios when dealing with various types of PDF documents, and languages. Furthermore, our method outperforms all state-of-the-arts with a wide margin. Finally, we introduce "SynthTabNet" a challenging synthetically generated dataset that reinforces missing characteristics from other datasets.
 
@@ -377,7 +377,7 @@ Here is a step-by-step description of the prediction postprocessing:
 - 3.a. If all IOU scores in a column are below the threshold, discard all predictions (structure and bounding boxes) for that column.
 - 4. Find the best-fitting content alignment for the predicted cells with good IOU per each column. The alignment of the column can be identified by the following formula:
 
-$$alignment = arg min c { D$\_{c}$ } D$\_{c}$ = max { x$\_{c}$ } - min { x$\_{c}$ } (4)$$
+<!-- formula-not-decoded -->
 
 where c is one of { left, centroid, right } and x$_{c}$ is the xcoordinate for the corresponding point.
 

tests/data/groundtruth/docling_v2/2206.01062.md

@@ -55,7 +55,7 @@ In this paper, we present the DocLayNet dataset. It provides pageby-page layout
 
 This enables experimentation with annotation uncertainty and quality control analysis.
 
-- (5) Pre-defined Train-, Test- & Validation-set : Like DocBank, we provide fixed train-, test- & validation-sets to ensure proportional representation of the class-labels. Further, we prevent leakage of unique layouts across sets, which has a large effect on model accuracy scores.
+- (5) Pre-defined Train-, Test- & Validation-set : Like DocBank, we provide fixed train-, test- & validation-sets to ensure proportional representation of the class-labels. Further, we prevent leakage of unique layouts across sets, which has a large effect on model accuracy scores.
 
 All aspects outlined above are detailed in Section 3. In Section 4, we will elaborate on how we designed and executed this large-scale human annotation campaign. We will also share key insights and lessons learned that might prove helpful for other parties planning to set up annotation campaigns.
 
@@ -77,9 +77,9 @@ Figure 2: Distribution of DocLayNet pages across document categories.
 
 <!-- image -->
 
-to a minimum, since they introduce difficulties in annotation (see Section 4). As a second condition, we focussed on medium to large documents ( > 10 pages) with technical content, dense in complex tables, figures, plots and captions. Such documents carry a lot of information value, but are often hard to analyse with high accuracy due to their challenging layouts. Counterexamples of documents not included in the dataset are receipts, invoices, hand-written documents or photographs showing "text in the wild".
+to a minimum, since they introduce difficulties in annotation (see Section 4). As a second condition, we focussed on medium to large documents ( &gt; 10 pages) with technical content, dense in complex tables, figures, plots and captions. Such documents carry a lot of information value, but are often hard to analyse with high accuracy due to their challenging layouts. Counterexamples of documents not included in the dataset are receipts, invoices, hand-written documents or photographs showing "text in the wild".
 
-The pages in DocLayNet can be grouped into six distinct categories, namely Financial Reports , Manuals , Scientific Articles , Laws & Regulations , Patents and Government Tenders . Each document category was sourced from various repositories. For example, Financial Reports contain both free-style format annual reports 2 which expose company-specific, artistic layouts as well as the more formal SEC filings. The two largest categories ( Financial Reports and Manuals ) contain a large amount of free-style layouts in order to obtain maximum variability. In the other four categories, we boosted the variability by mixing documents from independent providers, such as different government websites or publishers. In Figure 2, we show the document categories contained in DocLayNet with their respective sizes.
+The pages in DocLayNet can be grouped into six distinct categories, namely Financial Reports , Manuals , Scientific Articles , Laws &amp; Regulations , Patents and Government Tenders . Each document category was sourced from various repositories. For example, Financial Reports contain both free-style format annual reports 2 which expose company-specific, artistic layouts as well as the more formal SEC filings. The two largest categories ( Financial Reports and Manuals ) contain a large amount of free-style layouts in order to obtain maximum variability. In the other four categories, we boosted the variability by mixing documents from independent providers, such as different government websites or publishers. In Figure 2, we show the document categories contained in DocLayNet with their respective sizes.
 
 We did not control the document selection with regard to language. The vast majority of documents contained in DocLayNet (close to 95%) are published in English language. However, DocLayNet also contains a number of documents in other languages such as German (2.5%), French (1.0%) and Japanese (1.0%). While the document language has negligible impact on the performance of computer vision methods such as object detection and segmentation models, it might prove challenging for layout analysis methods which exploit textual features.
 
@@ -192,7 +192,7 @@ In Table 2, we present baseline experiments (given in mAP) on Mask R-CNN [12], F
 
 Table 3: Performance of a Mask R-CNN R50 network in mAP@0.5-0.95 scores trained on DocLayNet with different class label sets. The reduced label sets were obtained by either down-mapping or dropping labels.
 
-Table 4: Performance of a Mask R-CNN R50 network with document-wise and page-wise split for different label sets. Naive page-wise split will result in GLYPH<tildelow> 10% point improvement.
+Table 4: Performance of a Mask R-CNN R50 network with document-wise and page-wise split for different label sets. Naive page-wise split will result in GLYPH&lt;tildelow&gt; 10% point improvement.
 
 | Class-count    |   11 | 6       | 5       | 4       |
 |----------------|------|---------|---------|---------|
@@ -243,7 +243,7 @@ Many documents in DocLayNet have a unique styling. In order to avoid overfitting
 
 Throughout this paper, we claim that DocLayNet's wider variety of document layouts leads to more robust layout detection models. In Table 5, we provide evidence for that. We trained models on each of the available datasets (PubLayNet, DocBank and DocLayNet) and evaluated them on the test sets of the other datasets. Due to the different label sets and annotation styles, a direct comparison is not possible. Hence, we focussed on the common labels among the datasets. Between PubLayNet and DocLayNet, these are Picture ,
 
-Table 5: Prediction Performance (mAP@0.5-0.95) of a Mask R-CNN R50 network across the PubLayNet, DocBank & DocLayNet data-sets. By evaluating on common label classes of each dataset, we observe that the DocLayNet-trained model has much less pronounced variations in performance across all datasets.
+Table 5: Prediction Performance (mAP@0.5-0.95) of a Mask R-CNN R50 network across the PubLayNet, DocBank &amp; DocLayNet data-sets. By evaluating on common label classes of each dataset, we observe that the DocLayNet-trained model has much less pronounced variations in performance across all datasets.
 
 |                 |            | Testing on   | Testing on   | Testing on   |
 |-----------------|------------|--------------|--------------|--------------|

tests/data/groundtruth/docling_v2/2305.03393v1.md

@@ -38,7 +38,7 @@ Approaches to formalize the logical structure and layout of tables in electronic
 
 Other work [20] aims at predicting a grid for each table and deciding which cells must be merged using an attention network. Im2Seq methods cast the problem as a sequence generation task [4,5,9,22], and therefore need an internal tablestructure representation language, which is often implemented with standard markup languages (e.g. HTML, LaTeX, Markdown). In theory, Im2Seq methods have a natural advantage over the OD and GNN methods by virtue of directly predicting the table-structure. As such, no post-processing or rules are needed in order to obtain the table-structure, which is necessary with OD and GNN approaches. In practice, this is not entirely true, because a predicted sequence of table-structure markup does not necessarily have to be syntactically correct. Hence, depending on the quality of the predicted sequence, some post-processing needs to be performed to ensure a syntactically valid (let alone correct) sequence.
 
-Within the Im2Seq method, we find several popular models, namely the encoder-dual-decoder model (EDD) [22], TableFormer [9], Tabsplitter[2] and Ye et. al. [19]. EDD uses two consecutive long short-term memory (LSTM) decoders to predict a table in HTML representation. The tag decoder predicts a sequence of HTML tags. For each decoded table cell ( <td> ), the attention is passed to the cell decoder to predict the content with an embedded OCR approach. The latter makes it susceptible to transcription errors in the cell content of the table. TableFormer address this reliance on OCR and uses two transformer decoders for HTML structure and cell bounding box prediction in an end-to-end architecture. The predicted cell bounding box is then used to extract text tokens from an originating (digital) PDF page, circumventing any need for OCR. TabSplitter [2] proposes a compact double-matrix representation of table rows and columns to do error detection and error correction of HTML structure sequences based on predictions from [19]. This compact double-matrix representation can not be used directly by the Img2seq model training, so the model uses HTML as an intermediate form. Chi et. al. [4] introduce a data set and a baseline method using bidirectional LSTMs to predict LaTeX code. Kayal [5] introduces Gated ResNet transformers to predict LaTeX code, and a separate OCR module to extract content.
+Within the Im2Seq method, we find several popular models, namely the encoder-dual-decoder model (EDD) [22], TableFormer [9], Tabsplitter[2] and Ye et. al. [19]. EDD uses two consecutive long short-term memory (LSTM) decoders to predict a table in HTML representation. The tag decoder predicts a sequence of HTML tags. For each decoded table cell ( &lt;td&gt; ), the attention is passed to the cell decoder to predict the content with an embedded OCR approach. The latter makes it susceptible to transcription errors in the cell content of the table. TableFormer address this reliance on OCR and uses two transformer decoders for HTML structure and cell bounding box prediction in an end-to-end architecture. The predicted cell bounding box is then used to extract text tokens from an originating (digital) PDF page, circumventing any need for OCR. TabSplitter [2] proposes a compact double-matrix representation of table rows and columns to do error detection and error correction of HTML structure sequences based on predictions from [19]. This compact double-matrix representation can not be used directly by the Img2seq model training, so the model uses HTML as an intermediate form. Chi et. al. [4] introduce a data set and a baseline method using bidirectional LSTMs to predict LaTeX code. Kayal [5] introduces Gated ResNet transformers to predict LaTeX code, and a separate OCR module to extract content.
 
 Im2Seq approaches have shown to be well-suited for the TSR task and allow a full end-to-end network design that can output the final table structure without pre- or post-processing logic. Furthermore, Im2Seq models have demonstrated to deliver state-of-the-art prediction accuracy [9]. This motivated the authors to investigate if the performance (both in accuracy and inference time) can be further improved by optimising the table structure representation language. We believe this is a necessary step before further improving neural network architectures for this task.
 
@@ -46,13 +46,13 @@ Im2Seq approaches have shown to be well-suited for the TSR task and allow a full
 
 All known Im2Seq based models for TSR fundamentally work in similar ways. Given an image of a table, the Im2Seq model predicts the structure of the table by generating a sequence of tokens. These tokens originate from a finite vocab-
 
-ulary and can be interpreted as a table structure. For example, with the HTML tokens <table> , </table> , <tr> , </tr> , <td> and </td> , one can construct simple table structures without any spanning cells. In reality though, one needs at least 28 HTML tokens to describe the most common complex tables observed in real-world documents [21,22], due to a variety of spanning cells definitions in the HTML token vocabulary.
+ulary and can be interpreted as a table structure. For example, with the HTML tokens &lt;table&gt; , &lt;/table&gt; , &lt;tr&gt; , &lt;/tr&gt; , &lt;td&gt; and &lt;/td&gt; , one can construct simple table structures without any spanning cells. In reality though, one needs at least 28 HTML tokens to describe the most common complex tables observed in real-world documents [21,22], due to a variety of spanning cells definitions in the HTML token vocabulary.
 
 Fig. 2. Frequency of tokens in HTML and OTSL as they appear in PubTabNet.
 
 <!-- image -->
 
-Obviously, HTML and other general-purpose markup languages were not designed for Im2Seq models. As such, they have some serious drawbacks. First, the token vocabulary needs to be artificially large in order to describe all plausible tabular structures. Since most Im2Seq models use an autoregressive approach, they generate the sequence token by token. Therefore, to reduce inference time, a shorter sequence length is critical. Every table-cell is represented by at least two tokens ( <td> and </td> ). Furthermore, when tokenizing the HTML structure, one needs to explicitly enumerate possible column-spans and row-spans as words. In practice, this ends up requiring 28 different HTML tokens (when including column- and row-spans up to 10 cells) just to describe every table in the PubTabNet dataset. Clearly, not every token is equally represented, as is depicted in Figure 2. This skewed distribution of tokens in combination with variable token row-length makes it challenging for models to learn the HTML structure.
+Obviously, HTML and other general-purpose markup languages were not designed for Im2Seq models. As such, they have some serious drawbacks. First, the token vocabulary needs to be artificially large in order to describe all plausible tabular structures. Since most Im2Seq models use an autoregressive approach, they generate the sequence token by token. Therefore, to reduce inference time, a shorter sequence length is critical. Every table-cell is represented by at least two tokens ( &lt;td&gt; and &lt;/td&gt; ). Furthermore, when tokenizing the HTML structure, one needs to explicitly enumerate possible column-spans and row-spans as words. In practice, this ends up requiring 28 different HTML tokens (when including column- and row-spans up to 10 cells) just to describe every table in the PubTabNet dataset. Clearly, not every token is equally represented, as is depicted in Figure 2. This skewed distribution of tokens in combination with variable token row-length makes it challenging for models to learn the HTML structure.
 
 Additionally, it would be desirable if the representation would easily allow an early detection of invalid sequences on-the-go, before the prediction of the entire table structure is completed. HTML is not well-suited for this purpose as the verification of incomplete sequences is non-trivial or even impossible.
 
@@ -194,7 +194,7 @@ Secondly, OTSL has more inherent structure and a significantly restricted vocabu
 - 12. Schreiber, S., Agne, S., Wolf, I., Dengel, A., Ahmed, S.: Deepdesrt: Deep learning for detection and structure recognition of tables in document images. In: 2017 14th IAPR international conference on document analysis and recognition (ICDAR). vol. 1, pp. 1162-1167. IEEE (2017)
 - 13. Siddiqui, S.A., Fateh, I.A., Rizvi, S.T.R., Dengel, A., Ahmed, S.: Deeptabstr: Deep learning based table structure recognition. In: 2019 International Conference on Document Analysis and Recognition (ICDAR). pp. 1403-1409 (2019). https:// doi.org/10.1109/ICDAR.2019.00226
 - 14. Smock, B., Pesala, R., Abraham, R.: PubTables-1M: Towards comprehensive table extraction from unstructured documents. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp. 4634-4642 (June 2022)
-- 15. Staar, P.W.J., Dolfi, M., Auer, C., Bekas, C.: Corpus conversion service: A machine learning platform to ingest documents at scale. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. pp. 774-782. KDD '18, Association for Computing Machinery, New York, NY, USA (2018). https://doi.org/10.1145/3219819.3219834 , https://doi.org/10. 1145/3219819.3219834
+- 15. Staar, P.W.J., Dolfi, M., Auer, C., Bekas, C.: Corpus conversion service: A machine learning platform to ingest documents at scale. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery &amp; Data Mining. pp. 774-782. KDD '18, Association for Computing Machinery, New York, NY, USA (2018). https://doi.org/10.1145/3219819.3219834 , https://doi.org/10. 1145/3219819.3219834
 - 16. Wang, X.: Tabular Abstraction, Editing, and Formatting. Ph.D. thesis, CAN (1996), aAINN09397
 - 17. Xue, W., Li, Q., Tao, D.: Res2tim: Reconstruct syntactic structures from table images. In: 2019 International Conference on Document Analysis and Recognition (ICDAR). pp. 749-755. IEEE (2019)
 

tests/data/groundtruth/docling_v2/code_and_formula.doctags.txt

@@ -7,7 +7,7 @@
 <section_header_level_1><location><page_2><loc_22><loc_84><loc_32><loc_85></location>Formula</section_header_level_1>
 <text><location><page_2><loc_22><loc_65><loc_80><loc_82></location>Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet.</text>
 <text><location><page_2><loc_22><loc_58><loc_80><loc_65></location>Duis autem vel eum iriure dolor in hendrerit in vulputate velit esse molestie consequat, vel illum dolore eu feugiat nulla facilisis at vero eros et accumsan et iusto odio dignissim qui blandit praesent luptatum zzril delenit augue duis dolore te feugait nulla facilisi. Lorem ipsum dolor sit amet, consectetuer adipiscing elit, sed diam nonummy nibh euismod tincidunt.</text>
-<formula><location><page_2><loc_47><loc_56><loc_56><loc_57></location>a 2 + 8 = 12</formula>
+<formula><location><page_2><loc_47><loc_56><loc_56><loc_57></location></formula>
 <text><location><page_2><loc_22><loc_38><loc_80><loc_55></location>Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet.</text>
 <text><location><page_2><loc_22><loc_29><loc_80><loc_38></location>Duis autem vel eum iriure dolor in hendrerit in vulputate velit esse molestie consequat, vel illum dolore eu feugiat nulla facilisis at vero eros et accumsan et iusto odio dignissim qui blandit praesent luptatum zzril delenit augue duis dolore te feugait nulla facilisi. Lorem ipsum dolor sit amet, consectetuer adipiscing elit, sed diam nonummy nibh euismod tincidunt ut laoreet dolore magna aliquam erat volutpat.</text>
 <text><location><page_2><loc_22><loc_21><loc_80><loc_29></location>Duis autem vel eum iriure dolor in hendrerit in vulputate velit esse molestie consequat, vel illum dolore eu feugiat nulla facilisis at vero eros et accumsan et iusto odio dignissim qui blandit praesent luptatum zzril delenit augue duis dolore te feugait nulla facilisi. Lorem ipsum dolor sit amet, consectetuer adipiscing elit, sed diam nonummy nibh euismod tincidunt ut laoreet dolore magna aliquam erat volutpat.</text>

tests/data/groundtruth/docling_v2/code_and_formula.md

@@ -16,7 +16,7 @@ Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod
 
 Duis autem vel eum iriure dolor in hendrerit in vulputate velit esse molestie consequat, vel illum dolore eu feugiat nulla facilisis at vero eros et accumsan et iusto odio dignissim qui blandit praesent luptatum zzril delenit augue duis dolore te feugait nulla facilisi. Lorem ipsum dolor sit amet, consectetuer adipiscing elit, sed diam nonummy nibh euismod tincidunt.
 
-$$a 2 + 8 = 12$$
+<!-- formula-not-decoded -->
 
 Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet.
 

tests/data/groundtruth/docling_v2/elife-56337.xml.md

@@ -18,7 +18,7 @@ TEs, especially long terminal repeat (LTR) retrotransposons, also known as endog
 
 We analyzed the RNA expression profiles of mouse KRAB-ZFPs across a wide range of tissues to identify candidates active in early embryos/ES cells. While the majority of KRAB-ZFPs are expressed at low levels and uniformly across tissues, a group of KRAB-ZFPs are highly and almost exclusively expressed in ES cells (Figure 1—figure supplement 1A). About two thirds of these KRAB-ZFPs are physically linked in two clusters on chromosome 2 (Chr2-cl) and 4 (Chr4-cl) (Figure 1—figure supplement 1B). These two clusters encode 40 and 21 KRAB-ZFP annotated genes, respectively, which, with one exception on Chr4-cl, do not have orthologues in rat or any other sequenced mammals (Supplementary file 1). The KRAB-ZFPs within these two genomic clusters also group together phylogenetically (Figure 1—figure supplement 1C), indicating these gene clusters arose by a series of recent segmental gene duplications (Kauzlaric et al., 2017).
 
-To determine the binding sites of the KRAB-ZFPs within these and other gene clusters, we expressed epitope-tagged KRAB-ZFPs using stably integrating vectors in mouse embryonic carcinoma (EC) or ES cells (Table 1, Supplementary file 1) and performed chromatin immunoprecipitation followed by deep sequencing (ChIP-seq). We then determined whether the identified binding sites are significantly enriched over annotated TEs and used the non-repetitive peak fraction to identify binding motifs. We discarded 7 of 68 ChIP-seq datasets because we could not obtain a binding motif or a target TE and manual inspection confirmed low signal to noise ratio. Of the remaining 61 KRAB-ZFPs, 51 significantly overlapped at least one TE subfamily (adjusted p-value<1e-5). Altogether, 81 LTR retrotransposon, 18 LINE, 10 SINE and one DNA transposon subfamilies were targeted by at least one of the 51 KRAB-ZFPs (Figure 1A and Supplementary file 1). Chr2-cl KRAB-ZFPs preferably bound IAPEz retrotransposons and L1-type LINEs, while Chr4-cl KRAB-ZFPs targeted various retrotransposons, including the closely related MMETn (hereafter referred to as ETn) and ETnERV (also known as MusD) elements (Figure 1A). ETn elements are non-autonomous LTR retrotransposons that require trans-complementation by the fully coding ETnERV elements that contain Gag, Pro and Pol genes (Ribet et al., 2004). These elements have accumulated to ~240 and~100 copies in the reference C57BL/6 genome, respectively, with ~550 solitary LTRs (Baust et al., 2003). Both ETn and ETnERVs are still active, generating polymorphisms and mutations in several mouse strains (Gagnier et al., 2019). The validity of our ChIP-seq screen was confirmed by the identification of binding motifs - which often resembled the computationally predicted motifs (Figure 1—figure supplement 2A) - for the majority of screened KRAB-ZFPs (Supplementary file 1). Moreover, predicted and experimentally determined motifs were found in targeted TEs in most cases (Supplementary file 1), and reporter repression assays confirmed KRAB-ZFP induced silencing for all the tested sequences (Figure 1—figure supplement 2B). Finally, we observed KAP1 and H3K9me3 enrichment at most of the targeted TEs in wild type ES cells, indicating that most of these KRAB-ZFPs are functionally active in the early embryo (Figure 1A).
+To determine the binding sites of the KRAB-ZFPs within these and other gene clusters, we expressed epitope-tagged KRAB-ZFPs using stably integrating vectors in mouse embryonic carcinoma (EC) or ES cells (Table 1, Supplementary file 1) and performed chromatin immunoprecipitation followed by deep sequencing (ChIP-seq). We then determined whether the identified binding sites are significantly enriched over annotated TEs and used the non-repetitive peak fraction to identify binding motifs. We discarded 7 of 68 ChIP-seq datasets because we could not obtain a binding motif or a target TE and manual inspection confirmed low signal to noise ratio. Of the remaining 61 KRAB-ZFPs, 51 significantly overlapped at least one TE subfamily (adjusted p-value&lt;1e-5). Altogether, 81 LTR retrotransposon, 18 LINE, 10 SINE and one DNA transposon subfamilies were targeted by at least one of the 51 KRAB-ZFPs (Figure 1A and Supplementary file 1). Chr2-cl KRAB-ZFPs preferably bound IAPEz retrotransposons and L1-type LINEs, while Chr4-cl KRAB-ZFPs targeted various retrotransposons, including the closely related MMETn (hereafter referred to as ETn) and ETnERV (also known as MusD) elements (Figure 1A). ETn elements are non-autonomous LTR retrotransposons that require trans-complementation by the fully coding ETnERV elements that contain Gag, Pro and Pol genes (Ribet et al., 2004). These elements have accumulated to ~240 and~100 copies in the reference C57BL/6 genome, respectively, with ~550 solitary LTRs (Baust et al., 2003). Both ETn and ETnERVs are still active, generating polymorphisms and mutations in several mouse strains (Gagnier et al., 2019). The validity of our ChIP-seq screen was confirmed by the identification of binding motifs - which often resembled the computationally predicted motifs (Figure 1—figure supplement 2A) - for the majority of screened KRAB-ZFPs (Supplementary file 1). Moreover, predicted and experimentally determined motifs were found in targeted TEs in most cases (Supplementary file 1), and reporter repression assays confirmed KRAB-ZFP induced silencing for all the tested sequences (Figure 1—figure supplement 2B). Finally, we observed KAP1 and H3K9me3 enrichment at most of the targeted TEs in wild type ES cells, indicating that most of these KRAB-ZFPs are functionally active in the early embryo (Figure 1A).
 
 We generally observed that KRAB-ZFPs present exclusively in mouse target TEs that are restricted to the mouse genome, indicating KRAB-ZFPs and their targets emerged together. For example, several mouse-specific KRAB-ZFPs in Chr2-cl and Chr4-cl target IAP and ETn elements which are only found in the mouse genome and are highly active. This is the strongest data to date supporting that recent KRAB-ZFP expansions in these young clusters is a response to recent TE activity. Likewise, ZFP599 and ZFP617, both conserved in Muroidea, bind to various ORR1-type LTRs which are present in the rat genome (Supplementary file 1). However, ZFP961, a KRAB-ZFP encoded on a small gene cluster on chromosome 8 that is conserved in Muroidea targets TEs that are only found in the mouse genome (e.g. ETn), a paradox we have previously observed with ZFP809, which also targets TEs that are evolutionarily younger than itself (Wolf et al., 2015b). The ZFP961 binding site is located at the 5’ end of the internal region of ETn and ETnERV elements, a sequence that usually contains the primer binding site (PBS), which is required to prime retroviral reverse transcription. Indeed, the ZFP961 motif closely resembles the PBSLys1,2 (Figure 1—figure supplement 3A), which had been previously identified as a KAP1-dependent target of retroviral repression (Yamauchi et al., 1995; Wolf et al., 2008). Repression of the PBSLys1,2 by ZFP961 was also confirmed in reporter assays (Figure 1—figure supplement 2B), indicating that ZFP961 is likely responsible for this silencing effect.
 
@@ -38,7 +38,7 @@ While we generally observed that TE-associated gene reactivation is not caused b
 
 ### ETn retrotransposition in Chr4-cl KO and WT mice
 
-IAP, ETn/ETnERV and MuLV/RLTR4 retrotransposons are highly polymorphic in inbred mouse strains (Nellåker et al., 2012), indicating that these elements are able to mobilize in the germ line. Since these retrotransposons are upregulated in Chr2-cl and Chr4-cl KO ES cells, we speculated that these KRAB-ZFP clusters evolved to minimize the risks of insertional mutagenesis by retrotransposition. To test this, we generated Chr2-cl and Chr4-cl KO mice via ES cell injection into blastocysts, and after germ line transmission we genotyped the offspring of heterozygous breeding pairs. While the offspring of Chr4-cl KO/WT parents were born close to Mendelian ratios in pure C57BL/6 and mixed C57BL/6 129Sv matings, one Chr4-cl KO/WT breeding pair gave birth to significantly fewer KO mice than expected (p-value=0.022) (Figure 4—figure supplement 1A). Likewise, two out of four Chr2-cl KO breeding pairs on mixed C57BL/6 129Sv matings failed to give birth to a single KO offspring (p-value<0.01) while the two other mating pairs produced KO offspring at near Mendelian ratios (Figure 4—figure supplement 1A). Altogether, these data indicate that KRAB-ZFP clusters are not absolutely essential in mice, but that genetic and/or epigenetic factors may contribute to reduced viability.
+IAP, ETn/ETnERV and MuLV/RLTR4 retrotransposons are highly polymorphic in inbred mouse strains (Nellåker et al., 2012), indicating that these elements are able to mobilize in the germ line. Since these retrotransposons are upregulated in Chr2-cl and Chr4-cl KO ES cells, we speculated that these KRAB-ZFP clusters evolved to minimize the risks of insertional mutagenesis by retrotransposition. To test this, we generated Chr2-cl and Chr4-cl KO mice via ES cell injection into blastocysts, and after germ line transmission we genotyped the offspring of heterozygous breeding pairs. While the offspring of Chr4-cl KO/WT parents were born close to Mendelian ratios in pure C57BL/6 and mixed C57BL/6 129Sv matings, one Chr4-cl KO/WT breeding pair gave birth to significantly fewer KO mice than expected (p-value=0.022) (Figure 4—figure supplement 1A). Likewise, two out of four Chr2-cl KO breeding pairs on mixed C57BL/6 129Sv matings failed to give birth to a single KO offspring (p-value&lt;0.01) while the two other mating pairs produced KO offspring at near Mendelian ratios (Figure 4—figure supplement 1A). Altogether, these data indicate that KRAB-ZFP clusters are not absolutely essential in mice, but that genetic and/or epigenetic factors may contribute to reduced viability.
 
 We reasoned that retrotransposon activation could account for the reduced viability of Chr2-cl and Chr4-cl KO mice in some matings. However, since only rare matings produced non-viable KO embryos, we instead turned to the viable KO mice to assay for increased transposon activity. RNA-seq in blood, brain and testis revealed that, with a few exceptions, retrotransposons upregulated in Chr2 and Chr4 KRAB-ZFP cluster KO ES cells are not expressed at higher levels in adult tissues (Figure 4—figure supplement 1B). Likewise, no strong transcriptional TE reactivation phenotype was observed in liver and kidney of Chr4-cl KO mice (data not shown) and ChIP-seq with antibodies against H3K4me1, H3K4me3 and H3K27ac in testis of Chr4-cl WT and KO mice revealed no increase of active histone marks at ETn elements or other TEs (data not shown). This indicates that Chr2-cl and Chr4-cl KRAB-ZFPs are primarily required for TE repression during early development. This is consistent with the high expression of these KRAB-ZFPs uniquely in ES cells (Figure 1—figure supplement 1A). To determine whether retrotransposition occurs at a higher frequency in Chr4-cl KO mice during development, we screened for novel ETn (ETn/ETnERV) and MuLV (MuLV/RLTR4\_MM) insertions in viable Chr4-cl KO mice. For this purpose, we developed a capture-sequencing approach to enrich for ETn/MuLV DNA and flanking sequences from genomic DNA using probes that hybridize with the 5’ and 3’ ends of ETn and MuLV LTRs prior to deep sequencing. We screened genomic DNA samples from a total of 76 mice, including 54 mice from ancestry-controlled Chr4-cl KO matings in various strain backgrounds, the two ES cell lines the Chr4-cl KO mice were generated from, and eight mice from a Chr2-cl KO mating which served as a control (since ETn and MuLVs are not activated in Chr2-cl KO ES cells) (Supplementary file 4). Using this approach, we were able to enrich reads mapping to ETn/MuLV LTRs about 2,000-fold compared to genome sequencing without capture. ETn/MuLV insertions were determined by counting uniquely mapped reads that were paired with reads mapping to ETn/MuLV elements (see materials and methods for details). To assess the efficiency of the capture approach, we determined what proportion of a set of 309 largely intact (two LTRs flanking an internal sequence) reference ETn elements could be identified using our sequencing data. 95% of these insertions were called with high confidence in the majority of our samples (data not shown), indicating that we are able to identify ETn insertions at a high recovery rate.
 
@@ -74,7 +74,7 @@ All gRNAs were expressed from the pX330-U6-Chimeric\_BB-CBh-hSpCas9 vector (RRID
 
 For ChIP-seq analysis of KRAB-ZFP expressing cells, 5–10 × 107 cells were crosslinked and immunoprecipitated with anti-FLAG (Sigma-Aldrich Cat# F1804, RRID:AB\_262044) or anti-HA (Abcam Cat# ab9110, RRID:AB\_307019 or Covance Cat# MMS-101P-200, RRID:AB\_10064068) antibody using one of two previously described protocols (O'Geen et al., 2010; Imbeault et al., 2017) as indicated in Supplementary file 1. H3K9me3 distribution in Chr4-cl, Chr10-cl, Chr13.1-cl and Chr13.2-cl KO ES cells was determined by native ChIP-seq with anti-H3K9me3 serum (Active Motif Cat# 39161, RRID:AB\_2532132) as described previously (Karimi et al., 2011). In Chr2-cl KO ES cells, H3K9me3 and KAP1 ChIP-seq was performed as previously described (Ecco et al., 2016). In Chr4-cl KO and WT ES cells KAP1 binding was determined by endogenous tagging of KAP1 with C-terminal GFP (Supplementary file 3), followed by FACS to enrich for GFP-positive cells and ChIP with anti-GFP (Thermo Fisher Scientific Cat# A-11122, RRID:AB\_221569) using a previously described protocol (O'Geen et al., 2010). For ChIP-seq analysis of active histone marks, cross-linked chromatin from ES cells or testis (from two-week old mice) was immunoprecipitated with antibodies against H3K4me3 (Abcam Cat# ab8580, RRID:AB\_306649), H3K4me1 (Abcam Cat# ab8895, RRID:AB\_306847) and H3K27ac (Abcam Cat# ab4729, RRID:AB\_2118291) following the protocol developed by O'Geen et al., 2010 or Khil et al., 2012 respectively.
 
-ChIP-seq libraries were constructed and sequenced as indicated in Supplementary file 4. Reads were mapped to the mm9 genome using Bowtie (RRID:SCR\_005476; settings: --best) or Bowtie2 (Langmead and Salzberg, 2012) as indicated in Supplementary file 4. Under these settings, reads that map to multiple genomic regions are assigned to the top-scored match and, if a set of equally good choices is encountered, a pseudo-random number is used to choose one location. Peaks were called using MACS14 (RRID:SCR\_013291) under high stringency settings (p<1e-10, peak enrichment >20) (Zhang et al., 2008). Peaks were called both over the Input control and a FLAG or HA control ChIP (unless otherwise stated in Supplementary file 4) and only peaks that were called in both settings were kept for further analysis. In cases when the stringency settings did not result in at least 50 peaks, the settings were changed to medium (p<1e-10, peak enrichment >10) or low (p<1e-5, peak enrichment >10) stringency (Supplementary file 4). For further analysis, all peaks were scaled to 200 bp regions centered around the peak summits. The overlap of the scaled peaks to each repeat element in UCSC Genome Browser (RRID:SCR\_005780) were calculated by using the bedfisher function (settings: -f 0.25) from BEDTools (RRID:SCR\_006646). The right-tailed p-values between pair-wise comparison of each ChIP-seq peak and repeat element were extracted, and then adjusted using the Benjamini-Hochberg approach implemented in the R function p.adjust(). Binding motifs were determined using only nonrepetitive (<10% repeat content) peaks with MEME (Bailey et al., 2009). MEME motifs were compared with in silico predicted motifs (Najafabadi et al., 2015) using Tomtom (Bailey et al., 2009) and considered as significantly overlapping with a False Discovery Rate (FDR) below 0.1. To find MEME and predicted motifs in repetitive peaks, we used FIMO (Bailey et al., 2009). Differential H3K9me3 and KAP1 distribution in WT and Chr2-cl or Chr4-cl KO ES cells at TEs was determined by counting ChIP-seq reads overlapping annotated insertions of each TE group using BEDTools (MultiCovBed). Additionally, ChIP-seq reads were counted at the TE fraction that was bound by Chr2-cl or Chr4-cl KRAB-ZFPs (overlapping with 200 bp peaks). Count tables were concatenated and analyzed using DESeq2 (Love et al., 2014). The previously published ChIP-seq datasets for KAP1 (Castro-Diaz et al., 2014) and H3K9me3 (Dan et al., 2014) were re-mapped using Bowtie (--best).
+ChIP-seq libraries were constructed and sequenced as indicated in Supplementary file 4. Reads were mapped to the mm9 genome using Bowtie (RRID:SCR\_005476; settings: --best) or Bowtie2 (Langmead and Salzberg, 2012) as indicated in Supplementary file 4. Under these settings, reads that map to multiple genomic regions are assigned to the top-scored match and, if a set of equally good choices is encountered, a pseudo-random number is used to choose one location. Peaks were called using MACS14 (RRID:SCR\_013291) under high stringency settings (p&lt;1e-10, peak enrichment &gt;20) (Zhang et al., 2008). Peaks were called both over the Input control and a FLAG or HA control ChIP (unless otherwise stated in Supplementary file 4) and only peaks that were called in both settings were kept for further analysis. In cases when the stringency settings did not result in at least 50 peaks, the settings were changed to medium (p&lt;1e-10, peak enrichment &gt;10) or low (p&lt;1e-5, peak enrichment &gt;10) stringency (Supplementary file 4). For further analysis, all peaks were scaled to 200 bp regions centered around the peak summits. The overlap of the scaled peaks to each repeat element in UCSC Genome Browser (RRID:SCR\_005780) were calculated by using the bedfisher function (settings: -f 0.25) from BEDTools (RRID:SCR\_006646). The right-tailed p-values between pair-wise comparison of each ChIP-seq peak and repeat element were extracted, and then adjusted using the Benjamini-Hochberg approach implemented in the R function p.adjust(). Binding motifs were determined using only nonrepetitive (&lt;10% repeat content) peaks with MEME (Bailey et al., 2009). MEME motifs were compared with in silico predicted motifs (Najafabadi et al., 2015) using Tomtom (Bailey et al., 2009) and considered as significantly overlapping with a False Discovery Rate (FDR) below 0.1. To find MEME and predicted motifs in repetitive peaks, we used FIMO (Bailey et al., 2009). Differential H3K9me3 and KAP1 distribution in WT and Chr2-cl or Chr4-cl KO ES cells at TEs was determined by counting ChIP-seq reads overlapping annotated insertions of each TE group using BEDTools (MultiCovBed). Additionally, ChIP-seq reads were counted at the TE fraction that was bound by Chr2-cl or Chr4-cl KRAB-ZFPs (overlapping with 200 bp peaks). Count tables were concatenated and analyzed using DESeq2 (Love et al., 2014). The previously published ChIP-seq datasets for KAP1 (Castro-Diaz et al., 2014) and H3K9me3 (Dan et al., 2014) were re-mapped using Bowtie (--best).
 
 ### Luciferase reporter assays
 
@@ -149,7 +149,7 @@ Key resources table:
 ## Figures
 
 Figure 1.: Genome-wide binding patterns of mouse KRAB-ZFPs.
-(A) Probability heatmap of KRAB-ZFP binding to TEs. Blue color intensity (main field) corresponds to -log10 (adjusted p-value) enrichment of ChIP-seq peak overlap with TE groups (Fisher’s exact test). The green/red color intensity (top panel) represents mean KAP1 (GEO accession: GSM1406445) and H3K9me3 (GEO accession: GSM1327148) enrichment (respectively) at peaks overlapping significantly targeted TEs (adjusted p-value<1e-5) in WT ES cells. (B) Summarized ChIP-seq signal for indicated KRAB-ZFPs and previously published KAP1 and H3K9me3 in WT ES cells across 127 intact ETn elements. (C) Heatmaps of KRAB-ZFP ChIP-seq signal at ChIP-seq peaks. For better comparison, peaks for all three KRAB-ZFPs were called with the same parameters (p<1e-10, peak enrichment >20). The top panel shows a schematic of the arrangement of the contact amino acid composition of each zinc finger. Zinc fingers are grouped and colored according to similarity, with amino acid differences relative to the five consensus fingers highlighted in white.
+(A) Probability heatmap of KRAB-ZFP binding to TEs. Blue color intensity (main field) corresponds to -log10 (adjusted p-value) enrichment of ChIP-seq peak overlap with TE groups (Fisher’s exact test). The green/red color intensity (top panel) represents mean KAP1 (GEO accession: GSM1406445) and H3K9me3 (GEO accession: GSM1327148) enrichment (respectively) at peaks overlapping significantly targeted TEs (adjusted p-value&lt;1e-5) in WT ES cells. (B) Summarized ChIP-seq signal for indicated KRAB-ZFPs and previously published KAP1 and H3K9me3 in WT ES cells across 127 intact ETn elements. (C) Heatmaps of KRAB-ZFP ChIP-seq signal at ChIP-seq peaks. For better comparison, peaks for all three KRAB-ZFPs were called with the same parameters (p&lt;1e-10, peak enrichment &gt;20). The top panel shows a schematic of the arrangement of the contact amino acid composition of each zinc finger. Zinc fingers are grouped and colored according to similarity, with amino acid differences relative to the five consensus fingers highlighted in white.
 Figure 1—source data 1.KRAB-ZFP expression in 40 mouse tissues and cell lines (ENCODE).Mean values of replicates are shown as log2 transcripts per million.
 Figure 1—source data 2.Probability heatmap of KRAB-ZFP binding to TEs.Values corresponds to -log10 (adjusted p-value) enrichment of ChIP-seq peak overlap with TE groups (Fisher’s exact test).
 
@@ -161,7 +161,7 @@ Figure 1—figure supplement 1.: ES cell-specific expression of KRAB-ZFP gene cl
 <!-- image -->
 
 Figure 1—figure supplement 2.: KRAB-ZFP binding motifs and their repression activity.
-(A) Comparison of computationally predicted (bottom) and experimentally determined (top) KRAB-ZFP binding motifs. Only significant pairs are shown (FDR < 0.1). (B) Luciferase reporter assays to confirm KRAB-ZFP repression of the identified target sites. Bars show the luciferase activity (normalized to Renilla luciferase) of reporter plasmids containing the indicated target sites cloned upstream of the SV40 promoter. Reporter plasmids were co-transfected into 293 T cells with a Renilla luciferase plasmid for normalization and plasmids expressing the targeting KRAB-ZFP. Normalized mean luciferase activity (from three replicates) is shown relative to luciferase activity of the reporter plasmid co-transfected with an empty pcDNA3.1 vector.
+(A) Comparison of computationally predicted (bottom) and experimentally determined (top) KRAB-ZFP binding motifs. Only significant pairs are shown (FDR &lt; 0.1). (B) Luciferase reporter assays to confirm KRAB-ZFP repression of the identified target sites. Bars show the luciferase activity (normalized to Renilla luciferase) of reporter plasmids containing the indicated target sites cloned upstream of the SV40 promoter. Reporter plasmids were co-transfected into 293 T cells with a Renilla luciferase plasmid for normalization and plasmids expressing the targeting KRAB-ZFP. Normalized mean luciferase activity (from three replicates) is shown relative to luciferase activity of the reporter plasmid co-transfected with an empty pcDNA3.1 vector.
 
 <!-- image -->
 
@@ -171,7 +171,7 @@ Figure 1—figure supplement 3.: KRAB-ZFP binding to ETn retrotransposons.
 <!-- image -->
 
 Figure 2.: Retrotransposon reactivation in KRAB-ZFP cluster KO ES cells.
-(A) RNA-seq analysis of TE expression in five KRAB-ZFP cluster KO ES cells. Green and grey squares on top of the panel represent KRAB-ZFPs with or without ChIP-seq data, respectively, within each deleted gene cluster. Reactivated TEs that are bound by one or several KRAB-ZFPs are indicated by green squares in the panel. Significantly up- and downregulated elements (adjusted p-value<0.05) are highlighted in red and green, respectively. (B) Differential KAP1 binding and H3K9me3 enrichment at TE groups (summarized across all insertions) in Chr2-cl and Chr4-cl KO ES cells. TE groups targeted by one or several KRAB-ZFPs encoded within the deleted clusters are highlighted in blue (differential enrichment over the entire TE sequences) and red (differential enrichment at TE regions that overlap with KRAB-ZFP ChIP-seq peaks). (C) DNA methylation status of CpG sites at indicated TE groups in WT and Chr4-cl KO ES cells grown in serum containing media or in hypomethylation-inducing media (2i + Vitamin C). P-values were calculated using paired t-test.
+(A) RNA-seq analysis of TE expression in five KRAB-ZFP cluster KO ES cells. Green and grey squares on top of the panel represent KRAB-ZFPs with or without ChIP-seq data, respectively, within each deleted gene cluster. Reactivated TEs that are bound by one or several KRAB-ZFPs are indicated by green squares in the panel. Significantly up- and downregulated elements (adjusted p-value&lt;0.05) are highlighted in red and green, respectively. (B) Differential KAP1 binding and H3K9me3 enrichment at TE groups (summarized across all insertions) in Chr2-cl and Chr4-cl KO ES cells. TE groups targeted by one or several KRAB-ZFPs encoded within the deleted clusters are highlighted in blue (differential enrichment over the entire TE sequences) and red (differential enrichment at TE regions that overlap with KRAB-ZFP ChIP-seq peaks). (C) DNA methylation status of CpG sites at indicated TE groups in WT and Chr4-cl KO ES cells grown in serum containing media or in hypomethylation-inducing media (2i + Vitamin C). P-values were calculated using paired t-test.
 Figure 2—source data 1.Differential H3K9me3 and KAP1 distribution in WT and KRAB-ZFP cluster KO ES cells at TE families and KRAB-ZFP bound TE insertions.Differential read counts and statistical testing were determined by DESeq2.
 
 <!-- image -->
@@ -182,7 +182,7 @@ Figure 2—figure supplement 1.: Epigenetic changes at TEs and TE-borne enhancer
 <!-- image -->
 
 Figure 3.: TE-dependent gene activation in KRAB-ZFP cluster KO ES cells.
-(A) Differential gene expression in Chr2-cl and Chr4-cl KO ES cells. Significantly up- and downregulated genes (adjusted p-value<0.05) are highlighted in red and green, respectively, KRAB-ZFP genes within the deleted clusters are shown in blue. (B) Correlation of TEs and gene deregulation. Plots show enrichment of TE groups within 100 kb of up- and downregulated genes relative to all genes. Significantly overrepresented LTR and LINE groups (adjusted p-value<0.1) are highlighted in blue and red, respectively. (C) Schematic view of the downstream region of Chst1 where a 5’ truncated ETn insertion is located. ChIP-seq (Input subtracted from ChIP) data for overexpressed epitope-tagged Gm13051 (a Chr4-cl KRAB-ZFP) in F9 EC cells, and re-mapped KAP1 (GEO accession: GSM1406445) and H3K9me3 (GEO accession: GSM1327148) in WT ES cells are shown together with RNA-seq data from Chr4-cl WT and KO ES cells (mapped using Bowtie (-a -m 1 --strata -v 2) to exclude reads that cannot be uniquely mapped). (D) RT-qPCR analysis of Chst1 mRNA expression in Chr4-cl WT and KO ES cells with or without the CRISPR/Cas9 deleted ETn insertion near Chst1. Values represent mean expression (normalized to Gapdh) from three biological replicates per sample (each performed in three technical replicates) in arbitrary units. Error bars represent standard deviation and asterisks indicate significance (p<0.01, Student’s t-test). n.s.: not significant. (E) Mean coverage of ChIP-seq data (Input subtracted from ChIP) in Chr4-cl WT and KO ES cells over 127 full-length ETn insertions. The binding sites of the Chr4-cl KRAB-ZFPs Rex2 and Gm13051 are indicated by dashed lines.
+(A) Differential gene expression in Chr2-cl and Chr4-cl KO ES cells. Significantly up- and downregulated genes (adjusted p-value&lt;0.05) are highlighted in red and green, respectively, KRAB-ZFP genes within the deleted clusters are shown in blue. (B) Correlation of TEs and gene deregulation. Plots show enrichment of TE groups within 100 kb of up- and downregulated genes relative to all genes. Significantly overrepresented LTR and LINE groups (adjusted p-value&lt;0.1) are highlighted in blue and red, respectively. (C) Schematic view of the downstream region of Chst1 where a 5’ truncated ETn insertion is located. ChIP-seq (Input subtracted from ChIP) data for overexpressed epitope-tagged Gm13051 (a Chr4-cl KRAB-ZFP) in F9 EC cells, and re-mapped KAP1 (GEO accession: GSM1406445) and H3K9me3 (GEO accession: GSM1327148) in WT ES cells are shown together with RNA-seq data from Chr4-cl WT and KO ES cells (mapped using Bowtie (-a -m 1 --strata -v 2) to exclude reads that cannot be uniquely mapped). (D) RT-qPCR analysis of Chst1 mRNA expression in Chr4-cl WT and KO ES cells with or without the CRISPR/Cas9 deleted ETn insertion near Chst1. Values represent mean expression (normalized to Gapdh) from three biological replicates per sample (each performed in three technical replicates) in arbitrary units. Error bars represent standard deviation and asterisks indicate significance (p&lt;0.01, Student’s t-test). n.s.: not significant. (E) Mean coverage of ChIP-seq data (Input subtracted from ChIP) in Chr4-cl WT and KO ES cells over 127 full-length ETn insertions. The binding sites of the Chr4-cl KRAB-ZFPs Rex2 and Gm13051 are indicated by dashed lines.
 
 <!-- image -->
 
@@ -194,7 +194,7 @@ Figure 4—source data 2.Sequences of capture-seq probes used to enrich genomic
 <!-- image -->
 
 Figure 4—figure supplement 1.: Birth statistics of KRAB-ZFP cluster KO mice and TE reactivation in adult tissues.
-(A) Birth statistics of Chr4- and Chr2-cl mice derived from KO/WT x KO/WT matings in different strain backgrounds. (B) RNA-seq analysis of TE expression in Chr2- (left) and Chr4-cl (right) KO tissues. TE groups with the highest reactivation phenotype in ES cells are shown separately. Significantly up- and downregulated elements (adjusted p-value<0.05) are highlighted in red and green, respectively. Experiments were performed in at least two biological replicates.
+(A) Birth statistics of Chr4- and Chr2-cl mice derived from KO/WT x KO/WT matings in different strain backgrounds. (B) RNA-seq analysis of TE expression in Chr2- (left) and Chr4-cl (right) KO tissues. TE groups with the highest reactivation phenotype in ES cells are shown separately. Significantly up- and downregulated elements (adjusted p-value&lt;0.05) are highlighted in red and green, respectively. Experiments were performed in at least two biological replicates.
 
