{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:S75NAYJ6H34U63TNQJDHECGWHM","short_pith_number":"pith:S75NAYJ6","schema_version":"1.0","canonical_sha256":"97fad0613e3ef94f6e6d82467208d63b20929c612b31985f6619873ac7499f00","source":{"kind":"arxiv","id":"2409.17141","version":1},"attestation_state":"computed","paper":{"title":"FineZip : Pushing the Limits of Large Language Models for Practical Lossless Text Compression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Akshat Gupta, Alp Eren Ozdarendeli, Anant Singh, Ashok Devireddy, Fazal Mittu, Gopala Anumanchipalli, Yihuan Bu","submitted_at":"2024-09-25T17:58:35Z","abstract_excerpt":"While the language modeling objective has been shown to be deeply connected with compression, it is surprising that modern LLMs are not employed in practical text compression systems. In this paper, we provide an in-depth analysis of neural network and transformer-based compression techniques to answer this question. We compare traditional text compression systems with neural network and LLM-based text compression methods. Although LLM-based systems significantly outperform conventional compression methods, they are highly impractical. Specifically, LLMZip, a recent text compression system usi"},"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":"2409.17141","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-25T17:58:35Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"f6756f75d5992dae039952ef239c64fac75bd91b1b266a5f52423796b4e8ebee","abstract_canon_sha256":"fbb1985d28e37858ecf826ecdd4a92a14763f5bfecbef7e9cde8dcf11a83c23b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:11:44.745307Z","signature_b64":"IiTvuRAx87zTVzV0KcgncI87jnyvBtGD2UgSWkLJ47alSuzWH/6w+Hm04aKVa0aZ5ehNvNA3kwVuVclOB46gAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"97fad0613e3ef94f6e6d82467208d63b20929c612b31985f6619873ac7499f00","last_reissued_at":"2026-07-05T09:11:44.744833Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:11:44.744833Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FineZip : Pushing the Limits of Large Language Models for Practical Lossless Text Compression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Akshat Gupta, Alp Eren Ozdarendeli, Anant Singh, Ashok Devireddy, Fazal Mittu, Gopala Anumanchipalli, Yihuan Bu","submitted_at":"2024-09-25T17:58:35Z","abstract_excerpt":"While the language modeling objective has been shown to be deeply connected with compression, it is surprising that modern LLMs are not employed in practical text compression systems. In this paper, we provide an in-depth analysis of neural network and transformer-based compression techniques to answer this question. We compare traditional text compression systems with neural network and LLM-based text compression methods. Although LLM-based systems significantly outperform conventional compression methods, they are highly impractical. Specifically, LLMZip, a recent text compression system usi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.17141","kind":"arxiv","version":1},"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/2409.17141/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":"2409.17141","created_at":"2026-07-05T09:11:44.744896+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.17141v1","created_at":"2026-07-05T09:11:44.744896+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.17141","created_at":"2026-07-05T09:11:44.744896+00:00"},{"alias_kind":"pith_short_12","alias_value":"S75NAYJ6H34U","created_at":"2026-07-05T09:11:44.744896+00:00"},{"alias_kind":"pith_short_16","alias_value":"S75NAYJ6H34U63TN","created_at":"2026-07-05T09:11:44.744896+00:00"},{"alias_kind":"pith_short_8","alias_value":"S75NAYJ6","created_at":"2026-07-05T09:11:44.744896+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.16256","citing_title":"DualComp: End-to-End Learning of a Unified Dual-Modality Lossless Compressor","ref_index":40,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S75NAYJ6H34U63TNQJDHECGWHM","json":"https://pith.science/pith/S75NAYJ6H34U63TNQJDHECGWHM.json","graph_json":"https://pith.science/api/pith-number/S75NAYJ6H34U63TNQJDHECGWHM/graph.json","events_json":"https://pith.science/api/pith-number/S75NAYJ6H34U63TNQJDHECGWHM/events.json","paper":"https://pith.science/paper/S75NAYJ6"},"agent_actions":{"view_html":"https://pith.science/pith/S75NAYJ6H34U63TNQJDHECGWHM","download_json":"https://pith.science/pith/S75NAYJ6H34U63TNQJDHECGWHM.json","view_paper":"https://pith.science/paper/S75NAYJ6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.17141&json=true","fetch_graph":"https://pith.science/api/pith-number/S75NAYJ6H34U63TNQJDHECGWHM/graph.json","fetch_events":"https://pith.science/api/pith-number/S75NAYJ6H34U63TNQJDHECGWHM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S75NAYJ6H34U63TNQJDHECGWHM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S75NAYJ6H34U63TNQJDHECGWHM/action/storage_attestation","attest_author":"https://pith.science/pith/S75NAYJ6H34U63TNQJDHECGWHM/action/author_attestation","sign_citation":"https://pith.science/pith/S75NAYJ6H34U63TNQJDHECGWHM/action/citation_signature","submit_replication":"https://pith.science/pith/S75NAYJ6H34U63TNQJDHECGWHM/action/replication_record"}},"created_at":"2026-07-05T09:11:44.744896+00:00","updated_at":"2026-07-05T09:11:44.744896+00:00"}