{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:Y5ZB7GL22RA4FWZWUIX2UTPML5","short_pith_number":"pith:Y5ZB7GL2","canonical_record":{"source":{"id":"2505.02656","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-05T14:03:22Z","cross_cats_sorted":[],"title_canon_sha256":"74361941cb4a362ced2696d80e1a9b9664be7b8faa2d5507df56b9accee30189","abstract_canon_sha256":"f1ea86030d9d1f8c7f4c72a571876a239e3ce2f3ac0926ddbc74aad082b099bf"},"schema_version":"1.0"},"canonical_sha256":"c7721f997ad441c2db36a22faa4dec5f75f1f74342059bfa40bcf287b69f66ad","source":{"kind":"arxiv","id":"2505.02656","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.02656","created_at":"2026-07-05T11:25:44Z"},{"alias_kind":"arxiv_version","alias_value":"2505.02656v3","created_at":"2026-07-05T11:25:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.02656","created_at":"2026-07-05T11:25:44Z"},{"alias_kind":"pith_short_12","alias_value":"Y5ZB7GL22RA4","created_at":"2026-07-05T11:25:44Z"},{"alias_kind":"pith_short_16","alias_value":"Y5ZB7GL22RA4FWZW","created_at":"2026-07-05T11:25:44Z"},{"alias_kind":"pith_short_8","alias_value":"Y5ZB7GL2","created_at":"2026-07-05T11:25:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:Y5ZB7GL22RA4FWZWUIX2UTPML5","target":"record","payload":{"canonical_record":{"source":{"id":"2505.02656","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-05T14:03:22Z","cross_cats_sorted":[],"title_canon_sha256":"74361941cb4a362ced2696d80e1a9b9664be7b8faa2d5507df56b9accee30189","abstract_canon_sha256":"f1ea86030d9d1f8c7f4c72a571876a239e3ce2f3ac0926ddbc74aad082b099bf"},"schema_version":"1.0"},"canonical_sha256":"c7721f997ad441c2db36a22faa4dec5f75f1f74342059bfa40bcf287b69f66ad","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:25:44.615207Z","signature_b64":"GDx2ntrsrLR/J/isBH16EkkLyjysyfNXAUbs703ahsuySRG9D/HsZ8UYHBvcEdNdOu1LG0DcuVnPTXJeeNdVCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7721f997ad441c2db36a22faa4dec5f75f1f74342059bfa40bcf287b69f66ad","last_reissued_at":"2026-07-05T11:25:44.614716Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:25:44.614716Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.02656","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:25:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MSOIEW5FvVqoxMHZfriJjsDCo9nBKb7Rvsqh4rLj1Q5kRdmMJOOiZZ7ic2pl8PmfQkL0ecawqvgRu3XEKRSYBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T23:13:07.398404Z"},"content_sha256":"73532c5ec4086c779217719fb14adaf60a455ca3b0f7c74e29308b4aafb3b16a","schema_version":"1.0","event_id":"sha256:73532c5ec4086c779217719fb14adaf60a455ca3b0f7c74e29308b4aafb3b16a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:Y5ZB7GL22RA4FWZWUIX2UTPML5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Proper Noun Diacritization for Arabic Wikipedia: A Benchmark Dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kurt Micallef, Mayar Nassar, Nizar Habash, Rawan Bondok, Salam Khalifa","submitted_at":"2025-05-05T14:03:22Z","abstract_excerpt":"Proper nouns in Arabic Wikipedia are frequently undiacritized, creating ambiguity in pronunciation and interpretation, especially for transliterated named entities of foreign origin. While transliteration and diacritization have been well-studied separately in Arabic NLP, their intersection remains underexplored. In this paper, we introduce a new manually diacritized dataset of Arabic proper nouns of various origins with their English Wikipedia equivalent glosses, and present the challenges and guidelines we followed to create it. We benchmark GPT-4o on the task of recovering full diacritizati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.02656","kind":"arxiv","version":3},"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/2505.02656/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":"2026-07-05T11:25:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/noICtlpHpGDjSSb6zRYUWg6o0d6inMqErWyCu2UOIGpyA9Li/WsXgbsXpRunNIvBROknDlWp04cHWNG1RXtAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T23:13:07.398784Z"},"content_sha256":"6c4f209e1d23dd6f045173f48d767a730b1607296ccdbc3c8e5a451fbd134830","schema_version":"1.0","event_id":"sha256:6c4f209e1d23dd6f045173f48d767a730b1607296ccdbc3c8e5a451fbd134830"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y5ZB7GL22RA4FWZWUIX2UTPML5/bundle.json","state_url":"https://pith.science/pith/Y