{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ZPLJFQYXDXYQNJBBQDWM2SN4ED","short_pith_number":"pith:ZPLJFQYX","canonical_record":{"source":{"id":"2507.15142","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-20T22:35:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"aa1a08360d9248ed52da7debf1f632202e7b120314dc362e526c2a88091c560b","abstract_canon_sha256":"da61ac8603786f76bee5c619a507181a9343225fe78c8e9948218b78fda04013"},"schema_version":"1.0"},"canonical_sha256":"cbd692c3171df106a42180eccd49bc20eb59778f812359ebf4a44a6ebf6209b4","source":{"kind":"arxiv","id":"2507.15142","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.15142","created_at":"2026-07-05T11:40:19Z"},{"alias_kind":"arxiv_version","alias_value":"2507.15142v1","created_at":"2026-07-05T11:40:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.15142","created_at":"2026-07-05T11:40:19Z"},{"alias_kind":"pith_short_12","alias_value":"ZPLJFQYXDXYQ","created_at":"2026-07-05T11:40:19Z"},{"alias_kind":"pith_short_16","alias_value":"ZPLJFQYXDXYQNJBB","created_at":"2026-07-05T11:40:19Z"},{"alias_kind":"pith_short_8","alias_value":"ZPLJFQYX","created_at":"2026-07-05T11:40:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ZPLJFQYXDXYQNJBBQDWM2SN4ED","target":"record","payload":{"canonical_record":{"source":{"id":"2507.15142","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-20T22:35:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"aa1a08360d9248ed52da7debf1f632202e7b120314dc362e526c2a88091c560b","abstract_canon_sha256":"da61ac8603786f76bee5c619a507181a9343225fe78c8e9948218b78fda04013"},"schema_version":"1.0"},"canonical_sha256":"cbd692c3171df106a42180eccd49bc20eb59778f812359ebf4a44a6ebf6209b4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:40:19.093500Z","signature_b64":"95DAxAM2/+uR2oEhRtRCv0CX7kRtlk5u9oWQX2i3SA73rUD8QNWf5pluACbWVKHDtojGyte92QVYsLWAU37uCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cbd692c3171df106a42180eccd49bc20eb59778f812359ebf4a44a6ebf6209b4","last_reissued_at":"2026-07-05T11:40:19.092998Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:40:19.092998Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.15142","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":"2026-07-05T11:40:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ybFRRRqSjxJ+B/Lg8FG1C0GAmJiaEggRpSKxof3waW8R8iKGz1+YQxauG4Av10U6VsXpXt6Z6Q09/0jv51i+CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:37:56.192953Z"},"content_sha256":"f348d4537268bf51af9e3fe65807ab9462f5e1683268539e4fa180c4806614f4","schema_version":"1.0","event_id":"sha256:f348d4537268bf51af9e3fe65807ab9462f5e1683268539e4fa180c4806614f4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ZPLJFQYXDXYQNJBBQDWM2SN4ED","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Case Against Implicit Standards: Homophone Normalization in Machine Translation for Languages that use the Ge'ez Script","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Atnafu Lambebo Tonja, Hellina Hailu Nigatu, Henok Biadglign Ademtew, Hizkel Mitiku Alemayehu, Negasi Haile Abadi, Seid Muhie Yimam, Tadesse Destaw Belay","submitted_at":"2025-07-20T22:35:08Z","abstract_excerpt":"Homophone normalization, where characters that have the same sound in a writing script are mapped to one character, is a pre-processing step applied in Amharic Natural Language Processing (NLP) literature. While this may improve performance reported by automatic metrics, it also results in models that are not able to understand different forms of writing in a single language. Further, there might be impacts in transfer learning, where models trained on normalized data do not generalize well to other languages. In this paper, we experiment with monolingual training and cross-lingual transfer to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.15142","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/2507.15142/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":"2026-07-05T11:40:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"REpJFRgzP/Ces3nzTN22565twxFtuXOupSo7LSM86yYVH5/QhVRjCxA22GkaqV/bqrUD51HeP8LSlOGrMzo8CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:37:56.193560Z"},"content_sha256":"4c281c46062d0319dfc36cc3b546d267b9ccc868523f58d5ef9a34cf95a2956b","schema_version":"1.0","event_id":"sha256:4c281c46062d0319dfc36cc3b546d267b9ccc868523f58d5ef9a34cf95a2956b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZPLJFQYXDXYQNJBBQDWM2SN4ED/bundle.json","state_url":"https://pith