 <!-- image -->
 
@@ -214,7 +214,7 @@ Figure 4—figure supplement 3.: Confirmation of novel ETn insertions identified
 - C Baust; L Gagnier; GJ Baillie; MJ Harris; DM Juriloff; DL Mager. Structure and expression of mobile ETnII retroelements and their coding-competent MusD relatives in the mouse. Journal of Virology (2003)
 - K Blaschke; KT Ebata; MM Karimi; JA Zepeda-Martínez; P Goyal; S Mahapatra; A Tam; DJ Laird; M Hirst; A Rao; MC Lorincz; M Ramalho-Santos. Vitamin C induces Tet-dependent DNA demethylation and a blastocyst-like state in ES cells. Nature (2013)
 - A Brodziak; E Ziółko; M Muc-Wierzgoń; E Nowakowska-Zajdel; T Kokot; K Klakla. The role of human endogenous retroviruses in the pathogenesis of autoimmune diseases. Medical Science Monitor : International Medical Journal of Experimental and Clinical Research (2012)
-- N Castro-Diaz; G Ecco; A Coluccio; A Kapopoulou; B Yazdanpanah; M Friedli; J Duc; SM Jang; P Turelli; D Trono. Evolutionally dynamic L1 regulation in embryonic stem cells. Genes & Development (2014)
+- N Castro-Diaz; G Ecco; A Coluccio; A Kapopoulou; B Yazdanpanah; M Friedli; J Duc; SM Jang; P Turelli; D Trono. Evolutionally dynamic L1 regulation in embryonic stem cells. Genes &amp; Development (2014)
 - EB Chuong; NC Elde; C Feschotte. Regulatory evolution of innate immunity through co-option of endogenous retroviruses. Science (2016)
 - J Dan; Y Liu; N Liu; M Chiourea; M Okuka; T Wu; X Ye; C Mou; L Wang; L Wang; Y Yin; J Yuan; B Zuo; F Wang; Z Li; X Pan; Z Yin; L Chen; DL Keefe; S Gagos; A Xiao; L Liu. Rif1 maintains telomere length homeostasis of ESCs by mediating heterochromatin silencing. Developmental Cell (2014)
 - A De Iaco; E Planet; A Coluccio; S Verp; J Duc; D Trono. DUX-family transcription factors regulate zygotic genome activation in placental mammals. Nature Genetics (2017)
@@ -238,7 +238,7 @@ Figure 4—figure supplement 3.: Confirmation of novel ETn insertions identified
 - JA Lehoczky; PE Thomas; KM Patrie; KM Owens; LM Villarreal; K Galbraith; J Washburn; CN Johnson; B Gavino; AD Borowsky; KJ Millen; P Wakenight; W Law; ML Van Keuren; G Gavrilina; ED Hughes; TL Saunders; L Brihn; JH Nadeau; JW Innis. A novel intergenic ETnII-β insertion mutation causes multiple malformations in Polypodia mice. PLOS Genetics (2013)
 - D Leung; T Du; U Wagner; W Xie; AY Lee; P Goyal; Y Li; KE Szulwach; P Jin; MC Lorincz; B Ren. Regulation of DNA methylation turnover at LTR retrotransposons and imprinted loci by the histone methyltransferase Setdb1. PNAS (2014)
 - J Lilue; AG Doran; IT Fiddes; M Abrudan; J Armstrong; R Bennett; W Chow; J Collins; S Collins; A Czechanski; P Danecek; M Diekhans; DD Dolle; M Dunn; R Durbin; D Earl; A Ferguson-Smith; P Flicek; J Flint; A Frankish; B Fu; M Gerstein; J Gilbert; L Goodstadt; J Harrow; K Howe; X Ibarra-Soria; M Kolmogorov; CJ Lelliott; DW Logan; J Loveland; CE Mathews; R Mott; P Muir; S Nachtweide; FCP Navarro; DT Odom; N Park; S Pelan; SK Pham; M Quail; L Reinholdt; L Romoth; L Shirley; C Sisu; M Sjoberg-Herrera; M Stanke; C Steward; M Thomas; G Threadgold; D Thybert; J Torrance; K Wong; J Wood; B Yalcin; F Yang; DJ Adams; B Paten; TM Keane. Sixteen diverse laboratory mouse reference genomes define strain-specific haplotypes and novel functional loci. Nature Genetics (2018)
-- S Liu; J Brind'Amour; MM Karimi; K Shirane; A Bogutz; L Lefebvre; H Sasaki; Y Shinkai; MC Lorincz. Setdb1  is required for germline development and silencing of H3K9me3-marked endogenous retroviruses in primordial germ cells. Genes & Development (2014)
+- S Liu; J Brind'Amour; MM Karimi; K Shirane; A Bogutz; L Lefebvre; H Sasaki; Y Shinkai; MC Lorincz. Setdb1  is required for germline development and silencing of H3K9me3-marked endogenous retroviruses in primordial germ cells. Genes &amp; Development (2014)
 - MI Love; W Huber; S Anders. Moderated estimation of fold change and dispersion for RNA-seq data with DESeq2. Genome Biology (2014)
 - F Lugani; R Arora; N Papeta; A Patel; Z Zheng; R Sterken; RA Singer; G Caridi; C Mendelsohn; L Sussel; VE Papaioannou; AG Gharavi. A retrotransposon insertion in the 5' regulatory domain of Ptf1a results in ectopic gene expression and multiple congenital defects in Danforth's short tail mouse. PLOS Genetics (2013)
 - TS Macfarlan; WD Gifford; S Driscoll; K Lettieri; HM Rowe; D Bonanomi; A Firth; O Singer; D Trono; SL Pfaff. Embryonic stem cell potency fluctuates with endogenous retrovirus activity. Nature (2012)
@@ -253,7 +253,7 @@ Figure 4—figure supplement 3.: Confirmation of novel ETn insertions identified
 - HM Rowe; J Jakobsson; D Mesnard; J Rougemont; S Reynard; T Aktas; PV Maillard; H Layard-Liesching; S Verp; J Marquis; F Spitz; DB Constam; D Trono. KAP1 controls endogenous retroviruses in embryonic stem cells. Nature (2010)
 - HM Rowe; A Kapopoulou; A Corsinotti; L Fasching; TS Macfarlan; Y Tarabay; S Viville; J Jakobsson; SL Pfaff; D Trono. TRIM28 repression of retrotransposon-based enhancers is necessary to preserve transcriptional dynamics in embryonic stem cells. Genome Research (2013)
 - SN Schauer; PE Carreira; R Shukla; DJ Gerhardt; P Gerdes; FJ Sanchez-Luque; P Nicoli; M Kindlova; S Ghisletti; AD Santos; D Rapoud; D Samuel; J Faivre; AD Ewing; SR Richardson; GJ Faulkner. L1 retrotransposition is a common feature of mammalian hepatocarcinogenesis. Genome Research (2018)
-- DC Schultz; K Ayyanathan; D Negorev; GG Maul; FJ Rauscher. SETDB1: a novel KAP-1-associated histone H3, lysine 9-specific methyltransferase that contributes to HP1-mediated silencing of euchromatic genes by KRAB zinc-finger proteins. Genes & Development (2002)
+- DC Schultz; K Ayyanathan; D Negorev; GG Maul; FJ Rauscher. SETDB1: a novel KAP-1-associated histone H3, lysine 9-specific methyltransferase that contributes to HP1-mediated silencing of euchromatic genes by KRAB zinc-finger proteins. Genes &amp; Development (2002)
 - K Semba; K Araki; K Matsumoto; H Suda; T Ando; A Sei; H Mizuta; K Takagi; M Nakahara; M Muta; G Yamada; N Nakagata; A Iida; S Ikegawa; Y Nakamura; M Araki; K Abe; K Yamamura. Ectopic expression of Ptf1a induces spinal defects, urogenital defects, and anorectal malformations in Danforth's short tail mice. PLOS Genetics (2013)
 - SP Sripathy; J Stevens; DC Schultz. The KAP1 corepressor functions to coordinate the assembly of de novo HP1-demarcated microenvironments of heterochromatin required for KRAB zinc finger protein-mediated transcriptional repression. Molecular and Cellular Biology (2006)
 - JH Thomas; S Schneider. Coevolution of retroelements and tandem zinc finger genes. Genome Research (2011)
@@ -263,6 +263,6 @@ Figure 4—figure supplement 3.: Confirmation of novel ETn insertions identified
 - J Wang; G Xie; M Singh; AT Ghanbarian; T Raskó; A Szvetnik; H Cai; D Besser; A Prigione; NV Fuchs; GG Schumann; W Chen; MC Lorincz; Z Ivics; LD Hurst; Z Izsvák. Primate-specific endogenous retrovirus-driven transcription defines naive-like stem cells. Nature (2014)
 - D Wolf; K Hug; SP Goff. TRIM28 mediates primer binding site-targeted silencing of Lys1,2 tRNA-utilizing retroviruses in embryonic cells. PNAS (2008)
 - G Wolf; D Greenberg; TS Macfarlan. Spotting the enemy within: targeted silencing of foreign DNA in mammalian genomes by the Krüppel-associated box zinc finger protein family. Mobile DNA (2015a)
-- G Wolf; P Yang; AC Füchtbauer; EM Füchtbauer; AM Silva; C Park; W Wu; AL Nielsen; FS Pedersen; TS Macfarlan. The KRAB zinc finger protein ZFP809 is required to initiate epigenetic silencing of endogenous retroviruses. Genes & Development (2015b)
+- G Wolf; P Yang; AC Füchtbauer; EM Füchtbauer; AM Silva; C Park; W Wu; AL Nielsen; FS Pedersen; TS Macfarlan. The KRAB zinc finger protein ZFP809 is required to initiate epigenetic silencing of endogenous retroviruses. Genes &amp; Development (2015b)
 - M Yamauchi; B Freitag; C Khan; B Berwin; E Barklis. Stem cell factor binding to retrovirus primer binding site silencers. Journal of Virology (1995)
 - Y Zhang; T Liu; CA Meyer; J Eeckhoute; DS Johnson; BE Bernstein; C Nusbaum; RM Myers; M Brown; W Li; XS Liu. Model-based analysis of ChIP-Seq (MACS). Genome Biology (2008)

tests/data/groundtruth/docling_v2/example_04.html.md

@@ -1,7 +1,7 @@
 # Data Table with Rowspan and Colspan
 
-| Header 1                   | Header 2 & 3 (colspan)     | Header 2 & 3 (colspan)     |
+| Header 1                   | Header 2 & 3 (colspan)     | Header 2 & 3 (colspan)     |
 |----------------------------|----------------------------|----------------------------|
-| Row 1 & 2, Col 1 (rowspan) | Row 1, Col 2               | Row 1, Col 3               |
-| Row 1 & 2, Col 1 (rowspan) | Row 2, Col 2 & 3 (colspan) | Row 2, Col 2 & 3 (colspan) |
+| Row 1 & 2, Col 1 (rowspan) | Row 1, Col 2               | Row 1, Col 3               |
+| Row 1 & 2, Col 1 (rowspan) | Row 2, Col 2 & 3 (colspan) | Row 2, Col 2 & 3 (colspan) |
 | Row 3, Col 1               | Row 3, Col 2               | Row 3, Col 3               |

tests/data/groundtruth/docling_v2/example_05.html.md

@@ -1,7 +1,7 @@
 # Omitted html and body tags
 
-| Header 1                   | Header 2 & 3 (colspan)     | Header 2 & 3 (colspan)     |
+| Header 1                   | Header 2 & 3 (colspan)     | Header 2 & 3 (colspan)     |
 |----------------------------|----------------------------|----------------------------|
-| Row 1 & 2, Col 1 (rowspan) | Row 1, Col 2               | Row 1, Col 3               |
-| Row 1 & 2, Col 1 (rowspan) | Row 2, Col 2 & 3 (colspan) | Row 2, Col 2 & 3 (colspan) |
+| Row 1 & 2, Col 1 (rowspan) | Row 1, Col 2               | Row 1, Col 3               |
+| Row 1 & 2, Col 1 (rowspan) | Row 2, Col 2 & 3 (colspan) | Row 2, Col 2 & 3 (colspan) |
 | Row 3, Col 1               | Row 3, Col 2               | Row 3, Col 3               |

tests/data/groundtruth/docling_v2/ipa20180000016.md

@@ -112,25 +112,25 @@ Examples of the first fluorescent material 71 specifically include fluorescent m
 
 (i−j)MgO.(j/2)Sc₂O₃.kMgF₂.mCaF₂.(1−n)GeO₂.(n/2)Mt₂O₃:zMn⁴⁺ (I)
 
-wherein Mt is at least one selected from the group consisting of Al, Ga, and In, and j, k, m, n, and z are numbers satisfying 2≦i≦4, 0≦j<0.5, 0<k<1.5, 0≦m<1.5, 0<n<0.5, and 0<z<0.05, respectively.
+wherein Mt is at least one selected from the group consisting of Al, Ga, and In, and j, k, m, n, and z are numbers satisfying 2≦i≦4, 0≦j&lt;0.5, 0&lt;k&lt;1.5, 0≦m&lt;1.5, 0&lt;n&lt;0.5, and 0&lt;z&lt;0.05, respectively.
 
 (Ca₁₋p₋qSrpEuq)AlSiN₃ (II)
 
-wherein p and q are numbers satisfying 0≦p≦1.0, 0<q<1.0, and p+q<1.0.
+wherein p and q are numbers satisfying 0≦p≦1.0, 0&lt;q&lt;1.0, and p+q&lt;1.0.
 
 MªvMbwMcfAl₃₋gSigNh (III)
 
-wherein Mª is at least one element selected from the group consisting of Ca, Sr, Ba, and Mg, Mb is at least one element selected from the group consisting of Li, Na, and K, Mc is at least one element selected from the group consisting of Eu, Ce, Tb, and Mn, v, w, f, g, and h are numbers satisfying 0.80≦v≦1.05, 0.80≦w≦1.05, 0.001<f≦0.1, 0≦g≦0.5, and 3.0≦h≦5.0, respectively.
+wherein Mª is at least one element selected from the group consisting of Ca, Sr, Ba, and Mg, Mb is at least one element selected from the group consisting of Li, Na, and K, Mc is at least one element selected from the group consisting of Eu, Ce, Tb, and Mn, v, w, f, g, and h are numbers satisfying 0.80≦v≦1.05, 0.80≦w≦1.05, 0.001&lt;f≦0.1, 0≦g≦0.5, and 3.0≦h≦5.0, respectively.
 
 (Ca₁₋r₋s₋tSrrBasEut)₂Si₅N₈ (IV)
 
-wherein r, s, and t are numbers satisfying 0≦r≦1.0, 0≦s≦1.0, 0<t<1.0, and r+s+t≦1.0.
+wherein r, s, and t are numbers satisfying 0≦r≦1.0, 0≦s≦1.0, 0&lt;t&lt;1.0, and r+s+t≦1.0.
 
 (Ca,Sr)S:Eu (V)
 
 A₂[M¹₁₋uMn⁴⁺uF₆] (VI)
 
-wherein A is at least one selected from the group consisting of K, Li, Na, Rb, Cs, and NH₄⁺, M¹ is at least one element selected from the group consisting of Group 4 elements and Group 14 elements, and u is the number satisfying 0<u<0.2.
+wherein A is at least one selected from the group consisting of K, Li, Na, Rb, Cs, and NH₄⁺, M¹ is at least one element selected from the group consisting of Group 4 elements and Group 14 elements, and u is the number satisfying 0&lt;u&lt;0.2.
 
 The content of the first fluorescent material 71 in the fluorescent member 50 is not particularly limited as long as the R/B ratio is within a range of 2.0 or more and 4.0 or less. The content of the first fluorescent material 71 in the fluorescent member 50 is, for example, 1 part by mass or more, preferably 5 parts by mass or more, and more preferably 8 parts by mass or more, per 100 parts by mass of the sealing material, and is preferably 200 parts by mass or less, more preferably 150 parts by mass or less, and still more preferably 100 parts by mass or less, per 100 parts by mass of the sealing material. When the content of the first fluorescent material 71 in the fluorescent member 50 is within the aforementioned range, the light emitted from the light emitting element 10 can be efficiently subjected to wavelength conversion, and light capable of promoting growth of plant can be emitted from the light emitting device 100.
 
@@ -148,7 +148,7 @@ The second fluorescent material 72 is preferably a fluorescent material having t
 
 (Ln₁₋ₓ₋yCeₓCry)₃M₅O₁₂ (1)
 
-wherein Ln is at least one rare earth element selected from the group consisting of rare earth elements excluding Ce, M is at least one element selected from the group consisting of Al, Ga, and In, and x and y are numbers satisfying 0.0002<x<0.50 and 0.0001<y<0.05, respectively.
+wherein Ln is at least one rare earth element selected from the group consisting of rare earth elements excluding Ce, M is at least one element selected from the group consisting of Al, Ga, and In, and x and y are numbers satisfying 0.0002&lt;x&lt;0.50 and 0.0001&lt;y&lt;0.05, respectively.
 
 In this case, the second fluorescent material 72 has a composition constituting a garnet structure, and therefore is tough against heat, light, and water, has an absorption peak wavelength of excited absorption spectrum in the vicinity of 420 nm or more and 470 nm or less, and sufficiently absorbs the light from the light emitting element 10, thereby enhancing light emitting intensity of the second fluorescent material 72, which is preferred. Furthermore, the second fluorescent material 72 is excited by light having light emission peak wavelength in a range of 380 nm or more and 490 nm or less and emits light having at least one light emission peak wavelength in a range of 680 nm or more and 800 nm or less.
 
@@ -156,9 +156,9 @@ In the second fluorescent material 72, from the standpoint of stability of a cry
 
 In the second fluorescent material 72, the value of the parameter x is more preferably in a range of 0.0005 or more and 0.400 or less (0.0005≦x≦0.400), and still more preferably in a range of 0.001 or more and 0.350 or less (0.001≦x≦0.350).
 
-In the second fluorescent material 72, the value of the parameter y is preferably in a range of exceeding 0.0005 and less than 0.040 (0.0005<y<0.040), and more preferably in a range of 0.001 or more and 0.026 or less (0.001≦y≦0.026).
+In the second fluorescent material 72, the value of the parameter y is preferably in a range of exceeding 0.0005 and less than 0.040 (0.0005&lt;y&lt;0.040), and more preferably in a range of 0.001 or more and 0.026 or less (0.001≦y≦0.026).
 
-The parameter x is an activation amount of Ce and the value of the parameter x is in a range of exceeding 0.0002 and less than 0.50 (0.0002<x<0.50), and the parameter y is an activation amount of Cr. When the value of the parameter y is in a range of exceeding 0.0001 and less than 0.05 (0.0001<y<0.05), the activation amount of Ce and the activation amount of Cr that are light emission centers contained in the crystal structure of the fluorescent material are within optimum ranges, the decrease of light emission intensity due to the decrease of light emission center can be suppressed, the decrease of light emission intensity due to concentration quenching caused by the increase of the activation amount can be suppressed, and light emission intensity can be enhanced.
+The parameter x is an activation amount of Ce and the value of the parameter x is in a range of exceeding 0.0002 and less than 0.50 (0.0002&lt;x&lt;0.50), and the parameter y is an activation amount of Cr. When the value of the parameter y is in a range of exceeding 0.0001 and less than 0.05 (0.0001&lt;y&lt;0.05), the activation amount of Ce and the activation amount of Cr that are light emission centers contained in the crystal structure of the fluorescent material are within optimum ranges, the decrease of light emission intensity due to the decrease of light emission center can be suppressed, the decrease of light emission intensity due to concentration quenching caused by the increase of the activation amount can be suppressed, and light emission intensity can be enhanced.
 
 ### Production Method of Second Fluorescent Material
 
@@ -218,7 +218,7 @@ wherein M¹¹ is at least one selected from the group consisting of Ca, Sr, Ba,
 
 Si₆₋bAlbObN₈₋b:Eu (ii)
 
-wherein b satisfies 0<b<4.2.
+wherein b satisfies 0&lt;b&lt;4.2.
 
 M¹³Ga₂S₄:Eu (iii)
 
@@ -365,7 +365,7 @@ The above disclosed subject matter shall be considered illustrative, and not res
 
 4. The light emitting device according to claim 2, wherein the another fluorescent material contains a first element Ln containing at least one element selected from the group consisting of rare earth elements excluding Ce, a second element M containing at least one element selected from the group consisting of Al, Ga and In, Ce, and Cr, and has a composition of an aluminate fluorescent material, and when a molar ratio of the second element M is taken as 5, a molar ratio of Ce is a product of a value of a parameter x and 3, and a molar ratio of Cr is a product of a value of a parameter y and 3, the value of the parameter x being in a range of exceeding 0.0002 and less than 0.50, and the value of the parameter y being in a range of exceeding 0.0001 and less than 0.05.
 
