{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/optical-character-recognition","name":"Optical Character Recognition (OCR)","slug":"optical-character-recognition","description_markdown":"**Optical Character Recognition** or **Optical Character Reader** (OCR) is the electronic or mechanical conversion of images of typed, handwritten or printed text into machine-encoded text, whether from a scanned document, a photo of a document, a scene-photo (for example the text on signs and billboards in a landscape photo, license plates in cars...) or from subtitle text superimposed on an image (for example: from a television broadcast)","categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Methodology","url":"/area/methodology"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":1243,"papers_with_code":462,"benchmarks":6,"benchmark_tables_in_archive":6,"benchmark_tables_shown":6,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":55,"subtasks":10,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/optical-character-recognition-on-benchmarking","slug":"optical-character-recognition-on-benchmarking","dataset":"Benchmarking Chinese Text Recognition: Datasets, Baselines, and an Empirical Study","dataset_url":null,"rows_in_archive":7,"metrics":["Accuracy (%)"],"first_row_in_archive_order":{"model":"DTrOCR","paper_title":"DTrOCR: Decoder-only Transformer for Optical Character Recognition","paper_url":"/paper/dtrocr-decoder-only-transformer-for-optical","paper_date":"2023-08-30","arxiv_id":"2308.15996","code_links":[{"title":"arvindrajan92/DTrOCR","url":"https://github.com/arvindrajan92/DTrOCR"}],"syntology":null}},{"leaderboard":"/sota/optical-character-recognition-ocr-on-videodb","slug":"optical-character-recognition-ocr-on-videodb","dataset":"VideoDB's OCR Benchmark Public Collection","dataset_url":"/dataset/videodb-s-ocr-benchmark-public-collection","rows_in_archive":5,"metrics":["Average Accuracy","Character Error Rate (CER)","Word Error Rate (WER)"],"first_row_in_archive_order":{"model":"GPT-4o","paper_title":"Benchmarking Vision-Language Models on Optical Character Recognition in Dynamic Video Environments","paper_url":"/paper/benchmarking-vision-language-models-on","paper_date":"2025-02-10","arxiv_id":"2502.06445","code_links":[{"title":"video-db/ocr-benchmark","url":"https://github.com/video-db/ocr-benchmark"}],"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/benchmarking-vision-language-models-on#ran","syntology_url":"https://syntology.ai/paper/2502.06445","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.06445"}},"official":{"repos":["video-db/ocr-benchmark"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/optical-character-recognition-on-fsns-test","slug":"optical-character-recognition-on-fsns-test","dataset":"FSNS - Test","dataset_url":"/dataset/fsns-test","rows_in_archive":3,"metrics":["Sequence error"],"first_row_in_archive_order":{"model":"AttentionOCR_Inception-resnet-v2_Location","paper_title":"Attention-based Extraction of Structured Information from Street View Imagery","paper_url":"/paper/attention-based-extraction-of-structured","paper_date":"2017-04-11","arxiv_id":"1704.03549","code_links":[{"title":"tensorflow/models","url":"https://github.com/tensorflow/models/tree/master/research/attention_ocr"},{"title":"tensorflow/models","url":"https://github.com/tensorflow/models"},{"title":"leandroschelb/attention_ocr","url":"https://github.com/leandroschelb/attention_ocr"}],"syntology":null}},{"leaderboard":"/sota/optical-character-recognition-ocr-on-sut","slug":"optical-character-recognition-ocr-on-sut","dataset":"SUT","dataset_url":"/dataset/sut","rows_in_archive":2,"metrics":["Character Error Rate (CER)"],"first_row_in_archive_order":{"model":"Tesseract","paper_title":"SUT: a new multi-purpose synthetic dataset for Farsi document image analysis","paper_url":"/paper/sut-a-new-multi-purpose-synthetic-dataset-for","paper_date":"2023-11-27","arxiv_id":null,"code_links":[{"title":"aliiafkari/SUT_Dataset","url":"https://github.com/aliiafkari/SUT_Dataset"}],"syntology":null}},{"leaderboard":"/sota/optical-character-recognition-on-i2l-140k","slug":"optical-character-recognition-on-i2l-140k","dataset":"I2L-140K","dataset_url":"/dataset/i2l-140k","rows_in_archive":2,"metrics":["BLEU"],"first_row_in_archive_order":{"model":"I2L-NOPOOL","paper_title":"Teaching Machines to Code: Neural Markup Generation with Visual Attention","paper_url":"/paper/teaching-machines-to-code-neural-markup","paper_date":"2018-02-15","arxiv_id":"1802.05415","code_links":[{"title":"untrix/im2latex","url":"https://github.com/untrix/im2latex"}],"syntology":null}},{"leaderboard":"/sota/optical-character-recognition-on-im2latex-1","slug":"optical-character-recognition-on-im2latex-1","dataset":"im2latex-100k","dataset_url":"/dataset/im2latex-100k","rows_in_archive":1,"metrics":["BLEU"],"first_row_in_archive_order":{"model":"I2L-STRIPS","paper_title":"Teaching Machines to Code: Neural Markup Generation with Visual Attention","paper_url":"/paper/teaching-machines-to-code-neural-markup","paper_date":"2018-02-15","arxiv_id":"1802.05415","code_links":[{"title":"untrix/im2latex","url":"https://github.com/untrix/im2latex"}],"syntology":null}}],"datasets":[{"url":"/dataset/iam","name":"IAM","full_name":"IAM Handwriting","num_papers_in_archive":198},{"url":"/dataset/funsd","name":"FUNSD","full_name":"Form Understanding in Noisy Scanned Documents","num_papers_in_archive":179},{"url":"/dataset/textcaps","name":"TextCaps","full_name":"","num_papers_in_archive":98},{"url":"/dataset/st-vqa","name":"ST-VQA","full_name":"Scene Text Visual Question Answering","num_papers_in_archive":90},{"url":"/dataset/icdar-2003","name":"ICDAR 2003","full_name":"ICDAR 2003","num_papers_in_archive":53},{"url":"/dataset/textocr","name":"TextOCR","full_name":"","num_papers_in_archive":37},{"url":"/dataset/scitsr","name":"SciTSR","full_name":null,"num_papers_in_archive":36},{"url":"/dataset/docbank","name":"DocBank","full_name":"","num_papers_in_archive":34},{"url":"/dataset/105941-images-natural-scenes-ocr-data-of-12","name":"105,941 Images Natural Scenes OCR Data of 12 Languages","full_name":"105,941 Images Natural Scenes OCR Data of 12 Languages","num_papers_in_archive":24},{"url":"/dataset/ufpr-alpr","name":"UFPR-ALPR","full_name":"","num_papers_in_archive":15},{"url":"/dataset/im2latex-100k","name":"im2latex-100k","full_name":"","num_papers_in_archive":12},{"url":"/dataset/mrr-benchmark","name":"MRR-Benchmark","full_name":"Multi-Modal Reading