{"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":"/dataset/cute80","name":"CUTE80","full_name":null,"description_markdown":"The CUTE80 dataset is a lightweight collection of images specifically designed for text detection in natural scene images. It contains a total of 13,000 annotated page images across five different popular categories: 1) Table 2) Figure 3) Natural image 4) Logo 5) ignature","description_withheld":null,"homepage":"https://github.com/mohtashim-nawaz/Cute80-Dataset","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[],"tasks":[{"name":"Scene Text Recognition","url":"/task/scene-text-recognition","datasets_with_task":"/datasets/task/scene-text-recognition"}],"languages":[],"variants":[],"data_loaders":[],"num_papers_in_archive":17,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/scene-text-recognition-on-cute80","task":"Scene Text Recognition","dataset_variant":"CUTE80","rows":18,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"CPPD","paper":"/paper/context-perception-parallel-decoder-for-scene","metrics":{"Accuracy":"99.7"},"code_links":[{"title":"PaddlePaddle/PaddleOCR","url":"https://github.com/PaddlePaddle/PaddleOCR"},{"title":"topdu/openocr","url":"https://github.com/topdu/openocr"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":14,"of":14,"counts":{"papers_with_a_benchmark_row":14,"with_a_code_link":13,"where_syntology_ran_a_sample":2,"not_listed_spam_title":0,"listed":14,"listed_where_code_ran":2,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":2,"listed_every_run_a_failure_of_syntologys_instrument":0,"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 with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/an-empirical-study-of-scaling-law-for-ocr","slug":"an-empirical-study-of-scaling-law-for-ocr","title":"An Empirical Study of Scaling Law for OCR","date":"2023-12-29","arxiv_id":"2401.00028","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/dtrocr-decoder-only-transformer-for-optical","slug":"dtrocr-decoder-only-transformer-for-optical","title":"DTrOCR: Decoder-only Transformer for Optical Character Recognition","date":"2023-08-30","arxiv_id":"2308.15996","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/context-perception-parallel-decoder-for-scene","slug":"context-perception-parallel-decoder-for-scene","title":"Context Perception Parallel Decoder for Scene Text Recognition","date":"2023-07-23","arxiv_id":"2307.12270","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/diffusionstr-diffusion-model-for-scene-text","slug":"diffusionstr-diffusion-model-for-scene-text","title":"DiffusionSTR: Diffusion Model for Scene Text Recognition","date":"2023-06-29","arxiv_id":"2306.16707","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/clip4str-a-simple-baseline-for-scene-text-1","slug":"clip4str-a-simple-baseline-for-scene-text-1","title":"CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model","date":"2023-05-23","arxiv_id":"2305.14014","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":3,"samples_unverified":4,"pointer_only_for_licence":2,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/clip4str-a-simple-baseline-for-scene-text-1#ran","syntology_url":"https://syntology.ai/paper/2305.14014","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14014"}}}},{"paper":"/paper/tps-attention-enhanced-thin-plate-spline-for","slug":"tps-attention-enhanced-thin-plate-spline-for","title":"TPS++: Attention-Enhanced Thin-Plate Spline for Scene Text Recognition","date":"2023-05-09","arxiv_id":"2305.05322","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/self-supervised-character-to-character","slug":"self-supervised-character-to-character","title":"Self-supervised Character-to-Character Distillation for Text Recognition","date":"2022-11-01","arxiv_id":"2211.00288","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/scene-text-recognition-with-permuted","slug":"scene-text-recognition-with-permuted","title":"Scene Text Recognition with Permuted Autoregressive Sequence Models","date":"2022-07-14","arxiv_id":"2207.06966","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":5,"samples_constructed":5,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":0,"official":{"repos":["baudm/parseq"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":5,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/scene-text-recognition-with-permuted#ran","syntology_url":"https://syntology.ai/paper/2207.06966","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.06966"}}}},{"paper":"/paper/a-glyph-driven-topology-enhancement-network","slug":"a-glyph-driven-topology-enhancement-network","title":"Self-supervised Implicit Glyph Attention for Text Recognition","date":"2022-03-07","arxiv_id":"2203.03382","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/visual-semantics-allow-for-textual-reasoning-1","slug":"visual-semantics-allow-for-textual-reasoning-1","title":"Visual Semantics Allow for Textual Reasoning Better in Scene Text Recognition","date":"2021-12-24","arxiv_id":"2112.12916","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/multi-modal-text-recognition-networks","slug":"multi-modal-text-recognition-networks","title":"Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features","date":"2021-11-30","arxiv_id":"2111.15263","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/cdistnet-perceiving-multi-domain-character","slug":"cdistnet-perceiving-multi-domain-character","title":"CDistNet: Perceiving Multi-Domain Character Distance for Robust Text