-5. The light emitting device according to claim 2, wherein the another fluorescent material has the composition represented by the following formula (I): (Ln₁₋ₓ₋yCeₓCry)₃M₅O₁₂ (I) wherein Ln is at least one rare earth element selected from the group consisting of rare earth elements excluding Ce, M is at least one element selected from the group consisting of Al, Ga, and In, and x and y are numbers satisfying 0.0002<x<0.50 and 0.0001<y<0.05.
+5. The light emitting device according to claim 2, wherein the another fluorescent material has the composition represented by the following formula (I): (Ln₁₋ₓ₋yCeₓCry)₃M₅O₁₂ (I) wherein Ln is at least one rare earth element selected from the group consisting of rare earth elements excluding Ce, M is at least one element selected from the group consisting of Al, Ga, and In, and x and y are numbers satisfying 0.0002&lt;x&lt;0.50 and 0.0001&lt;y&lt;0.05.
 
 6. The light emitting device according to claim 2, the light emitting device being used in plant cultivation.
 

tests/data/groundtruth/docling_v2/pntd.0008301.xml.md

@@ -1,6 +1,6 @@
 # Risk factors associated with failing pre-transmission assessment surveys (pre-TAS) in lymphatic filariasis elimination programs: Results of a multi-country analysis
 
-Burgert-Brucker Clara R.; 1: Global Health Division, RTI International, Washington, DC, United States of America; Zoerhoff Kathryn L.; 1: Global Health Division, RTI International, Washington, DC, United States of America; Headland Maureen; 1: Global Health Division, RTI International, Washington, DC, United States of America, 2: Global Health, Population, and Nutrition, FHI 360, Washington, DC, United States of America; Shoemaker Erica A.; 1: Global Health Division, RTI International, Washington, DC, United States of America; Stelmach Rachel; 1: Global Health Division, RTI International, Washington, DC, United States of America; Karim Mohammad Jahirul; 3: Department of Disease Control, Ministry of Health and Family Welfare, Dhaka, Bangladesh; Batcho Wilfrid; 4: National Control Program of Communicable Diseases, Ministry of Health, Cotonou, Benin; Bougouma Clarisse; 5: Lymphatic Filariasis Elimination Program, Ministère de la Santé, Ouagadougou, Burkina Faso; Bougma Roland; 5: Lymphatic Filariasis Elimination Program, Ministère de la Santé, Ouagadougou, Burkina Faso; Benjamin Didier Biholong; 6: National Onchocerciasis and Lymphatic Filariasis Control Program, Ministry of Health, Yaounde, Cameroon; Georges Nko'Ayissi; 6: National Onchocerciasis and Lymphatic Filariasis Control Program, Ministry of Health, Yaounde, Cameroon; Marfo Benjamin; 7: Neglected Tropical Diseases Programme, Ghana Health Service, Accra, Ghana; Lemoine Jean Frantz; 8: Ministry of Health, Port-au-Prince, Haiti; Pangaribuan Helena Ullyartha; 9: National Institute Health Research & Development, Ministry of Health, Jakarta, Indonesia; Wijayanti Eksi; 9: National Institute Health Research & Development, Ministry of Health, Jakarta, Indonesia; Coulibaly Yaya Ibrahim; 10: Filariasis Unit, International Center of Excellence in Research, Faculty of Medicine and Odontostomatology, Bamako, Mali; Doumbia Salif Seriba; 10: Filariasis Unit, International Center of Excellence in Research, Faculty of Medicine and Odontostomatology, Bamako, Mali; Rimal Pradip; 11: Epidemiology and Disease Control Division, Department of Health Service, Kathmandu, Nepal; Salissou Adamou Bacthiri; 12: Programme Onchocercose et Filariose Lymphatique, Ministère de la Santé, Niamey, Niger; Bah Yukaba; 13: National Neglected Tropical Disease Program, Ministry of Health and Sanitation, Freetown, Sierra Leone; Mwingira Upendo; 14: Neglected Tropical Disease Control Programme, National Institute for Medical Research, Dar es Salaam, Tanzania; Nshala Andreas; 15: IMA World Health/Tanzania NTD Control Programme, Uppsala University, & TIBA Fellow, Dar es Salaam, Tanzania; Muheki Edridah; 16: Programme to Eliminate Lymphatic Filariasis, Ministry of Health, Kampala, Uganda; Shott Joseph; 17: Division of Neglected Tropical Diseases, Office of Infectious Diseases, Bureau for Global Health, USAID, Washington, DC, United States of America; Yevstigneyeva Violetta; 17: Division of Neglected Tropical Diseases, Office of Infectious Diseases, Bureau for Global Health, USAID, Washington, DC, United States of America; Ndayishimye Egide; 2: Global Health, Population, and Nutrition, FHI 360, Washington, DC, United States of America; Baker Margaret; 1: Global Health Division, RTI International, Washington, DC, United States of America; Kraemer John; 1: Global Health Division, RTI International, Washington, DC, United States of America, 18: Georgetown University, Washington, DC, United States of America; Brady Molly; 1: Global Health Division, RTI International, Washington, DC, United States of America
+Burgert-Brucker Clara R.; 1: Global Health Division, RTI International, Washington, DC, United States of America; Zoerhoff Kathryn L.; 1: Global Health Division, RTI International, Washington, DC, United States of America; Headland Maureen; 1: Global Health Division, RTI International, Washington, DC, United States of America, 2: Global Health, Population, and Nutrition, FHI 360, Washington, DC, United States of America; Shoemaker Erica A.; 1: Global Health Division, RTI International, Washington, DC, United States of America; Stelmach Rachel; 1: Global Health Division, RTI International, Washington, DC, United States of America; Karim Mohammad Jahirul; 3: Department of Disease Control, Ministry of Health and Family Welfare, Dhaka, Bangladesh; Batcho Wilfrid; 4: National Control Program of Communicable Diseases, Ministry of Health, Cotonou, Benin; Bougouma Clarisse; 5: Lymphatic Filariasis Elimination Program, Ministère de la Santé, Ouagadougou, Burkina Faso; Bougma Roland; 5: Lymphatic Filariasis Elimination Program, Ministère de la Santé, Ouagadougou, Burkina Faso; Benjamin Didier Biholong; 6: National Onchocerciasis and Lymphatic Filariasis Control Program, Ministry of Health, Yaounde, Cameroon; Georges Nko'Ayissi; 6: National Onchocerciasis and Lymphatic Filariasis Control Program, Ministry of Health, Yaounde, Cameroon; Marfo Benjamin; 7: Neglected Tropical Diseases Programme, Ghana Health Service, Accra, Ghana; Lemoine Jean Frantz; 8: Ministry of Health, Port-au-Prince, Haiti; Pangaribuan Helena Ullyartha; 9: National Institute Health Research & Development, Ministry of Health, Jakarta, Indonesia; Wijayanti Eksi; 9: National Institute Health Research & Development, Ministry of Health, Jakarta, Indonesia; Coulibaly Yaya Ibrahim; 10: Filariasis Unit, International Center of Excellence in Research, Faculty of Medicine and Odontostomatology, Bamako, Mali; Doumbia Salif Seriba; 10: Filariasis Unit, International Center of Excellence in Research, Faculty of Medicine and Odontostomatology, Bamako, Mali; Rimal Pradip; 11: Epidemiology and Disease Control Division, Department of Health Service, Kathmandu, Nepal; Salissou Adamou Bacthiri; 12: Programme Onchocercose et Filariose Lymphatique, Ministère de la Santé, Niamey, Niger; Bah Yukaba; 13: National Neglected Tropical Disease Program, Ministry of Health and Sanitation, Freetown, Sierra Leone; Mwingira Upendo; 14: Neglected Tropical Disease Control Programme, National Institute for Medical Research, Dar es Salaam, Tanzania; Nshala Andreas; 15: IMA World Health/Tanzania NTD Control Programme, Uppsala University, & TIBA Fellow, Dar es Salaam, Tanzania; Muheki Edridah; 16: Programme to Eliminate Lymphatic Filariasis, Ministry of Health, Kampala, Uganda; Shott Joseph; 17: Division of Neglected Tropical Diseases, Office of Infectious Diseases, Bureau for Global Health, USAID, Washington, DC, United States of America; Yevstigneyeva Violetta; 17: Division of Neglected Tropical Diseases, Office of Infectious Diseases, Bureau for Global Health, USAID, Washington, DC, United States of America; Ndayishimye Egide; 2: Global Health, Population, and Nutrition, FHI 360, Washington, DC, United States of America; Baker Margaret; 1: Global Health Division, RTI International, Washington, DC, United States of America; Kraemer John; 1: Global Health Division, RTI International, Washington, DC, United States of America, 18: Georgetown University, Washington, DC, United States of America; Brady Molly; 1: Global Health Division, RTI International, Washington, DC, United States of America
 
 ## Abstract
 
@@ -36,7 +36,7 @@ Potential covariates were derived from the available data for each factor in the
 
 #### Baseline prevalence
 
-Baseline prevalence can be assumed as a proxy for local transmission conditions [14] and correlates with prevalence after MDA [14–20]. Baseline prevalence for each district was measured by either blood smears to measure Mf or rapid diagnostic tests to measure Ag. Other studies have modeled Mf and Ag prevalence separately, due to lack of a standardized correlation between the two, especially at pre-MDA levels [21,22]. However, because WHO mapping guidance states that MDA is required if either Mf or Ag is ≥1% and there were not enough data to model each separately, we combined baseline prevalence values regardless of diagnostic test used. We created two variables for use in the analysis (1) using the cut-off of <5% or ≥5% (dataset median value of 5%) and (2) using the cut-off of <10% or ≥10%.
+Baseline prevalence can be assumed as a proxy for local transmission conditions [14] and correlates with prevalence after MDA [14–20]. Baseline prevalence for each district was measured by either blood smears to measure Mf or rapid diagnostic tests to measure Ag. Other studies have modeled Mf and Ag prevalence separately, due to lack of a standardized correlation between the two, especially at pre-MDA levels [21,22]. However, because WHO mapping guidance states that MDA is required if either Mf or Ag is ≥1% and there were not enough data to model each separately, we combined baseline prevalence values regardless of diagnostic test used. We created two variables for use in the analysis (1) using the cut-off of &lt;5% or ≥5% (dataset median value of 5%) and (2) using the cut-off of &lt;10% or ≥10%.
 
 #### Agent
 
@@ -90,9 +90,9 @@ This paper reports for the first time factors associated with pre-TAS results fr
 
 Though diagnostic test used was selected for the final log-binomial model, neither category (FTS or ICT) were significant after interaction with high baseline. FTS alone is significant in the bivariate analysis compared to ICT or Mf. This result is not surprising given previous research which found that FTS was more sensitive than ICT [45].
 
-Elevation was the only environmental domain variable selected for the final log-binomial model during the model selection process, with areas of lower elevation (<350m) found to be at 3.07 times higher risk to fail pre-TAS compared to districts with a higher elevation. Similar results related to elevation were found in previous studies [8,31], including Goldberg et al. [7], who used a cutoff of 200 meters. Elevation likely also encompasses some related environmental concepts, such as vector habitat, greenness (EVI), or rainfall, which impact vector chances of survival.
+Elevation was the only environmental domain variable selected for the final log-binomial model during the model selection process, with areas of lower elevation (&lt;350m) found to be at 3.07 times higher risk to fail pre-TAS compared to districts with a higher elevation. Similar results related to elevation were found in previous studies [8,31], including Goldberg et al. [7], who used a cutoff of 200 meters. Elevation likely also encompasses some related environmental concepts, such as vector habitat, greenness (EVI), or rainfall, which impact vector chances of survival.
 
-The small number of failures overall prevented the inclusion of a large number of variables in the final log-binomial model. However, other variables that are associated with failure as identified in the bivariate analyses, such as Culex vector, higher population density, higher EVI, higher rainfall and more rounds of MDA, should not be discounted when making programmatic decisions. Other models have shown that Culex as the predominant vector in a district, compared to Anopheles, results in more intense interventions needed to reach elimination [24,41]. Higher population density, which was also found to predict TAS failure [7], could be related to different vector species’ transmission dynamics in urban areas, as well as the fact that MDAs are harder to conduct and to accurately measure in urban areas [46,47]. Both higher enhanced vegetation index (>0.3) and higher rainfall (>700 mm per year) contribute to expansion of vector habitats and population. Additionally, having more than five rounds of MDA before pre-TAS was also statistically significantly associated with higher failure in the bivariate analysis. It is unclear why higher number of rounds is associated with first pre-TAS failure given that other research has shown the opposite [15,16].
+The small number of failures overall prevented the inclusion of a large number of variables in the final log-binomial model. However, other variables that are associated with failure as identified in the bivariate analyses, such as Culex vector, higher population density, higher EVI, higher rainfall and more rounds of MDA, should not be discounted when making programmatic decisions. Other models have shown that Culex as the predominant vector in a district, compared to Anopheles, results in more intense interventions needed to reach elimination [24,41]. Higher population density, which was also found to predict TAS failure [7], could be related to different vector species’ transmission dynamics in urban areas, as well as the fact that MDAs are harder to conduct and to accurately measure in urban areas [46,47]. Both higher enhanced vegetation index (&gt;0.3) and higher rainfall (&gt;700 mm per year) contribute to expansion of vector habitats and population. Additionally, having more than five rounds of MDA before pre-TAS was also statistically significantly associated with higher failure in the bivariate analysis. It is unclear why higher number of rounds is associated with first pre-TAS failure given that other research has shown the opposite [15,16].
 
 All other variables included in this analysis were not significantly associated with pre-TAS failure in our analysis. Goldberg et al. found Brugia spp. to be significantly associated with failure, but our results did not. This is likely due in part to the small number of districts with Brugia spp. in our dataset (6%) compared to 46% in the Goldberg et al. article [7]. MDA coverage levels were not significantly associated with pre-TAS failure, likely due to the lack of variance in the coverage data since WHO guidance dictates a minimum of five rounds of MDA with ≥65% epidemiological coverage to be eligible to implement pre-TAS. It should not be interpreted as evidence that high MDA coverage levels are not necessary to lower prevalence.
 
@@ -110,16 +110,16 @@ Table 1: Categorization of potential factors influencing pre-TAS results.
 
 | Domain                 | Factor                | Covariate                     | Description                                                     | Reference Group      | Summary statistic   | Temporal Resolution   | Source             |
 |------------------------|-----------------------|-------------------------------|-----------------------------------------------------------------|----------------------|---------------------|-----------------------|--------------------|
-| Prevalence             | Baseline prevalence   | 5% cut off                    | Maximum reported mapping or baseline sentinel site prevalence   | <5%                  | Maximum             | Varies                | Programmatic data  |
-| Prevalence             | Baseline prevalence   | 10% cut off                   | Maximum reported mapping or baseline sentinel site prevalence   | <10%                 | Maximum             | Varies                | Programmatic data  |
-| Agent                  | Parasite              | Parasite                      | Predominate parasite in district                                | W. bancrofti & mixed | Binary value        | 2018                  | Programmatic data  |
-| Environment            | Vector                | Vector                        | Predominate vector in district                                  | Anopheles & Mansonia | Binary value        | 2018                  | Country expert     |
-| Environment            | Geography             | Elevation                     | Elevation measured in meters                                    | >350                 | Mean                | 2000                  | CGIAR-CSI SRTM [9] |
-| Environment            | Geography             | District area                 | Area measured in km2                                            | >2,500               | Maximum sum         | Static                | Programmatic data  |
-| Environment            | Climate               | EVI                           | Enhanced vegetation index                                       | > 0.3                | Mean                | 2015                  | MODIS [10]         |
+| Prevalence             | Baseline prevalence   | 5% cut off                    | Maximum reported mapping or baseline sentinel site prevalence   | &lt;5%                  | Maximum             | Varies                | Programmatic data  |
+| Prevalence             | Baseline prevalence   | 10% cut off                   | Maximum reported mapping or baseline sentinel site prevalence   | &lt;10%                 | Maximum             | Varies                | Programmatic data  |
+| Agent                  | Parasite              | Parasite                      | Predominate parasite in district                                | W. bancrofti &amp; mixed | Binary value        | 2018                  | Programmatic data  |
+| Environment            | Vector                | Vector                        | Predominate vector in district                                  | Anopheles &amp; Mansonia | Binary value        | 2018                  | Country expert     |
+| Environment            | Geography             | Elevation                     | Elevation measured in meters                                    | &gt;350                 | Mean                | 2000                  | CGIAR-CSI SRTM [9] |
+| Environment            | Geography             | District area                 | Area measured in km2                                            | &gt;2,500               | Maximum sum         | Static                | Programmatic data  |
+| Environment            | Climate               | EVI                           | Enhanced vegetation index                                       | &gt; 0.3                | Mean                | 2015                  | MODIS [10]         |
 | Environment            | Climate               | Rainfall                      | Annual rainfall measured in mm                                  | ≤ 700                | Mean                | 2015                  | CHIRPS [11]        |
 | Environment            | Socio-economic        | Population density            | Number of people per km2                                        | ≤ 100                | Mean                | 2015                  | WorldPop [12]      |
-| Environment            | Socio-economic        | Nighttime lights              | Nighttime light index from 0 to 63                              | >1.5                 | Mean                | 2015                  | VIIRS [13]         |
+| Environment            | Socio-economic        | Nighttime lights              | Nighttime light index from 0 to 63                              | &gt;1.5                 | Mean                | 2015                  | VIIRS [13]         |
 | Environment            | Co-endemicity         | Co-endemic for onchocerciasis | Part or all of district is also endemic for onchocerciases      | Non-endemic          | Binary value        | 2018                  | Programmatic data  |
 | MDA                    | Drug efficacy         | Drug package                  | DEC-ALB or IVM-ALB                                              | DEC-ALB              | Binary value        | 2018                  | Programmatic data  |
 | MDA                    | Implementation of MDA | Coverage                      | Median MDA coverage for last 5 rounds                           | ≥ 65%                | Median              | Varies                | Programmatic data  |
@@ -136,12 +136,12 @@ Table 2: Adjusted risk ratios for pre-TAS failure from log-binomial model sensit
 | Number of Failures                          | 74               | 74                         | 44                       | 72                                   | 46                              |
 | Number of total districts                   | (N = 554)        | (N = 420)                  | (N = 407)                | (N = 518)                            | (N = 414)                       |
 | Covariate                                   | RR (95% CI)      | RR (95% CI)                | RR (95% CI)              | RR (95% CI)                          | RR (95% CI)                     |
-| Baseline prevalence > = 10% & used FTS test | 2.38 (0.96–5.90) | 1.23 (0.52–2.92)           | 14.52 (1.79–117.82)      | 2.61 (1.03–6.61)                     | 15.80 (1.95–127.67)             |
-| Baseline prevalence > = 10% & used ICT test | 0.80 (0.20–3.24) | 0.42 (0.11–1.68)           | 1.00 (0.00–0.00)         | 0.88 (0.21–3.60)                     | 1.00 (0.00–0.00)                |
+| Baseline prevalence &gt; = 10% &amp; used FTS test | 2.38 (0.96–5.90) | 1.23 (0.52–2.92)           | 14.52 (1.79–117.82)      | 2.61 (1.03–6.61)                     | 15.80 (1.95–127.67)             |
+| Baseline prevalence &gt; = 10% &amp; used ICT test | 0.80 (0.20–3.24) | 0.42 (0.11–1.68)           | 1.00 (0.00–0.00)         | 0.88 (0.21–3.60)                     | 1.00 (0.00–0.00)                |
 | +Used FTS test                              | 1.16 (0.52–2.59) | 2.40 (1.12–5.11)           | 0.15 (0.02–1.11)         | 1.03 (0.45–2.36)                     | 0.13 (0.02–0.96)                |
 | +Used ICT test                              | 0.92 (0.32–2.67) | 1.47 (0.51–4.21)           | 0.33 (0.04–2.54)         | 0.82 (0.28–2.43)                     | 0.27 (0.03–2.04)                |
-| +Baseline prevalence > = 10%                | 2.52 (1.37–4.64) | 2.42 (1.31–4.47)           | 2.03 (1.06–3.90)         | 2.30 (1.21–4.36)                     | 2.01 (1.07–3.77)                |
-| Elevation < 350m                            | 3.07 (1.95–4.83) | 2.21 (1.42–3.43)           | 4.68 (2.22–9.87)         | 3.04 (1.93–4.79)                     | 3.76 (1.92–7.37)                |
+| +Baseline prevalence &gt; = 10%                | 2.52 (1.37–4.64) | 2.42 (1.31–4.47)           | 2.03 (1.06–3.90)         | 2.30 (1.21–4.36)                     | 2.01 (1.07–3.77)                |
+| Elevation &lt; 350m                            | 3.07 (1.95–4.83) | 2.21 (1.42–3.43)           | 4.68 (2.22–9.87)         | 3.04 (1.93–4.79)                     | 3.76 (1.92–7.37)                |
 