Benchmark","num_papers_in_archive":11},{"url":"/dataset/rodosol-alpr","name":"RodoSol-ALPR","full_name":"","num_papers_in_archive":8},{"url":"/dataset/ssig-segplate","name":"SSIG-SegPlate","full_name":"","num_papers_in_archive":8},{"url":"/dataset/kannada-mnist","name":"Kannada-MNIST","full_name":"","num_papers_in_archive":7},{"url":"/dataset/iiit-ar-13k","name":"IIIT-AR-13K","full_name":"","num_papers_in_archive":6},{"url":"/dataset/midv-2019","name":"MIDV-2019","full_name":"","num_papers_in_archive":6},{"url":"/dataset/mle2e","name":"MLe2e","full_name":"","num_papers_in_archive":6},{"url":"/dataset/chinese-text-in-the-wild","name":"Chinese Text in the Wild","full_name":"","num_papers_in_archive":5},{"url":"/dataset/infinity-mm","name":"Infinity-MM","full_name":"","num_papers_in_archive":5},{"url":"/dataset/twitter100k","name":"Twitter100k","full_name":"","num_papers_in_archive":5},{"url":"/dataset/chineselp","name":"ChineseLP","full_name":"","num_papers_in_archive":4},{"url":"/dataset/ddi-100","name":"DDI-100","full_name":"Distorted Document Images","num_papers_in_archive":4},{"url":"/dataset/banglalekha-isolated","name":"BanglaLekha-Isolated","full_name":"","num_papers_in_archive":3},{"url":"/dataset/fsns-test","name":"FSNS - Test","full_name":"","num_papers_in_archive":3},{"url":"/dataset/high-quality-invoice-images-for-ocr","name":"High-Quality Invoice Images for OCR","full_name":"","num_papers_in_archive":3},{"url":"/dataset/imgur5k","name":"Imgur5K","full_name":"","num_papers_in_archive":3},{"url":"/dataset/newspaper-navigator","name":"Newspaper Navigator","full_name":"","num_papers_in_archive":3},{"url":"/dataset/mcscset","name":"MCSCSet","full_name":"","num_papers_in_archive":2},{"url":"/dataset/molparser-7m","name":"MolParser-7M","full_name":"","num_papers_in_archive":2},{"url":"/dataset/msda","name":"MSDA","full_name":"Multi-source domain adaptation dataset for text recognition","num_papers_in_archive":2},{"url":"/dataset/ufpr-amr-dataset","name":"UFPR-AMR","full_name":"","num_papers_in_archive":2},{"url":"/dataset/aceparse","name":"AceParse","full_name":"","num_papers_in_archive":1},{"url":"/dataset/an-extensive-dataset-of-handwritten-central","name":"An extensive dataset of handwritten central Kurdish isolated characters","full_name":"Rebin M. Ahmed","num_papers_in_archive":1},{"url":"/dataset/arabic-img2md","name":"arabic-img2md","full_name":"Arabic Img2MD","num_papers_in_archive":1},{"url":"/dataset/bln600","name":"BLN600","full_name":"BLN600: A Parallel Corpus of Machine/Human Transcribed Nineteenth Century Newspaper Texts","num_papers_in_archive":1},{"url":"/dataset/copel-amr-dataset","name":"Copel-AMR","full_name":"","num_papers_in_archive":1},{"url":"/dataset/doc3dshade","name":"Doc3DShade","full_name":"","num_papers_in_archive":1},{"url":"/dataset/fics-pcb-image-collection-fpic","name":"FICS PCB Image Collection (FPIC)","full_name":"","num_papers_in_archive":1},{"url":"/dataset/i2l-140k","name":"I2L-140K","full_name":"","num_papers_in_archive":1},{"url":"/dataset/illusionchar-test","name":"IllusionChar_test","full_name":"","num_papers_in_archive":1},{"url":"/dataset/large-labelled-logo-dataset-l3d","name":"Large Labelled Logo Dataset (L3D)","full_name":"","num_papers_in_archive":1},{"url":"/dataset/matrivasha","name":"MatriVasha:","full_name":"MatriVasha: Compound Character atasetD","num_papers_in_archive":1},{"url":"/dataset/ncse-v2-0","name":"NCSE v2.0","full_name":"NCSE v2.0: A Dataset of OCR-Processed 19th Century English Newspapers","num_papers_in_archive":1},{"url":"/dataset/psocr","name":"PsOCR","full_name":"Pashto OCR Dataset","num_papers_in_archive":1},{"url":"/dataset/sut","name":"SUT","full_name":"SUT: a new multi-purpose synthetic dataset for Farsi document image analysis","num_papers_in_archive":1},{"url":"/dataset/utrset-real","name":"UTRSet-Real","full_name":"","num_papers_in_archive":1},{"url":"/dataset/utrset-synth","name":"UTRSet-Synth","full_name":"","num_papers_in_archive":1},{"url":"/dataset/videodb-s-ocr-benchmark-public-collection","name":"VideoDB's OCR Benchmark Public Collection","full_name":"VideoDB's OCR Benchmark Public Collection","num_papers_in_archive":1},{"url":"/dataset/webli","name":"WebLI","full_name":"Web Language Image","num_papers_in_archive":1},{"url":"/dataset/codescan","name":"CodeSCAN","full_name":"ScreenCast ANalysis for Video Programming Tutorials","num_papers_in_archive":0},{"url":"/dataset/hindi-text-image-dataset","name":"Hindi Text Image Dataset | Hindi in the wild","full_name":"datacluster.ai","num_papers_in_archive":0},{"url":"/dataset/indian-signboard-image-dataset-text-in-image","name":"Indian Signboard Image Dataset | Text in Image","full_name":"datacluster.ai","num_papers_in_archive":0},{"url":"/dataset/ts-tr","name":"TS-TR","full_name":"Turkish Scene Text Recognition Dataset","num_papers_in_archive":0},{"url":"/dataset/visiting-card-id-card-images-hindi-english","name":"Visiting Card | ID Card Images | Hindi-English","full_name":"datacluster.ai","num_papers_in_archive":0}],"subtasks":[{"url":"/task/active-learning","name":"Active Learning"},{"url":"/task/grapheme-detection","name":"Grapheme Detection"},{"url":"/task/handwriting-recognition","name":"Handwriting Recognition"},{"url":"/task/handwritten-chinese-text-recognition","name":"Handwritten Chinese Text Recognition"},{"url":"/task/handwritten-digit-image-synthesis","name":"Handwritten Digit Image Synthesis"},{"url":"/task/handwritten-digit-recognition","name":"Handwritten Digit Recognition"},{"url":"/task/handwritten-text-recognition","name":"Handwritten Text Recognition"},{"url":"/task/irregular-text-recognition","name":"Irregular Text Recognition"},{"url":"/task/offline-handwritten-chinese-character","name":"Offline Handwritten Chinese Character Recognition"},{"url":"/task/word-spotting-in-handwritten-documents","name":"Word Spotting In Handwritten Documents"}],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":13,"rows_per_page":100,"shown":100,"of":1243,"of_with_code":462,"tagged_in_all":1243,"counts":{"archive_papers_tagged":1243,"with_a_code_link":462,"where_syntology_ran_a_sample":76,"not_listed_spam_title":0,"listed":1243,"listed_where_code_ran":76,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":64,"every_run_a_failure_of_syntologys_instrument":12,"listed_with_a_run_with_no_instrument_failure":64,"listed_every_run_a_failure_of_syntologys_instrument":12,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/an-end-to-end-trainable-neural-network-for","slug":"an-end-to-end-trainable-neural-network-for","title":"An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition","date":"2015-07-21","arxiv_id":"1507.05717","repositories_listed":85,"syntology":{"n":81,"n_ran":66,"n_constructed":0,"n_ran_checked":49,"n_instrument":17,"n_unverified":15,"n_honours":1,"n_violates":1,"n_no_contract":47,"n_pointer_only":17,"phrase":"66 ran (of which 0 constructed an object rather than computing a result; 49 with no instrument failure: 1 honoured, 1 violated, 