{"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/text-compression","name":"Text Compression","slug":"text-compression","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":"derived"},"counts":{"papers_tagged":43,"papers_with_code":18,"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":0,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[],"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":43,"of":43,"of_with_code":18,"tagged_in_all":43,"counts":{"archive_papers_tagged":43,"with_a_code_link":18,"where_syntology_ran_a_sample":2,"not_listed_spam_title":0,"listed":43,"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 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/llms-may-dominate-information-access-neural","slug":"llms-may-dominate-information-access-neural","title":"Neural Retrievers are Biased Towards LLM-Generated Content","date":"2023-10-31","arxiv_id":"2310.20501","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/llms-may-dominate-information-access-neural#ran","syntology_url":"https://syntology.ai/paper/2310.20501","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.20501"}},"official":{"repos":["kid-22/llm4ir-bias","kid-22/source-bias"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/llmzip-lossless-text-compression-using-large","slug":"llmzip-lossless-text-compression-using-large","title":"LLMZip: Lossless Text Compression using Large Language Models","date":"2023-06-06","arxiv_id":"2306.04050","repositories_listed":2,"syntology":null},{"url":"/paper/tokalign-efficient-vocabulary-adaptation-via","slug":"tokalign-efficient-vocabulary-adaptation-via","title":"TokAlign: Efficient Vocabulary Adaptation via Token Alignment","date":"2025-06-04","arxiv_id":"2506.03523","repositories_listed":1,"syntology":null},{"url":"/paper/scaling-multi-document-event-summarization","slug":"scaling-multi-document-event-summarization","title":"Scaling Multi-Document Event Summarization: Evaluating Compression vs. Full-Text Approaches","date":"2025-02-10","arxiv_id":"2502.06617","repositories_listed":1,"syntology":null},{"url":"/paper/l3tc-leveraging-rwkv-for-learned-lossless-low","slug":"l3tc-leveraging-rwkv-for-learned-lossless-low","title":"L3TC: Leveraging RWKV for Learned Lossless Low-Complexity Text Compression","date":"2024-12-21","arxiv_id":"2412.16642","repositories_listed":1,"syntology":null},{"url":"/paper/intellectseeker-a-personalized-literature","slug":"intellectseeker-a-personalized-literature","title":"IntellectSeeker: A Personalized Literature Management System with the Probabilistic Model and Large Language Model","date":"2024-12-10","arxiv_id":"2412.07213","repositories_listed":1,"syntology":null},{"url":"/paper/finezip-pushing-the-limits-of-large-language","slug":"finezip-pushing-the-limits-of-large-language","title":"FineZip : Pushing the Limits of Large Language Models for Practical Lossless Text Compression","date":"2024-09-25","arxiv_id":"2409.17141","repositories_listed":1,"syntology":null},{"url":"/paper/alphazip-neural-network-enhanced-lossless","slug":"alphazip-neural-network-enhanced-lossless","title":"AlphaZip: Neural Network-Enhanced Lossless Text Compression","date":"2024-09-23","arxiv_id":"2409.15046","repositories_listed":1,"syntology":null},{"url":"/paper/bpe-gets-picky-efficient-vocabulary","slug":"bpe-gets-picky-efficient-vocabulary","title":"BPE Gets Picky: Efficient Vocabulary Refinement During Tokenizer Training","date":"2024-09-06","arxiv_id":"2409.04599","repositories_listed":1,"syntology":null},{"url":"/paper/xcompress-llm-assisted-python-based-text","slug":"xcompress-llm-assisted-python-based-text","title":"XCompress: LLM assisted Python-based text compression toolkit","date":"2024-08-12","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/recurrent-context-compression-efficiently","slug":"recurrent-context-compression-efficiently","title":"Recurrent Context Compression: Efficiently Expanding the Context Window of