{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:TD6UYM4BYTSXPFN3K34FVRU43V","short_pith_number":"pith:TD6UYM4B","canonical_record":{"source":{"id":"2606.20993","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-18T23:50:54Z","cross_cats_sorted":[],"title_canon_sha256":"012a01d787c53230548cdb13c4f2b415811d07a7692644142479fcd5ed8be6f2","abstract_canon_sha256":"1666340ec98c6430c261eabfa3639f790506b3deecb204b80a90f6f45ba8357c"},"schema_version":"1.0"},"canonical_sha256":"98fd4c3381c4e57795bb56f85ac69cdd755b95212587ff2b12b0787915993e4c","source":{"kind":"arxiv","id":"2606.20993","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.20993","created_at":"2026-06-23T01:12:24Z"},{"alias_kind":"arxiv_version","alias_value":"2606.20993v1","created_at":"2026-06-23T01:12:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.20993","created_at":"2026-06-23T01:12:24Z"},{"alias_kind":"pith_short_12","alias_value":"TD6UYM4BYTSX","created_at":"2026-06-23T01:12:24Z"},{"alias_kind":"pith_short_16","alias_value":"TD6UYM4BYTSXPFN3","created_at":"2026-06-23T01:12:24Z"},{"alias_kind":"pith_short_8","alias_value":"TD6UYM4B","created_at":"2026-06-23T01:12:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:TD6UYM4BYTSXPFN3K34FVRU43V","target":"record","payload":{"canonical_record":{"source":{"id":"2606.20993","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-18T23:50:54Z","cross_cats_sorted":[],"title_canon_sha256":"012a01d787c53230548cdb13c4f2b415811d07a7692644142479fcd5ed8be6f2","abstract_canon_sha256":"1666340ec98c6430c261eabfa3639f790506b3deecb204b80a90f6f45ba8357c"},"schema_version":"1.0"},"canonical_sha256":"98fd4c3381c4e57795bb56f85ac69cdd755b95212587ff2b12b0787915993e4c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T01:12:24.622090Z","signature_b64":"b3/zmZRLTvj4HBqikd53296JXaOmdk6NaUhBBoo81JMJDw0BQ+gthPGpCtWnnSvenXUmSMxSlJrkBKDTHQ/NDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"98fd4c3381c4e57795bb56f85ac69cdd755b95212587ff2b12b0787915993e4c","last_reissued_at":"2026-06-23T01:12:24.621633Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T01:12:24.621633Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.20993","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":"2026-06-23T01:12:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Je1I6p003ozV7V5Ohyf95REJi6l/FwFcG0yb6/PnpPFOtOD88yBrAkU3pYXQD4uCkZfuLjAAjL76ZreaDnlACQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T04:17:49.514143Z"},"content_sha256":"baddfe2216df32aafeff24a1c20ceb4cea4cc4dabdc1de1d59945c2b1e65f315","schema_version":"1.0","event_id":"sha256:baddfe2216df32aafeff24a1c20ceb4cea4cc4dabdc1de1d59945c2b1e65f315"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:TD6UYM4BYTSXPFN3K34FVRU43V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Phonemes to the Rescue: Multilingual Tokenization Based on International Phonetic Alphabet","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ekaterina Shutova, Julie Kallini, Milan Mileti\\'c","submitted_at":"2026-06-18T23:50:54Z","abstract_excerpt":"Multilingual language models often exhibit performance disparities across languages that can arise as early as the tokenization stage. Widely-used subword tokenization approaches favor high-resource languages, and tokenizer-free methods still yield longer sequences for scripts with a higher bytes-per-character ratio. To address these shortcomings, we propose to use the International Phonetic Alphabet (IPA) as a language-agnostic input representation for multilingual tokenizers. IPA provides a compact symbol inventory, greater cross-lingual character overlap, and a more balanced byte-per-charac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.20993","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/2606.20993/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":"2026-06-23T01:12:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9O00u2xy+kxBHOEx9+xQNgUi3qWFewZVJuCdDpRHYNgYv4gHrcj7HrRAWwXk/J1WLheCXwmzCTyRlW+NFw+nCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T04:17:49.514530Z"},"content_sha256":"0a5ac41d7e0ee2563945c80e7e57ca2814461bafd0e8b713aeb6876d6c633ff6","schema_version":"1.0","event_id":"sha256:0a5ac41d7e0ee2563945c80e7e57ca2814461bafd0e8b713aeb6876d6c633ff6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TD6UYM4BYTSXPFN3K34FVRU43V/bundle.json","state_url":"https://pith