47 with no contract checked; 17 where Syntology's instrument failed) · 15 unverified","sample_list":"/paper/an-end-to-end-trainable-neural-network-for#ran","syntology_url":"https://syntology.ai/paper/1507.05717","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1507.05717"}},"official":null}},{"url":"/paper/east-an-efficient-and-accurate-scene-text","slug":"east-an-efficient-and-accurate-scene-text","title":"EAST: An Efficient and Accurate Scene Text Detector","date":"2017-04-11","arxiv_id":"1704.03155","repositories_listed":31,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/east-an-efficient-and-accurate-scene-text#ran","syntology_url":"https://syntology.ai/paper/1704.03155","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1704.03155"}},"official":null}},{"url":"/paper/shape-robust-text-detection-with-progressive-1","slug":"shape-robust-text-detection-with-progressive-1","title":"Shape Robust Text Detection with Progressive Scale Expansion Network","date":"2019-03-28","arxiv_id":"1903.12473","repositories_listed":19,"syntology":null},{"url":"/paper/real-time-scene-text-detection-with","slug":"real-time-scene-text-detection-with","title":"Real-time Scene Text Detection with Differentiable Binarization","date":"2019-11-20","arxiv_id":"1911.08947","repositories_listed":15,"syntology":{"n":25,"n_ran":20,"n_constructed":0,"n_ran_checked":17,"n_instrument":3,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":17,"n_pointer_only":1,"phrase":"20 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/real-time-scene-text-detection-with#ran","syntology_url":"https://syntology.ai/paper/1911.08947","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.08947"}},"official":{"repos":["MhLiao/DB"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/image-to-markup-generation-with-coarse-to","slug":"image-to-markup-generation-with-coarse-to","title":"Image-to-Markup Generation with Coarse-to-Fine Attention","date":"2016-09-16","arxiv_id":"1609.04938","repositories_listed":14,"syntology":{"n":13,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/image-to-markup-generation-with-coarse-to#ran","syntology_url":"https://syntology.ai/paper/1609.04938","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1609.04938"}},"official":{"repos":["harvardnlp/im2markup"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}},{"url":"/paper/pp-ocr-a-practical-ultra-lightweight-ocr","slug":"pp-ocr-a-practical-ultra-lightweight-ocr","title":"PP-OCR: A Practical Ultra Lightweight OCR System","date":"2020-09-21","arxiv_id":"2009.09941","repositories_listed":10,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/pp-ocr-a-practical-ultra-lightweight-ocr#ran","syntology_url":"https://syntology.ai/paper/2009.09941","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.09941"}},"official":{"repos":["PaddlePaddle/PaddleOCR"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/trocr-transformer-based-optical-character","slug":"trocr-transformer-based-optical-character","title":"TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models","date":"2021-09-21","arxiv_id":"2109.10282","repositories_listed":8,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/trocr-transformer-based-optical-character#ran","syntology_url":"https://syntology.ai/paper/2109.10282","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.10282"}},"official":{"repos":["microsoft/unilm"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/show-attend-and-read-a-simple-and-strong","slug":"show-attend-and-read-a-simple-and-strong","title":"Show, Attend and Read: A Simple and Strong Baseline for Irregular Text Recognition","date":"2018-11-02","arxiv_id":"1811.00751","repositories_listed":8,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/show-attend-and-read-a-simple-and-strong#ran","syntology_url":"https://syntology.ai/paper/1811.00751","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.00751"}},"official":null}},{"url":"/paper/a-multi-object-rectified-attention-network","slug":"a-multi-object-rectified-attention-network","title":"A Multi-Object Rectified Attention Network for Scene Text Recognition","date":"2019-01-10","arxiv_id":"1901.03003","repositories_listed":7,"syntology":null},{"url":"/paper/image-based-table-recognition-data-model-and","slug":"image-based-table-recognition-data-model-and","title":"Image-based table recognition: data, model, and evaluation","date":"2019-11-25","arxiv_id":"1911.10683","repositories_listed":6,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/image-based-table-recognition-data-model-and#ran","syntology_url":"https://syntology.ai/paper/1911.10683","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.10683"}},"official":{"repos":["ibm-aur-nlp/PubTabNet"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/donut-document-understanding-transformer","slug":"donut-document-understanding-transformer","title":"OCR-free Document Understanding Transformer","date":"2021-11-30","arxiv_id":"2111.15664","repositories_listed":5,"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/donut-document-understanding-transformer#ran","syntology_url":"https://syntology.ai/paper/2111.15664","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.15664"}},"official":{"repos":["clovaai/donut"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/exploring-cross-image-pixel-contrast-for","slug":"exploring-cross-image-pixel-contrast-for","title":"Exploring Cross-Image Pixel Contrast for Semantic Segmentation","date":"2021-01-28","arxiv_id":"2101.11939","repositories_listed":5,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/exploring-cross-image-pixel-contrast-for#ran","syntology_url":"https://syntology.ai/paper/2101.11939","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.11939"}},"official":{"repos":["tfzhou/ContrastiveSeg"],"state":"official: not harvested","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"url":"/paper/chinese-text-in-the-wild","slug":"chinese-text-in-the-wild","title":"Chinese Text in the Wild","date":"2018-02-28","arxiv_id":"1803.00085","repositories_listed":5,"syntology":null},{"url":"/paper/robust-scene-text-recognition-with-automatic","slug":"robust-scene-text-recognition-with-automatic","title":"Robust Scene Text Recognition with Automatic Rectification","date":"2016-03-12","arxiv_id":"1603.03915","repositories_listed":5,"syntology":null},{"url":"/paper/pix2struct-screenshot-parsing-as-pretraining","slug":"pix2struct-screenshot-parsing-as-pretraining","title":"Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding","date":"2022-10-07","arxiv_id":"2210.03347","repositories_listed":4,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/pix2struct-screenshot-parsing-as-pretraining#ran","syntology_url":"https://syntology.ai/paper/2210.03347","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.03347"}},"official":{"repos":["google-research/pix2struct"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/dit-self-supervised-pre-training-for-document","slug":"dit-self-supervised-pre-training-for-document","title":"DiT: