{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:LQ6OQ7EXOQYAOQXLAUCRPZ4VTH","short_pith_number":"pith:LQ6OQ7EX","canonical_record":{"source":{"id":"2604.06191","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-03-11T04:10:35Z","cross_cats_sorted":["cs.AI","cs.CL","cs.SD"],"title_canon_sha256":"7da72b745669f941c53f604c963e5f999c8fab871f1dab17223f411087c0e19e","abstract_canon_sha256":"a85077a7c51d43c1937f223da245ec11944ec938a12518197b1b027bcb8af9c6"},"schema_version":"1.0"},"canonical_sha256":"5c3ce87c9774300742eb050517e79599de7bbb2f40a420b492b19a049aedab0e","source":{"kind":"arxiv","id":"2604.06191","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.06191","created_at":"2026-06-23T01:12:04Z"},{"alias_kind":"arxiv_version","alias_value":"2604.06191v2","created_at":"2026-06-23T01:12:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.06191","created_at":"2026-06-23T01:12:04Z"},{"alias_kind":"pith_short_12","alias_value":"LQ6OQ7EXOQYA","created_at":"2026-06-23T01:12:04Z"},{"alias_kind":"pith_short_16","alias_value":"LQ6OQ7EXOQYAOQXL","created_at":"2026-06-23T01:12:04Z"},{"alias_kind":"pith_short_8","alias_value":"LQ6OQ7EX","created_at":"2026-06-23T01:12:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:LQ6OQ7EXOQYAOQXLAUCRPZ4VTH","target":"record","payload":{"canonical_record":{"source":{"id":"2604.06191","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-03-11T04:10:35Z","cross_cats_sorted":["cs.AI","cs.CL","cs.SD"],"title_canon_sha256":"7da72b745669f941c53f604c963e5f999c8fab871f1dab17223f411087c0e19e","abstract_canon_sha256":"a85077a7c51d43c1937f223da245ec11944ec938a12518197b1b027bcb8af9c6"},"schema_version":"1.0"},"canonical_sha256":"5c3ce87c9774300742eb050517e79599de7bbb2f40a420b492b19a049aedab0e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T01:12:04.509899Z","signature_b64":"cC3Mum4NFv2WkZxGgEv5K1oOWaYNVhqcxmE+rLLkOetEEytDXr1auh1eBXBMqdYKyyYWNQ0NYq1+XTIi+Hz4Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c3ce87c9774300742eb050517e79599de7bbb2f40a420b492b19a049aedab0e","last_reissued_at":"2026-06-23T01:12:04.509307Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T01:12:04.509307Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2604.06191","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-23T01:12:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ifcSHkc1ahdMqQLojGZDysWEjr4CEA+Wkp5oLOIELJC6KvgPA543MCDDxjT0No6xh+Bx5zdAJrUGgmbwOGdZDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T20:17:22.027090Z"},"content_sha256":"290e97ebfba37f4240f720557b9c50f64f34c37031ac82282ba1674c2f8ce628","schema_version":"1.0","event_id":"sha256:290e97ebfba37f4240f720557b9c50f64f34c37031ac82282ba1674c2f8ce628"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:LQ6OQ7EXOQYAOQXLAUCRPZ4VTH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Harf-Speech: A Clinically Aligned Framework for Arabic Phoneme-Level Speech Assessment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Harf-Speech scores Arabic pronunciation at the phoneme level with 0.791 correlation to expert pathologists.","cross_cats":["cs.AI","cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Abdulrhman Aljouie, Asif Azad, Ayah Othman Sindi, Bdour Alwuqaysi, Ehsan Hoque, MD Sadik Hossain Shanto, Mohammad Sadat Hossain, Sabri Boughorbel, Yahya Bokhari","submitted_at":"2026-03-11T04:10:35Z","abstract_excerpt":"Automated phoneme-level pronunciation assessment is vital for scalable speech therapy and language learning, yet validated tools for Arabic remain scarce. We present Harf-Speech, a modular system scoring Arabic pronunciation at the phoneme level on a clinical scale. It combines an MSA phonetizer, a fine-tuned speech-to-phoneme model, Levenshtein alignment, and a blended scorer using longest common subsequence and edit-distance metrics. We fine-tune three ASR architectures on Arabic phoneme data and benchmark them with zero-shot multimodal models; the best, OmniASR-CTC-1B-v2, achieves 8.92% pho"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Harf-Speech attains a Pearson correlation of 0.791 and ICC(2,1) of 0.659 with mean expert scores, outperforming existing end-to-end assessment frameworks.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The 40 utterances scored by three pathologists are representative of the clinical population and that the blended LCS-plus-edit-distance metric faithfully captures the clinical judgment used by experts.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Harf-Speech delivers phoneme-level Arabic pronunciation scores that correlate 0.79 with certified speech-language pathologists on 40 utterances.