{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:MDPANUQYO3SVYDJ32DCHHCYYP3","short_pith_number":"pith:MDPANUQY","canonical_record":{"source":{"id":"2408.02430","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-08-05T12:38:39Z","cross_cats_sorted":[],"title_canon_sha256":"12bd1a40168984a923b352ead2ae1b754407ef23c8543fc1e8e8bddcce2ab446","abstract_canon_sha256":"dfe1b7031e98fa5cad17442058d34796fc5b886556e71b18ab798edec00a8ea0"},"schema_version":"1.0"},"canonical_sha256":"60de06d21876e55c0d3bd0c4738b187eea0ba94bdeb3ae6737d020b8c5a0ca71","source":{"kind":"arxiv","id":"2408.02430","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.02430","created_at":"2026-07-05T08:52:12Z"},{"alias_kind":"arxiv_version","alias_value":"2408.02430v1","created_at":"2026-07-05T08:52:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.02430","created_at":"2026-07-05T08:52:12Z"},{"alias_kind":"pith_short_12","alias_value":"MDPANUQYO3SV","created_at":"2026-07-05T08:52:12Z"},{"alias_kind":"pith_short_16","alias_value":"MDPANUQYO3SVYDJ3","created_at":"2026-07-05T08:52:12Z"},{"alias_kind":"pith_short_8","alias_value":"MDPANUQY","created_at":"2026-07-05T08:52:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:MDPANUQYO3SVYDJ32DCHHCYYP3","target":"record","payload":{"canonical_record":{"source":{"id":"2408.02430","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-08-05T12:38:39Z","cross_cats_sorted":[],"title_canon_sha256":"12bd1a40168984a923b352ead2ae1b754407ef23c8543fc1e8e8bddcce2ab446","abstract_canon_sha256":"dfe1b7031e98fa5cad17442058d34796fc5b886556e71b18ab798edec00a8ea0"},"schema_version":"1.0"},"canonical_sha256":"60de06d21876e55c0d3bd0c4738b187eea0ba94bdeb3ae6737d020b8c5a0ca71","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:52:12.609824Z","signature_b64":"q6BHCAGFeZ2v/rBLq9pfIe02QEsfUWDi44Wdu4uXDbPnhaffevGjgrKhoW4M9tOTPKR5BWgh3/lsE9RFD2nFBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60de06d21876e55c0d3bd0c4738b187eea0ba94bdeb3ae6737d020b8c5a0ca71","last_reissued_at":"2026-07-05T08:52:12.609410Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:52:12.609410Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.02430","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":"2026-07-05T08:52:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6h0dZSMqMTNxh9OMU3KHcs2IRm/vg2bsBAMui+IlmbuYd60Kq4GvqJKea5i7BMfo9MAXIyfLFZeP8+Yk/Hr+DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T07:56:08.454752Z"},"content_sha256":"d18b6e9f3027d70b0576d5845ef8cce319409029435f7e15ef73f5954f83deac","schema_version":"1.0","event_id":"sha256:d18b6e9f3027d70b0576d5845ef8cce319409029435f7e15ef73f5954f83deac"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:MDPANUQYO3SVYDJ32DCHHCYYP3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond Orthography: Automatic Recovery of Short Vowels and Dialectal Sounds in Arabic","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Ahmed Ali, Hamdy Mubarak, Shammur Absar Chowdhury, Yassine El Kheir","submitted_at":"2024-08-05T12:38:39Z","abstract_excerpt":"This paper presents a novel Dialectal Sound and Vowelization Recovery framework, designed to recognize borrowed and dialectal sounds within phonologically diverse and dialect-rich languages, that extends beyond its standard orthographic sound sets. The proposed framework utilized a quantized sequence of input with(out) continuous pretrained self-supervised representation. We show the efficacy of the pipeline using limited data for Arabic, a dialect-rich language containing more than 22 major dialects. Phonetically correct transcribed speech resources for dialectal Arabic are scarce. Therefore,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.02430","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/2408.02430/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":"2026-07-05T08:52:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DsfULIugtXcYeTEaR3mWN53XQEgNUeXtCGd+CE1oE0BUVAQZSRTm4jYq4e2zk8RgZHd/kVw46YNgaOiZhKh4Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T07:56:08.455563Z"},"content_sha256":"b996b74efc1f4d1589296937bbd6b2b1d66e126237ba3fdec6f987cf83526bef","schema_version":"1.0","event_id":"sha256:b996b74efc1f4d1589296937bbd6b2b1d66e126237ba3fdec6f987cf83526bef"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MDPANUQYO3SVYDJ32DCHHCYYP3/bundle.json","state_url":"https