Self-supervised Pre-training for Document Image Transformer","date":"2022-03-04","arxiv_id":"2203.02378","repositories_listed":4,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/dit-self-supervised-pre-training-for-document#ran","syntology_url":"https://syntology.ai/paper/2203.02378","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.02378"}},"official":{"repos":["microsoft/unilm"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/de-gan-a-conditional-generative-adversarial-1","slug":"de-gan-a-conditional-generative-adversarial-1","title":"DE-GAN: A Conditional Generative Adversarial Network for Document Enhancement","date":"2020-10-17","arxiv_id":"2010.08764","repositories_listed":4,"syntology":null},{"url":"/paper/aster-an-attentional-scene-text-recognizer","slug":"aster-an-attentional-scene-text-recognizer","title":"ASTER: An Attentional Scene Text Recognizer with Flexible Rectification","date":"2018-06-25","arxiv_id":null,"repositories_listed":4,"syntology":null},{"url":"/paper/nrtr-a-no-recurrence-sequence-to-sequence","slug":"nrtr-a-no-recurrence-sequence-to-sequence","title":"NRTR: A No-Recurrence Sequence-to-Sequence Model For Scene Text Recognition","date":"2018-06-04","arxiv_id":"1806.00926","repositories_listed":4,"syntology":null},{"url":"/paper/end-to-end-interpretation-of-the-french","slug":"end-to-end-interpretation-of-the-french","title":"End-to-End Interpretation of the French Street Name Signs Dataset","date":"2017-02-13","arxiv_id":"1702.03970","repositories_listed":4,"syntology":null},{"url":"/paper/coco-text-dataset-and-benchmark-for-text","slug":"coco-text-dataset-and-benchmark-for-text","title":"COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural Images","date":"2016-01-26","arxiv_id":"1601.07140","repositories_listed":4,"syntology":null},{"url":"/paper/scrambled-text-training-language-models-to","slug":"scrambled-text-training-language-models-to","title":"Scrambled text: training Language Models to correct OCR errors using synthetic data","date":"2024-09-29","arxiv_id":"2409.19735","repositories_listed":3,"syntology":null},{"url":"/paper/swift-a-scalable-lightweight-infrastructure","slug":"swift-a-scalable-lightweight-infrastructure","title":"SWIFT:A Scalable lightWeight Infrastructure for Fine-Tuning","date":"2024-08-10","arxiv_id":"2408.05517","repositories_listed":3,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/swift-a-scalable-lightweight-infrastructure#ran","syntology_url":"https://syntology.ai/paper/2408.05517","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.05517"}},"official":{"repos":["modelscope/ms-swift","modelscope/swift"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/docreal-robust-document-dewarping-of-real","slug":"docreal-robust-document-dewarping-of-real","title":"DocReal: Robust Document Dewarping of Real-Life Images via Attention-Enhanced Control Point Prediction","date":"2023-12-01","arxiv_id":null,"repositories_listed":3,"syntology":null},{"url":"/paper/nougat-neural-optical-understanding-for","slug":"nougat-neural-optical-understanding-for","title":"Nougat: Neural Optical Understanding for Academic Documents","date":"2023-08-25","arxiv_id":"2308.13418","repositories_listed":3,"syntology":{"n":14,"n_ran":13,"n_constructed":0,"n_ran_checked":12,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":1,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/nougat-neural-optical-understanding-for#ran","syntology_url":"https://syntology.ai/paper/2308.13418","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.13418"}},"official":{"repos":["facebookresearch/nougat"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/layout-and-task-aware-instruction-prompt-for","slug":"layout-and-task-aware-instruction-prompt-for","title":"Layout and Task Aware Instruction Prompt for Zero-shot Document Image Question Answering","date":"2023-06-01","arxiv_id":"2306.00526","repositories_listed":3,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/layout-and-task-aware-instruction-prompt-for#ran","syntology_url":"https://syntology.ai/paper/2306.00526","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.00526"}},"official":{"repos":["wenjinw/latin-prompt"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/llama-adapter-v2-parameter-efficient-visual","slug":"llama-adapter-v2-parameter-efficient-visual","title":"LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model","date":"2023-04-28","arxiv_id":"2304.15010","repositories_listed":3,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/llama-adapter-v2-parameter-efficient-visual#ran","syntology_url":"https://syntology.ai/paper/2304.15010","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.15010"}},"official":{"repos":["zrrskywalker/llama-adapter"],"state":"official: not harvested","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"url":"/paper/glyphdraw-learning-to-draw-chinese-characters","slug":"glyphdraw-learning-to-draw-chinese-characters","title":"GlyphDraw: Seamlessly Rendering Text with Intricate Spatial Structures in Text-to-Image Generation","date":"2023-03-31","arxiv_id":"2303.17870","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/glyphdraw-learning-to-draw-chinese-characters#ran","syntology_url":"https://syntology.ai/paper/2303.17870","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.17870"}},"official":{"repos":["OPPO-Mente-Lab/GlyphDraw"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/meta-album-multi-domain-meta-dataset-for-few-1","slug":"meta-album-multi-domain-meta-dataset-for-few-1","title":"Meta-Album: Multi-domain Meta-Dataset for Few-Shot Image Classification","date":"2023-02-16","arxiv_id":"2302.08909","repositories_listed":3,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/meta-album-multi-domain-meta-dataset-for-few-1#ran","syntology_url":"https://syntology.ai/paper/2302.08909","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.08909"}},"official":{"repos":["dustincarrion/cd-metadl","ihsaan-ullah/meta-album","ihsanullah2131/meta-album"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/ocr-vqgan-taming-text-within-image-generation","slug":"ocr-vqgan-taming-text-within-image-generation","title":"OCR-VQGAN: Taming Text-within-Image Generation","date":"2022-10-19","arxiv_id":"2210.11248","repositories_listed":3,"syntology":null},{"url":"/paper/multi-granularity-prediction-for-scene-text","slug":"multi-granularity-prediction-for-scene-text","title":"Multi-Granularity Prediction