LLM","date":"2024-06-10","arxiv_id":"2406.06110","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/recurrent-context-compression-efficiently#ran","syntology_url":"https://syntology.ai/paper/2406.06110","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.06110"}},"official":{"repos":["WUHU-G/RCC_Transformer"],"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/llmlingua-2-data-distillation-for-efficient","slug":"llmlingua-2-data-distillation-for-efficient","title":"LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression","date":"2024-03-19","arxiv_id":"2403.12968","repositories_listed":1,"syntology":null},{"url":"/paper/gzip-versus-bag-of-words-for-text","slug":"gzip-versus-bag-of-words-for-text","title":"Gzip versus bag-of-words for text classification","date":"2023-07-27","arxiv_id":"2307.15002","repositories_listed":1,"syntology":null},{"url":"/paper/a-novel-metric-for-evaluating-semantics","slug":"a-novel-metric-for-evaluating-semantics","title":"Contextualized Semantic Distance between Highly Overlapped Texts","date":"2021-10-04","arxiv_id":"2110.01176","repositories_listed":1,"syntology":null},{"url":"/paper/data-efficient-neural-text-compression-with","slug":"data-efficient-neural-text-compression-with","title":"Data-efficient Neural Text Compression with Interactive Learning","date":"2019-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/a-batch-noise-contrastive-estimation-approach","slug":"a-batch-noise-contrastive-estimation-approach","title":"A Batch Noise Contrastive Estimation Approach for Training Large Vocabulary Language Models","date":"2017-08-20","arxiv_id":"1708.05997","repositories_listed":1,"syntology":null},{"url":"/paper/authorship-verification-based-on-compression","slug":"authorship-verification-based-on-compression","title":"Authorship Verification based on Compression-Models","date":"2017-06-01","arxiv_id":"1706.00516","repositories_listed":1,"syntology":null},{"url":"/paper/syntactically-informed-text-compression-with","slug":"syntactically-informed-text-compression-with","title":"Syntactically Informed Text Compression with Recurrent Neural Networks","date":"2016-08-08","arxiv_id":"1608.02893","repositories_listed":1,"syntology":null},{"url":null,"slug":"beyond-text-compression-evaluating-tokenizers","title":"Beyond Text Compression: Evaluating Tokenizers Across Scales","date":"2025-06-03","arxiv_id":"2506.03101","repositories_listed":0,"syntology":null},{"url":null,"slug":"measuring-information-distortion-in","title":"Measuring Information Distortion in Hierarchical Ultra long Novel Generation:The Optimal Expansion Ratio","date":"2025-05-18","arxiv_id":"2505.12572","repositories_listed":0,"syntology":null},{"url":null,"slug":"hypernym-mercury-token-optimization-through","title":"Hypernym Mercury: Token Optimization Through Semantic Field Constriction And Reconstruction From Hypernyms. A New Text Compression Method","date":"2025-05-12","arxiv_id":"2505.08058","repositories_listed":0,"syntology":null},{"url":null,"slug":"lossless-compression-of-large-language-model","title":"Lossless Compression of Large Language Model-Generated Text via Next-Token Prediction","date":"2025-05-07","arxiv_id":"2505.06297","repositories_listed":0,"syntology":null},{"url":null,"slug":"text-compression-for-efficient-language","title":"Text Compression for Efficient Language Generation","date":"2025-03-14","arxiv_id":"2503.11426","repositories_listed":0,"syntology":null},{"url":null,"slug":"assessing-human-editing-effort-on-llm","title":"Assessing Human Editing Effort on LLM-Generated Texts via Compression-Based Edit Distance","date":"2024-12-23","arxiv_id":"2412.17321","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-enhanced-text-compression-approach-using","title":"An Enhanced Text Compression Approach Using Transformer-based Language Models","date":"2024-12-15","arxiv_id":"2412.15250","repositories_listed":0,"syntology":null},{"url":null,"slug":"theoretical-analysis-of-byte-pair-encoding","title":"Theoretical Analysis of Byte-Pair Encoding","date":"2024-11-13","arxiv_id":"2411.08671","repositories_listed":0,"syntology":null},{"url":null,"slug":"variational-bayesian-methods-for-a-tree","title":"Variational Bayesian Methods for a Tree-Structured Stick-Breaking Process Mixture of Gaussians by Application of the Bayes Codes for