{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:SEXO3V6WISBU6LMWAQ6UQVY7J4","short_pith_number":"pith:SEXO3V6W","canonical_record":{"source":{"id":"2607.17689","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-20T08:37:31Z","cross_cats_sorted":[],"title_canon_sha256":"8443b74f7564bf88b88ffe15d525364822feb8e1e6b7ba9c48493f7b2c69fba1","abstract_canon_sha256":"6257bb934bf2c95bb80685f59f3c535aaae7adcc2dc96e44be8a573af7766cb2"},"schema_version":"1.0"},"canonical_sha256":"912eedd7d644834f2d96043d48571f4f26d9e3729531353e741ce691b20fac38","source":{"kind":"arxiv","id":"2607.17689","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.17689","created_at":"2026-07-21T02:21:54Z"},{"alias_kind":"arxiv_version","alias_value":"2607.17689v1","created_at":"2026-07-21T02:21:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.17689","created_at":"2026-07-21T02:21:54Z"},{"alias_kind":"pith_short_12","alias_value":"SEXO3V6WISBU","created_at":"2026-07-21T02:21:54Z"},{"alias_kind":"pith_short_16","alias_value":"SEXO3V6WISBU6LMW","created_at":"2026-07-21T02:21:54Z"},{"alias_kind":"pith_short_8","alias_value":"SEXO3V6W","created_at":"2026-07-21T02:21:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:SEXO3V6WISBU6LMWAQ6UQVY7J4","target":"record","payload":{"canonical_record":{"source":{"id":"2607.17689","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-20T08:37:31Z","cross_cats_sorted":[],"title_canon_sha256":"8443b74f7564bf88b88ffe15d525364822feb8e1e6b7ba9c48493f7b2c69fba1","abstract_canon_sha256":"6257bb934bf2c95bb80685f59f3c535aaae7adcc2dc96e44be8a573af7766cb2"},"schema_version":"1.0"},"canonical_sha256":"912eedd7d644834f2d96043d48571f4f26d9e3729531353e741ce691b20fac38","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T02:21:54.808954Z","signature_b64":"p2PQ+37dUqirEOpJa89MgV5KBabwuf7TyQJyxV1KUuYloseT8rWbcPvfbKW8gZtvOynZCk7SigpwpbwR5YKqBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"912eedd7d644834f2d96043d48571f4f26d9e3729531353e741ce691b20fac38","last_reissued_at":"2026-07-21T02:21:54.806409Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T02:21:54.806409Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.17689","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":"2026-07-21T02:21:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AezU3mL0zRtWstCFbazYPaISS0qCQMwHfVsvd9tJdlqp7r4Ex70ZZYIDKy4zTZKhIv+q78K8IupC7BA6bTRkCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T05:26:35.059384Z"},"content_sha256":"3f0d2c0f26327f1e170fa406b86006e470d6a808865dc999c8a16809205521a2","schema_version":"1.0","event_id":"sha256:3f0d2c0f26327f1e170fa406b86006e470d6a808865dc999c8a16809205521a2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:SEXO3V6WISBU6LMWAQ6UQVY7J4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Tokenizing Crosslingual Homographs","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Rotem Brillant, Yuval Pinter","submitted_at":"2026-07-20T08:37:31Z","abstract_excerpt":"Multilingual language models rely on shared subword vocabularies to represent multiple languages within a limited number of token units. While such sharing is often useful, it can also create cases in which identical surface forms are treated too uniformly across languages, even when their meanings or usage differ. We investigate this limitation through cross-lingual homographs and false friends, and examine whether introducing language information earlier in the tokenization process can improve their treatment. We propose a simple tokenizer-level intervention based on language cues: language-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.17689","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/2607.17689/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":"2026-07-21T02:21:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PlTKzpdV6m7xTOaicKKSVpfdXLFny+jmTGN1L3uVLwtjqd4o/Rq/XhN2jH1JlFJySQ+YmOzMPp0e1WmuaGpoDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T05:26:35.060005Z"},"content_sha256":"6e0f1119dd32657909e21ffd14a629c1e00a41f1cae4747c616f447fc910fa73","schema_version":"1.0","event_id":"sha256:6e0f1119dd32657909e21ffd14a629c1e00a41f1cae4747c616f447fc910fa73"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SEXO3V6WISBU6LMWAQ6UQVY7J4/bundle.json","state_url":"https://pith.science