for Scene Text Recognition","date":"2022-09-08","arxiv_id":"2209.03592","repositories_listed":3,"syntology":null},{"url":"/paper/when-counting-meets-hmer-counting-aware","slug":"when-counting-meets-hmer-counting-aware","title":"When Counting Meets HMER: Counting-Aware Network for Handwritten Mathematical Expression Recognition","date":"2022-07-23","arxiv_id":"2207.11463","repositories_listed":3,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/when-counting-meets-hmer-counting-aware#ran","syntology_url":"https://syntology.ai/paper/2207.11463","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.11463"}},"official":{"repos":["lbh1024/can"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/tableformer-table-structure-understanding","slug":"tableformer-table-structure-understanding","title":"TableFormer: Table Structure Understanding with Transformers","date":"2022-03-02","arxiv_id":"2203.01017","repositories_listed":3,"syntology":null},{"url":"/paper/docscanner-robust-document-image","slug":"docscanner-robust-document-image","title":"DocScanner: Robust Document Image Rectification with Progressive Learning","date":"2021-10-28","arxiv_id":"2110.14968","repositories_listed":3,"syntology":null},{"url":"/paper/pp-ocrv2-bag-of-tricks-for-ultra-lightweight","slug":"pp-ocrv2-bag-of-tricks-for-ultra-lightweight","title":"PP-OCRv2: Bag of Tricks for Ultra Lightweight OCR System","date":"2021-09-07","arxiv_id":"2109.03144","repositories_listed":3,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/pp-ocrv2-bag-of-tricks-for-ultra-lightweight#ran","syntology_url":"https://syntology.ai/paper/2109.03144","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.03144"}},"official":{"repos":["PaddlePaddle/PaddleOCR"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/divnoising-diversity-denoising-with-fully","slug":"divnoising-diversity-denoising-with-fully","title":"Fully Unsupervised Diversity Denoising with Convolutional Variational Autoencoders","date":"2020-06-10","arxiv_id":"2006.06072","repositories_listed":3,"syntology":null},{"url":"/paper/seed-semantics-enhanced-encoder-decoder","slug":"seed-semantics-enhanced-encoder-decoder","title":"SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition","date":"2020-05-22","arxiv_id":"2005.10977","repositories_listed":3,"syntology":null},{"url":"/paper/towards-accurate-scene-text-recognition-with","slug":"towards-accurate-scene-text-recognition-with","title":"Towards Accurate Scene Text Recognition with Semantic Reasoning Networks","date":"2020-03-27","arxiv_id":"2003.12294","repositories_listed":3,"syntology":null},{"url":"/paper/scrabblegan-semi-supervised-varying-length","slug":"scrabblegan-semi-supervised-varying-length","title":"ScrabbleGAN: Semi-Supervised Varying Length Handwritten Text Generation","date":"2020-03-23","arxiv_id":"2003.10557","repositories_listed":3,"syntology":{"n":15,"n_ran":14,"n_constructed":0,"n_ran_checked":11,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":3,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/scrabblegan-semi-supervised-varying-length#ran","syntology_url":"https://syntology.ai/paper/2003.10557","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.10557"}},"official":null}},{"url":"/paper/multimodal-deep-networks-for-text-and-image","slug":"multimodal-deep-networks-for-text-and-image","title":"Multimodal deep networks for text and image-based document classification","date":"2019-07-15","arxiv_id":"1907.06370","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/multimodal-deep-networks-for-text-and-image#ran","syntology_url":"https://syntology.ai/paper/1907.06370","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.06370"}},"official":{"repos":["Quicksign/ocrized-text-dataset"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/190513538","slug":"190513538","title":"FUNSD: A Dataset for Form Understanding in Noisy Scanned Documents","date":"2019-05-27","arxiv_id":"1905.13538","repositories_listed":3,"syntology":null},{"url":"/paper/stroke-extraction-for-offline-handwritten","slug":"stroke-extraction-for-offline-handwritten","title":"Stroke extraction for offline handwritten mathematical expression recognition","date":"2019-05-16","arxiv_id":"1905.06749","repositories_listed":3,"syntology":null},{"url":"/paper/e2e-mlt-an-unconstrained-end-to-end-method","slug":"e2e-mlt-an-unconstrained-end-to-end-method","title":"E2E-MLT - an Unconstrained End-to-End Method for Multi-Language Scene Text","date":"2018-01-30","arxiv_id":"1801.09919","repositories_listed":3,"syntology":null},{"url":"/paper/stn-ocr-a-single-neural-network-for-text","slug":"stn-ocr-a-single-neural-network-for-text","title":"STN-OCR: A single Neural Network for Text Detection and Text Recognition","date":"2017-07-27","arxiv_id":"1707.08831","repositories_listed":3,"syntology":null},{"url":"/paper/attention-based-extraction-of-structured","slug":"attention-based-extraction-of-structured","title":"Attention-based Extraction of Structured Information from Street View Imagery","date":"2017-04-11","arxiv_id":"1704.03549","repositories_listed":3,"syntology":null},{"url":"/paper/on-path-to-multimodal-historical-reasoning","slug":"on-path-to-multimodal-historical-reasoning","title":"On Path to Multimodal Historical Reasoning: HistBench and HistAgent","date":"2025-05-26","arxiv_id":"2505.20246","repositories_listed":2,"syntology":null},{"url":"/paper/multimodal-llms-for-ocr-ocr-post-correction","slug":"multimodal-llms-for-ocr-ocr-post-correction","title":"Multimodal LLMs for OCR, OCR Post-Correction, and Named Entity Recognition in Historical Documents","date":"2025-04-01","arxiv_id":"2504.00414","repositories_listed":2,"syntology":null},{"url":"/paper/jochre-3-and-the-yiddish-ocr-corpus","slug":"jochre-3-and-the-yiddish-ocr-corpus","title":"Jochre 3 and the Yiddish OCR corpus","date":"2025-01-14","arxiv_id":"2501.08442","repositories_listed":2,"syntology":null},{"url":"/paper/comparative-analysis-of-optical-character","slug":"comparative-analysis-of-optical-character","title":"Comparative analysis of optical character recognition methods for Sámi texts from the National Library of Norway","date":"2025-01-13","arxiv_id":"2501.07300","repositories_listed":2,"syntology":null},{"url":"/paper/mineru-an-open-source-solution-for-precise","slug":"mineru-an-open-source-solution-for-precise","title":"MinerU: An Open-Source Solution for Precise Document Content