Papers › PubLayNet: largest dataset ever for document layout analysis

PubLayNet: largest dataset ever for document layout analysis

16 Aug 2019arXiv:1908.07836archive 2025-07-28

Xu Zhong, Jianbin Tang, Antonio Jimeno Yepes

Recognizing the layout of unstructured digital documents is an important step when parsing the documents into structured machine-readable format for downstream applications. Deep neural networks that are developed for computer vision have been proven to be an effective method to analyze layout of document images. However, document layout datasets that are currently publicly available are several magnitudes smaller than established computing vision datasets. Models have to be trained by transfer learning from a base model that is pre-trained on a traditional computer vision dataset. In this paper, we develop the PubLayNet dataset for document layout analysis by automatically matching the XML representations and the content of over 1 million PDF articles that are publicly available on PubMed Central. The size of the dataset is comparable to established computer vision datasets, containing over 360 thousand document images, where typical document layout elements are annotated. The experiments demonstrate that deep neural networks trained on PubLayNet accurately recognize the layout of scientific articles. The pre-trained models are also a more effective base mode for transfer learning on a different document domain. We release the dataset (https://github.com/ibm-aur-nlp/PubLayNet) to support development and evaluation of more advanced models for document layout analysis.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1908.07836")

Code

Syntology Ran 7 of 13 code samples harvested from 2 repositories linked to this paper; 6 have no recorded run. Of those that ran: 2 ran · fixture could not drive it; 5 ran with no contract checked.

By repository: official repository: 1 sample from 1 repository, 1 ran; community (archive-listed): 12 samples from 1 repository, 6 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

ibm-aur-nlp/PubLayNet officialmentioned in papermentioned on GitHub report
adlnlp/doc_gcn mentioned on GitHubtf report
ibm-aur-nlp/PubTabNet mentioned on GitHubNOASSERTION report
phamquiluan/publaynet mentioned on GitHubpytorch report
pisalore/FRCNN_teX-annotator mentioned on GitHub report
hpanwar08/detectron2 pytorchApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

13 samples harvested; 7 ran; 0 honoured the contract we drafted; 6 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran · fixture could not drive it
5ran
6unverified

Licence: 13 of the 13 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

convert_PubLayNet_blob_to_target_blob ibm-aur-nlp/PubLayNet/pre-trained-models/convert_PubLayNet_model.py official repository ran · fixture could not drive it licence not identified · pointer only · ef1e85717438b077 · report
batched_nms hpanwar08/detectron2/detectron2/layers/nms.py community (archive-listed) ran Apache-2.0 recorded; this copy not marked cleared · pointer only · 0df9d3b583fbc6cb · report
cat hpanwar08/detectron2/detectron2/layers/wrappers.py community (archive-listed) ran · fixture could not drive it Apache-2.0 recorded; this copy not marked cleared · pointer only · 6cbf46794989b731 · report
convert_basic_c2_names hpanwar08/detectron2/detectron2/checkpoint/c2_model_loading.py community (archive-listed) ran Apache-2.0 recorded; this copy not marked cleared · pointer only · e8526a516b4f9206 · report
convert_c2_detectron_names hpanwar08/detectron2/detectron2/checkpoint/c2_model_loading.py community (archive-listed) ran Apache-2.0 recorded; this copy not marked cleared · pointer only · 52810b504f0d1066 · report
pad_masks hpanwar08/detectron2/detectron2/layers/mask_ops.py community (archive-listed) ran fingerprinted Apache-2.0 recorded; this copy not marked cleared · pointer only · 406f84cf799ed34d · report
paste_mask_in_image_old hpanwar08/detectron2/detectron2/layers/mask_ops.py community (archive-listed) ran Apache-2.0 recorded; this copy not marked cleared · pointer only · d03592674030077f · report
batched_nms_rotated hpanwar08/detectron2/detectron2/layers/nms.py community (archive-listed) unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · 4845964b76bba6c5 · report
get_checkpoint_url hpanwar08/detectron2/detectron2/model_zoo/model_zoo.py community (archive-listed) unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · 9555d17b677901ab · report
get_config_file hpanwar08/detectron2/detectron2/model_zoo/model_zoo.py community (archive-listed) unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · 10d4b4b249a78f42 · report
interpolate hpanwar08/detectron2/detectron2/layers/wrappers.py community (archive-listed) unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · e3055ddd5ac36b0b · report
nms_rotated hpanwar08/detectron2/detectron2/layers/nms.py community (archive-listed) unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · d3fa37a000ad294d · report
paste_masks_in_image hpanwar08/detectron2/detectron2/layers/mask_ops.py community (archive-listed) unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · f74abd7e1355f8cd · report

Tasks

ArticlesDocument Layout AnalysisTransfer Learning

Datasets

Introduced by this paper, per the archive.

PubLayNet

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Document Layout Analysis PubLayNet val Mask RCNN Figure 0.949 #12 of 15 Archive leaderboard report
Document Layout Analysis PubLayNet val Mask RCNN List 0.886 #12 of 15 Archive leaderboard report
Document Layout Analysis PubLayNet val Mask RCNN Overall 0.910 #12 of 15 Archive leaderboard report
Document Layout Analysis PubLayNet val Mask RCNN Table 0.960 #12 of 15 Archive leaderboard report
Document Layout Analysis PubLayNet val Mask RCNN Text 0.916 #12 of 15 Archive leaderboard report
Document Layout Analysis PubLayNet val Mask RCNN Title 0.840 #12 of 15 Archive leaderboard report
Document Layout Analysis PubLayNet val Faster RCNN Figure 0.937 #13 of 15 Archive leaderboard report
Document Layout Analysis PubLayNet val Faster RCNN List 0.883 #13 of 15 Archive leaderboard report
Document Layout Analysis PubLayNet val Faster RCNN Overall 0.902 #13 of 15 Archive leaderboard report
Document Layout Analysis PubLayNet val Faster RCNN Table 0.954 #13 of 15 Archive leaderboard report
Document Layout Analysis PubLayNet val Faster RCNN Text 0.910 #13 of 15 Archive leaderboard report
Document Layout Analysis PubLayNet val Faster RCNN Title 0.826 #13 of 15 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections