{"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/decipherment","name":"Decipherment","slug":"decipherment","description_markdown":null,"categories":[{"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":46,"papers_with_code":12,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"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":1,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/chinese-gigaword","name":"Chinese Gigaword","full_name":"Chinese Gigaword","num_papers_in_archive":2}],"subtasks":[],"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":1,"rows_per_page":100,"shown":46,"of":46,"of_with_code":12,"tagged_in_all":46,"counts":{"archive_papers_tagged":46,"with_a_code_link":12,"where_syntology_ran_a_sample":3,"not_listed_spam_title":0,"listed":46,"listed_where_code_ran":3,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":3,"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 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/style-transfer-from-non-parallel-text-by","slug":"style-transfer-from-non-parallel-text-by","title":"Style Transfer from Non-Parallel Text by Cross-Alignment","date":"2017-05-26","arxiv_id":"1705.09655","repositories_listed":12,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":1,"n_instrument":5,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/style-transfer-from-non-parallel-text-by#ran","syntology_url":"https://syntology.ai/paper/1705.09655","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1705.09655"}},"official":{"repos":["shentianxiao/language-style-transfer"],"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/a-probabilistic-formulation-of-unsupervised-1","slug":"a-probabilistic-formulation-of-unsupervised-1","title":"A Probabilistic Formulation of Unsupervised Text Style Transfer","date":"2020-02-10","arxiv_id":"2002.03912","repositories_listed":5,"syntology":{"n":25,"n_ran":18,"n_constructed":13,"n_ran_checked":11,"n_instrument":7,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":12,"phrase":"18 ran (of which 13 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 7 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/a-probabilistic-formulation-of-unsupervised-1#ran","syntology_url":"https://syntology.ai/paper/2002.03912","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.03912"}},"official":{"repos":["cindyxinyiwang/deep-latent-sequence-model"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/an-open-dataset-for-oracle-bone-script","slug":"an-open-dataset-for-oracle-bone-script","title":"An open dataset for oracle bone script recognition and decipherment","date":"2024-01-27","arxiv_id":"2401.15365","repositories_listed":2,"syntology":null},{"url":"/paper/oraclefusion-assisting-the-decipherment-of","slug":"oraclefusion-assisting-the-decipherment-of","title":"OracleFusion: Assisting the Decipherment of Oracle Bone Script with Structurally Constrained Semantic Typography","date":"2025-06-26","arxiv_id":"2506.21101","repositories_listed":1,"syntology":null},{"url":"/paper/deciphering-oracle-bone-language-with","slug":"deciphering-oracle-bone-language-with","title":"Deciphering Oracle Bone Language with Diffusion Models","date":"2024-06-02","arxiv_id":"2406.00684","repositories_listed":1,"syntology":{"n":12,"n_ran":7,"n_constructed":0,"n_ran_checked":2,"n_instrument":5,"n_unverified":5,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":12,"phrase":"7 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; 5 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/deciphering-oracle-bone-language-with#ran","syntology_url":"https://syntology.ai/paper/2406.00684","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.00684"}},"official":{"repos":["guanhaisu/obsd"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/deciphering-undersegmented-ancient-scripts","slug":"deciphering-undersegmented-ancient-scripts","title":"Deciphering Undersegmented Ancient Scripts Using Phonetic Prior","date":"2020-10-21","arxiv_id":"2010.11054","repositories_listed":1,"syntology":null},{"url":"/paper/phonetic-and-visual-priors-for-decipherment","slug":"phonetic-and-visual-priors-for-decipherment","title":"Phonetic and Visual Priors for Decipherment of Informal Romanization","date":"2020-05-05","arxiv_id":"2005.02517","repositories_listed":1,"syntology":null},{"url":"/paper/neural-decipherment-via-minimum-cost-flow","slug":"neural-decipherment-via-minimum-cost-flow","title":"Neural Decipherment via Minimum-Cost Flow: from Ugaritic to Linear B","date":"2019-06-16","arxiv_id":"1906.06718","repositories_listed":1,"syntology":null},{"url":"/paper/sign-clustering-and-topic-extraction-in-proto","slug":"sign-clustering-and-topic-extraction-in-proto","title":"Sign Clustering and Topic Extraction in Proto-Elamite","date":"2019-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/a-grounded-unsupervised-universal-part-of","slug":"a-grounded-unsupervised-universal-part-of","title":"A Grounded Unsupervised Universal Part-of-Speech Tagger for Low-Resource Languages","date":"2019-04-10","arxiv_id":"1904.05426","repositories_listed":1,"syntology":null},{"url":"/paper/decipherment-of-historical-manuscript-images","slug":"decipherment-of-historical-manuscript-images","title":"Decipherment of Historical Manuscript Images","date":"2018-10-09","arxiv_id":"1810.04297","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-text-style-transfer-using","slug":"unsupervised-text-style-transfer-using","title":"Unsupervised Text Style Transfer using Language Models as Discriminators","date":"2018-05-30","arxiv_id":"1805.11749","repositories_listed":1,"syntology":null},{"url":null,"slug":"ancient-script-image-recognition-and","title":"Ancient Script Image Recognition and Processing: A Review","date":"2025-06-24","arxiv_id":"2506.19208","repositories_listed":0,"syntology":null},{"url":null,"slug":"reasoning-over-the-glyphs-evaluation-of-llm-s","title":"Reasoning Over the Glyphs: Evaluation of LLM's Decipherment of Rare Scripts","date":"2025-01-29","arxiv_id":"2501.17785","repositories_listed":0,"syntology":null},{"url":null,"slug":"determination-of-language-families-using-deep","title":"Determination of language families using deep learning","date":"2024-09-04","arxiv_id":"2409.02393","repositories_listed":0,"syntology":null},{"url":null,"slug":"oracle-bone-inscriptions-multi-modal-dataset","title":"Oracle