{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PCFNSK4HSBTTHKH7C54HR4UTYJ","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":"52f1a6a802137413a998d9e032124349980a6a7ad6afe017003fabe3e60d544d","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-06T18:14:43Z","title_canon_sha256":"56e9a7e3f59cce241884e41caaa21a173e9a7fb1682322a1cb43695e3a056394"},"schema_version":"1.0","source":{"id":"2508.04796","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.04796","created_at":"2026-07-05T11:57:38Z"},{"alias_kind":"arxiv_version","alias_value":"2508.04796v2","created_at":"2026-07-05T11:57:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.04796","created_at":"2026-07-05T11:57:38Z"},{"alias_kind":"pith_short_12","alias_value":"PCFNSK4HSBTT","created_at":"2026-07-05T11:57:38Z"},{"alias_kind":"pith_short_16","alias_value":"PCFNSK4HSBTTHKH7","created_at":"2026-07-05T11:57:38Z"},{"alias_kind":"pith_short_8","alias_value":"PCFNSK4H","created_at":"2026-07-05T11:57:38Z"}],"graph_snapshots":[{"event_id":"sha256:d8ca475b879991b2f2098c65fb8c979a01ec900c8a6ec1eef39cd8e41b5f97b3","target":"graph","created_at":"2026-07-05T11:57:38Z","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/2508.04796/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tokenization is the first -- and often least scrutinized -- step of most NLP pipelines. Standard algorithms for learning tokenizers rely on frequency-based objectives, which favor languages dominant in the training data and consequently leave lower-resource languages with tokenizations that are disproportionately longer, morphologically implausible, or even riddled with <UNK> placeholders. This phenomenon ultimately amplifies computational and financial inequalities between users from different language backgrounds. To remedy this, we introduce Parity-aware Byte Pair Encoding (BPE), a variant ","authors_text":"Antoine Bosselut, Clara Meister, Debjit Paul, Joel Niklaus, Negar Foroutan, Rico Sennrich, Sina Ahmadi","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-06T18:14:43Z","title":"Parity-Aware Byte-Pair Encoding: Improving Cross-lingual Fairness in Tokenization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.04796","kind":"arxiv","version":2},"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":"sha256:50837f1f5b637ded739aece5854940b559c3788e2279561df02ccffb5f48d898","target":"record","created_at":"2026-07-05T11:57:38Z","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":"52f1a6a802137413a998d9e032124349980a6a7ad6afe017003fabe3e60d544d","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-06T18:14:43Z","title_canon_sha256":"56e9a7e3f59cce241884e41caaa21a173e9a7fb1682322a1cb43695e3a056394"},"schema_version":"1.0","source":{"id":"2508.04796","kind":"arxiv","version":2}},"canonical_sha256":"788ad92b87906733a8ff177878f293c276bebe8f57d99932fe2a5cb92dc05719","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"788ad92b87906733a8ff177878f293c276bebe8f57d99932fe2a5cb92dc05719","first_computed_at":"2026-07-05T11:57:38.499289Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:57:38.499289Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/wE3KXkG9F4ZnujajfE1PoZv/lrVrOpwpl2XFt3hfslYzGQlyaxttr/TRsN5eSDCO4Mgc2oYTHF/EmfoLSojDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:57:38.499757Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.04796","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:50837f1f5b637ded739aece5854940b559c3788e2279561df02ccffb5f48d898","sha256:d8ca475b879991b2f2098c65fb8c979a01ec900c8a6ec1eef39cd8e41b5f97b3"],"state_sha256":"dee7860ab7fdcc9ff4905d2d0df3fc1dcb75530b2958f0f2f7ae78caa89c83f4"}