.science/pith/TD6UYM4BYTSXPFN3K34FVRU43V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TD6UYM4BYTSXPFN3K34FVRU43V/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":"2026-06-28T04:17:49Z","links":{"resolver":"https://pith.science/pith/TD6UYM4BYTSXPFN3K34FVRU43V","bundle":"https://pith.science/pith/TD6UYM4BYTSXPFN3K34FVRU43V/bundle.json","state":"https://pith.science/pith/TD6UYM4BYTSXPFN3K34FVRU43V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TD6UYM4BYTSXPFN3K34FVRU43V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TD6UYM4BYTSXPFN3K34FVRU43V","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":"1666340ec98c6430c261eabfa3639f790506b3deecb204b80a90f6f45ba8357c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-18T23:50:54Z","title_canon_sha256":"012a01d787c53230548cdb13c4f2b415811d07a7692644142479fcd5ed8be6f2"},"schema_version":"1.0","source":{"id":"2606.20993","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.20993","created_at":"2026-06-23T01:12:24Z"},{"alias_kind":"arxiv_version","alias_value":"2606.20993v1","created_at":"2026-06-23T01:12:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.20993","created_at":"2026-06-23T01:12:24Z"},{"alias_kind":"pith_short_12","alias_value":"TD6UYM4BYTSX","created_at":"2026-06-23T01:12:24Z"},{"alias_kind":"pith_short_16","alias_value":"TD6UYM4BYTSXPFN3","created_at":"2026-06-23T01:12:24Z"},{"alias_kind":"pith_short_8","alias_value":"TD6UYM4B","created_at":"2026-06-23T01:12:24Z"}],"graph_snapshots":[{"event_id":"sha256:0a5ac41d7e0ee2563945c80e7e57ca2814461bafd0e8b713aeb6876d6c633ff6","target":"graph","created_at":"2026-06-23T01:12:24Z","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/2606.20993/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multilingual language models often exhibit performance disparities across languages that can arise as early as the tokenization stage. Widely-used subword tokenization approaches favor high-resource languages, and tokenizer-free methods still yield longer sequences for scripts with a higher bytes-per-character ratio. To address these shortcomings, we propose to use the International Phonetic Alphabet (IPA) as a language-agnostic input representation for multilingual tokenizers. IPA provides a compact symbol inventory, greater cross-lingual character overlap, and a more balanced byte-per-charac","authors_text":"Ekaterina Shutova, Julie Kallini, Milan Mileti\\'c","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-18T23:50:54Z","title":"Phonemes to the Rescue: Multilingual Tokenization Based on International Phonetic Alphabet"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.20993","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:baddfe2216df32aafeff24a1c20ceb4cea4cc4dabdc1de1d59945c2b1e65f315","target":"record","created_at":"2026-06-23T01:12:24Z","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":"1666340ec98c6430c261eabfa3639f790506b3deecb204b80a90f6f45ba8357c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-18T23:50:54Z","title_canon_sha256":"012a01d787c53230548cdb13c4f2b415811d07a7692644142479fcd5ed8be6f2"},"schema_version":"1.0","source":{"id":"2606.20993","kind":"arxiv","version":1}},"canonical_sha256":"98fd4c3381c4e57795bb56f85ac69cdd755b95212587ff2b12b0787915993e4c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"98fd4c3381c4e57795bb56f85ac69cdd755b95212587ff2b12b0787915993e4c","first_computed_at":"2026-06-23T01:12:24.621633Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T01:12:24.621633Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"b3/zmZRLTvj4HBqikd53296JXaOmdk6NaUhBBoo81JMJDw0BQ+gthPGpCtWnnSvenXUmSMxSlJrkBKDTHQ/NDg==","signature_status":"signed_v1","signed_at":"2026-06-23T01:12:24.622090Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.20993","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:baddfe2216df32aafeff24a1c20ceb4cea4cc4dabdc1de1d59945c2b1e65f315","sha256:0a5ac41d7e0ee2563945c80e7e57ca2814461bafd0e8b713aeb6876d6c633ff6"],"state_sha256":"f19b09e9f7a1399a4568de2f81aa1f5005839917a72d1bc9299cf9613bd02ae7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2Wg84QosCOm8b3igsQenTHLftCppPnexXo16i1bJiQr+cUrp3376n3qMaCZxtWjEDCwBFndNvj0OdvBpRiOwCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T04:17:49.516515Z","bundle_sha256":"62de0010592495aba104d92dc0d9ef6f5c0e1c93e73f832ce1f5b8d9655d13d1"}}