{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DUNW7PW5B6YLTT5VHD3IVHU2Q7","short_pith_number":"pith:DUNW7PW5","schema_version":"1.0","canonical_sha256":"1d1b6fbedd0fb0b9cfb538f68a9e9a87d732b8f2803dff1859f5a66ee186981b","source":{"kind":"arxiv","id":"2606.24086","version":1},"attestation_state":"computed","paper":{"title":"A Fusion-Aware Two-Stage Framework for Mispronunciation Detection and Diagnosis in Low-Resource Modern Standard Arabic","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Gongping Huang, Jacob Benesty, Jingdong Chen, Jing Yang, Pan Li, Shuqing Zhang, Ting Dang, Yongyi Deng","submitted_at":"2026-06-23T03:02:00Z","abstract_excerpt":"Accurate phoneme recognition is pivotal for mispronunciation detection and diagnosis (MDD) in modern standard Arabic (MSA), yet remains constrained by data scarcity and the synthetic-real domain gap. This work proposes a two-stage end-to-end framework. It integrates a pre-trained encoder with causal dilated temporal convolutional networks to preserve fine-grained phonetic variations. A hierarchical two-stage strategy first learns general mappings from native/synthetic corpora, then adapts to scarce real learner data to mitigate domain shift without over-correction. Prediction stability is furt"},"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":"2606.24086","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-06-23T03:02:00Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"8eec8cdc6874792048467b7e73fc6a8b3a7359626384469723da2393743cabdc","abstract_canon_sha256":"7f590a20562db32227bb0091cc01dc4d5fdb080c67a991c3a695019f36d9bb1f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-24T01:14:39.973247Z","signature_b64":"0nkdZCq2lfj2D6vHwGLkLCYKB8mRf27EIz2g+5n+RK9Dl6NT58Ij0ZpX8Ipz+N/OBAVVQXCZ5QcRpRdj4r5DDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d1b6fbedd0fb0b9cfb538f68a9e9a87d732b8f2803dff1859f5a66ee186981b","last_reissued_at":"2026-06-24T01:14:39.972831Z","signature_status":"signed_v1","first_computed_at":"2026-06-24T01:14:39.972831Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Fusion-Aware Two-Stage Framework for Mispronunciation Detection and Diagnosis in Low-Resource Modern Standard Arabic","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Gongping Huang, Jacob Benesty, Jingdong Chen, Jing Yang, Pan Li, Shuqing Zhang, Ting Dang, Yongyi Deng","submitted_at":"2026-06-23T03:02:00Z","abstract_excerpt":"Accurate phoneme recognition is pivotal for mispronunciation detection and diagnosis (MDD) in modern standard Arabic (MSA), yet remains constrained by data scarcity and the synthetic-real domain gap. This work proposes a two-stage end-to-end framework. It integrates a pre-trained encoder with causal dilated temporal convolutional networks to preserve fine-grained phonetic variations. A hierarchical two-stage strategy first learns general mappings from native/synthetic corpora, then adapts to scarce real learner data to mitigate domain shift without over-correction. Prediction stability is furt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.24086","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/2606.24086/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":"2606.24086","created_at":"2026-06-24T01:14:39.972888+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.24086v1","created_at":"2026-06-24T01:14:39.972888+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.24086","created_at":"2026-06-24T01:14:39.972888+00:00"},{"alias_kind":"pith_short_12","alias_value":"DUNW7PW5B6YL","created_at":"2026-06-24T01:14:39.972888+00:00"},{"alias_kind":"pith_short_16","alias_value":"DUNW7PW5B6YLTT5V","created_at":"2026-06-24T01:14:39.972888+00:00"},{"alias_kind":"pith_short_8","alias_value":"DUNW7PW5","created_at":"2026-06-24T01:14:39.972888+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/DUNW7PW5B6YLTT5VHD3IVHU2Q7","json":"https://pith.science/pith/DUNW7PW5B6YLTT5VHD3IVHU2Q7.json","graph_json":"https://pith.science/api/pith-number/DUNW7PW5B6YLTT5VHD3IVHU2Q7/graph.json","events_json":"https://pith.science/api/pith-number/DUNW7PW5B6YLTT5VHD3IVHU2Q7/events.json","paper":"https://pith.science/paper/DUNW7PW5"},"agent_actions":{"view_html":"https://pith.science/pith/DUNW7PW5B6YLTT5VHD3IVHU2Q7","download_json":"https://pith.science/pith/DUNW7PW5B6YLTT5VHD3IVHU2Q7.json","view_paper":"https://pith.science/paper/DUNW7PW5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.24086&json=true","fetch_graph":"https://pith.science/api/pith-number/DUNW7PW5B6YLTT5VHD3IVHU2Q7/graph.json","fetch_events":"https://pith.science/api/pith-number/DUNW7PW5B6YLTT5VHD3IVHU2Q7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DUNW7PW5B6YLTT5VHD3IVHU2Q7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DUNW7PW5B6YLTT5VHD3IVHU2Q7/action/storage_attestation","attest_author":"https://pith.science/pith/DUNW7PW5B6YLTT5VHD3IVHU2Q7/action/author_attestation","sign_citation":"https://pith.science/pith/DUNW7PW5B6YLTT5VHD3IVHU2Q7/action/citation_signature","submit_replication":"https://pith.science/pith/DUNW7PW5B6YLTT5VHD3IVHU2Q7/action/replication_record"}},"created_at":"2026-06-24T01:14:39.972888+00:00","updated_at":"2026-06-24T01:14:39.972888+00:00"}