://pith.science/pith/MDPANUQYO3SVYDJ32DCHHCYYP3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MDPANUQYO3SVYDJ32DCHHCYYP3/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":"2026-08-09T07:56:08Z","links":{"resolver":"https://pith.science/pith/MDPANUQYO3SVYDJ32DCHHCYYP3","bundle":"https://pith.science/pith/MDPANUQYO3SVYDJ32DCHHCYYP3/bundle.json","state":"https://pith.science/pith/MDPANUQYO3SVYDJ32DCHHCYYP3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MDPANUQYO3SVYDJ32DCHHCYYP3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MDPANUQYO3SVYDJ32DCHHCYYP3","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":"dfe1b7031e98fa5cad17442058d34796fc5b886556e71b18ab798edec00a8ea0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-08-05T12:38:39Z","title_canon_sha256":"12bd1a40168984a923b352ead2ae1b754407ef23c8543fc1e8e8bddcce2ab446"},"schema_version":"1.0","source":{"id":"2408.02430","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.02430","created_at":"2026-07-05T08:52:12Z"},{"alias_kind":"arxiv_version","alias_value":"2408.02430v1","created_at":"2026-07-05T08:52:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.02430","created_at":"2026-07-05T08:52:12Z"},{"alias_kind":"pith_short_12","alias_value":"MDPANUQYO3SV","created_at":"2026-07-05T08:52:12Z"},{"alias_kind":"pith_short_16","alias_value":"MDPANUQYO3SVYDJ3","created_at":"2026-07-05T08:52:12Z"},{"alias_kind":"pith_short_8","alias_value":"MDPANUQY","created_at":"2026-07-05T08:52:12Z"}],"graph_snapshots":[{"event_id":"sha256:b996b74efc1f4d1589296937bbd6b2b1d66e126237ba3fdec6f987cf83526bef","target":"graph","created_at":"2026-07-05T08:52:12Z","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/2408.02430/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents a novel Dialectal Sound and Vowelization Recovery framework, designed to recognize borrowed and dialectal sounds within phonologically diverse and dialect-rich languages, that extends beyond its standard orthographic sound sets. The proposed framework utilized a quantized sequence of input with(out) continuous pretrained self-supervised representation. We show the efficacy of the pipeline using limited data for Arabic, a dialect-rich language containing more than 22 major dialects. Phonetically correct transcribed speech resources for dialectal Arabic are scarce. Therefore,","authors_text":"Ahmed Ali, Hamdy Mubarak, Shammur Absar Chowdhury, Yassine El Kheir","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-08-05T12:38:39Z","title":"Beyond Orthography: Automatic Recovery of Short Vowels and Dialectal Sounds in Arabic"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.02430","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:d18b6e9f3027d70b0576d5845ef8cce319409029435f7e15ef73f5954f83deac","target":"record","created_at":"2026-07-05T08:52:12Z","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":"dfe1b7031e98fa5cad17442058d34796fc5b886556e71b18ab798edec00a8ea0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-08-05T12:38:39Z","title_canon_sha256":"12bd1a40168984a923b352ead2ae1b754407ef23c8543fc1e8e8bddcce2ab446"},"schema_version":"1.0","source":{"id":"2408.02430","kind":"arxiv","version":1}},"canonical_sha256":"60de06d21876e55c0d3bd0c4738b187eea0ba94bdeb3ae6737d020b8c5a0ca71","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"60de06d21876e55c0d3bd0c4738b187eea0ba94bdeb3ae6737d020b8c5a0ca71","first_computed_at":"2026-07-05T08:52:12.609410Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:52:12.609410Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"q6BHCAGFeZ2v/rBLq9pfIe02QEsfUWDi44Wdu4uXDbPnhaffevGjgrKhoW4M9tOTPKR5BWgh3/lsE9RFD2nFBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:52:12.609824Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.02430","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d18b6e9f3027d70b0576d5845ef8cce319409029435f7e15ef73f5954f83deac","sha256:b996b74efc1f4d1589296937bbd6b2b1d66e126237ba3fdec6f987cf83526bef"],"state_sha256":"5eb97113682b14a90c4491bc4bfb93357130b815e011ceb17a7b6c7b4f70ed8f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gRo9sBKlKG1sQf6jo31R8UjjmHGl859Nn7ypBWX/jqS21f5VA5RglbKTChMBSWMDYF4gLsIOminRqFUZWNYICg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T07:56:08.462987Z","bundle_sha256":"e25684458d72c46cdadd9dd0e33ed6c55abf1deb6350efd0d9850c69db776eb0"}}