{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GQXR6QBEY74AORCIRBO2EPTJC3","short_pith_number":"pith:GQXR6QBE","schema_version":"1.0","canonical_sha256":"342f1f4024c7f8074448885da23e6916d62d7c42f3825f569d288ff233f65b17","source":{"kind":"arxiv","id":"2605.25928","version":1},"attestation_state":"computed","paper":{"title":"Thaka at KSAA-2026 Task 2: Regularized Fine-Tuning for Arabic Speech Diacritization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Abdullah Aldahlawi, Hassan Alqaeri, Meshal Alamr","submitted_at":"2026-05-25T15:07:48Z","abstract_excerpt":"We describe the winning system for Task 2 of the KSAA-2026 Shared Task on Arabic Speech Dictation with Automatic Diacritization. The task requires producing fully diacritized Arabic text from speech audio and undiacritized transcripts, with only 2,327 training samples available and no external data permitted. Our system fine-tunes CATT-Whisper, a character-level multimodal model combining a pretrained CATT text encoder with a frozen Whisper speech encoder. The key to our approach is training regularization: R-Drop consistency regularization, Optuna-optimized hyperparameters with high weight de"},"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":"2605.25928","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-25T15:07:48Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"3dd417da5f04adb4e6521cea3418f5ed1d58d0c5a869b8b8a78895a5ddb0ff18","abstract_canon_sha256":"d07fbdb4e92a33c065573b8ab1bc27788d5411653fa758a0c18d7cc0c13aeb5e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:05:18.786044Z","signature_b64":"KtGVyWKGJ2s3v2giOpmYr2jnl+Hp9y39/JTuraroDql5X9wsFofT/7l4TaadwYeMzGAbtYNF54IXHmQ7bSWxBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"342f1f4024c7f8074448885da23e6916d62d7c42f3825f569d288ff233f65b17","last_reissued_at":"2026-05-26T02:05:18.785425Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:05:18.785425Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Thaka at KSAA-2026 Task 2: Regularized Fine-Tuning for Arabic Speech Diacritization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Abdullah Aldahlawi, Hassan Alqaeri, Meshal Alamr","submitted_at":"2026-05-25T15:07:48Z","abstract_excerpt":"We describe the winning system for Task 2 of the KSAA-2026 Shared Task on Arabic Speech Dictation with Automatic Diacritization. The task requires producing fully diacritized Arabic text from speech audio and undiacritized transcripts, with only 2,327 training samples available and no external data permitted. Our system fine-tunes CATT-Whisper, a character-level multimodal model combining a pretrained CATT text encoder with a frozen Whisper speech encoder. The key to our approach is training regularization: R-Drop consistency regularization, Optuna-optimized hyperparameters with high weight de"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.25928","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/2605.25928/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":"2605.25928","created_at":"2026-05-26T02:05:18.785526+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.25928v1","created_at":"2026-05-26T02:05:18.785526+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.25928","created_at":"2026-05-26T02:05:18.785526+00:00"},{"alias_kind":"pith_short_12","alias_value":"GQXR6QBEY74A","created_at":"2026-05-26T02:05:18.785526+00:00"},{"alias_kind":"pith_short_16","alias_value":"GQXR6QBEY74AORCI","created_at":"2026-05-26T02:05:18.785526+00:00"},{"alias_kind":"pith_short_8","alias_value":"GQXR6QBE","created_at":"2026-05-26T02:05:18.785526+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/GQXR6QBEY74AORCIRBO2EPTJC3","json":"https://pith.science/pith/GQXR6QBEY74AORCIRBO2EPTJC3.json","graph_json":"https://pith.science/api/pith-number/GQXR6QBEY74AORCIRBO2EPTJC3/graph.json","events_json":"https://pith.science/api/pith-number/GQXR6QBEY74AORCIRBO2EPTJC3/events.json","paper":"https://pith.science/paper/GQXR6QBE"},"agent_actions":{"view_html":"https://pith.science/pith/GQXR6QBEY74AORCIRBO2EPTJC3","download_json":"https://pith.science/pith/GQXR6QBEY74AORCIRBO2EPTJC3.json","view_paper":"https://pith.science/paper/GQXR6QBE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.25928&json=true","fetch_graph":"https://pith.science/api/pith-number/GQXR6QBEY74AORCIRBO2EPTJC3/graph.json","fetch_events":"https://pith.science/api/pith-number/GQXR6QBEY74AORCIRBO2EPTJC3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GQXR6QBEY74AORCIRBO2EPTJC3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GQXR6QBEY74AORCIRBO2EPTJC3/action/storage_attestation","attest_author":"https://pith.science/pith/GQXR6QBEY74AORCIRBO2EPTJC3/action/author_attestation","sign_citation":"https://pith.science/pith/GQXR6QBEY74AORCIRBO2EPTJC3/action/citation_signature","submit_replication":"https://pith.science/pith/GQXR6QBEY74AORCIRBO2EPTJC3/action/replication_record"}},"created_at":"2026-05-26T02:05:18.785526+00:00","updated_at":"2026-05-26T02:05:18.785526+00:00"}