{"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/papers/13","list_of":"/task/optical-character-recognition","task":"Optical Character Recognition (OCR)","archive":{"snapshot":"2025-07-28"},"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)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":13,"pages_in_order":13,"rows_per_page":100,"rows":[1201,1243],"of":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"},"first_page":"/task/optical-character-recognition","prev":"/task/optical-character-recognition/papers/12","next":null,"papers":[{"url":null,"slug":"synergy-of-nederlab-and","title":"Synergy of Nederlab and","date":"2014-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-interplay-between-lexical-and-syntactic","title":"The Interplay Between Lexical and Syntactic Resources in Incremental Parsebanking","date":"2014-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"automated-error-detection-in-digitized","title":"Automated Error Detection in Digitized Cultural Heritage Documents","date":"2014-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"bootstrapping-a-historical-commodities","title":"Bootstrapping a historical commodities lexicon with SKOS and DBpedia","date":"2014-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"chispa-on-the-go-a-mobile-chinese-spanish","title":"CHISPA on the GO: A mobile Chinese-Spanish translation service for travellers in trouble","date":"2014-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"cora-a-web-based-annotation-tool-for","title":"CorA: A web-based annotation tool for historical and other non-standard language data","date":"2014-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"extraction-of-line-word-character-segments","title":"Extraction of Line Word Character Segments Directly from Run Length Compressed Printed Text Documents","date":"2014-03-30","arxiv_id":"1403.7783","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-novel-method-for-the-recognition-of","title":"A Novel Method for the Recognition of Isolated Handwritten Arabic Characters","date":"2014-02-26","arxiv_id":"1402.6650","repositories_listed":0,"syntology":null},{"url":null,"slug":"bangla-text-recognition-from-video-sequence-a","title":"Bangla Text Recognition from Video Sequence: A New Focus","date":"2014-01-06","arxiv_id":"1401.1190","repositories_listed":0,"syntology":null},{"url":null,"slug":"generalizing-analytic-shrinkage-for-arbitrary","title":"Generalizing Analytic Shrinkage for Arbitrary Covariance Structures","date":"2013-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-adaptive-value-of-information-for","title":"Learning Adaptive Value of Information for Structured Prediction","date":"2013-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-maximum-entropy-approach-to-chinese","title":"A Maximum Entropy Approach to Chinese Spelling Check","date":"2013-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"sinica-iasl-chinese-spelling-check-system-at","title":"Sinica-IASL Chinese spelling check system at Sighan-7","date":"2013-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"categorizing-ancient-documents","title":"Categorizing ancient documents","date":"2013-08-28","arxiv_id":"1308.6311","repositories_listed":0,"syntology":null},{"url":null,"slug":"morphological-annotation-of-old-and-middle","title":"Morphological annotation of Old and Middle Hungarian corpora","date":"2013-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-task-learning-for-improved","title":"Multi-Task Learning for Improved Discriminative Training in SMT","date":"2013-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"reranking-with-linguistic-and-semantic","title":"Reranking with Linguistic and Semantic Features for Arabic Optical Character Recognition","date":"2013-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-mathematics-of-language-learning","title":"The mathematics of language learning","date":"2013-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-transcription-of-historical","title":"Unsupervised Transcription of Historical Documents","date":"2013-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"finite-state-approach-to-the-kazakh-nominal","title":"Finite State Approach to the Kazakh Nominal Paradigm","date":"2013-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"k-algorithm-a-modified-technique-for-noise","title":"K-Algorithm A Modified Technique for Noise Removal in Handwritten Documents","date":"2013-06-06","arxiv_id":"1306.1462","repositories_listed":0,"syntology":null},{"url":null,"slug":"grouping-language-model-boundary-words-to","title":"Grouping Language Model Boundary Words to Speed K--Best Extraction from Hypergraphs","date":"2013-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"reading-ancient-coin-legends-object","title":"Reading Ancient Coin Legends: Object Recognition vs. OCR","date":"2013-04-26","arxiv_id":"1304.7184","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-statistical-transliteration-for","title":"Leveraging Statistical Transliteration for Dictionary-Based English-Bengali CLIR of OCR`d Text","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"volume-regularization-for-binary","title":"Volume Regularization for Binary Classification","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-possibilistic-approach-for-automatic-word","title":"A Possibilistic Approach for Automatic Word Sense Disambiguation","date":"2012-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"combining-ocr-outputs-for-logical-document","title":"Combining OCR Outputs for Logical Document Structure Markup. Technical Background to the ACL 2012 Contributed Task","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-an-acl-anthology-corpus-with-logical","title":"Towards an ACL Anthology Corpus with Logical Document Structure. An Overview of the ACL 2012 Contributed Task","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-free-and-open-source-tool-that-reads-movie","title":"A free and open-source tool that reads movie subtitles aloud","date":"2012-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"comparing-human-versus-automatic-feature","title":"Comparing human versus automatic feature extraction for fine-grained elementary readability assessment","date":"2012-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"digitizing-18th-century-french-literature","title":"Digitizing 18th-Century French Literature: Comparing transcription methods for a critical edition text","date":"2012-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"extended-named-entities-annotation-on-ocred","title":"Extended Named Entities Annotation on OCRed Documents: From Corpus Constitution to Evaluation Campaign","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"introducing-the-reference-corpus-of","title":"Introducing the Reference Corpus of Contemporary Portuguese Online","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"linguistic-resources-for-handwriting","title":"Linguistic Resources for Handwriting Recognition and Translation Evaluation","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-goo300k-corpus-of-historical-slovene","title":"The goo300k corpus of historical Slovene","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"tree-structured-named-entity-recognition-on","title":"Tree-Structured Named Entity Recognition on OCR Data: Analysis, Processing and Results","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"an-unsupervised-and-data-driven-approach-for","title":"An Unsupervised and Data-Driven Approach for Spell Checking in Vietnamese OCR-scanned Texts","date":"2012-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"language-classification-and-segmentation-of","title":"Language Classification and Segmentation of Noisy Documents in Hebrew Scripts","date":"2012-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"measuring-contextual-fitness-using-error","title":"Measuring Contextual Fitness Using Error Contexts Extracted from the Wikipedia Revision History","date":"2012-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"iterative-learning-for-reliable-crowdsourcing","title":"Iterative Learning for Reliable Crowdsourcing Systems","date":"2011-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"budget-optimal-task-allocation-for-reliable","title":"Budget-Optimal Task Allocation for Reliable Crowdsourcing Systems","date":"2011-10-17","arxiv_id":"1110.3564","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-machine-learning-to-machine-reasoning","title":"From Machine Learning to Machine Reasoning","date":"2011-02-09","arxiv_id":"1102.1808","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-offline-technique-for-localization-of","title":"An Offline Technique for Localization of License Plates for Indian Commercial Vehicles","date":"2010-03-04","arxiv_id":"1003.1072","repositories_listed":0,"syntology":null}],"record_sha256":"abe09f4c1c3f1140a5a80e47d65f65ec2db5a0030bebb236ea7f6eba8e1cbdfc","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}