{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:WEGSQ6JLWVNHXOD3PN5PIU4EIE","short_pith_number":"pith:WEGSQ6JL","schema_version":"1.0","canonical_sha256":"b10d28792bb55a7bb87b7b7af453844106fcc6a89e897b353cf3fa0a5472c74f","source":{"kind":"arxiv","id":"1701.04047","version":1},"attestation_state":"computed","paper":{"title":"Making compression algorithms for Unicode text","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.IT"],"primary_cat":"cs.IT","authors_text":"Adam Gleave, Christian Steinruecken","submitted_at":"2017-01-15T14:17:13Z","abstract_excerpt":"The majority of online content is written in languages other than English, and is most commonly encoded in UTF-8, the world's dominant Unicode character encoding. Traditional compression algorithms typically operate on individual bytes. While this approach works well for the single-byte ASCII encoding, it works poorly for UTF-8, where characters often span multiple bytes. Previous research has focused on developing Unicode compressors from scratch, which often failed to outperform established algorithms such as bzip2. We develop a technique to modify byte-based compressors to operate directly "},"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":"1701.04047","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IT","submitted_at":"2017-01-15T14:17:13Z","cross_cats_sorted":["math.IT"],"title_canon_sha256":"8dfc430697b3359a85be091bce846c591c98863290024046cff1724828fb6977","abstract_canon_sha256":"183eac8713292015f7bd0f4c5278c0d60c539c6018b80960c4205f23e9533c2d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:52:47.994638Z","signature_b64":"d2luG+y+rj2ZdAAVWjUCTITmim+15F8IMKwTPXizF81XtrWc71JOB84zISh7U4lNMDdP7oh8uic/UNJurvSoBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b10d28792bb55a7bb87b7b7af453844106fcc6a89e897b353cf3fa0a5472c74f","last_reissued_at":"2026-05-18T00:52:47.993998Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:52:47.993998Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Making compression algorithms for Unicode text","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.IT"],"primary_cat":"cs.IT","authors_text":"Adam Gleave, Christian Steinruecken","submitted_at":"2017-01-15T14:17:13Z","abstract_excerpt":"The majority of online content is written in languages other than English, and is most commonly encoded in UTF-8, the world's dominant Unicode character encoding. Traditional compression algorithms typically operate on individual bytes. While this approach works well for the single-byte ASCII encoding, it works poorly for UTF-8, where characters often span multiple bytes. Previous research has focused on developing Unicode compressors from scratch, which often failed to outperform established algorithms such as bzip2. We develop a technique to modify byte-based compressors to operate directly "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1701.04047","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":""},"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":"1701.04047","created_at":"2026-05-18T00:52:47.994093+00:00"},{"alias_kind":"arxiv_version","alias_value":"1701.04047v1","created_at":"2026-05-18T00:52:47.994093+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1701.04047","created_at":"2026-05-18T00:52:47.994093+00:00"},{"alias_kind":"pith_short_12","alias_value":"WEGSQ6JLWVNH","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_16","alias_value":"WEGSQ6JLWVNHXOD3","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_8","alias_value":"WEGSQ6JL","created_at":"2026-05-18T12:31:53.515858+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WEGSQ6JLWVNHXOD3PN5PIU4EIE","json":"https://pith.science/pith/WEGSQ6JLWVNHXOD3PN5PIU4EIE.json","graph_json":"https://pith.science/api/pith-number/WEGSQ6JLWVNHXOD3PN5PIU4EIE/graph.json","events_json":"https://pith.science/api/pith-number/WEGSQ6JLWVNHXOD3PN5PIU4EIE/events.json","paper":"https://pith.science/paper/WEGSQ6JL"},"agent_actions":{"view_html":"https://pith.science/pith/WEGSQ6JLWVNHXOD3PN5PIU4EIE","download_json":"https://pith.science/pith/WEGSQ6JLWVNHXOD3PN5PIU4EIE.json","view_paper":"https://pith.science/paper/WEGSQ6JL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1701.04047&json=true","fetch_graph":"https://pith.science/api/pith-number/WEGSQ6JLWVNHXOD3PN5PIU4EIE/graph.json","fetch_events":"https://pith.science/api/pith-number/WEGSQ6JLWVNHXOD3PN5PIU4EIE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WEGSQ6JLWVNHXOD3PN5PIU4EIE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WEGSQ6JLWVNHXOD3PN5PIU4EIE/action/storage_attestation","attest_author":"https://pith.science/pith/WEGSQ6JLWVNHXOD3PN5PIU4EIE/action/author_attestation","sign_citation":"https://pith.science/pith/WEGSQ6JLWVNHXOD3PN5PIU4EIE/action/citation_signature","submit_replication":"https://pith.science/pith/WEGSQ6JLWVNHXOD3PN5PIU4EIE/action/replication_record"}},"created_at":"2026-05-18T00:52:47.994093+00:00","updated_at":"2026-05-18T00:52:47.994093+00:00"}