{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:WEGSQ6JLWVNHXOD3PN5PIU4EIE","short_pith_number":"pith:WEGSQ6JL","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"},"canonical_sha256":"b10d28792bb55a7bb87b7b7af453844106fcc6a89e897b353cf3fa0a5472c74f","source":{"kind":"arxiv","id":"1701.04047","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1701.04047","created_at":"2026-05-18T00:52:47Z"},{"alias_kind":"arxiv_version","alias_value":"1701.04047v1","created_at":"2026-05-18T00:52:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1701.04047","created_at":"2026-05-18T00:52:47Z"},{"alias_kind":"pith_short_12","alias_value":"WEGSQ6JLWVNH","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"WEGSQ6JLWVNHXOD3","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"WEGSQ6JL","created_at":"2026-05-18T12:31:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:WEGSQ6JLWVNHXOD3PN5PIU4EIE","target":"record","payload":{"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"},"canonical_sha256":"b10d28792bb55a7bb87b7b7af453844106fcc6a89e897b353cf3fa0a5472c74f","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"},"source_kind":"arxiv","source_id":"1701.04047","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:52:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a6oIrNVdZ2vnqeQ6PW3KQoTakwKrq6pGxXcdLOHr8QIv2maS/leZBX5FYywZiO7XzeMRX83LloaHn4Qd58SjAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T01:46:13.912787Z"},"content_sha256":"394521f0e47cd5aa9da11cb611e835bb52c600c5deaa10bcf73292adfbba503a","schema_version":"1.0","event_id":"sha256:394521f0e47cd5aa9da11cb611e835bb52c600c5deaa10bcf73292adfbba503a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:WEGSQ6JLWVNHXOD3PN5PIU4EIE","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:52:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CwTAwJcdKcHAJrVmHaHNLNKaLRvtXkqbTFRxadyFJrwIssFW+avhYgTlSf9ABU9mqFmW11S+K22zQlF72X59AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T01:46:13.921312Z"},"content_sha256":"694b1a2d6bd3ad44ee1ca7c71e0dd966fee08bc3c7539c9e3bc445ca4a7f596d","schema_version":"1.0","event_id":"sha256:694b1a2d6bd3ad44ee1ca7c71e0dd966fee08bc3c7539c9e3bc445ca4a7f596d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WEGSQ6JLWVNHXOD3PN5PIU4EIE/bundle.json","state_url":"https://pith.science/pith/WEGSQ6JLWVNHXOD3PN5PIU4EIE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WEGSQ6JLWVNHXOD3PN5PIU4EIE/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-11T01:46:13Z","links":{"resolver":"https://pith.science/pith/WEGSQ6JLWVNHXOD3PN5PIU4EIE","bundle":"https://pith.science/pith/WEGSQ6JLWVNHXOD3PN5PIU4EIE/bundle.json","state":"https://pith.science/pith/WEGSQ6JLWVNHXOD3PN5PIU4EIE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WEGSQ6JLWVNHXOD3PN5PIU4EIE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:WEGSQ6JLWVNHXOD3PN5PIU4EIE","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":"183eac8713292015f7bd0f4c5278c0d60c539c6018b80960c4205f23e9533c2d","cross_cats_sorted":["math.IT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IT","submitted_at":"2017-01-15T14:17:13Z","title_canon_sha256":"8dfc430697b3359a85be091bce846c591c98863290024046cff1724828fb6977"},"schema_version":"1.0","source":{"id":"1701.04047","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1701.04047","created_at":"2026-05-18T00:52:47Z"},{"alias_kind":"arxiv_version","alias_value":"1701.04047v1","created_at":"2026-05-18T00:52:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1701.04047","created_at":"2026-05-18T00:52:47Z"},{"alias_kind":"pith_short_12","alias_value":"WEGSQ6JLWVNH","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"WEGSQ6JLWVNHXOD3","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"WEGSQ6JL","created_at":"2026-05-18T12:31:53Z"}],"graph_snapshots":[{"event_id":"sha256:694b1a2d6bd3ad44ee1ca7c71e0dd966fee08bc3c7539c9e3bc445ca4a7f596d","target":"graph","created_at":"2026-05-18T00:52:47Z","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"},"paper":{"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 ","authors_text":"Adam Gleave, Christian Steinruecken","cross_cats":["math.IT"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IT","submitted_at":"2017-01-15T14:17:13Z","title":"Making compression algorithms for Unicode text"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1701.04047","kind":"arxiv","version":1},"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":"sha256:394521f0e47cd5aa9da11cb611e835bb52c600c5deaa10bcf73292adfbba503a","target":"record","created_at":"2026-05-18T00:52:47Z","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":"183eac8713292015f7bd0f4c5278c0d60c539c6018b80960c4205f23e9533c2d","cross_cats_sorted":["math.IT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IT","submitted_at":"2017-01-15T14:17:13Z","title_canon_sha256":"8dfc430697b3359a85be091bce846c591c98863290024046cff1724828fb6977"},"schema_version":"1.0","source":{"id":"1701.04047","kind":"arxiv","version":1}},"canonical_sha256":"b10d28792bb55a7bb87b7b7af453844106fcc6a89e897b353cf3fa0a5472c74f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b10d28792bb55a7bb87b7b7af453844106fcc6a89e897b353cf3fa0a5472c74f","first_computed_at":"2026-05-18T00:52:47.993998Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:52:47.993998Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"d2luG+y+rj2ZdAAVWjUCTITmim+15F8IMKwTPXizF81XtrWc71JOB84zISh7U4lNMDdP7oh8uic/UNJurvSoBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:52:47.994638Z","signed_message":"canonical_sha256_bytes"},"source_id":"1701.04047","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:394521f0e47cd5aa9da11cb611e835bb52c600c5deaa10bcf73292adfbba503a","sha256:694b1a2d6bd3ad44ee1ca7c71e0dd966fee08bc3c7539c9e3bc445ca4a7f596d"],"state_sha256":"64b9701adc6cac514db974a3708c74727e3d63064be06311706c741eb075de7d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sHrkSUbCp06S8nddfMocaq94QFjLtUUTVmxVQNpz74/fChYaMyxgApEA2mSDTKmFsS4Y6txCFRQkQyissaHqCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T01:46:13.939112Z","bundle_sha256":"7be56324e037d116f465703b3b5ae5801c1de3560c07db1d6e9740e83c623155"}}