{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:E2LOO2N3TNPAG73AGWYB47KU43","short_pith_number":"pith:E2LOO2N3","canonical_record":{"source":{"id":"2406.05760","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-09T12:29:55Z","cross_cats_sorted":[],"title_canon_sha256":"a8576d6e5ad93b8ad009aaffa79c06976397521b79b1749e8d107591b6e12eef","abstract_canon_sha256":"333724393ef5b0c7380a23c83e7966d00cb8837875753b4e180a41270fb72042"},"schema_version":"1.0"},"canonical_sha256":"2696e769bb9b5e037f6035b01e7d54e6c619db13a72271b7003b26817d86b9a5","source":{"kind":"arxiv","id":"2406.05760","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.05760","created_at":"2026-07-05T08:29:33Z"},{"alias_kind":"arxiv_version","alias_value":"2406.05760v1","created_at":"2026-07-05T08:29:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.05760","created_at":"2026-07-05T08:29:33Z"},{"alias_kind":"pith_short_12","alias_value":"E2LOO2N3TNPA","created_at":"2026-07-05T08:29:33Z"},{"alias_kind":"pith_short_16","alias_value":"E2LOO2N3TNPAG73A","created_at":"2026-07-05T08:29:33Z"},{"alias_kind":"pith_short_8","alias_value":"E2LOO2N3","created_at":"2026-07-05T08:29:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:E2LOO2N3TNPAG73AGWYB47KU43","target":"record","payload":{"canonical_record":{"source":{"id":"2406.05760","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-09T12:29:55Z","cross_cats_sorted":[],"title_canon_sha256":"a8576d6e5ad93b8ad009aaffa79c06976397521b79b1749e8d107591b6e12eef","abstract_canon_sha256":"333724393ef5b0c7380a23c83e7966d00cb8837875753b4e180a41270fb72042"},"schema_version":"1.0"},"canonical_sha256":"2696e769bb9b5e037f6035b01e7d54e6c619db13a72271b7003b26817d86b9a5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:29:33.382271Z","signature_b64":"S01GU38yHsATyBgMdTL/hZ8MlIFRfxlK9aQXRUVH05JbwTDwJ4z16dURCkIrixQctU4Z0qjfo1k39IS/9q3OBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2696e769bb9b5e037f6035b01e7d54e6c619db13a72271b7003b26817d86b9a5","last_reissued_at":"2026-07-05T08:29:33.381893Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:29:33.381893Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.05760","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":"2026-07-05T08:29:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aa1SAuhSgLP7aM8wxCELv+zSQ8Kf5Db2KEwcw8Hekh+a/wz8cGo8VbfOOw0r5gPM8bfCYkUXY/rT+SXlvt9iAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T23:19:17.474262Z"},"content_sha256":"ff5fd347a31668a3c81dea52f97f9df38b2cbf6983a9a81731ae2fdc67c2c730","schema_version":"1.0","event_id":"sha256:ff5fd347a31668a3c81dea52f97f9df38b2cbf6983a9a81731ae2fdc67c2c730"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:E2LOO2N3TNPAG73AGWYB47KU43","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Arabic Diacritics in the Wild: Exploiting Opportunities for Improved Diacritization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Go Inoue, Nizar Habash, Ossama Obeid, Salman Elgamal, Tameem Kabbani","submitted_at":"2024-06-09T12:29:55Z","abstract_excerpt":"The widespread absence of diacritical marks in Arabic text poses a significant challenge for Arabic natural language processing (NLP). This paper explores instances of naturally occurring diacritics, referred to as \"diacritics in the wild,\" to unveil patterns and latent information across six diverse genres: news articles, novels, children's books, poetry, political documents, and ChatGPT outputs. We present a new annotated dataset that maps real-world partially diacritized words to their maximal full diacritization in context. Additionally, we propose extensions to the analyze-and-disambiguat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.05760","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/2406.05760/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":"2026-07-05T08:29:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ky9JP7I010ws5KB9wNT1kN9i8peJNN2sI78+KTtgEzwtCYUSq2GKfz8hLLJLC910el8XCqgURfF8e1QsO72oBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T23:19:17.474762Z"},"content_sha256":"8efde4362735812e6ad790764f43c030d5cf741be7a003832c0005c805e9b110","schema_version":"1.0","event_id":"sha256:8efde4362735812e6ad790764f43c030d5cf741be7a003832c0005c805e9b110"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/E2LOO2N3TNPAG73AGWYB47KU43/bundle.json","state_url":"https://pith.science