 ## Figures
 

tests/data/groundtruth/docling_v2/pone.0234687.xml.md

@@ -62,7 +62,7 @@ The CH4 emissions from enteric fermentation intensity (g (kg ECM)-1) was a funct
 
 The CH4 emission from manure (kg (kg ECM)-1) was a function of daily CH4 emission from manure (kg cow-1) and daily ECM (kg cow-1). The daily CH4 emission from manure was estimated according to IPCC [38], which considered daily volatile solid (VS) excreted (kg DM cow-1) in manure. The daily VS was estimated as proposed by Eugène et al. [44] as: VS = NDOMI + (UE × GE) × (OM/18.45), where: VS = volatile solid excretion on an organic matter (OM) basis (kg day-1), NDOMI = non-digestible OM intake (kg day-1): (1- OM digestibility) × OM intake, UE = urinary energy excretion as a fraction of GE (0.04), GE = gross energy intake (MJ day-1), OM = organic matter (g), 18.45 = conversion factor for dietary GE per kg of DM (MJ kg-1).
 
-The OM digestibility was estimated as a function of chemical composition, using equations published by INRA [21], which takes into account the effects of digestive interactions due to feeding level, the proportion of concentrate and rumen protein balance on OM digestibility. For scenarios where cows had access to grazing, the amount of calculated VS were corrected as a function of the time at pasture. The biodegradability of manure factor (0.13 for dairy cows in Latin America) and methane conversion factor (MCF) values were taken from IPCC [38]. The MCF values for pit storage below animal confinements (> 1 month) were used for the calculation, taking into account the annual average temperature (16.6ºC) or the average temperatures during the growth period of temperate (14.4ºC) or tropical (21ºC) annual pastures, which were 31%, 26% and 46%, respectively.
+The OM digestibility was estimated as a function of chemical composition, using equations published by INRA [21], which takes into account the effects of digestive interactions due to feeding level, the proportion of concentrate and rumen protein balance on OM digestibility. For scenarios where cows had access to grazing, the amount of calculated VS were corrected as a function of the time at pasture. The biodegradability of manure factor (0.13 for dairy cows in Latin America) and methane conversion factor (MCF) values were taken from IPCC [38]. The MCF values for pit storage below animal confinements (> 1 month) were used for the calculation, taking into account the annual average temperature (16.6ºC) or the average temperatures during the growth period of temperate (14.4ºC) or tropical (21ºC) annual pastures, which were 31%, 26% and 46%, respectively.
 
 The N2O-N emissions from urine and feces were estimated considering the proportion of N excreted as manure and storage or as urine and dung deposited by grazing animals. These proportions were calculated based on the proportion of daily time that animals stayed on pasture (7 h/24 h = 0.29) or confinement (1−0.29 = 0.71). For lactating heifers and cows, the total amount of N excreted was calculated by the difference between N intake and milk N excretion. For heifers and non-lactating cows, urinary and fecal N excretion were estimated as proposed by Reed et al. [45] (Table 3: equations 10 and 12, respectively). The N2O emissions from stored manure as well as urine and dung during grazing were calculated based on the conversion of N2O-N emissions to N2O emissions, where N2O emissions = N2O-N emissions × 44/28. The emission factors were 0.002 kg N2O-N (kg N)-1 stored in a pit below animal confinements, and 0.02 kg N2O-N (kg of urine and dung)-1 deposited on pasture [38]. The indirect N2O emissions from storage manure and urine and dung deposits on pasture were also estimated using the IPCC [38] emission factors.
 
@@ -106,7 +106,7 @@ The lower C footprint in scenarios with access to pasture, when local emission f
 
 The enteric CH4 intensity was similar between different scenarios (Fig 2), showing the greatest sensitivity index, with values ranging from 0.53 to 0.62, which indicate that for a 10% change in this source, the C footprint may change between 5.3 and 6.2% (Fig 3). The large effect of enteric CH4 emissions on the whole C footprint was expected, because the impact of enteric CH4 on GHG emissions of milk production in different dairy systems has been estimated to range from 44 to 60% of the total CO2e [50,52,57,58]. However, emissions in feed production may be the most important source of GHG when emission factors for producing concentrate feeds are greater than 0.7 kg CO2e kg-1 [59], which did not happen in this study.
 
-The lack of difference in enteric CH4 emissions in different systems can be explained by the narrow range of NDF content in diets (<4% difference). This non-difference is due to the lower NDF content of annual temperate pastures (495 g (kg DM)-1) compared to corn silage (550 g (kg DM)-1). Hence, an expected, increase NDF content with decreased concentrate was partially offset by an increase in the pasture proportion relatively low in NDF. This is in agreement with studies conducted in southern Brazil, which have shown that the actual enteric CH4 emissions may decrease with inclusion of temperate pastures in cows receiving corn silage and soybean meal [60] or increase enteric CH4 emissions when dairy cows grazing a temperate pasture was supplemented with corn silage [61]. Additionally, enteric CH4 emissions did not differ between dairy cows receiving TMR exclusively or grazing a tropical pasture in the same scenarios as in this study [26].
+The lack of difference in enteric CH4 emissions in different systems can be explained by the narrow range of NDF content in diets (&lt;4% difference). This non-difference is due to the lower NDF content of annual temperate pastures (495 g (kg DM)-1) compared to corn silage (550 g (kg DM)-1). Hence, an expected, increase NDF content with decreased concentrate was partially offset by an increase in the pasture proportion relatively low in NDF. This is in agreement with studies conducted in southern Brazil, which have shown that the actual enteric CH4 emissions may decrease with inclusion of temperate pastures in cows receiving corn silage and soybean meal [60] or increase enteric CH4 emissions when dairy cows grazing a temperate pasture was supplemented with corn silage [61]. Additionally, enteric CH4 emissions did not differ between dairy cows receiving TMR exclusively or grazing a tropical pasture in the same scenarios as in this study [26].
 
 ### Emissions from excreta and feed production
 

tests/data/groundtruth/docling_v2/redp5110_sampled.md

@@ -63,10 +63,10 @@ Solution Brief IBM Systems Lab Services and Training
 
 ## Highlights
 
-- GLYPH<g115>GLYPH<g3> GLYPH<g40>GLYPH<g81>GLYPH<g75>GLYPH<g68>GLYPH<g81>GLYPH<g70>GLYPH<g72>GLYPH<g3> GLYPH<g87>GLYPH<g75>GLYPH<g72>GLYPH<g3> GLYPH<g83>GLYPH<g72>GLYPH<g85>GLYPH<g73>GLYPH<g82>GLYPH<g85>GLYPH<g80>GLYPH<g68>GLYPH<g81>GLYPH<g70>GLYPH<g72>GLYPH<g3> GLYPH<g82>GLYPH<g73>GLYPH<g3> GLYPH<g92>GLYPH<g82>GLYPH<g88>GLYPH<g85> GLYPH<g3> GLYPH<g71>GLYPH<g68>GLYPH<g87>GLYPH<g68>GLYPH<g69>GLYPH<g68>GLYPH<g86>GLYPH<g72>GLYPH<g3> GLYPH<g82>GLYPH<g83>GLYPH<g72>GLYPH<g85>GLYPH<g68>GLYPH<g87>GLYPH<g76>GLYPH<g82>GLYPH<g81>GLYPH<g86>
-- GLYPH<g115>GLYPH<g3> GLYPH<g40>GLYPH<g68>GLYPH<g85> GLYPH<g81>GLYPH<g3> GLYPH<g74>GLYPH<g85>GLYPH<g72>GLYPH<g68>GLYPH<g87>GLYPH<g72>GLYPH<g85>GLYPH<g3> GLYPH<g85>GLYPH<g72>GLYPH<g87>GLYPH<g88>GLYPH<g85> GLYPH<g81>GLYPH<g3> GLYPH<g82>GLYPH<g81>GLYPH<g3> GLYPH<g44>GLYPH<g55>GLYPH<g3> GLYPH<g83>GLYPH<g85>GLYPH<g82>GLYPH<g77>GLYPH<g72>GLYPH<g70>GLYPH<g87>GLYPH<g86> GLYPH<g3> GLYPH<g87>GLYPH<g75>GLYPH<g85>GLYPH<g82>GLYPH<g88>GLYPH<g74>GLYPH<g75>GLYPH<g3> GLYPH<g80>GLYPH<g82>GLYPH<g71>GLYPH<g72>GLYPH<g85> GLYPH<g81>GLYPH<g76>GLYPH<g93>GLYPH<g68>GLYPH<g87>GLYPH<g76>GLYPH<g82>GLYPH<g81>GLYPH<g3> GLYPH<g82>GLYPH<g73>GLYPH<g3> GLYPH<g71>GLYPH<g68>GLYPH<g87>GLYPH<g68>GLYPH<g69>GLYPH<g68>GLYPH<g86>GLYPH<g72>GLYPH<g3> GLYPH<g68>GLYPH<g81>GLYPH<g71> GLYPH<g3> GLYPH<g68>GLYPH<g83>GLYPH<g83>GLYPH<g79>GLYPH<g76>GLYPH<g70>GLYPH<g68>GLYPH<g87>GLYPH<g76>GLYPH<g82>GLYPH<g81>GLYPH<g86>
-- GLYPH<g115>GLYPH<g3> GLYPH<g53>GLYPH<g72>GLYPH<g79>GLYPH<g92>GLYPH<g3> GLYPH<g82>GLYPH<g81>GLYPH<g3> GLYPH<g44>GLYPH<g37>GLYPH<g48>GLYPH<g3> GLYPH<g72>GLYPH<g91>GLYPH<g83>GLYPH<g72>GLYPH<g85>GLYPH<g87>GLYPH<g3> GLYPH<g70>GLYPH<g82>GLYPH<g81>GLYPH<g86>GLYPH<g88>GLYPH<g79>GLYPH<g87>GLYPH<g76>GLYPH<g81>GLYPH<g74>GLYPH<g15>GLYPH<g3> GLYPH<g86>GLYPH<g78>GLYPH<g76>GLYPH<g79>GLYPH<g79>GLYPH<g86> GLYPH<g3> GLYPH<g86>GLYPH<g75>GLYPH<g68>GLYPH<g85>GLYPH<g76>GLYPH<g81>GLYPH<g74>GLYPH<g3> GLYPH<g68>GLYPH<g81>GLYPH<g71>GLYPH<g3> GLYPH<g85>GLYPH<g72>GLYPH<g81>GLYPH<g82>GLYPH<g90>GLYPH<g81>GLYPH<g3> GLYPH<g86>GLYPH<g72>GLYPH<g85>GLYPH<g89>GLYPH<g76>GLYPH<g70>GLYPH<g72>GLYPH<g86>
-- GLYPH<g115>GLYPH<g3> GLYPH<g55> GLYPH<g68>GLYPH<g78>GLYPH<g72>GLYPH<g3> GLYPH<g68>GLYPH<g71>GLYPH<g89>GLYPH<g68>GLYPH<g81>GLYPH<g87>GLYPH<g68>GLYPH<g74>GLYPH<g72>GLYPH<g3> GLYPH<g82>GLYPH<g73>GLYPH<g3> GLYPH<g68>GLYPH<g70>GLYPH<g70>GLYPH<g72>GLYPH<g86>GLYPH<g86>GLYPH<g3> GLYPH<g87>GLYPH<g82>GLYPH<g3> GLYPH<g68> GLYPH<g3> GLYPH<g90>GLYPH<g82>GLYPH<g85>GLYPH<g79>GLYPH<g71>GLYPH<g90>GLYPH<g76>GLYPH<g71>GLYPH<g72>GLYPH<g3> GLYPH<g86>GLYPH<g82>GLYPH<g88>GLYPH<g85>GLYPH<g70>GLYPH<g72>GLYPH<g3> GLYPH<g82>GLYPH<g73>GLYPH<g3> GLYPH<g72>GLYPH<g91>GLYPH<g83>GLYPH<g72>GLYPH<g85>GLYPH<g87>GLYPH<g76>GLYPH<g86>GLYPH<g72>
+- GLYPH&lt;g115&gt;GLYPH&lt;g3&gt; GLYPH&lt;g40&gt;GLYPH&lt;g81&gt;GLYPH&lt;g75&gt;GLYPH&lt;g68&gt;GLYPH&lt;g81&gt;GLYPH&lt;g70&gt;GLYPH&lt;g72&gt;GLYPH&lt;g3&gt; GLYPH&lt;g87&gt;GLYPH&lt;g75&gt;GLYPH&lt;g72&gt;GLYPH&lt;g3&gt; GLYPH&lt;g83&gt;GLYPH&lt;g72&gt;GLYPH&lt;g85&gt;GLYPH&lt;g73&gt;GLYPH&lt;g82&gt;GLYPH&lt;g85&gt;GLYPH&lt;g80&gt;GLYPH&lt;g68&gt;GLYPH&lt;g81&gt;GLYPH&lt;g70&gt;GLYPH&lt;g72&gt;GLYPH&lt;g3&gt; GLYPH&lt;g82&gt;GLYPH&lt;g73&gt;GLYPH&lt;g3&gt; GLYPH&lt;g92&gt;GLYPH&lt;g82&gt;GLYPH&lt;g88&gt;GLYPH&lt;g85&gt; GLYPH&lt;g3&gt; GLYPH&lt;g71&gt;GLYPH&lt;g68&gt;GLYPH&lt;g87&gt;GLYPH&lt;g68&gt;GLYPH&lt;g69&gt;GLYPH&lt;g68&gt;GLYPH&lt;g86&gt;GLYPH&lt;g72&gt;GLYPH&lt;g3&gt; GLYPH&lt;g82&gt;GLYPH&lt;g83&gt;GLYPH&lt;g72&gt;GLYPH&lt;g85&gt;GLYPH&lt;g68&gt;GLYPH&lt;g87&gt;GLYPH&lt;g76&gt;GLYPH&lt;g82&gt;GLYPH&lt;g81&gt;GLYPH&lt;g86&gt;
+- GLYPH&lt;g115&gt;GLYPH&lt;g3&gt; GLYPH&lt;g40&gt;GLYPH&lt;g68&gt;GLYPH&lt;g85&gt; GLYPH&lt;g81&gt;GLYPH&lt;g3&gt; GLYPH&lt;g74&gt;GLYPH&lt;g85&gt;GLYPH&lt;g72&gt;GLYPH&lt;g68&gt;GLYPH&lt;g87&gt;GLYPH&lt;g72&gt;GLYPH&lt;g85&gt;GLYPH&lt;g3&gt; GLYPH&lt;g85&gt;GLYPH&lt;g72&gt;GLYPH&lt;g87&gt;GLYPH&lt;g88&gt;GLYPH&lt;g85&gt; GLYPH&lt;g81&gt;GLYPH&lt;g3&gt; GLYPH&lt;g82&gt;GLYPH&lt;g81&gt;GLYPH&lt;g3&gt; GLYPH&lt;g44&gt;GLYPH&lt;g55&gt;GLYPH&lt;g3&gt; GLYPH&lt;g83&gt;GLYPH&lt;g85&gt;GLYPH&lt;g82&gt;GLYPH&lt;g77&gt;GLYPH&lt;g72&gt;GLYPH&lt;g70&gt;GLYPH&lt;g87&gt;GLYPH&lt;g86&gt; GLYPH&lt;g3&gt; GLYPH&lt;g87&gt;GLYPH&lt;g75&gt;GLYPH&lt;g85&gt;GLYPH&lt;g82&gt;GLYPH&lt;g88&gt;GLYPH&lt;g74&gt;GLYPH&lt;g75&gt;GLYPH&lt;g3&gt; GLYPH&lt;g80&gt;GLYPH&lt;g82&gt;GLYPH&lt;g71&gt;GLYPH&lt;g72&gt;GLYPH&lt;g85&gt; GLYPH&lt;g81&gt;GLYPH&lt;g76&gt;GLYPH&lt;g93&gt;GLYPH&lt;g68&gt;GLYPH&lt;g87&gt;GLYPH&lt;g76&gt;GLYPH&lt;g82&gt;GLYPH&lt;g81&gt;GLYPH&lt;g3&gt; GLYPH&lt;g82&gt;GLYPH&lt;g73&gt;GLYPH&lt;g3&gt; GLYPH&lt;g71&gt;GLYPH&lt;g68&gt;GLYPH&lt;g87&gt;GLYPH&lt;g68&gt;GLYPH&lt;g69&gt;GLYPH&lt;g68&gt;GLYPH&lt;g86&gt;GLYPH&lt;g72&gt;GLYPH&lt;g3&gt; GLYPH&lt;g68&gt;GLYPH&lt;g81&gt;GLYPH&lt;g71&gt; GLYPH&lt;g3&gt; GLYPH&lt;g68&gt;GLYPH&lt;g83&gt;GLYPH&lt;g83&gt;GLYPH&lt;g79&gt;GLYPH&lt;g76&gt;GLYPH&lt;g70&gt;GLYPH&lt;g68&gt;GLYPH&lt;g87&gt;GLYPH&lt;g76&gt;GLYPH&lt;g82&gt;GLYPH&lt;g81&gt;GLYPH&lt;g86&gt;
+- GLYPH&lt;g115&gt;GLYPH&lt;g3&gt; GLYPH&lt;g53&gt;GLYPH&lt;g72&gt;GLYPH&lt;g79&gt;GLYPH&lt;g92&gt;GLYPH&lt;g3&gt; GLYPH&lt;g82&gt;GLYPH&lt;g81&gt;GLYPH&lt;g3&gt; GLYPH&lt;g44&gt;GLYPH&lt;g37&gt;GLYPH&lt;g48&gt;GLYPH&lt;g3&gt; GLYPH&lt;g72&gt;GLYPH&lt;g91&gt;GLYPH&lt;g83&gt;GLYPH&lt;g72&gt;GLYPH&lt;g85&gt;GLYPH&lt;g87&gt;GLYPH&lt;g3&gt; GLYPH&lt;g70&gt;GLYPH&lt;g82&gt;GLYPH&lt;g81&gt;GLYPH&lt;g86&gt;GLYPH&lt;g88&gt;GLYPH&lt;g79&gt;GLYPH&lt;g87&gt;GLYPH&lt;g76&gt;GLYPH&lt;g81&gt;GLYPH&lt;g74&gt;GLYPH&lt;g15&gt;GLYPH&lt;g3&gt; GLYPH&lt;g86&gt;GLYPH&lt;g78&gt;GLYPH&lt;g76&gt;GLYPH&lt;g79&gt;GLYPH&lt;g79&gt;GLYPH&lt;g86&gt; GLYPH&lt;g3&gt; GLYPH&lt;g86&gt;GLYPH&lt;g75&gt;GLYPH&lt;g68&gt;GLYPH&lt;g85&gt;GLYPH&lt;g76&gt;GLYPH&lt;g81&gt;GLYPH&lt;g74&gt;GLYPH&lt;g3&gt; GLYPH&lt;g68&gt;GLYPH&lt;g81&gt;GLYPH&lt;g71&gt;GLYPH&lt;g3&gt; GLYPH&lt;g85&gt;GLYPH&lt;g72&gt;GLYPH&lt;g81&gt;GLYPH&lt;g82&gt;GLYPH&lt;g90&gt;GLYPH&lt;g81&gt;GLYPH&lt;g3&gt; GLYPH&lt;g86&gt;GLYPH&lt;g72&gt;GLYPH&lt;g85&gt;GLYPH&lt;g89&gt;GLYPH&lt;g76&gt;GLYPH&lt;g70&gt;GLYPH&lt;g72&gt;GLYPH&lt;g86&gt;
+- GLYPH&lt;g115&gt;GLYPH&lt;g3&gt; GLYPH&lt;g55&gt; GLYPH&lt;g68&gt;GLYPH&lt;g78&gt;GLYPH&lt;g72&gt;GLYPH&lt;g3&gt; GLYPH&lt;g68&gt;GLYPH&lt;g71&gt;GLYPH&lt;g89&gt;GLYPH&lt;g68&gt;GLYPH&lt;g81&gt;GLYPH&lt;g87&gt;GLYPH&lt;g68&gt;GLYPH&lt;g74&gt;GLYPH&lt;g72&gt;GLYPH&lt;g3&gt; GLYPH&lt;g82&gt;GLYPH&lt;g73&gt;GLYPH&lt;g3&gt; GLYPH&lt;g68&gt;GLYPH&lt;g70&gt;GLYPH&lt;g70&gt;GLYPH&lt;g72&gt;GLYPH&lt;g86&gt;GLYPH&lt;g86&gt;GLYPH&lt;g3&gt; GLYPH&lt;g87&gt;GLYPH&lt;g82&gt;GLYPH&lt;g3&gt; GLYPH&lt;g68&gt; GLYPH&lt;g3&gt; GLYPH&lt;g90&gt;GLYPH&lt;g82&gt;GLYPH&lt;g85&gt;GLYPH&lt;g79&gt;GLYPH&lt;g71&gt;GLYPH&lt;g90&gt;GLYPH&lt;g76&gt;GLYPH&lt;g71&gt;GLYPH&lt;g72&gt;GLYPH&lt;g3&gt; GLYPH&lt;g86&gt;GLYPH&lt;g82&gt;GLYPH&lt;g88&gt;GLYPH&lt;g85&gt;GLYPH&lt;g70&gt;GLYPH&lt;g72&gt;GLYPH&lt;g3&gt; GLYPH&lt;g82&gt;GLYPH&lt;g73&gt;GLYPH&lt;g3&gt; GLYPH&lt;g72&gt;GLYPH&lt;g91&gt;GLYPH&lt;g83&gt;GLYPH&lt;g72&gt;GLYPH&lt;g85&gt;GLYPH&lt;g87&gt;GLYPH&lt;g76&gt;GLYPH&lt;g86&gt;GLYPH&lt;g72&gt;
 
