{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:JOPDBC2UC67TZY6E5PTA565L3C","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"8bd9d591a1356a37c532671a00e4da972d77549afbc03888b2eda9a6001b5788","cross_cats_sorted":["cs.CL","cs.LG","math.IT"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IT","submitted_at":"2023-06-06T22:42:00Z","title_canon_sha256":"9eb81502b6078ae4d2c007da51db30a89e19f676c96828edd6e3c6524eec245f"},"schema_version":"1.0","source":{"id":"2306.04050","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.04050","created_at":"2026-07-05T06:24:50Z"},{"alias_kind":"arxiv_version","alias_value":"2306.04050v2","created_at":"2026-07-05T06:24:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.04050","created_at":"2026-07-05T06:24:50Z"},{"alias_kind":"pith_short_12","alias_value":"JOPDBC2UC67T","created_at":"2026-07-05T06:24:50Z"},{"alias_kind":"pith_short_16","alias_value":"JOPDBC2UC67TZY6E","created_at":"2026-07-05T06:24:50Z"},{"alias_kind":"pith_short_8","alias_value":"JOPDBC2U","created_at":"2026-07-05T06:24:50Z"}],"graph_snapshots":[{"event_id":"sha256:b88b331ee86302ca8e18a72ef9643a3bfcd71c9d4ab69907b590949ad978c992","target":"graph","created_at":"2026-07-05T06:24:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2306.04050/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chandra Shekhara Kaushik Valmeekam, Dileep Kalathil, Jean-Francois Chamberland, Krishna Narayanan, Srinivas Shakkottai","cross_cats":["cs.CL","cs.LG","math.IT"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IT","submitted_at":"2023-06-06T22:42:00Z","title":"LLMZip: Lossless Text Compression using Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.04050","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:432f22e577aa3d208cdaad14a1341c6566436d29ef2a5a65a894e14801ebc15e","target":"record","created_at":"2026-07-05T06:24:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"8bd9d591a1356a37c532671a00e4da972d77549afbc03888b2eda9a6001b5788","cross_cats_sorted":["cs.CL","cs.LG","math.IT"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IT","submitted_at":"2023-06-06T22:42:00Z","title_canon_sha256":"9eb81502b6078ae4d2c007da51db30a89e19f676c96828edd6e3c6524eec245f"},"schema_version":"1.0","source":{"id":"2306.04050","kind":"arxiv","version":2}},"canonical_sha256":"4b9e308b5417bf3ce3c4ebe60efbabd88111362baf205341b03be0319b488ba7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4b9e308b5417bf3ce3c4ebe60efbabd88111362baf205341b03be0319b488ba7","first_computed_at":"2026-07-05T06:24:50.506399Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:24:50.506399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"t9+2w3fKatEqxT9jDHfMeDMrFbnbDdE+zZnUjxoezGtJqJI5dl+FlxY5hE3lX4Lit/EjH4mTUGe+J1J0u7xdBg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:24:50.506831Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.04050","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:432f22e577aa3d208cdaad14a1341c6566436d29ef2a5a65a894e14801ebc15e","sha256:b88b331ee86302ca8e18a72ef9643a3bfcd71c9d4ab69907b590949ad978c992"],"state_sha256":"17c611106f43bb08a2b1e6038fc08d62e04096c01ba9ae6526344410bdb3c514"}