{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:3EZDNWTYL3EZLA2YWX7YR5UUVZ","short_pith_number":"pith:3EZDNWTY","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"},"canonical_sha256":"d93236da785ec9958358b5ff88f694ae51d7bab1827319a9ff749f2bbf8190c8","source":{"kind":"arxiv","id":"2605.30813","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.30813","created_at":"2026-06-01T01:03:18Z"},{"alias_kind":"arxiv_version","alias_value":"2605.30813v1","created_at":"2026-06-01T01:03:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30813","created_at":"2026-06-01T01:03:18Z"},{"alias_kind":"pith_short_12","alias_value":"3EZDNWTYL3EZ","created_at":"2026-06-01T01:03:18Z"},{"alias_kind":"pith_short_16","alias_value":"3EZDNWTYL3EZLA2Y","created_at":"2026-06-01T01:03:18Z"},{"alias_kind":"pith_short_8","alias_value":"3EZDNWTY","created_at":"2026-06-01T01:03:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:3EZDNWTYL3EZLA2YWX7YR5UUVZ","target":"record","payload":{"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"},"canonical_sha256":"d93236da785ec9958358b5ff88f694ae51d7bab1827319a9ff749f2bbf8190c8","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"},"source_kind":"arxiv","source_id":"2605.30813","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":"2026-06-01T01:03:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W5v09o2sEW+jyXeXIfm8Ki2I6RWGjDzuFIODxAhfYGM/Uuvca/rQJ/J+64b2ucrl77fKyMTLnMlgsZBjsHb2CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T01:06:09.010697Z"},"content_sha256":"7fc4bfe36456dc1aaf8e4b374ea16390068af8ab4822257362a4e39d3ca5be90","schema_version":"1.0","event_id":"sha256:7fc4bfe36456dc1aaf8e4b374ea16390068af8ab4822257362a4e39d3ca5be90"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:3EZDNWTYL3EZLA2YWX7YR5UUVZ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-01T01:03:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qNxLBiYF2vW8YUjOgfkpa+n3MonyRqUYPgnJ0qqgGVzB1i75/vSLC9XOr609aD3bfLoOSERS0NQdyyRjY0g/Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T01:06:09.011072Z"},"content_sha256":"47b412c33c7b2c8ed74db867573d55a0676e984ccca47970bac332b9c81e7533","schema_version":"1.0","event_id":"sha256:47b412c33c7b2c8ed74db867573d55a0676e984ccca47970bac332b9c81e7533"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3EZDNWTYL3EZLA2YWX7YR5UUVZ/bundle.json","state_url":"https://pith.science/pith/3EZDNWTYL3EZLA2YWX7YR5UUVZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3EZDNWTYL3EZLA2YWX7YR5UUVZ/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":"2026-08-05T01:06:09Z","links":{"resolver":"https://pith.science/pith/3EZDNWTYL3EZLA2YWX7YR5UUVZ","bundle":"https://pith.science/pith/3EZDNWTYL3EZLA2YWX7YR5UUVZ/bundle.json","state":"https://pith.science/pith/3EZDNWTYL3EZLA2YWX7YR5UUVZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3EZDNWTYL3EZLA2YWX7YR5UUVZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3EZDNWTYL3EZLA2YWX7YR5UUVZ","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":"6e3b4e74df86632762e39241b71669ee98368a1213766d3c7a18ad0b8019947c","cross_cats_sorted":["cs.DS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-29T04:04:32Z","title_canon_sha256":"0f6a68d54c6e715b77ced1657350169cab21429a3485858e73ea8e65c069ff9a"},"schema_version":"1.0","source":{"id":"2605.30813","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.30813","created_at":"2026-06-01T01:03:18Z"},{"alias_kind":"arxiv_version","alias_value":"2605.30813v1","created_at":"2026-06-01T01:03:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30813","created_at":"2026-06-01T01:03:18Z"},{"alias_kind":"pith_short_12","alias_value":"3EZDNWTYL3EZ","created_at":"2026-06-01T01:03:18Z"},{"alias_kind":"pith_short_16","alias_value":"3EZDNWTYL3EZLA2Y","created_at":"2026-06-01T01:03:18Z"},{"alias_kind":"pith_short_8","alias_value":"3EZDNWTY","created_at":"2026-06-01T01:03:18Z"}],"graph_snapshots":[{"event_id":"sha256:47b412c33c7b2c8ed74db867573d55a0676e984ccca47970bac332b9c81e7533","target":"graph","created_at":"2026-06-01T01:03:18Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2605.30813/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Ruihao Gong, Shenghu Jiang","cross_cats":["cs.DS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-29T04:04:32Z","title":"Incremental BPE Tokenization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30813","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":"sha256:7fc4bfe36456dc1aaf8e4b374ea16390068af8ab4822257362a4e39d3ca5be90","target":"record","created_at":"2026-06-01T01:03:18Z","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":"6e3b4e74df86632762e39241b71669ee98368a1213766d3c7a18ad0b8019947c","cross_cats_sorted":["cs.DS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-29T04:04:32Z","title_canon_sha256":"0f6a68d54c6e715b77ced1657350169cab21429a3485858e73ea8e65c069ff9a"},"schema_version":"1.0","source":{"id":"2605.30813","kind":"arxiv","version":1}},"canonical_sha256":"d93236da785ec9958358b5ff88f694ae51d7bab1827319a9ff749f2bbf8190c8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d93236da785ec9958358b5ff88f694ae51d7bab1827319a9ff749f2bbf8190c8","first_computed_at":"2026-06-01T01:03:18.288511Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-01T01:03:18.288511Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"icr26V+iYmN34kzhcoabLx0U580anPar4pO44/aBN2m0151PbjhDWuYw9DZ+fdAVznJho0Y6NXdhyxzBuWyeCA==","signature_status":"signed_v1","signed_at":"2026-06-01T01:03:18.289381Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.30813","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7fc4bfe36456dc1aaf8e4b374ea16390068af8ab4822257362a4e39d3ca5be90","sha256:47b412c33c7b2c8ed74db867573d55a0676e984ccca47970bac332b9c81e7533"],"state_sha256":"ed97325a750c1eff2356da183a41bc674321f9481a2b761882945d6f5f3c1f13"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IwlorZ0lRJaiNnxo0YFPZTT2mzuA0P/HMmKxXmPkZXvY3oras+EuyQxAMWKuGYQTltWAYrOpTSjCIhVC6KVDDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T01:06:09.013392Z","bundle_sha256":"feebe1271f6747fafc26dbd2b109e3ccd6992f6f9ae31b72cfb36b372d22767d"}}