 <!-- image -->
 
@@ -130,20 +130,20 @@ Businesses must make a serious effort to secure their data and recognize that se
 
 This chapter describes how you can secure and protect data in DB2 for i. The following topics are covered in this chapter:
 
-- GLYPH<SM590000> Security fundamentals
-- GLYPH<SM590000> Current state of IBM i security
-- GLYPH<SM590000> DB2 for i security controls
+- GLYPH&lt;SM590000&gt; Security fundamentals
+- GLYPH&lt;SM590000&gt; Current state of IBM i security
+- GLYPH&lt;SM590000&gt; DB2 for i security controls
 
 ## 1.1 Security fundamentals
 
 Before reviewing database security techniques, there are two fundamental steps in securing information assets that must be described:
 
-- GLYPH<SM590000> First, and most important, is the definition of a company's security policy . Without a security policy, there is no definition of what are acceptable practices for using, accessing, and storing information by who, what, when, where, and how. A security policy should minimally address three things: confidentiality, integrity, and availability.
+- GLYPH&lt;SM590000&gt; First, and most important, is the definition of a company's security policy . Without a security policy, there is no definition of what are acceptable practices for using, accessing, and storing information by who, what, when, where, and how. A security policy should minimally address three things: confidentiality, integrity, and availability.
 - The monitoring and assessment of adherence to the security policy determines whether your security strategy is working. Often, IBM security consultants are asked to perform security assessments for companies without regard to the security policy. Although these assessments can be useful for observing how the system is defined and how data is being accessed, they cannot determine the level of security without a security policy. Without a security policy, it really is not an assessment as much as it is a baseline for monitoring the changes in the security settings that are captured.
 
 A security policy is what defines whether the system and its settings are secure (or not).
 
-- GLYPH<SM590000> The second fundamental in securing data assets is the use of resource security . If implemented properly, resource security prevents data breaches from both internal and external intrusions. Resource security controls are closely tied to the part of the security policy that defines who should have access to what information resources. A hacker might be good enough to get through your company firewalls and sift his way through to your system, but if they do not have explicit access to your database, the hacker cannot compromise your information assets.
+- GLYPH&lt;SM590000&gt; The second fundamental in securing data assets is the use of resource security . If implemented properly, resource security prevents data breaches from both internal and external intrusions. Resource security controls are closely tied to the part of the security policy that defines who should have access to what information resources. A hacker might be good enough to get through your company firewalls and sift his way through to your system, but if they do not have explicit access to your database, the hacker cannot compromise your information assets.
 
 With your eyes now open to the importance of securing information assets, the rest of this chapter reviews the methods that are available for securing database resources on IBM i.
 
@@ -173,9 +173,9 @@ Figure 1-2 Existing row and column controls
 
 The following CL commands can be used to work with, display, or change function usage IDs:
 
-- GLYPH<SM590000> Work Function Usage ( WRKFCNUSG )
-- GLYPH<SM590000> Change Function Usage ( CHGFCNUSG )
-- GLYPH<SM590000> Display Function Usage ( DSPFCNUSG )
+- GLYPH&lt;SM590000&gt; Work Function Usage ( WRKFCNUSG )
+- GLYPH&lt;SM590000&gt; Change Function Usage ( CHGFCNUSG )
+- GLYPH&lt;SM590000&gt; Display Function Usage ( DSPFCNUSG )
 
 For example, the following CHGFCNUSG command shows granting authorization to user HBEDOYA to administer and manage RCAC rules:
 
@@ -191,8 +191,8 @@ Table 2-1 FUNCTION\_USAGE view
 |---------------|-------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------|
 | FUNCTION\_ID   | VARCHAR(30) | ID of the function.                                                                                                                                                   |
 | USER\_NAME     | VARCHAR(10) | Name of the user profile that has a usage setting for this  function.                                                                                                 |
-| USAGE         | VARCHAR(7)  | Usage setting: GLYPH<SM590000> ALLOWED: The user profile is allowed to use the function. GLYPH<SM590000> DENIED: The user profile is not allowed to use the function. |
-| USER\_TYPE     | VARCHAR(5)  | Type of user profile: GLYPH<SM590000> USER: The user profile is a user. GLYPH<SM590000> GROUP: The user profile is a group.                                           |
+| USAGE         | VARCHAR(7)  | Usage setting: GLYPH&lt;SM590000&gt; ALLOWED: The user profile is allowed to use the function. GLYPH&lt;SM590000&gt; DENIED: The user profile is not allowed to use the function. |
+| USER\_TYPE     | VARCHAR(5)  | Type of user profile: GLYPH&lt;SM590000&gt; USER: The user profile is a user. GLYPH&lt;SM590000&gt; GROUP: The user profile is a group.                                           |
 
 To discover who has authorization to define and manage RCAC, you can use the query that is shown in Example 2-1.
 
@@ -273,11 +273,11 @@ Table 3-1 Special registers and their corresponding values
 
 Figure 3-5 shows the difference in the special register values when an adopted authority is used:
 
-- GLYPH<SM590000> A user connects to the server using the user profile ALICE.
-- GLYPH<SM590000> USER and CURRENT USER initially have the same value of ALICE.
-- GLYPH<SM590000> ALICE calls an SQL procedure that is named proc1, which is owned by user profile JOE and was created to adopt JOE's authority when it is called.
-- GLYPH<SM590000> While the procedure is running, the special register USER still contains the value of ALICE because it excludes any adopted authority. The special register CURRENT USER contains the value of JOE because it includes any adopted authority.
-- GLYPH<SM590000> When proc1 ends, the session reverts to its original state with both USER and CURRENT USER having the value of ALICE.
+- GLYPH&lt;SM590000&gt; A user connects to the server using the user profile ALICE.
+- GLYPH&lt;SM590000&gt; USER and CURRENT USER initially have the same value of ALICE.
+- GLYPH&lt;SM590000&gt; ALICE calls an SQL procedure that is named proc1, which is owned by user profile JOE and was created to adopt JOE's authority when it is called.
+- GLYPH&lt;SM590000&gt; While the procedure is running, the special register USER still contains the value of ALICE because it excludes any adopted authority. The special register CURRENT USER contains the value of JOE because it includes any adopted authority.
+- GLYPH&lt;SM590000&gt; When proc1 ends, the session reverts to its original state with both USER and CURRENT USER having the value of ALICE.
 
 Figure 3-5 Special registers and adopted authority
 
@@ -318,7 +318,7 @@ Here is an example of using the VERIFY\_GROUP\_FOR\_USER function:
 - 3. If a user is connected to the server using user profile JANE, all of the following function invocations return a value of 1:
 
 ```
-VERIFY\_GROUP\_FOR\_USER (CURRENT\_USER, 'MGR') VERIFY\_GROUP\_FOR\_USER (CURRENT\_USER, 'JANE', 'MGR') VERIFY\_GROUP\_FOR\_USER (CURRENT\_USER, 'JANE', 'MGR', 'STEVE') The following function invocation returns a value of 0: VERIFY\_GROUP\_FOR\_USER (CURRENT\_USER, 'JUDY', 'TONY')
+VERIFY_GROUP_FOR_USER (CURRENT_USER, 'MGR') VERIFY_GROUP_FOR_USER (CURRENT_USER, 'JANE', 'MGR') VERIFY_GROUP_FOR_USER (CURRENT_USER, 'JANE', 'MGR', 'STEVE') The following function invocation returns a value of 0: VERIFY_GROUP_FOR_USER (CURRENT_USER, 'JUDY', 'TONY')
 ```
 
 RETURN
@@ -326,7 +326,7 @@ RETURN
 CASE
 
 ```
-WHEN VERIFY\_GROUP\_FOR\_USER ( SESSION\_USER , 'HR', 'EMP' ) = 1 THEN EMPLOYEES . DATE\_OF\_BIRTH WHEN VERIFY\_GROUP\_FOR\_USER ( SESSION\_USER , 'MGR' ) = 1 AND SESSION\_USER = EMPLOYEES . USER\_ID THEN EMPLOYEES . DATE\_OF\_BIRTH WHEN VERIFY\_GROUP\_FOR\_USER ( SESSION\_USER , 'MGR' ) = 1 AND SESSION\_USER <> EMPLOYEES . USER\_ID THEN ( 9999 || '-' || MONTH ( EMPLOYEES . DATE\_OF\_BIRTH ) || '-' || DAY (EMPLOYEES.DATE\_OF\_BIRTH )) ELSE NULL END ENABLE ;
+WHEN VERIFY_GROUP_FOR_USER ( SESSION_USER , 'HR', 'EMP' ) = 1 THEN EMPLOYEES . DATE_OF_BIRTH WHEN VERIFY_GROUP_FOR_USER ( SESSION_USER , 'MGR' ) = 1 AND SESSION_USER = EMPLOYEES . USER_ID THEN EMPLOYEES . DATE_OF_BIRTH WHEN VERIFY_GROUP_FOR_USER ( SESSION_USER , 'MGR' ) = 1 AND SESSION_USER <> EMPLOYEES . USER_ID THEN ( 9999 || '-' || MONTH ( EMPLOYEES . DATE_OF_BIRTH ) || '-' || DAY (EMPLOYEES.DATE_OF_BIRTH )) ELSE NULL END ENABLE ;
 ```
 