/pith/SEXO3V6WISBU6LMWAQ6UQVY7J4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SEXO3V6WISBU6LMWAQ6UQVY7J4/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":"2026-08-22T05:26:35Z","links":{"resolver":"https://pith.science/pith/SEXO3V6WISBU6LMWAQ6UQVY7J4","bundle":"https://pith.science/pith/SEXO3V6WISBU6LMWAQ6UQVY7J4/bundle.json","state":"https://pith.science/pith/SEXO3V6WISBU6LMWAQ6UQVY7J4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SEXO3V6WISBU6LMWAQ6UQVY7J4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SEXO3V6WISBU6LMWAQ6UQVY7J4","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":"6257bb934bf2c95bb80685f59f3c535aaae7adcc2dc96e44be8a573af7766cb2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-20T08:37:31Z","title_canon_sha256":"8443b74f7564bf88b88ffe15d525364822feb8e1e6b7ba9c48493f7b2c69fba1"},"schema_version":"1.0","source":{"id":"2607.17689","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.17689","created_at":"2026-07-21T02:21:54Z"},{"alias_kind":"arxiv_version","alias_value":"2607.17689v1","created_at":"2026-07-21T02:21:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.17689","created_at":"2026-07-21T02:21:54Z"},{"alias_kind":"pith_short_12","alias_value":"SEXO3V6WISBU","created_at":"2026-07-21T02:21:54Z"},{"alias_kind":"pith_short_16","alias_value":"SEXO3V6WISBU6LMW","created_at":"2026-07-21T02:21:54Z"},{"alias_kind":"pith_short_8","alias_value":"SEXO3V6W","created_at":"2026-07-21T02:21:54Z"}],"graph_snapshots":[{"event_id":"sha256:6e0f1119dd32657909e21ffd14a629c1e00a41f1cae4747c616f447fc910fa73","target":"graph","created_at":"2026-07-21T02:21:54Z","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/2607.17689/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multilingual language models rely on shared subword vocabularies to represent multiple languages within a limited number of token units. While such sharing is often useful, it can also create cases in which identical surface forms are treated too uniformly across languages, even when their meanings or usage differ. We investigate this limitation through cross-lingual homographs and false friends, and examine whether introducing language information earlier in the tokenization process can improve their treatment. We propose a simple tokenizer-level intervention based on language cues: language-","authors_text":"Rotem Brillant, Yuval Pinter","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-20T08:37:31Z","title":"Tokenizing Crosslingual Homographs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.17689","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":"sha256:3f0d2c0f26327f1e170fa406b86006e470d6a808865dc999c8a16809205521a2","target":"record","created_at":"2026-07-21T02:21:54Z","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":"6257bb934bf2c95bb80685f59f3c535aaae7adcc2dc96e44be8a573af7766cb2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-20T08:37:31Z","title_canon_sha256":"8443b74f7564bf88b88ffe15d525364822feb8e1e6b7ba9c48493f7b2c69fba1"},"schema_version":"1.0","source":{"id":"2607.17689","kind":"arxiv","version":1}},"canonical_sha256":"912eedd7d644834f2d96043d48571f4f26d9e3729531353e741ce691b20fac38","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"912eedd7d644834f2d96043d48571f4f26d9e3729531353e741ce691b20fac38","first_computed_at":"2026-07-21T02:21:54.806409Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-21T02:21:54.806409Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"p2PQ+37dUqirEOpJa89MgV5KBabwuf7TyQJyxV1KUuYloseT8rWbcPvfbKW8gZtvOynZCk7SigpwpbwR5YKqBw==","signature_status":"signed_v1","signed_at":"2026-07-21T02:21:54.808954Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.17689","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3f0d2c0f26327f1e170fa406b86006e470d6a808865dc999c8a16809205521a2","sha256:6e0f1119dd32657909e21ffd14a629c1e00a41f1cae4747c616f447fc910fa73"],"state_sha256":"da9923b7c0d94ba9fecb128b6c33c8d53e0baff367672e51ee6baa096149d26b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qoy5ZBnlP7S/6B4oh+gcExBGVEB2zjvJLqg2qON3qxdOPY7Wdmd3mjzb2S1VSawaED8FpTgfaU/EkJ72YtVwBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T05:26:35.065219Z","bundle_sha256":"0e1f244bd2330ef24f08a2d600bf49d8f5f9eb6c391656668cc28f8166098100"}}