{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UKN4CYQGPSGDOV2E3AV3NYHUTR","short_pith_number":"pith:UKN4CYQG","schema_version":"1.0","canonical_sha256":"a29bc162067c8c375744d82bb6e0f49c4d937dde074d9c2248714ab6beb55cf9","source":{"kind":"arxiv","id":"2412.15250","version":1},"attestation_state":"computed","paper":{"title":"An Enhanced Text Compression Approach Using Transformer-based Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.IT","cs.LG","math.IT"],"primary_cat":"cs.CL","authors_text":"Anika Tasnim Rodela, Chowdhury Mofizur Rahman, Mahbub E Sobhani, Swakkhar Shatabda","submitted_at":"2024-12-15T03:01:17Z","abstract_excerpt":"Text compression shrinks textual data while keeping crucial information, eradicating constraints on storage, bandwidth, and computational efficacy. The integration of lossless compression techniques with transformer-based text decompression has received negligible attention, despite the increasing volume of English text data in communication. The primary barrier in advancing text compression and restoration involves optimizing transformer-based approaches with efficient pre-processing and integrating lossless compression algorithms, that remained unresolved in the prior attempts. Here, we prop"},"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":"2412.15250","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-15T03:01:17Z","cross_cats_sorted":["cs.IT","cs.LG","math.IT"],"title_canon_sha256":"4303bbf079d6987c2ed4a67c4b66f34d523e5024a810b79360ec611a3d049094","abstract_canon_sha256":"508f36c29a65ff8d07e35c2fa20010ff6b36f7bff0f2cc42d6d90638fb15eb25"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:52:00.445411Z","signature_b64":"BsefxR3kmNKDkw1r+JP0i4DxwFlKkdFDx/3GReB0MZAOifZGgTl3ALxhw3yHizrKfet6mHDwozZK8no3ni32CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a29bc162067c8c375744d82bb6e0f49c4d937dde074d9c2248714ab6beb55cf9","last_reissued_at":"2026-07-05T09:52:00.444933Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:52:00.444933Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Enhanced Text Compression Approach Using Transformer-based Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.IT","cs.LG","math.IT"],"primary_cat":"cs.CL","authors_text":"Anika Tasnim Rodela, Chowdhury Mofizur Rahman, Mahbub E Sobhani, Swakkhar Shatabda","submitted_at":"2024-12-15T03:01:17Z","abstract_excerpt":"Text compression shrinks textual data while keeping crucial information, eradicating constraints on storage, bandwidth, and computational efficacy. The integration of lossless compression techniques with transformer-based text decompression has received negligible attention, despite the increasing volume of English text data in communication. The primary barrier in advancing text compression and restoration involves optimizing transformer-based approaches with efficient pre-processing and integrating lossless compression algorithms, that remained unresolved in the prior attempts. Here, we prop"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.15250","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/2412.15250/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":"2412.15250","created_at":"2026-07-05T09:52:00.444993+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.15250v1","created_at":"2026-07-05T09:52:00.444993+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.15250","created_at":"2026-07-05T09:52:00.444993+00:00"},{"alias_kind":"pith_short_12","alias_value":"UKN4CYQGPSGD","created_at":"2026-07-05T09:52:00.444993+00:00"},{"alias_kind":"pith_short_16","alias_value":"UKN4CYQGPSGDOV2E","created_at":"2026-07-05T09:52:00.444993+00:00"},{"alias_kind":"pith_short_8","alias_value":"UKN4CYQG","created_at":"2026-07-05T09:52:00.444993+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.00592","citing_title":"M+: Extending MemoryLLM with Scalable Long-Term Memory","ref_index":2020,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UKN4CYQGPSGDOV2E3AV3NYHUTR","json":"https://pith.science/pith/UKN4CYQGPSGDOV2E3AV3NYHUTR.json","graph_json":"https://pith.science/api/pith-number/UKN4CYQGPSGDOV2E3AV3NYHUTR/graph.json","events_json":"https://pith.science/api/pith-number/UKN4CYQGPSGDOV2E3AV3NYHUTR/events.json","paper":"https://pith.science/paper/UKN4CYQG"},"agent_actions":{"view_html":"https://pith.science/pith/UKN4CYQGPSGDOV2E3AV3NYHUTR","download_json":"https://pith.science/pith/UKN4CYQGPSGDOV2E3AV3NYHUTR.json","view_paper":"https://pith.science/paper/UKN4CYQG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.15250&json=true","fetch_graph":"https://pith.science/api/pith-number/UKN4CYQGPSGDOV2E3AV3NYHUTR/graph.json","fetch_events":"https://pith.science/api/pith-number/UKN4CYQGPSGDOV2E3AV3NYHUTR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UKN4CYQGPSGDOV2E3AV3NYHUTR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UKN4CYQGPSGDOV2E3AV3NYHUTR/action/storage_attestation","attest_author":"https://pith.science/pith/UKN4CYQGPSGDOV2E3AV3NYHUTR/action/author_attestation","sign_citation":"https://pith.science/pith/UKN4CYQGPSGDOV2E3AV3NYHUTR/action/citation_signature","submit_replication":"https://pith.science/pith/UKN4CYQGPSGDOV2E3AV3NYHUTR/action/replication_record"}},"created_at":"2026-07-05T09:52:00.444993+00:00","updated_at":"2026-07-05T09:52:00.444993+00:00"}