Context Tree Models","date":"2024-05-01","arxiv_id":"2405.00385","repositories_listed":0,"syntology":null},{"url":null,"slug":"unpacking-tokenization-evaluating-text","title":"Unpacking Tokenization: Evaluating Text Compression and its Correlation with Model Performance","date":"2024-03-10","arxiv_id":"2403.06265","repositories_listed":0,"syntology":null},{"url":null,"slug":"semantic-text-compression-for-classification","title":"Semantic Text Compression for Classification","date":"2023-09-19","arxiv_id":"2309.10809","repositories_listed":0,"syntology":null},{"url":null,"slug":"entropyrank-unsupervised-keyphrase-extraction","title":"EntropyRank: Unsupervised Keyphrase Extraction via Side-Information Optimization for Language Model-based Text Compression","date":"2023-08-25","arxiv_id":"2308.13399","repositories_listed":0,"syntology":null},{"url":null,"slug":"approximating-human-like-few-shot-learning","title":"Approximating Human-Like Few-shot Learning with GPT-based Compression","date":"2023-08-14","arxiv_id":"2308.06942","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimal-alphabet-for-single-text-compression","title":"Optimal alphabet for single text compression","date":"2022-01-13","arxiv_id":"2201.05234","repositories_listed":0,"syntology":null},{"url":null,"slug":"text-compression-aided-transformer-encoding","title":"Text Compression-aided Transformer Encoding","date":"2021-02-11","arxiv_id":"2102.05951","repositories_listed":0,"syntology":null},{"url":null,"slug":"machine-translation-with-unsupervised-length","title":"Machine Translation with Unsupervised Length-Constraints","date":"2020-04-07","arxiv_id":"2004.03176","repositories_listed":0,"syntology":null},{"url":null,"slug":"deleter-leveraging-bert-to-perform","title":"Deleter: Leveraging BERT to Perform Unsupervised Successive Text Compression","date":"2019-09-07","arxiv_id":"1909.03223","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-study-for-image-compression-using-re-pair","title":"A study for Image compression using Re-Pair algorithm","date":"2019-01-30","arxiv_id":"1901.10744","repositories_listed":0,"syntology":null},{"url":null,"slug":"text-compression-for-sentiment-analysis-via","title":"Text Compression for Sentiment Analysis via Evolutionary Algorithms","date":"2017-09-20","arxiv_id":"1709.06990","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-neural-network-approach-for-mixing-language","title":"A Neural Network Approach for Mixing Language Models","date":"2017-08-23","arxiv_id":"1708.06989","repositories_listed":0,"syntology":null},{"url":null,"slug":"long-short-range-context-neural-networks-for","title":"Long-Short Range Context Neural Networks for Language Modeling","date":"2017-08-22","arxiv_id":"1708.06555","repositories_listed":0,"syntology":null},{"url":null,"slug":"sequential-recurrent-neural-networks-for","title":"Sequential Recurrent Neural Networks for Language Modeling","date":"2017-03-23","arxiv_id":"1703.08068","repositories_listed":0,"syntology":null},{"url":null,"slug":"tuple-oriented-compression-for-large-scale","title":"Tuple-oriented Compression for Large-scale Mini-batch Stochastic Gradient Descent","date":"2017-02-22","arxiv_id":"1702.06943","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-and-dialect-discrimination-using","title":"Language and Dialect Discrimination Using Compression-Inspired Language Models","date":"2016-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"lexis-an-optimization-framework-for","title":"Lexis: An Optimization Framework for Discovering the Hierarchical Structure of Sequential Data","date":"2016-02-17","arxiv_id":"1602.05561","repositories_listed":0,"syntology":null}],"syntology_records":2,"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":2,"papers_where_code_ran_first_page":"/task/text-compression/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/text-compression/papers/ran/1","json":"/task/text-compression/papers/ran/1.json","rows":2}],"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":"55039ff061e4696315ef6bcf3a9709b0b4c7104912c9383ac1fdef39eb026b7e","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}