5ZB7GL22RA4FWZWUIX2UTPML5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y5ZB7GL22RA4FWZWUIX2UTPML5/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":"2026-07-08T23:13:07Z","links":{"resolver":"https://pith.science/pith/Y5ZB7GL22RA4FWZWUIX2UTPML5","bundle":"https://pith.science/pith/Y5ZB7GL22RA4FWZWUIX2UTPML5/bundle.json","state":"https://pith.science/pith/Y5ZB7GL22RA4FWZWUIX2UTPML5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y5ZB7GL22RA4FWZWUIX2UTPML5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:Y5ZB7GL22RA4FWZWUIX2UTPML5","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":"f1ea86030d9d1f8c7f4c72a571876a239e3ce2f3ac0926ddbc74aad082b099bf","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-05T14:03:22Z","title_canon_sha256":"74361941cb4a362ced2696d80e1a9b9664be7b8faa2d5507df56b9accee30189"},"schema_version":"1.0","source":{"id":"2505.02656","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.02656","created_at":"2026-07-05T11:25:44Z"},{"alias_kind":"arxiv_version","alias_value":"2505.02656v3","created_at":"2026-07-05T11:25:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.02656","created_at":"2026-07-05T11:25:44Z"},{"alias_kind":"pith_short_12","alias_value":"Y5ZB7GL22RA4","created_at":"2026-07-05T11:25:44Z"},{"alias_kind":"pith_short_16","alias_value":"Y5ZB7GL22RA4FWZW","created_at":"2026-07-05T11:25:44Z"},{"alias_kind":"pith_short_8","alias_value":"Y5ZB7GL2","created_at":"2026-07-05T11:25:44Z"}],"graph_snapshots":[{"event_id":"sha256:6c4f209e1d23dd6f045173f48d767a730b1607296ccdbc3c8e5a451fbd134830","target":"graph","created_at":"2026-07-05T11:25:44Z","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/2505.02656/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Proper nouns in Arabic Wikipedia are frequently undiacritized, creating ambiguity in pronunciation and interpretation, especially for transliterated named entities of foreign origin. While transliteration and diacritization have been well-studied separately in Arabic NLP, their intersection remains underexplored. In this paper, we introduce a new manually diacritized dataset of Arabic proper nouns of various origins with their English Wikipedia equivalent glosses, and present the challenges and guidelines we followed to create it. We benchmark GPT-4o on the task of recovering full diacritizati","authors_text":"Kurt Micallef, Mayar Nassar, Nizar Habash, Rawan Bondok, Salam Khalifa","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-05T14:03:22Z","title":"Proper Noun Diacritization for Arabic Wikipedia: A Benchmark Dataset"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.02656","kind":"arxiv","version":3},"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":"sha256:73532c5ec4086c779217719fb14adaf60a455ca3b0f7c74e29308b4aafb3b16a","target":"record","created_at":"2026-07-05T11:25:44Z","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":"f1ea86030d9d1f8c7f4c72a571876a239e3ce2f3ac0926ddbc74aad082b099bf","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-05T14:03:22Z","title_canon_sha256":"74361941cb4a362ced2696d80e1a9b9664be7b8faa2d5507df56b9accee30189"},"schema_version":"1.0","source":{"id":"2505.02656","kind":"arxiv","version":3}},"canonical_sha256":"c7721f997ad441c2db36a22faa4dec5f75f1f74342059bfa40bcf287b69f66ad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c7721f997ad441c2db36a22faa4dec5f75f1f74342059bfa40bcf287b69f66ad","first_computed_at":"2026-07-05T11:25:44.614716Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:25:44.614716Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GDx2ntrsrLR/J/isBH16EkkLyjysyfNXAUbs703ahsuySRG9D/HsZ8UYHBvcEdNdOu1LG0DcuVnPTXJeeNdVCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:25:44.615207Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.02656","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:73532c5ec4086c779217719fb14adaf60a455ca3b0f7c74e29308b4aafb3b16a","sha256:6c4f209e1d23dd6f045173f48d767a730b1607296ccdbc3c8e5a451fbd134830"],"state_sha256":"e7ace607249129b21437349f219e923e7289d0efe83ad26374c133fc2b293c77"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j0lgePZWlO/tSNuUGthKSILAAvpwrPqq+qd1/lD+g9xdSSeG3alyzEPlF/rFnX5JwmWpvmTOlpXAOM5RqveqCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T23:13:07.400899Z","bundle_sha256":"e025d251debcd525fed94777d001582092c17af446e8be723ed38ed9a3d9732e"}}