Extraction","date":"2024-09-27","arxiv_id":"2409.18839","repositories_listed":2,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":2,"n_instrument":6,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":8,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mineru-an-open-source-solution-for-precise#ran","syntology_url":"https://syntology.ai/paper/2409.18839","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.18839"}},"official":{"repos":["opendatalab/mineru","opendatalab/PDF-Extract-Kit"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/mmmu-pro-a-more-robust-multi-discipline","slug":"mmmu-pro-a-more-robust-multi-discipline","title":"MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark","date":"2024-09-04","arxiv_id":"2409.02813","repositories_listed":2,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/mmmu-pro-a-more-robust-multi-discipline#ran","syntology_url":"https://syntology.ai/paper/2409.02813","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.02813"}},"official":null}},{"url":"/paper/eagle-exploring-the-design-space-for","slug":"eagle-exploring-the-design-space-for","title":"Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders","date":"2024-08-28","arxiv_id":"2408.15998","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/eagle-exploring-the-design-space-for#ran","syntology_url":"https://syntology.ai/paper/2408.15998","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.15998"}},"official":{"repos":["nvlabs/eagle"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/2408-01800","slug":"2408-01800","title":"MiniCPM-V: A GPT-4V Level MLLM on Your Phone","date":"2024-08-03","arxiv_id":"2408.01800","repositories_listed":2,"syntology":{"n":14,"n_ran":11,"n_constructed":0,"n_ran_checked":5,"n_instrument":6,"n_unverified":3,"n_honours":1,"n_violates":2,"n_no_contract":2,"n_pointer_only":6,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 2 violated, 2 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/2408-01800#ran","syntology_url":"https://syntology.ai/paper/2408.01800","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.01800"}},"official":{"repos":["OpenBMB/MiniCPM-o"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/viocrvqa-novel-benchmark-dataset-and-vision","slug":"viocrvqa-novel-benchmark-dataset-and-vision","title":"ViOCRVQA: Novel Benchmark Dataset and Vision Reader for Visual Question Answering by Understanding Vietnamese Text in Images","date":"2024-04-29","arxiv_id":"2404.18397","repositories_listed":2,"syntology":null},{"url":"/paper/vitextvqa-a-large-scale-visual-question","slug":"vitextvqa-a-large-scale-visual-question","title":"ViTextVQA: A Large-Scale Visual Question Answering Dataset for Evaluating Vietnamese Text Comprehension in Images","date":"2024-04-16","arxiv_id":"2404.10652","repositories_listed":2,"syntology":null},{"url":"/paper/naf-dpm-a-nonlinear-activation-free-diffusion","slug":"naf-dpm-a-nonlinear-activation-free-diffusion","title":"NAF-DPM: A Nonlinear Activation-Free Diffusion Probabilistic Model for Document Enhancement","date":"2024-04-08","arxiv_id":"2404.05669","repositories_listed":2,"syntology":null},{"url":"/paper/memorais-an-optical-character-recognition-and","slug":"memorais-an-optical-character-recognition-and","title":"memorAIs: an Optical Character Recognition and Rule-Based Medication Intake Reminder-Generating Solution","date":"2023-12-11","arxiv_id":"2312.06841","repositories_listed":2,"syntology":null},{"url":"/paper/automatic-recognition-of-learning-resource","slug":"automatic-recognition-of-learning-resource","title":"Automatic Recognition of Learning Resource Category in a Digital Library","date":"2023-11-28","arxiv_id":"2401.12220","repositories_listed":2,"syntology":null},{"url":"/paper/data-generation-for-post-ocr-correction-of","slug":"data-generation-for-post-ocr-correction-of","title":"Data Generation for Post-OCR correction of Cyrillic handwriting","date":"2023-11-27","arxiv_id":"2311.15896","repositories_listed":2,"syntology":null},{"url":"/paper/optimization-of-image-processing-algorithms","slug":"optimization-of-image-processing-algorithms","title":"Optimization of Image Processing Algorithms for Character Recognition in Cultural Typewritten Documents","date":"2023-11-27","arxiv_id":"2311.15740","repositories_listed":2,"syntology":null},{"url":"/paper/chemscraper-graphics-extraction-molecular","slug":"chemscraper-graphics-extraction-molecular","title":"ChemScraper: Leveraging PDF Graphics Instructions for Molecular Diagram Parsing","date":"2023-11-20","arxiv_id":"2311.12161","repositories_listed":2,"syntology":null},{"url":"/paper/figstep-jailbreaking-large-vision-language","slug":"figstep-jailbreaking-large-vision-language","title":"FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts","date":"2023-11-09","arxiv_id":"2311.05608","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/figstep-jailbreaking-large-vision-language#ran","syntology_url":"https://syntology.ai/paper/2311.05608","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.05608"}},"official":{"repos":["thuccslab/figstep"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/jl-lemma-derived-optimal-projections-for","slug":"jl-lemma-derived-optimal-projections-for","title":"Optimal Projections for Discriminative Dictionary Learning using the JL-lemma","date":"2023-08-27","arxiv_id":"2308.13991","repositories_listed":2,"syntology":null},{"url":"/paper/multi-granularity-prediction-with-learnable","slug":"multi-granularity-prediction-with-learnable","title":"Multi-Granularity Prediction with Learnable Fusion for Scene Text Recognition","date":"2023-07-25","arxiv_id":"2307.13244","repositories_listed":2,"syntology":null},{"url":"/paper/multimodal-machine-learning-for-extraction-of","slug":"multimodal-machine-learning-for-extraction-of","title":"Modular Multimodal Machine Learning for Extraction of Theorems and Proofs in Long Scientific Documents (Extended Version)","date":"2023-07-18","arxiv_id":"2307.09047","repositories_listed":2,"syntology":null},{"url":"/paper/llavar-enhanced-visual-instruction-tuning-for","slug":"llavar-enhanced-visual-instruction-tuning-for","title":"LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding","date":"2023-06-29","arxiv_id":"2306.17107","repositories_listed":2,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":0,"n_instrument":6,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/llavar-enhanced-visual-instruction-tuning-for#ran","syntology_url":"https://syntology.ai/paper/2306.17107","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.17107"}},"official":{"repos":["SALT-NLP/LLaVAR"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official","unlocated"]}}},{"url":"/paper/super-resolution-of-license-plate-images","slug":"super-resolution-of-license-plate-images","title":"Super-Resolution of License Plate Images Using Attention Modules and Sub-Pixel Convolution Layers","date":"2023-05-27","arxiv_id":"2305.17313","repositories_listed":2,"syntology":null},{"url":"/paper/text-detection-forgot-about-document-ocr","slug":"text-detection-forgot-about-document-ocr","title":"Text