{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4IZWWX7JZM4TRY5DSIITPJVQ6S","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":"cba9e8325b2e11a69903147d9157045a39ba07104a70badc5df7360e0257a6ef","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-03T16:05:20Z","title_canon_sha256":"f8ac2c720e95d2c5051310ea8995f5e9c7e41bb08d2171e00afa25f58552964b"},"schema_version":"1.0","source":{"id":"2407.03236","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.03236","created_at":"2026-07-05T08:43:29Z"},{"alias_kind":"arxiv_version","alias_value":"2407.03236v3","created_at":"2026-07-05T08:43:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.03236","created_at":"2026-07-05T08:43:29Z"},{"alias_kind":"pith_short_12","alias_value":"4IZWWX7JZM4T","created_at":"2026-07-05T08:43:29Z"},{"alias_kind":"pith_short_16","alias_value":"4IZWWX7JZM4TRY5D","created_at":"2026-07-05T08:43:29Z"},{"alias_kind":"pith_short_8","alias_value":"4IZWWX7J","created_at":"2026-07-05T08:43:29Z"}],"graph_snapshots":[{"event_id":"sha256:6d570f5ae3edceb5ea2609d0ab934f3e9f3dd70bdba6ccc0e46118dfbc71b5f0","target":"graph","created_at":"2026-07-05T08:43:29Z","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/2407.03236/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tashkeel, or Arabic Text Diacritization (ATD), greatly enhances the comprehension of Arabic text by removing ambiguity and minimizing the risk of misinterpretations caused by its absence. It plays a crucial role in improving Arabic text processing, particularly in applications such as text-to-speech and machine translation. This paper introduces a new approach to training ATD models. First, we finetuned two transformers, encoder-only and encoder-decoder, that were initialized from a pretrained character-based BERT. Then, we applied the Noisy-Student approach to boost the performance of the bes","authors_text":"Ahmad Ghannam, Faris Alasmary, Orjuwan Zaafarani","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-03T16:05:20Z","title":"CATT: Character-based Arabic Tashkeel Transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.03236","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":"sha256:9eff7a00c41000590fe76aa3834ba04e4cf097f9866c22e14badb4d0bbbb96f1","target":"record","created_at":"2026-07-05T08:43:29Z","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":"cba9e8325b2e11a69903147d9157045a39ba07104a70badc5df7360e0257a6ef","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-03T16:05:20Z","title_canon_sha256":"f8ac2c720e95d2c5051310ea8995f5e9c7e41bb08d2171e00afa25f58552964b"},"schema_version":"1.0","source":{"id":"2407.03236","kind":"arxiv","version":3}},"canonical_sha256":"e2336b5fe9cb3938e3a3921137a6b0f4bece426da3fa2c00c3e93ff8a360ae32","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e2336b5fe9cb3938e3a3921137a6b0f4bece426da3fa2c00c3e93ff8a360ae32","first_computed_at":"2026-07-05T08:43:29.838867Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:43:29.838867Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vX7NWaa2rEA3L/4YD2p1LDBUtAtuR/DkqNT9C/Tleg2fKimmDf34NIUnpkSoTbz5q05yJ1KX/zr4mdDCNI60DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:43:29.839349Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.03236","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9eff7a00c41000590fe76aa3834ba04e4cf097f9866c22e14badb4d0bbbb96f1","sha256:6d570f5ae3edceb5ea2609d0ab934f3e9f3dd70bdba6ccc0e46118dfbc71b5f0"],"state_sha256":"185c0e50309672dd542eb74cd3bf7462927a3acc32dd5e4c2e701198e77d4267"}