{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3EZDNWTYL3EZLA2YWX7YR5UUVZ","short_pith_number":"pith:3EZDNWTY","schema_version":"1.0","canonical_sha256":"d93236da785ec9958358b5ff88f694ae51d7bab1827319a9ff749f2bbf8190c8","source":{"kind":"arxiv","id":"2605.30813","version":1},"attestation_state":"computed","paper":{"title":"Incremental BPE Tokenization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DS"],"primary_cat":"cs.CL","authors_text":"Ruihao Gong, Shenghu Jiang","submitted_at":"2026-05-29T04:04:32Z","abstract_excerpt":"We propose a novel algorithm for incremental Byte Pair Encoding (BPE) tokenization. The algorithm processes each input byte in worst-case $\\mathcal{O}(\\log^2 t)$ time, leading to an overall complexity of $\\mathcal{O}(n \\log^2 t)$, where $n$ is the input length and $t$ is the maximum token length. The algorithm incrementally maintains BPE tokenization results for every prefix of the input text, implementing the standard BPE merge procedure defined by a fixed set of merge rules. This enables efficient partial tokenization in streaming settings. Functioning as a drop-in replacement for standard B"},"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":"2605.30813","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-29T04:04:32Z","cross_cats_sorted":["cs.DS"],"title_canon_sha256":"0f6a68d54c6e715b77ced1657350169cab21429a3485858e73ea8e65c069ff9a","abstract_canon_sha256":"6e3b4e74df86632762e39241b71669ee98368a1213766d3c7a18ad0b8019947c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:03:18.289381Z","signature_b64":"icr26V+iYmN34kzhcoabLx0U580anPar4pO44/aBN2m0151PbjhDWuYw9DZ+fdAVznJho0Y6NXdhyxzBuWyeCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d93236da785ec9958358b5ff88f694ae51d7bab1827319a9ff749f2bbf8190c8","last_reissued_at":"2026-06-01T01:03:18.288511Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:03:18.288511Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Incremental BPE Tokenization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DS"],"primary_cat":"cs.CL","authors_text":"Ruihao Gong, Shenghu Jiang","submitted_at":"2026-05-29T04:04:32Z","abstract_excerpt":"We propose a novel algorithm for incremental Byte Pair Encoding (BPE) tokenization. The algorithm processes each input byte in worst-case $\\mathcal{O}(\\log^2 t)$ time, leading to an overall complexity of $\\mathcal{O}(n \\log^2 t)$, where $n$ is the input length and $t$ is the maximum token length. The algorithm incrementally maintains BPE tokenization results for every prefix of the input text, implementing the standard BPE merge procedure defined by a fixed set of merge rules. This enables efficient partial tokenization in streaming settings. Functioning as a drop-in replacement for standard B"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30813","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/2605.30813/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":"2605.30813","created_at":"2026-06-01T01:03:18.288639+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.30813v1","created_at":"2026-06-01T01:03:18.288639+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30813","created_at":"2026-06-01T01:03:18.288639+00:00"},{"alias_kind":"pith_short_12","alias_value":"3EZDNWTYL3EZ","created_at":"2026-06-01T01:03:18.288639+00:00"},{"alias_kind":"pith_short_16","alias_value":"3EZDNWTYL3EZLA2Y","created_at":"2026-06-01T01:03:18.288639+00:00"},{"alias_kind":"pith_short_8","alias_value":"3EZDNWTY","created_at":"2026-06-01T01:03:18.288639+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/3EZDNWTYL3EZLA2YWX7YR5UUVZ","json":"https://pith.science/pith/3EZDNWTYL3EZLA2YWX7YR5UUVZ.json","graph_json":"https://pith.science/api/pith-number/3EZDNWTYL3EZLA2YWX7YR5UUVZ/graph.json","events_json":"https://pith.science/api/pith-number/3EZDNWTYL3EZLA2YWX7YR5UUVZ/events.json","paper":"https://pith.science/paper/3EZDNWTY"},"agent_actions":{"view_html":"https://pith.science/pith/3EZDNWTYL3EZLA2YWX7YR5UUVZ","download_json":"https://pith.science/pith/3EZDNWTYL3EZLA2YWX7YR5UUVZ.json","view_paper":"https://pith.science/paper/3EZDNWTY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.30813&json=true","fetch_graph":"https://pith.science/api/pith-number/3EZDNWTYL3EZLA2YWX7YR5UUVZ/graph.json","fetch_events":"https://pith.science/api/pith-number/3EZDNWTYL3EZLA2YWX7YR5UUVZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3EZDNWTYL3EZLA2YWX7YR5UUVZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3EZDNWTYL3EZLA2YWX7YR5UUVZ/action/storage_attestation","attest_author":"https://pith.science/pith/3EZDNWTYL3EZLA2YWX7YR5UUVZ/action/author_attestation","sign_citation":"https://pith.science/pith/3EZDNWTYL3EZLA2YWX7YR5UUVZ/action/citation_signature","submit_replication":"https://pith.science/pith/3EZDNWTYL3EZLA2YWX7YR5UUVZ/action/replication_record"}},"created_at":"2026-06-01T01:03:18.288639+00:00","updated_at":"2026-06-01T01:03:18.288639+00:00"}