Detection Forgot About Document OCR","date":"2022-10-14","arxiv_id":"2210.07903","repositories_listed":2,"syntology":null},{"url":"/paper/levenshtein-ocr","slug":"levenshtein-ocr","title":"Levenshtein OCR","date":"2022-09-08","arxiv_id":"2209.03594","repositories_listed":2,"syntology":null},{"url":"/paper/german-parliamentary-corpus-gerparcor","slug":"german-parliamentary-corpus-gerparcor","title":"German Parliamentary Corpus (GerParCor)","date":"2022-04-21","arxiv_id":"2204.10422","repositories_listed":2,"syntology":null},{"url":"/paper/doctr-document-image-transformer-for","slug":"doctr-document-image-transformer-for","title":"DocTr: Document Image Transformer for Geometric Unwarping and Illumination Correction","date":"2021-10-25","arxiv_id":"2110.12942","repositories_listed":2,"syntology":null},{"url":"/paper/wenetspeech-a-10000-hours-multi-domain","slug":"wenetspeech-a-10000-hours-multi-domain","title":"WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognition","date":"2021-10-07","arxiv_id":"2110.03370","repositories_listed":2,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/wenetspeech-a-10000-hours-multi-domain#ran","syntology_url":"https://syntology.ai/paper/2110.03370","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.03370"}},"official":{"repos":["wenet-e2e/wenetspeech"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/bros-a-layout-aware-pre-trained-language","slug":"bros-a-layout-aware-pre-trained-language","title":"BROS: A Pre-trained Language Model Focusing on Text and Layout for Better Key Information Extraction from Documents","date":"2021-08-10","arxiv_id":"2108.04539","repositories_listed":2,"syntology":{"n":13,"n_ran":13,"n_constructed":0,"n_ran_checked":11,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/bros-a-layout-aware-pre-trained-language#ran","syntology_url":"https://syntology.ai/paper/2108.04539","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.04539"}},"official":{"repos":["clovaai/bros"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/automatic-metadata-extraction-incorporating","slug":"automatic-metadata-extraction-incorporating","title":"Automatic Metadata Extraction Incorporating Visual Features from Scanned Electronic Theses and Dissertations","date":"2021-07-01","arxiv_id":"2107.00516","repositories_listed":2,"syntology":null},{"url":"/paper/operationalizing-a-national-digital-library","slug":"operationalizing-a-national-digital-library","title":"Operationalizing a National Digital Library: The Case for a Norwegian Transformer Model","date":"2021-04-19","arxiv_id":"2104.09617","repositories_listed":2,"syntology":null},{"url":"/paper/pgnet-real-time-arbitrarily-shaped-text","slug":"pgnet-real-time-arbitrarily-shaped-text","title":"PGNet: Real-time Arbitrarily-Shaped Text Spotting with Point Gathering Network","date":"2021-04-12","arxiv_id":"2104.05458","repositories_listed":2,"syntology":null},{"url":"/paper/ocr-post-correction-for-endangered-language","slug":"ocr-post-correction-for-endangered-language","title":"OCR Post Correction for Endangered Language Texts","date":"2020-11-10","arxiv_id":"2011.05402","repositories_listed":2,"syntology":null},{"url":"/paper/tokenization-repair-in-the-presence-of","slug":"tokenization-repair-in-the-presence-of","title":"Tokenization Repair in the Presence of Spelling Errors","date":"2020-10-15","arxiv_id":"2010.07878","repositories_listed":2,"syntology":null},{"url":"/paper/multi-label-classification-of-common-bengali","slug":"multi-label-classification-of-common-bengali","title":"A Large Multi-Target Dataset of Common Bengali Handwritten Graphemes","date":"2020-10-01","arxiv_id":"2010.00170","repositories_listed":2,"syntology":null},{"url":"/paper/a-deep-learning-approach-to-geographical","slug":"a-deep-learning-approach-to-geographical","title":"A Deep Learning Approach to Geographical Candidate Selection through Toponym Matching","date":"2020-09-17","arxiv_id":"2009.08114","repositories_listed":2,"syntology":null},{"url":"/paper/attack-of-the-tails-yes-you-really-can","slug":"attack-of-the-tails-yes-you-really-can","title":"Attack of the Tails: Yes, You Really Can Backdoor Federated Learning","date":"2020-07-09","arxiv_id":"2007.05084","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/attack-of-the-tails-yes-you-really-can#ran","syntology_url":"https://syntology.ai/paper/2007.05084","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.05084"}},"official":{"repos":["ksreenivasan/OOD_Federated_Learning"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/structured-multimodal-attentions-for-textvqa","slug":"structured-multimodal-attentions-for-textvqa","title":"Structured Multimodal Attentions for TextVQA","date":"2020-06-01","arxiv_id":"2006.00753","repositories_listed":2,"syntology":null},{"url":"/paper/the-newspaper-navigator-dataset-extracting","slug":"the-newspaper-navigator-dataset-extracting","title":"The Newspaper Navigator Dataset: Extracting And Analyzing Visual Content from 16 Million Historic Newspaper Pages in Chronicling America","date":"2020-05-04","arxiv_id":"2005.01583","repositories_listed":2,"syntology":null},{"url":"/paper/pick-processing-key-information-extraction","slug":"pick-processing-key-information-extraction","title":"PICK: Processing Key Information Extraction from Documents using Improved Graph Learning-Convolutional Networks","date":"2020-04-16","arxiv_id":"2004.07464","repositories_listed":2,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/pick-processing-key-information-extraction#ran","syntology_url":"https://syntology.ai/paper/2004.07464","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.07464"}},"official":{"repos":["wenwenyu/PICK-pytorch"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/deep-relational-reasoning-graph-network-for","slug":"deep-relational-reasoning-graph-network-for","title":"Deep Relational Reasoning Graph Network for Arbitrary Shape Text Detection","date":"2020-03-17","arxiv_id":"2003.07493","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/deep-relational-reasoning-graph-network-for#ran","syntology_url":"https://syntology.ai/paper/2003.07493","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.07493"}},"official":{"repos":["GXYM/DRRG"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/ddi-100-dataset-for-text-detection-and","slug":"ddi-100-dataset-for-text-detection-and","title":"DDI-100: Dataset for Text Detection and Recognition","date":"2019-12-25","arxiv_id":"1912.11658","repositories_listed":2,"syntology":null},{"url":"/paper/deeperase-weakly-supervised-ink-artifact","slug":"deeperase-weakly-supervised-ink-artifact","title":"DeepErase: Weakly Supervised Ink Artifact Removal in Document Text