 - 2. The other column to mask in this example is the TAX\_ID information. In this example, the rules to enforce include the following ones:
@@ -339,7 +339,7 @@ WHEN VERIFY\_GROUP\_FOR\_USER ( SESSION\_USER , 'HR', 'EMP' ) = 1 THEN EMPLOYEES
 Example 3-9 Creating a mask on the TAX\_ID column
 
 ```
-CREATE MASK HR\_SCHEMA.MASK\_TAX\_ID\_ON\_EMPLOYEES ON HR\_SCHEMA.EMPLOYEES AS EMPLOYEES FOR COLUMN TAX\_ID RETURN CASE WHEN VERIFY\_GROUP\_FOR\_USER ( SESSION\_USER , 'HR' ) = 1 THEN EMPLOYEES . TAX\_ID WHEN VERIFY\_GROUP\_FOR\_USER ( SESSION\_USER , 'MGR' ) = 1 AND SESSION\_USER = EMPLOYEES . USER\_ID THEN EMPLOYEES . TAX\_ID WHEN VERIFY\_GROUP\_FOR\_USER ( SESSION\_USER , 'MGR' ) = 1 AND SESSION\_USER <> EMPLOYEES . USER\_ID THEN ( 'XXX-XX-' CONCAT QSYS2 . SUBSTR ( EMPLOYEES . TAX\_ID , 8 , 4 ) ) WHEN VERIFY\_GROUP\_FOR\_USER ( SESSION\_USER , 'EMP' ) = 1 THEN EMPLOYEES . TAX\_ID ELSE 'XXX-XX-XXXX' END ENABLE ;
+CREATE MASK HR_SCHEMA.MASK_TAX_ID_ON_EMPLOYEES ON HR_SCHEMA.EMPLOYEES AS EMPLOYEES FOR COLUMN TAX_ID RETURN CASE WHEN VERIFY_GROUP_FOR_USER ( SESSION_USER , 'HR' ) = 1 THEN EMPLOYEES . TAX_ID WHEN VERIFY_GROUP_FOR_USER ( SESSION_USER , 'MGR' ) = 1 AND SESSION_USER = EMPLOYEES . USER_ID THEN EMPLOYEES . TAX_ID WHEN VERIFY_GROUP_FOR_USER ( SESSION_USER , 'MGR' ) = 1 AND SESSION_USER <> EMPLOYEES . USER_ID THEN ( 'XXX-XX-' CONCAT QSYS2 . SUBSTR ( EMPLOYEES . TAX_ID , 8 , 4 ) ) WHEN VERIFY_GROUP_FOR_USER ( SESSION_USER , 'EMP' ) = 1 THEN EMPLOYEES . TAX_ID ELSE 'XXX-XX-XXXX' END ENABLE ;
 ```
 
 - 3. Figure 3-10 shows the masks that are created in the HR\_SCHEMA.
@@ -386,7 +386,7 @@ Figure 4-69 Index advice with no RCAC
 <!-- image -->
 
 ```
-THEN C . CUSTOMER\_TAX\_ID WHEN QSYS2 . VERIFY\_GROUP\_FOR\_USER ( SESSION\_USER , 'TELLER' ) = 1 THEN ( 'XXX-XX-' CONCAT QSYS2 . SUBSTR ( C . CUSTOMER\_TAX\_ID , 8 , 4 ) ) WHEN QSYS2 . VERIFY\_GROUP\_FOR\_USER ( SESSION\_USER , 'CUSTOMER' ) = 1 THEN C . CUSTOMER\_TAX\_ID ELSE 'XXX-XX-XXXX' END ENABLE ; CREATE MASK BANK\_SCHEMA.MASK\_DRIVERS\_LICENSE\_ON\_CUSTOMERS ON BANK\_SCHEMA.CUSTOMERS AS C FOR COLUMN CUSTOMER\_DRIVERS\_LICENSE\_NUMBER RETURN CASE WHEN QSYS2 . VERIFY\_GROUP\_FOR\_USER ( SESSION\_USER , 'ADMIN' ) = 1 THEN C . CUSTOMER\_DRIVERS\_LICENSE\_NUMBER WHEN QSYS2 . VERIFY\_GROUP\_FOR\_USER ( SESSION\_USER , 'TELLER' ) = 1 THEN C . CUSTOMER\_DRIVERS\_LICENSE\_NUMBER WHEN QSYS2 . VERIFY\_GROUP\_FOR\_USER ( SESSION\_USER , 'CUSTOMER' ) = 1 THEN C . CUSTOMER\_DRIVERS\_LICENSE\_NUMBER ELSE '*************' END ENABLE ; CREATE MASK BANK\_SCHEMA.MASK\_LOGIN\_ID\_ON\_CUSTOMERS ON BANK\_SCHEMA.CUSTOMERS AS C FOR COLUMN CUSTOMER\_LOGIN\_ID RETURN CASE WHEN QSYS2 . VERIFY\_GROUP\_FOR\_USER ( SESSION\_USER , 'ADMIN' ) = 1 THEN C . CUSTOMER\_LOGIN\_ID WHEN QSYS2 . VERIFY\_GROUP\_FOR\_USER ( SESSION\_USER , 'CUSTOMER' ) = 1 THEN C . CUSTOMER\_LOGIN\_ID ELSE '*****' END ENABLE ; CREATE MASK BANK\_SCHEMA.MASK\_SECURITY\_QUESTION\_ON\_CUSTOMERS ON BANK\_SCHEMA.CUSTOMERS AS C FOR COLUMN CUSTOMER\_SECURITY\_QUESTION RETURN CASE WHEN QSYS2 . VERIFY\_GROUP\_FOR\_USER ( SESSION\_USER , 'ADMIN' ) = 1 THEN C . CUSTOMER\_SECURITY\_QUESTION WHEN QSYS2 . VERIFY\_GROUP\_FOR\_USER ( SESSION\_USER , 'CUSTOMER' ) = 1 THEN C . CUSTOMER\_SECURITY\_QUESTION ELSE '*****' END ENABLE ; CREATE MASK BANK\_SCHEMA.MASK\_SECURITY\_QUESTION\_ANSWER\_ON\_CUSTOMERS ON BANK\_SCHEMA.CUSTOMERS AS C FOR COLUMN CUSTOMER\_SECURITY\_QUESTION\_ANSWER RETURN CASE WHEN QSYS2 . VERIFY\_GROUP\_FOR\_USER ( SESSION\_USER , 'ADMIN' ) = 1 THEN C . CUSTOMER\_SECURITY\_QUESTION\_ANSWER WHEN QSYS2 . VERIFY\_GROUP\_FOR\_USER ( SESSION\_USER , 'CUSTOMER' ) = 1 THEN C . CUSTOMER\_SECURITY\_QUESTION\_ANSWER ELSE '*****' END ENABLE ; ALTER TABLE BANK\_SCHEMA.CUSTOMERS ACTIVATE ROW ACCESS CONTROL ACTIVATE COLUMN ACCESS CONTROL ;
+THEN C . CUSTOMER_TAX_ID WHEN QSYS2 . VERIFY_GROUP_FOR_USER ( SESSION_USER , 'TELLER' ) = 1 THEN ( 'XXX-XX-' CONCAT QSYS2 . SUBSTR ( C . CUSTOMER_TAX_ID , 8 , 4 ) ) WHEN QSYS2 . VERIFY_GROUP_FOR_USER ( SESSION_USER , 'CUSTOMER' ) = 1 THEN C . CUSTOMER_TAX_ID ELSE 'XXX-XX-XXXX' END ENABLE ; CREATE MASK BANK_SCHEMA.MASK_DRIVERS_LICENSE_ON_CUSTOMERS ON BANK_SCHEMA.CUSTOMERS AS C FOR COLUMN CUSTOMER_DRIVERS_LICENSE_NUMBER RETURN CASE WHEN QSYS2 . VERIFY_GROUP_FOR_USER ( SESSION_USER , 'ADMIN' ) = 1 THEN C . CUSTOMER_DRIVERS_LICENSE_NUMBER WHEN QSYS2 . VERIFY_GROUP_FOR_USER ( SESSION_USER , 'TELLER' ) = 1 THEN C . CUSTOMER_DRIVERS_LICENSE_NUMBER WHEN QSYS2 . VERIFY_GROUP_FOR_USER ( SESSION_USER , 'CUSTOMER' ) = 1 THEN C . CUSTOMER_DRIVERS_LICENSE_NUMBER ELSE '*************' END ENABLE ; CREATE MASK BANK_SCHEMA.MASK_LOGIN_ID_ON_CUSTOMERS ON BANK_SCHEMA.CUSTOMERS AS C FOR COLUMN CUSTOMER_LOGIN_ID RETURN CASE WHEN QSYS2 . VERIFY_GROUP_FOR_USER ( SESSION_USER , 'ADMIN' ) = 1 THEN C . CUSTOMER_LOGIN_ID WHEN QSYS2 . VERIFY_GROUP_FOR_USER ( SESSION_USER , 'CUSTOMER' ) = 1 THEN C . CUSTOMER_LOGIN_ID ELSE '*****' END ENABLE ; CREATE MASK BANK_SCHEMA.MASK_SECURITY_QUESTION_ON_CUSTOMERS ON BANK_SCHEMA.CUSTOMERS AS C FOR COLUMN CUSTOMER_SECURITY_QUESTION RETURN CASE WHEN QSYS2 . VERIFY_GROUP_FOR_USER ( SESSION_USER , 'ADMIN' ) = 1 THEN C . CUSTOMER_SECURITY_QUESTION WHEN QSYS2 . VERIFY_GROUP_FOR_USER ( SESSION_USER , 'CUSTOMER' ) = 1 THEN C . CUSTOMER_SECURITY_QUESTION ELSE '*****' END ENABLE ; CREATE MASK BANK_SCHEMA.MASK_SECURITY_QUESTION_ANSWER_ON_CUSTOMERS ON BANK_SCHEMA.CUSTOMERS AS C FOR COLUMN CUSTOMER_SECURITY_QUESTION_ANSWER RETURN CASE WHEN QSYS2 . VERIFY_GROUP_FOR_USER ( SESSION_USER , 'ADMIN' ) = 1 THEN C . CUSTOMER_SECURITY_QUESTION_ANSWER WHEN QSYS2 . VERIFY_GROUP_FOR_USER ( SESSION_USER , 'CUSTOMER' ) = 1 THEN C . CUSTOMER_SECURITY_QUESTION_ANSWER ELSE '*****' END ENABLE ; ALTER TABLE BANK_SCHEMA.CUSTOMERS ACTIVATE ROW ACCESS CONTROL ACTIVATE COLUMN ACCESS CONTROL ;
 ```
 
 Back cover

tests/data/groundtruth/docling_v2/wiki_duck.html.md

@@ -389,22 +389,22 @@ The 1992 Disney film The Mighty Ducks, starring Emilio Estevez, chose the duck a
 4. ^ Visca, Curt; Visca, Kelley (2003). How to Draw Cartoon Birds. The Rosen Publishing Group. ISBN 9780823961566.
 5. ^ a b c d Carboneras 1992, p. 536.
 6. ^ Livezey 1986, pp. 737–738.
-7. ^ Madsen, McHugh & de Kloet 1988, p. 452.
-8. ^ Donne-Goussé, Laudet & Hänni 2002, pp. 353–354.
+7. ^ Madsen, McHugh & de Kloet 1988, p. 452.
+8. ^ Donne-Goussé, Laudet & Hänni 2002, pp. 353–354.
 9. ^ a b c d e f Carboneras 1992, p. 540.
-10. ^ Elphick, Dunning & Sibley 2001, p. 191.
+10. ^ Elphick, Dunning & Sibley 2001, p. 191.
 11. ^ Kear 2005, p. 448.
 12. ^ Kear 2005, p. 622–623.
 13. ^ Kear 2005, p. 686.
-14. ^ Elphick, Dunning & Sibley 2001, p. 193.
+14. ^ Elphick, Dunning & Sibley 2001, p. 193.
 15. ^ a b c d e f g Carboneras 1992, p. 537.
 16. ^ American Ornithologists' Union 1998, p. xix.
 17. ^ American Ornithologists' Union 1998.
 18. ^ Carboneras 1992, p. 538.
-19. ^ Christidis & Boles 2008, p. 62.
+19. ^ Christidis & Boles 2008, p. 62.
 20. ^ Shirihai 2008, pp. 239, 245.
-21. ^ a b Pratt, Bruner & Berrett 1987, pp. 98–107.
-22. ^ Fitter, Fitter & Hosking 2000, pp. 52–3.
+21. ^ a b Pratt, Bruner & Berrett 1987, pp. 98–107.
+22. ^ Fitter, Fitter & Hosking 2000, pp. 52–3.
 23. ^ "Pacific Black Duck". www.wiresnr.org. Retrieved 2018-04-27.
 24. ^ Ogden, Evans. "Dabbling Ducks". CWE. Retrieved 2006-11-02.
 25. ^ Karl Mathiesen (16 March 2015). "Don't feed the ducks bread, say conservationists". The Guardian. Retrieved 13 November 2016.
@@ -412,7 +412,7 @@ The 1992 Disney film The Mighty Ducks, starring Emilio Estevez, chose the duck a
 27. ^ Smith, Cyndi M.; Cooke, Fred; Robertson, Gregory J.; Goudie, R. Ian; Boyd, W. Sean (2000). "Long-Term Pair Bonds in Harlequin Ducks". The Condor. 102 (1): 201–205. doi:10.1093/condor/102.1.201. hdl:10315/13797.
 28. ^ "If You Find An Orphaned Duckling - Wildlife Rehabber". wildliferehabber.com. Archived from the original on 2018-09-23. Retrieved 2018-12-22.
 29. ^ Carver, Heather (2011). The Duck Bible. Lulu.com. ISBN 9780557901562.[self-published source]
-30. ^ Titlow, Budd (2013-09-03). Bird Brains: Inside the Strange Minds of Our Fine Feathered Friends. Rowman & Littlefield. ISBN 9780762797707.
+30. ^ Titlow, Budd (2013-09-03). Bird Brains: Inside the Strange Minds of Our Fine Feathered Friends. Rowman & Littlefield. ISBN 9780762797707.
 31. ^ Amos, Jonathan (2003-09-08). "Sound science is quackers". BBC News. Retrieved 2006-11-02.
 32. ^ "Mythbusters Episode 8". 12 December 2003.
 33. ^ Erlandson 1994, p. 171.
@@ -446,10 +446,10 @@ The 1992 Disney film The Mighty Ducks, starring Emilio Estevez, chose the duck a
 - Christidis, Les; Boles, Walter E., eds. (2008). Systematics and Taxonomy of Australian Birds. Collingwood, VIC: Csiro Publishing. ISBN 978-0-643-06511-6.
 - Donne-Goussé, Carole; Laudet, Vincent; Hänni, Catherine (July 2002). "A molecular phylogeny of Anseriformes based on mitochondrial DNA analysis". Molecular Phylogenetics and Evolution. 23 (3): 339–356. Bibcode:2002MolPE..23..339D. doi:10.1016/S1055-7903(02)00019-2. PMID 12099792.
 - Elphick, Chris; Dunning, John B. Jr.; Sibley, David, eds. (2001). The Sibley Guide to Bird Life and Behaviour. London: Christopher Helm. ISBN 978-0-7136-6250-4.
-- Erlandson, Jon M. (1994). Early Hunter-Gatherers of the California Coast. New York, NY: Springer Science & Business Media. ISBN 978-1-4419-3231-0.
+- Erlandson, Jon M. (1994). Early Hunter-Gatherers of the California Coast. New York, NY: Springer Science & Business Media. ISBN 978-1-4419-3231-0.
 - Fieldhouse, Paul (2002). Food, Feasts, and Faith: An Encyclopedia of Food Culture in World Religions. Vol. I: A–K. Santa Barbara: ABC-CLIO. ISBN 978-1-61069-412-4.
 - Fitter, Julian; Fitter, Daniel; Hosking, David (2000). Wildlife of the Galápagos. Princeton, NJ: Princeton University Press. ISBN 978-0-691-10295-5.
-- Higman, B. W. (2012). How Food Made History. Chichester, UK: John Wiley & Sons. ISBN 978-1-4051-8947-7.
+- Higman, B. W. (2012). How Food Made History. Chichester, UK: John Wiley & Sons. ISBN 978-1-4051-8947-7.
 - Hume, Julian H. (2012). Extinct Birds. London: Christopher Helm. ISBN 978-1-4729-3744-5.
 - Jeffries, Richard (2008). Holocene Hunter-Gatherers of the Lower Ohio River Valley. Tuscaloosa: University of Alabama Press. ISBN 978-0-8173-1658-7.
 - Kear, Janet, ed. (2005). Ducks, Geese and Swans: Species Accounts (Cairina to Mergus). Bird Families of the World. Oxford: Oxford University Press. ISBN 978-0-19-861009-0.
@@ -457,7 +457,7 @@ The 1992 Disney film The Mighty Ducks, starring Emilio Estevez, chose the duck a
 - Madsen, Cort S.; McHugh, Kevin P.; de Kloet, Siwo R. (July 1988). "A partial classification of waterfowl (Anatidae) based on single-copy DNA" (PDF). The Auk. 105 (3): 452–459. doi:10.1093/auk/105.3.452. Archived (PDF) from the original on 2022-10-09.
 - Maisels, Charles Keith (1999). Early Civilizations of the Old World. London: Routledge. ISBN 978-0-415-10975-8.
 - Pratt, H. Douglas; Bruner, Phillip L.; Berrett, Delwyn G. (1987). A Field Guide to the Birds of Hawaii and the Tropical Pacific. Princeton, NJ: Princeton University Press. ISBN 0-691-02399-9.
-- Rau, Charles (1876). Early Man in Europe. New York: Harper & Brothers. LCCN 05040168.
+- Rau, Charles (1876). Early Man in Europe. New York: Harper & Brothers. LCCN 05040168.
 - Shirihai, Hadoram (2008). A Complete Guide to Antarctic Wildlife. Princeton, NJ, US: Princeton University Press. ISBN 978-0-691-13666-0.
 - Sued-Badillo, Jalil (2003). Autochthonous Societies. General History of the Caribbean. Paris: UNESCO. ISBN 978-92-3-103832-7.
 - Thorpe, I. J. (1996). The Origins of Agriculture in Europe. New York: Routledge. ISBN 978-0-415-08009-5.