.science/pith/ZPLJFQYXDXYQNJBBQDWM2SN4ED/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZPLJFQYXDXYQNJBBQDWM2SN4ED/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":"2026-07-07T04:37:56Z","links":{"resolver":"https://pith.science/pith/ZPLJFQYXDXYQNJBBQDWM2SN4ED","bundle":"https://pith.science/pith/ZPLJFQYXDXYQNJBBQDWM2SN4ED/bundle.json","state":"https://pith.science/pith/ZPLJFQYXDXYQNJBBQDWM2SN4ED/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZPLJFQYXDXYQNJBBQDWM2SN4ED/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZPLJFQYXDXYQNJBBQDWM2SN4ED","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":"da61ac8603786f76bee5c619a507181a9343225fe78c8e9948218b78fda04013","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-20T22:35:08Z","title_canon_sha256":"aa1a08360d9248ed52da7debf1f632202e7b120314dc362e526c2a88091c560b"},"schema_version":"1.0","source":{"id":"2507.15142","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.15142","created_at":"2026-07-05T11:40:19Z"},{"alias_kind":"arxiv_version","alias_value":"2507.15142v1","created_at":"2026-07-05T11:40:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.15142","created_at":"2026-07-05T11:40:19Z"},{"alias_kind":"pith_short_12","alias_value":"ZPLJFQYXDXYQ","created_at":"2026-07-05T11:40:19Z"},{"alias_kind":"pith_short_16","alias_value":"ZPLJFQYXDXYQNJBB","created_at":"2026-07-05T11:40:19Z"},{"alias_kind":"pith_short_8","alias_value":"ZPLJFQYX","created_at":"2026-07-05T11:40:19Z"}],"graph_snapshots":[{"event_id":"sha256:4c281c46062d0319dfc36cc3b546d267b9ccc868523f58d5ef9a34cf95a2956b","target":"graph","created_at":"2026-07-05T11:40:19Z","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/2507.15142/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Homophone normalization, where characters that have the same sound in a writing script are mapped to one character, is a pre-processing step applied in Amharic Natural Language Processing (NLP) literature. While this may improve performance reported by automatic metrics, it also results in models that are not able to understand different forms of writing in a single language. Further, there might be impacts in transfer learning, where models trained on normalized data do not generalize well to other languages. In this paper, we experiment with monolingual training and cross-lingual transfer to","authors_text":"Atnafu Lambebo Tonja, Hellina Hailu Nigatu, Henok Biadglign Ademtew, Hizkel Mitiku Alemayehu, Negasi Haile Abadi, Seid Muhie Yimam, Tadesse Destaw Belay","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-20T22:35:08Z","title":"A Case Against Implicit Standards: Homophone Normalization in Machine Translation for Languages that use the Ge'ez Script"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.15142","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:f348d4537268bf51af9e3fe65807ab9462f5e1683268539e4fa180c4806614f4","target":"record","created_at":"2026-07-05T11:40:19Z","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":"da61ac8603786f76bee5c619a507181a9343225fe78c8e9948218b78fda04013","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-20T22:35:08Z","title_canon_sha256":"aa1a08360d9248ed52da7debf1f632202e7b120314dc362e526c2a88091c560b"},"schema_version":"1.0","source":{"id":"2507.15142","kind":"arxiv","version":1}},"canonical_sha256":"cbd692c3171df106a42180eccd49bc20eb59778f812359ebf4a44a6ebf6209b4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cbd692c3171df106a42180eccd49bc20eb59778f812359ebf4a44a6ebf6209b4","first_computed_at":"2026-07-05T11:40:19.092998Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:40:19.092998Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"95DAxAM2/+uR2oEhRtRCv0CX7kRtlk5u9oWQX2i3SA73rUD8QNWf5pluACbWVKHDtojGyte92QVYsLWAU37uCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:40:19.093500Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.15142","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f348d4537268bf51af9e3fe65807ab9462f5e1683268539e4fa180c4806614f4","sha256:4c281c46062d0319dfc36cc3b546d267b9ccc868523f58d5ef9a34cf95a2956b"],"state_sha256":"cc45f21b98302fe168e355236ab7479ac984ebae662b257c92ae977472fdfcb2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tnxcEicJEDEcE/epI7pMOb02vmp6luGdf+kTQ8//lrQ8YnDGD+TcQ3BFXffg0149/csTregtwmv6QKusVCaLBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T04:37:56.196891Z","bundle_sha256":"894219bcab5154fca379917830f73c1495b112e62ae7baf2d4c57d98ad8ef03f"}}