Images","date":"2019-10-15","arxiv_id":"1910.07070","repositories_listed":2,"syntology":null},{"url":"/paper/rosetta-large-scale-system-for-text-detection","slug":"rosetta-large-scale-system-for-text-detection","title":"Rosetta: Large scale system for text detection and recognition in images","date":"2019-10-11","arxiv_id":"1910.05085","repositories_listed":2,"syntology":null},{"url":"/paper/nass-ai-towards-digitization-of-parliamentary","slug":"nass-ai-towards-digitization-of-parliamentary","title":"NASS-AI: Towards Digitization of Parliamentary Bills using Document Level Embedding and Bidirectional Long Short-Term Memory","date":"2019-10-02","arxiv_id":"1910.04865","repositories_listed":2,"syntology":null},{"url":"/paper/a-robust-real-time-automatic-license-plate","slug":"a-robust-real-time-automatic-license-plate","title":"A Robust Real-Time Automatic License Plate Recognition Based on the YOLO Detector","date":"2018-02-26","arxiv_id":"1802.09567","repositories_listed":2,"syntology":null},{"url":"/paper/case-study-of-a-highly-automated-layout","slug":"case-study-of-a-highly-automated-layout","title":"Case Study of a highly automated Layout Analysis and OCR of an incunabulum: 'Der Heiligen Leben' (1488)","date":"2017-01-20","arxiv_id":"1701.07395","repositories_listed":2,"syntology":null},{"url":"/paper/larex-a-semi-automatic-open-source-tool-for","slug":"larex-a-semi-automatic-open-source-tool-for","title":"LAREX - A semi-automatic open-source Tool for Layout Analysis and Region Extraction on Early Printed Books","date":"2017-01-20","arxiv_id":"1701.07396","repositories_listed":2,"syntology":null},{"url":"/paper/an-unsupervised-model-of-orthographic","slug":"an-unsupervised-model-of-orthographic","title":"An Unsupervised Model of Orthographic Variation for Historical Document Transcription","date":"2016-06-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/a-model-of-diffuse-galactic-radio-emission","slug":"a-model-of-diffuse-galactic-radio-emission","title":"A model of diffuse Galactic Radio Emission from 10 MHz to 100 GHz","date":"2008-02-12","arxiv_id":"0802.1525","repositories_listed":2,"syntology":null},{"url":"/paper/orchestrator-agent-trust-a-modular-agentic-ai","slug":"orchestrator-agent-trust-a-modular-agentic-ai","title":"Orchestrator-Agent Trust: A Modular Agentic AI Visual Classification System with Trust-Aware Orchestration and RAG-Based Reasoning","date":"2025-07-09","arxiv_id":"2507.10571","repositories_listed":1,"syntology":null},{"url":"/paper/paddleocr-3-0-technical-report","slug":"paddleocr-3-0-technical-report","title":"PaddleOCR 3.0 Technical Report","date":"2025-07-08","arxiv_id":"2507.05595","repositories_listed":1,"syntology":null},{"url":"/paper/reviving-cultural-heritage-a-novel-approach","slug":"reviving-cultural-heritage-a-novel-approach","title":"Reviving Cultural Heritage: A Novel Approach for Comprehensive Historical Document Restoration","date":"2025-07-07","arxiv_id":"2507.05108","repositories_listed":1,"syntology":{"n":17,"n_ran":15,"n_constructed":0,"n_ran_checked":6,"n_instrument":9,"n_unverified":2,"n_honours":2,"n_violates":1,"n_no_contract":3,"n_pointer_only":17,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 1 violated, 3 with no contract checked; 9 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/reviving-cultural-heritage-a-novel-approach#ran","syntology_url":"https://syntology.ai/paper/2507.05108","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2507.05108"}},"official":null}},{"url":"/paper/drishtikon-multi-granular-visual-grounding","slug":"drishtikon-multi-granular-visual-grounding","title":"DrishtiKon: Multi-Granular Visual Grounding for Text-Rich Document Images","date":"2025-06-26","arxiv_id":"2506.21316","repositories_listed":1,"syntology":null},{"url":"/paper/2506-08300","slug":"2506-08300","title":"Institutional Books 1.0: A 242B token dataset from Harvard Library's collections, refined for accuracy and usability","date":"2025-06-10","arxiv_id":"2506.08300","repositories_listed":1,"syntology":null},{"url":"/paper/megahan97k-a-large-scale-dataset-for-mega","slug":"megahan97k-a-large-scale-dataset-for-mega","title":"MegaHan97K: A Large-Scale Dataset for Mega-Category Chinese Character Recognition with over 97K Categories","date":"2025-06-05","arxiv_id":"2506.04807","repositories_listed":1,"syntology":null}],"syntology_records":34,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":76,"papers_where_code_ran_first_page":"/task/optical-character-recognition/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":13,"url":"/task/optical-character-recognition/papers/2","json":"/task/optical-character-recognition/papers/2.json","rows":100},{"order":"archive","page":3,"of":13,"url":"/task/optical-character-recognition/papers/3","json":"/task/optical-character-recognition/papers/3.json","rows":100},{"order":"archive","page":4,"of":13,"url":"/task/optical-character-recognition/papers/4","json":"/task/optical-character-recognition/papers/4.json","rows":100},{"order":"archive","page":5,"of":13,"url":"/task/optical-character-recognition/papers/5","json":"/task/optical-character-recognition/papers/5.json","rows":100},{"order":"archive","page":6,"of":13,"url":"/task/optical-character-recognition/papers/6","json":"/task/optical-character-recognition/papers/6.json","rows":100},{"order":"archive","page":7,"of":13,"url":"/task/optical-character-recognition/papers/7","json":"/task/optical-character-recognition/papers/7.json","rows":100},{"order":"archive","page":8,"of":13,"url":"/task/optical-character-recognition/papers/8","json":"/task/optical-character-recognition/papers/8.json","rows":100},{"order":"archive","page":9,"of":13,"url":"/task/optical-character-recognition/papers/9","json":"/task/optical-character-recognition/papers/9.json","rows":100},{"order":"archive","page":10,"of":13,"url":"/task/optical-character-recognition/papers/10","json":"/task/optical-character-recognition/papers/10.json","rows":100},{"order":"archive","page":11,"of":13,"url":"/task/optical-character-recognition/papers/11","json":"/task/optical-character-recognition/papers/11.json","rows":100},{"order":"archive","page":12,"of":13,"url":"/task/optical-character-recognition/papers/12","json":"/task/optical-character-recognition/papers/12.json","rows":100},{"order":"archive","page":13,"of":13,"url":"/task/optical-character-recognition/papers/13","json":"/task/optical-character-recognition/papers/13.json","rows":43},{"order":"ran","page":1,"of":1,"url":"/task/optical-character-recognition/papers/ran/1","json":"/task/optical-character-recognition/papers/ran/1.json","rows":76}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"ce2659bf15ff3d6729ad8dc218df0faa80b66523cd49cf3b3f5debdc9c75b4ac","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}