{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LD7SQQ4SZIXOP3NXENVBEH4NEG","short_pith_number":"pith:LD7SQQ4S","schema_version":"1.0","canonical_sha256":"58ff284392ca2ee7edb7236a121f8d21bd42dafef93a04b3e8629b883eecca4b","source":{"kind":"arxiv","id":"2504.21635","version":2},"attestation_state":"computed","paper":{"title":"Sadeed: Advancing Arabic Diacritization Through Small Language Model","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Khalil Hennara, Mohamed Motaism Hamed, Muhammad Hreden, Safwan AlModhayan, Sara Chrouf, Zeina Aldallal","submitted_at":"2025-04-30T13:37:24Z","abstract_excerpt":"Arabic text diacritization remains a persistent challenge in natural language processing due to the language's morphological richness. In this paper, we introduce Sadeed, a novel approach based on a fine-tuned decoder-only language model adapted from Kuwain 1.5B Hennara et al. [2025], a compact model originally trained on diverse Arabic corpora. Sadeed is fine-tuned on carefully curated, high-quality diacritized datasets, constructed through a rigorous data-cleaning and normalization pipeline. Despite utilizing modest computational resources, Sadeed achieves competitive results compared to pro"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2504.21635","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-30T13:37:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e1d3092d88cac482ff71c101d8aa9149c8438bf6bd8ff51c9956a8ed74c0ead1","abstract_canon_sha256":"76fcc5b1a8c418783977f4645cbe0ed082c675cc207df18c2faeed4af7be073b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:56:56.701976Z","signature_b64":"37bqabXImU3jfRykgftF9eegaMyH3o1em6k3nHlRdbHRyI/DrqVQzPvft1VGMZJY8n52+Ed+yor0/+/91w8EBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58ff284392ca2ee7edb7236a121f8d21bd42dafef93a04b3e8629b883eecca4b","last_reissued_at":"2026-07-05T11:56:56.701465Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:56:56.701465Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sadeed: Advancing Arabic Diacritization Through Small Language Model","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Khalil Hennara, Mohamed Motaism Hamed, Muhammad Hreden, Safwan AlModhayan, Sara Chrouf, Zeina Aldallal","submitted_at":"2025-04-30T13:37:24Z","abstract_excerpt":"Arabic text diacritization remains a persistent challenge in natural language processing due to the language's morphological richness. In this paper, we introduce Sadeed, a novel approach based on a fine-tuned decoder-only language model adapted from Kuwain 1.5B Hennara et al. [2025], a compact model originally trained on diverse Arabic corpora. Sadeed is fine-tuned on carefully curated, high-quality diacritized datasets, constructed through a rigorous data-cleaning and normalization pipeline. Despite utilizing modest computational resources, Sadeed achieves competitive results compared to pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.21635","kind":"arxiv","version":2},"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/2504.21635/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2504.21635","created_at":"2026-07-05T11:56:56.701525+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.21635v2","created_at":"2026-07-05T11:56:56.701525+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.21635","created_at":"2026-07-05T11:56:56.701525+00:00"},{"alias_kind":"pith_short_12","alias_value":"LD7SQQ4SZIXO","created_at":"2026-07-05T11:56:56.701525+00:00"},{"alias_kind":"pith_short_16","alias_value":"LD7SQQ4SZIXOP3NX","created_at":"2026-07-05T11:56:56.701525+00:00"},{"alias_kind":"pith_short_8","alias_value":"LD7SQQ4S","created_at":"2026-07-05T11:56:56.701525+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LD7SQQ4SZIXOP3NXENVBEH4NEG","json":"https://pith.science/pith/LD7SQQ4SZIXOP3NXENVBEH4NEG.json","graph_json":"https://pith.science/api/pith-number/LD7SQQ4SZIXOP3NXENVBEH4NEG/graph.json","events_json":"https://pith.science/api/pith-number/LD7SQQ4SZIXOP3NXENVBEH4NEG/events.json","paper":"https://pith.science/paper/LD7SQQ4S"},"agent_actions":{"view_html":"https://pith.science/pith/LD7SQQ4SZIXOP3NXENVBEH4NEG","download_json":"https://pith.science/pith/LD7SQQ4SZIXOP3NXENVBEH4NEG.json","view_paper":"https://pith.science/paper/LD7SQQ4S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.21635&json=true","fetch_graph":"https://pith.science/api/pith-number/LD7SQQ4SZIXOP3NXENVBEH4NEG/graph.json","fetch_events":"https://pith.science/api/pith-number/LD7SQQ4SZIXOP3NXENVBEH4NEG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LD7SQQ4SZIXOP3NXENVBEH4NEG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LD7SQQ4SZIXOP3NXENVBEH4NEG/action/storage_attestation","attest_author":"https://pith.science/pith/LD7SQQ4SZIXOP3NXENVBEH4NEG/action/author_attestation","sign_citation":"https://pith.science/pith/LD7SQQ4SZIXOP3NXENVBEH4NEG/action/citation_signature","submit_replication":"https://pith.science/pith/LD7SQQ4SZIXOP3NXENVBEH4NEG/action/replication_record"}},"created_at":"2026-07-05T11:56:56.701525+00:00","updated_at":"2026-07-05T11:56:56.701525+00:00"}