Recognition","date":"2021-11-22","arxiv_id":"2111.11011","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/look-back-again-dual-parallel-attention","slug":"look-back-again-dual-parallel-attention","title":"Look Back Again: Dual Parallel Attention Network for Accurate and Robust Scene Text Recognition","date":"2021-08-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":2,"syntology":null}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/an-empirical-study-of-scaling-law-for-ocr","slug":"an-empirical-study-of-scaling-law-for-ocr","title":"An Empirical Study of Scaling Law for OCR","date":"2023-12-29","arxiv_id":"2401.00028","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/dtrocr-decoder-only-transformer-for-optical","slug":"dtrocr-decoder-only-transformer-for-optical","title":"DTrOCR: Decoder-only Transformer for Optical Character Recognition","date":"2023-08-30","arxiv_id":"2308.15996","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/context-perception-parallel-decoder-for-scene","slug":"context-perception-parallel-decoder-for-scene","title":"Context Perception Parallel Decoder for Scene Text Recognition","date":"2023-07-23","arxiv_id":"2307.12270","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/diffusionstr-diffusion-model-for-scene-text","slug":"diffusionstr-diffusion-model-for-scene-text","title":"DiffusionSTR: Diffusion Model for Scene Text Recognition","date":"2023-06-29","arxiv_id":"2306.16707","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/clip4str-a-simple-baseline-for-scene-text-1","slug":"clip4str-a-simple-baseline-for-scene-text-1","title":"CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model","date":"2023-05-23","arxiv_id":"2305.14014","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":3,"samples_unverified":4,"pointer_only_for_licence":2,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/clip4str-a-simple-baseline-for-scene-text-1#ran","syntology_url":"https://syntology.ai/paper/2305.14014","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14014"}}}},{"paper":"/paper/tps-attention-enhanced-thin-plate-spline-for","slug":"tps-attention-enhanced-thin-plate-spline-for","title":"TPS++: Attention-Enhanced Thin-Plate Spline for Scene Text Recognition","date":"2023-05-09","arxiv_id":"2305.05322","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/self-supervised-character-to-character","slug":"self-supervised-character-to-character","title":"Self-supervised Character-to-Character Distillation for Text Recognition","date":"2022-11-01","arxiv_id":"2211.00288","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/scene-text-recognition-with-permuted","slug":"scene-text-recognition-with-permuted","title":"Scene Text Recognition with Permuted Autoregressive Sequence Models","date":"2022-07-14","arxiv_id":"2207.06966","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":5,"samples_constructed":5,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":0,"official":{"repos":["baudm/parseq"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":5,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/scene-text-recognition-with-permuted#ran","syntology_url":"https://syntology.ai/paper/2207.06966","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.06966"}}}},{"paper":"/paper/a-glyph-driven-topology-enhancement-network","slug":"a-glyph-driven-topology-enhancement-network","title":"Self-supervised Implicit Glyph Attention for Text Recognition","date":"2022-03-07","arxiv_id":"2203.03382","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/visual-semantics-allow-for-textual-reasoning-1","slug":"visual-semantics-allow-for-textual-reasoning-1","title":"Visual Semantics Allow for Textual Reasoning Better in Scene Text Recognition","date":"2021-12-24","arxiv_id":"2112.12916","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/multi-modal-text-recognition-networks","slug":"multi-modal-text-recognition-networks","title":"Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features","date":"2021-11-30","arxiv_id":"2111.15263","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/cdistnet-perceiving-multi-domain-character","slug":"cdistnet-perceiving-multi-domain-character","title":"CDistNet: Perceiving Multi-Domain Character Distance for Robust Text Recognition","date":"2021-11-22","arxiv_id":"2111.11011","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/look-back-again-dual-parallel-attention","slug":"look-back-again-dual-parallel-attention","title":"Look Back Again: Dual Parallel Attention Network for Accurate and Robust Scene Text Recognition","date":"2021-08-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":2,"syntology":null}],"papers_where_code_ran":2,"papers_where_code_ran_first_page":"/dataset/cute80/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/dataset/cute80/papers/ran/1","json":"/dataset/cute80/papers/ran/1.json","rows":2}],"row_route":"each paper's syntology object 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","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":2,"samples_harvested":18,"samples_ran":11,"samples_constructed":5,"samples_ran_checked":8,"samples_ran_instrument_failed":3,"samples_unverified":7,"pointer_only_for_licence":2,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":2,"papers_with_a_run_with_no_instrument_failure":2,"papers_where_every_run_was_an_instrument_failure":0,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_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'","samples_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_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"6d9f426de986bd3e9d7505541c987ab76fc3a0c01c122c0d904291a1b18e7d5d","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}