/pith/E2LOO2N3TNPAG73AGWYB47KU43/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/E2LOO2N3TNPAG73AGWYB47KU43/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":"2026-08-09T23:19:17Z","links":{"resolver":"https://pith.science/pith/E2LOO2N3TNPAG73AGWYB47KU43","bundle":"https://pith.science/pith/E2LOO2N3TNPAG73AGWYB47KU43/bundle.json","state":"https://pith.science/pith/E2LOO2N3TNPAG73AGWYB47KU43/state.json","well_known_bundle":"https://pith.science/.well-known/pith/E2LOO2N3TNPAG73AGWYB47KU43/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:E2LOO2N3TNPAG73AGWYB47KU43","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":"333724393ef5b0c7380a23c83e7966d00cb8837875753b4e180a41270fb72042","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-09T12:29:55Z","title_canon_sha256":"a8576d6e5ad93b8ad009aaffa79c06976397521b79b1749e8d107591b6e12eef"},"schema_version":"1.0","source":{"id":"2406.05760","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.05760","created_at":"2026-07-05T08:29:33Z"},{"alias_kind":"arxiv_version","alias_value":"2406.05760v1","created_at":"2026-07-05T08:29:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.05760","created_at":"2026-07-05T08:29:33Z"},{"alias_kind":"pith_short_12","alias_value":"E2LOO2N3TNPA","created_at":"2026-07-05T08:29:33Z"},{"alias_kind":"pith_short_16","alias_value":"E2LOO2N3TNPAG73A","created_at":"2026-07-05T08:29:33Z"},{"alias_kind":"pith_short_8","alias_value":"E2LOO2N3","created_at":"2026-07-05T08:29:33Z"}],"graph_snapshots":[{"event_id":"sha256:8efde4362735812e6ad790764f43c030d5cf741be7a003832c0005c805e9b110","target":"graph","created_at":"2026-07-05T08:29:33Z","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/2406.05760/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The widespread absence of diacritical marks in Arabic text poses a significant challenge for Arabic natural language processing (NLP). This paper explores instances of naturally occurring diacritics, referred to as \"diacritics in the wild,\" to unveil patterns and latent information across six diverse genres: news articles, novels, children's books, poetry, political documents, and ChatGPT outputs. We present a new annotated dataset that maps real-world partially diacritized words to their maximal full diacritization in context. Additionally, we propose extensions to the analyze-and-disambiguat","authors_text":"Go Inoue, Nizar Habash, Ossama Obeid, Salman Elgamal, Tameem Kabbani","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-09T12:29:55Z","title":"Arabic Diacritics in the Wild: Exploiting Opportunities for Improved Diacritization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.05760","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:ff5fd347a31668a3c81dea52f97f9df38b2cbf6983a9a81731ae2fdc67c2c730","target":"record","created_at":"2026-07-05T08:29:33Z","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":"333724393ef5b0c7380a23c83e7966d00cb8837875753b4e180a41270fb72042","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-09T12:29:55Z","title_canon_sha256":"a8576d6e5ad93b8ad009aaffa79c06976397521b79b1749e8d107591b6e12eef"},"schema_version":"1.0","source":{"id":"2406.05760","kind":"arxiv","version":1}},"canonical_sha256":"2696e769bb9b5e037f6035b01e7d54e6c619db13a72271b7003b26817d86b9a5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2696e769bb9b5e037f6035b01e7d54e6c619db13a72271b7003b26817d86b9a5","first_computed_at":"2026-07-05T08:29:33.381893Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:29:33.381893Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S01GU38yHsATyBgMdTL/hZ8MlIFRfxlK9aQXRUVH05JbwTDwJ4z16dURCkIrixQctU4Z0qjfo1k39IS/9q3OBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:29:33.382271Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.05760","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ff5fd347a31668a3c81dea52f97f9df38b2cbf6983a9a81731ae2fdc67c2c730","sha256:8efde4362735812e6ad790764f43c030d5cf741be7a003832c0005c805e9b110"],"state_sha256":"3e41f150f96212a9d6edca6b897285756ee25b59afc7f94a84808d627454b25a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2ujT0THdq6UOUTq4ORUUKvEMA27KyL9cQfA3V0SzndoT5QcVLUJnHXN3LySnVTZqDVh2pzCwxo1TSR4UPS2oBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T23:19:17.479746Z","bundle_sha256":"dd4cc8eb5efd7cff0724d780467c52d03361d5ae084fd6eaf1feb2ebc77ace8f"}}