{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JOPDBC2UC67TZY6E5PTA565L3C","short_pith_number":"pith:JOPDBC2U","schema_version":"1.0","canonical_sha256":"4b9e308b5417bf3ce3c4ebe60efbabd88111362baf205341b03be0319b488ba7","source":{"kind":"arxiv","id":"2306.04050","version":2},"attestation_state":"computed","paper":{"title":"LLMZip: Lossless Text Compression using Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG","math.IT"],"primary_cat":"cs.IT","authors_text":"Chandra Shekhara Kaushik Valmeekam, Dileep Kalathil, Jean-Francois Chamberland, Krishna Narayanan, Srinivas Shakkottai","submitted_at":"2023-06-06T22:42:00Z","abstract_excerpt":"We provide new estimates of an asymptotic upper bound on the entropy of English using the large language model LLaMA-7B as a predictor for the next token given a window of past tokens. This estimate is significantly smaller than currently available estimates in \\cite{cover1978convergent}, \\cite{lutati2023focus}. A natural byproduct is an algorithm for lossless compression of English text which combines the prediction from the large language model with a lossless compression scheme. Preliminary results from limited experiments suggest that our scheme outperforms state-of-the-art text compressio"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2306.04050","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IT","submitted_at":"2023-06-06T22:42:00Z","cross_cats_sorted":["cs.CL","cs.LG","math.IT"],"title_canon_sha256":"9eb81502b6078ae4d2c007da51db30a89e19f676c96828edd6e3c6524eec245f","abstract_canon_sha256":"8bd9d591a1356a37c532671a00e4da972d77549afbc03888b2eda9a6001b5788"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:24:50.506831Z","signature_b64":"t9+2w3fKatEqxT9jDHfMeDMrFbnbDdE+zZnUjxoezGtJqJI5dl+FlxY5hE3lX4Lit/EjH4mTUGe+J1J0u7xdBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b9e308b5417bf3ce3c4ebe60efbabd88111362baf205341b03be0319b488ba7","last_reissued_at":"2026-07-05T06:24:50.506399Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:24:50.506399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLMZip: Lossless Text Compression using Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG","math.IT"],"primary_cat":"cs.IT","authors_text":"Chandra Shekhara Kaushik Valmeekam, Dileep Kalathil, Jean-Francois Chamberland, Krishna Narayanan, Srinivas Shakkottai","submitted_at":"2023-06-06T22:42:00Z","abstract_excerpt":"We provide new estimates of an asymptotic upper bound on the entropy of English using the large language model LLaMA-7B as a predictor for the next token given a window of past tokens. This estimate is significantly smaller than currently available estimates in \\cite{cover1978convergent}, \\cite{lutati2023focus}. A natural byproduct is an algorithm for lossless compression of English text which combines the prediction from the large language model with a lossless compression scheme. Preliminary results from limited experiments suggest that our scheme outperforms state-of-the-art text compressio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.04050","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2306.04050/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2306.04050","created_at":"2026-07-05T06:24:50.506468+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.04050v2","created_at":"2026-07-05T06:24:50.506468+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.04050","created_at":"2026-07-05T06:24:50.506468+00:00"},{"alias_kind":"pith_short_12","alias_value":"JOPDBC2UC67T","created_at":"2026-07-05T06:24:50.506468+00:00"},{"alias_kind":"pith_short_16","alias_value":"JOPDBC2UC67TZY6E","created_at":"2026-07-05T06:24:50.506468+00:00"},{"alias_kind":"pith_short_8","alias_value":"JOPDBC2U","created_at":"2026-07-05T06:24:50.506468+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22873","citing_title":"SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08184","citing_title":"TextEconomizer: Enhancing Lossy Text Compression with Denoising Transformers and Entropy Coding","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06273","citing_title":"Adapting Diffusion Language Models for Lossless Pixel-Level Image Transmission","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22873","citing_title":"SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29000","citing_title":"Text-Preserving Lossy Text Compression: A Study of Strategic Deletion and LLM Reconstruction","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2309.10668","citing_title":"Language Modeling Is Compression","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01991","citing_title":"Real-Time Text Transmission via LLM-Based Entropy Coding over Fixed-Rate Channels","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JOPDBC2UC67TZY6E5PTA565L3C","json":"https://pith.science/pith/JOPDBC2UC67TZY6E5PTA565L3C.json","graph_json":"https://pith.science/api/pith-number/JOPDBC2UC67TZY6E5PTA565L3C/graph.json","events_json":"https://pith.science/api/pith-number/JOPDBC2UC67TZY6E5PTA565L3C/events.json","paper":"https://pith.science/paper/JOPDBC2U"},"agent_actions":{"view_html":"https://pith.science/pith/JOPDBC2UC67TZY6E5PTA565L3C","download_json":"https://pith.science/pith/JOPDBC2UC67TZY6E5PTA565L3C.json","view_paper":"https://pith.science/paper/JOPDBC2U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.04050&json=true","fetch_graph":"https://pith.science/api/pith-number/JOPDBC2UC67TZY6E5PTA565L3C/graph.json","fetch_events":"https://pith.science/api/pith-number/JOPDBC2UC67TZY6E5PTA565L3C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JOPDBC2UC67TZY6E5PTA565L3C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JOPDBC2UC67TZY6E5PTA565L3C/action/storage_attestation","attest_author":"https://pith.science/pith/JOPDBC2UC67TZY6E5PTA565L3C/action/author_attestation","sign_citation":"https://pith.science/pith/JOPDBC2UC67TZY6E5PTA565L3C/action/citation_signature","submit_replication":"https://pith.science/pith/JOPDBC2UC67TZY6E5PTA565L3C/action/replication_record"}},"created_at":"2026-07-05T06:24:50.506468+00:00","updated_at":"2026-07-05T06:24:50.506468+00:00"}