{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KAVM4RMQZGFQ4UNQUHDBYW4O4U","short_pith_number":"pith:KAVM4RMQ","schema_version":"1.0","canonical_sha256":"502ace4590c98b0e51b0a1c61c5b8ee5339cdc6d8135d223149b692d96e8825b","source":{"kind":"arxiv","id":"2505.06297","version":1},"attestation_state":"computed","paper":{"title":"Lossless Compression of Large Language Model-Generated Text via Next-Token Prediction","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Chun Jason Xue, Holger Pirk, Yu Mao","submitted_at":"2025-05-07T17:42:35Z","abstract_excerpt":"As large language models (LLMs) continue to be deployed and utilized across domains, the volume of LLM-generated data is growing rapidly. This trend highlights the increasing importance of effective and lossless compression for such data in modern text management systems. However, compressing LLM-generated data presents unique challenges compared to traditional human- or machine-generated content. Traditional machine-generated data is typically derived from computational processes or device outputs, often highly structured and limited to low-level elements like labels or numerical values. This"},"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":"2505.06297","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-07T17:42:35Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"ac6a2129faf1431063ae1c00c1b6b3501af27a31d0f8672c04d959f98e0a2ba4","abstract_canon_sha256":"b21177cba5391dab2995f7b7f36359740b49f55735249d8163f473d423215614"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:06.846471Z","signature_b64":"shYsQ6nNgpi9kHCOB21eJdRh2t4hXP5tFH6gICvbRy1mJHe+P3zODhQzQdlW9F525vcpORCvhc9+fEZ3C88TAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"502ace4590c98b0e51b0a1c61c5b8ee5339cdc6d8135d223149b692d96e8825b","last_reissued_at":"2026-07-05T11:01:06.845973Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:06.845973Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lossless Compression of Large Language Model-Generated Text via Next-Token Prediction","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Chun Jason Xue, Holger Pirk, Yu Mao","submitted_at":"2025-05-07T17:42:35Z","abstract_excerpt":"As large language models (LLMs) continue to be deployed and utilized across domains, the volume of LLM-generated data is growing rapidly. This trend highlights the increasing importance of effective and lossless compression for such data in modern text management systems. However, compressing LLM-generated data presents unique challenges compared to traditional human- or machine-generated content. Traditional machine-generated data is typically derived from computational processes or device outputs, often highly structured and limited to low-level elements like labels or numerical values. This"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.06297","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/2505.06297/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":"2505.06297","created_at":"2026-07-05T11:01:06.846033+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.06297v1","created_at":"2026-07-05T11:01:06.846033+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.06297","created_at":"2026-07-05T11:01:06.846033+00:00"},{"alias_kind":"pith_short_12","alias_value":"KAVM4RMQZGFQ","created_at":"2026-07-05T11:01:06.846033+00:00"},{"alias_kind":"pith_short_16","alias_value":"KAVM4RMQZGFQ4UNQ","created_at":"2026-07-05T11:01:06.846033+00:00"},{"alias_kind":"pith_short_8","alias_value":"KAVM4RMQ","created_at":"2026-07-05T11:01:06.846033+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08184","citing_title":"TextEconomizer: Enhancing Lossy Text Compression with Denoising Transformers and Entropy Coding","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KAVM4RMQZGFQ4UNQUHDBYW4O4U","json":"https://pith.science/pith/KAVM4RMQZGFQ4UNQUHDBYW4O4U.json","graph_json":"https://pith.science/api/pith-number/KAVM4RMQZGFQ4UNQUHDBYW4O4U/graph.json","events_json":"https://pith.science/api/pith-number/KAVM4RMQZGFQ4UNQUHDBYW4O4U/events.json","paper":"https://pith.science/paper/KAVM4RMQ"},"agent_actions":{"view_html":"https://pith.science/pith/KAVM4RMQZGFQ4UNQUHDBYW4O4U","download_json":"https://pith.science/pith/KAVM4RMQZGFQ4UNQUHDBYW4O4U.json","view_paper":"https://pith.science/paper/KAVM4RMQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.06297&json=true","fetch_graph":"https://pith.science/api/pith-number/KAVM4RMQZGFQ4UNQUHDBYW4O4U/graph.json","fetch_events":"https://pith.science/api/pith-number/KAVM4RMQZGFQ4UNQUHDBYW4O4U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KAVM4RMQZGFQ4UNQUHDBYW4O4U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KAVM4RMQZGFQ4UNQUHDBYW4O4U/action/storage_attestation","attest_author":"https://pith.science/pith/KAVM4RMQZGFQ4UNQUHDBYW4O4U/action/author_attestation","sign_citation":"https://pith.science/pith/KAVM4RMQZGFQ4UNQUHDBYW4O4U/action/citation_signature","submit_replication":"https://pith.science/pith/KAVM4RMQZGFQ4UNQUHDBYW4O4U/action/replication_record"}},"created_at":"2026-07-05T11:01:06.846033+00:00","updated_at":"2026-07-05T11:01:06.846033+00:00"}