Bone Inscriptions Multi-modal Dataset","date":"2024-07-04","arxiv_id":"2407.03900","repositories_listed":0,"syntology":null},{"url":null,"slug":"decipherment-aware-multilingual-learning-in","title":"Decipherment-Aware Multilingual Learning in Jointly Trained Language Models","date":"2024-06-11","arxiv_id":"2406.07231","repositories_listed":0,"syntology":null},{"url":null,"slug":"segmentation-of-maya-hieroglyphs-through-fine","title":"Segmentation of Maya hieroglyphs through fine-tuned foundation models","date":"2024-05-26","arxiv_id":"2405.16426","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-open-dataset-for-the-evolution-of-oracle","title":"An open dataset for the evolution of oracle bone characters: EVOBC","date":"2024-01-23","arxiv_id":"2401.12467","repositories_listed":0,"syntology":null},{"url":null,"slug":"chatabl-abductive-learning-via-natural","title":"ChatABL: Abductive Learning via Natural Language Interaction with ChatGPT","date":"2023-04-21","arxiv_id":"2304.11107","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-inscription-to-semi-automatic-annotation","title":"From Inscription to Semi-automatic Annotation of Maya Hieroglyphic Texts","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"dorabella-cipher-as-musical-inspiration","title":"Dorabella Cipher as Musical Inspiration","date":"2021-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"deciphering-speech-a-zero-resource-approach","title":"Deciphering Speech: a Zero-Resource Approach to Cross-Lingual Transfer in ASR","date":"2021-11-12","arxiv_id":"2111.06799","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-text-gan-for-language-generation-with-non","title":"A Text GAN for Language Generation with Non-Autoregressive Generator","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"can-sequence-to-sequence-models-crack","title":"Can Sequence-to-Sequence Models Crack Substitution Ciphers?","date":"2020-12-30","arxiv_id":"2012.15229","repositories_listed":0,"syntology":null},{"url":null,"slug":"decipherment-for-adversarial-offensive","title":"Decipherment for Adversarial Offensive Language Detection","date":"2018-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"decipherment-of-substitution-ciphers-with","title":"Decipherment of Substitution Ciphers with Neural Language Models","date":"2018-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"fine-grained-coordinated-cross-lingual-text","title":"Fine-grained Coordinated Cross-lingual Text Stream Alignment for Endless Language Knowledge Acquisition","date":"2018-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"feature-based-decipherment-for-machine","title":"Feature-Based Decipherment for Machine Translation","date":"2018-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-models-for-alignment-and-data","title":"Generative Models for Alignment and Data Efficiency in Language","date":"2018-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"protein-word-detection-using-text","title":"Protein Word Detection using Text Segmentation Techniques","date":"2017-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"aligning-coordinated-text-streams-through","title":"Aligning Coordinated Text Streams through Burst Information Network Construction and Decipherment","date":"2016-09-27","arxiv_id":"1609.08237","repositories_listed":0,"syntology":null},{"url":null,"slug":"decoding-anagrammed-texts-written-in-an","title":"Decoding Anagrammed Texts Written in an Unknown Language and Script","date":"2016-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"feature-based-decipherment-for-large","title":"Feature-based Decipherment for Large Vocabulary Machine Translation","date":"2015-08-10","arxiv_id":"1508.02142","repositories_listed":0,"syntology":null},{"url":null,"slug":"unifying-bayesian-inference-and-vector-space","title":"Unifying Bayesian Inference and Vector Space Models for Improved Decipherment","date":"2015-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"unravela-decipherment-toolkit","title":"UNRAVEL---A Decipherment Toolkit","date":"2015-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"model-invertibility-regularization-sequence","title":"Model Invertibility Regularization: Sequence Alignment With or Without Parallel Data","date":"2015-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-parallel-data-joint-word-alignment-and","title":"Beyond Parallel Data: Joint Word Alignment and Decipherment Improves Machine Translation","date":"2014-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"improved-decipherment-of-homophonic-ciphers","title":"Improved Decipherment of Homophonic Ciphers","date":"2014-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"em-decipherment-for-large-vocabularies","title":"EM Decipherment for Large Vocabularies","date":"2014-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"decipherment-with-a-million-random-restarts","title":"Decipherment with a Million Random Restarts","date":"2013-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"dependency-based-decipherment-for-resource","title":"Dependency-Based Decipherment for Resource-Limited Machine Translation","date":"2013-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"decipherment","title":"Decipherment","date":"2013-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"decipherment-complexity-in-11-substitution","title":"Decipherment Complexity in 1:1 Substitution Ciphers","date":"2013-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"scalable-decipherment-for-machine-translation","title":"Scalable Decipherment for Machine Translation via Hash Sampling","date":"2013-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"large-scale-decipherment-for-out-of-domain","title":"Large Scale Decipherment for Out-of-Domain Machine Translation","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"syntology_records":3,"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":3,"papers_where_code_ran_first_page":"/task/decipherment/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":"ran","page":1,"of":1,"url":"/task/decipherment/papers/ran/1","json":"/task/decipherment/papers/ran/1.json","rows":3}],"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":"0e1a71f39f20047b5a580d54eed56e9f1e9d7cbb599b48174e5590bfbb9f54ac","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}