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Harf-Speech scores Arabic pronunciation at the phoneme level with 0.791 correlation to expert pathologists.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"49c329ded3649b5fee6b73e115b2646794f663a6b46d5e5bef41489b010ec591"},"source":{"id":"2604.06191","kind":"arxiv","version":2},"verdict":{"id":"57a87f6b-1df2-4115-a99a-a41f29e8692d","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T13:37:38.480667Z","strongest_claim":"Harf-Speech attains a Pearson correlation of 0.791 and ICC(2,1) of 0.659 with mean expert scores, outperforming existing end-to-end assessment frameworks.","one_line_summary":"Harf-Speech delivers phoneme-level Arabic pronunciation scores that correlate 0.79 with certified speech-language pathologists on 40 utterances.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The 40 utterances scored by three pathologists are representative of the clinical population and that the blended LCS-plus-edit-distance metric faithfully captures the clinical judgment used by experts.","pith_extraction_headline":"Harf-Speech scores Arabic pronunciation at the phoneme level with 0.791 correlation to expert pathologists."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.06191/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":2,"snapshot_sha256":"6af27d2f2e76041dab127244f663de9259ffb1c0df052de5b323f80f26e4802d"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"57a87f6b-1df2-4115-a99a-a41f29e8692d"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-23T01:12:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iingHvdrtFkPIW2UBD32eVyERFFPFwEEQi1B7UOO+J6Hff/niIgBiakn/7cZmUeJgCec8YFEeTJS+qPmbqzoCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T20:17:22.027552Z"},"content_sha256":"72a07568b7b1509e6cd357892513c207584108a802a6fea001d26af9d59e1f1f","schema_version":"1.0","event_id":"sha256:72a07568b7b1509e6cd357892513c207584108a802a6fea001d26af9d59e1f1f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LQ6OQ7EXOQYAOQXLAUCRPZ4VTH/bundle.json","state_url":"https://pith.science/pith/LQ6OQ7EXOQYAOQXLAUCRPZ4VTH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LQ6OQ7EXOQYAOQXLAUCRPZ4VTH/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":"2026-06-27T20:17:22Z","links":{"resolver":"https://pith.science/pith/LQ6OQ7EXOQYAOQXLAUCRPZ4VTH","bundle":"https://pith.science/pith/LQ6OQ7EXOQYAOQXLAUCRPZ4VTH/bundle.json","state":"https://pith.science/pith/LQ6OQ7EXOQYAOQXLAUCRPZ4VTH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LQ6OQ7EXOQYAOQXLAUCRPZ4VTH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LQ6OQ7EXOQYAOQXLAUCRPZ4VTH","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":"a85077a7c51d43c1937f223da245ec11944ec938a12518197b1b027bcb8af9c6","cross_cats_sorted":["cs.AI","cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-03-11T04:10:35Z","title_canon_sha256":"7da72b745669f941c53f604c963e5f999c8fab871f1dab17223f411087c0e19e"},"schema_version":"1.0","source":{"id":"2604.06191","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.06191","created_at":"2026-06-23T01:12:04Z"},{"alias_kind":"arxiv_version","alias_value":"2604.06191v2","created_at":"2026-06-23T01:12:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.06191","created_at":"2026-06-23T01:12:04Z"},{"alias_kind":"pith_short_12","alias_value":"LQ6OQ7EXOQYA","created_at":"2026-06-23T01:12:04Z"},{"alias_kind":"pith_short_16","alias_value":"LQ6OQ7EXOQYAOQXL","created_at":"2026-06-23T01:12:04Z"},{"alias_kind":"pith_short_8","alias_value":"LQ6OQ7EX","created_at":"2026-06-23T01:12:04Z"}],"graph_snapshots":[{"event_id":"sha256:72a07568b7b1509e6cd357892513c207584108a802a6fea001d26af9d59e1f1f","target":"graph","created_at":"2026-06-23T01:12:04Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Harf-Speech attains a Pearson correlation of 0.791 and ICC(2,1) of 0.659 with mean expert scores, outperforming existing end-to-end assessment frameworks."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The 40 utterances scored by three pathologists are representative of the clinical population and that the blended LCS-plus-edit-distance metric faithfully captures the clinical judgment used by experts."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Harf-Speech delivers phoneme-level Arabic pronunciation scores that correlate 0.79 with certified speech-language pathologists on 40 utterances."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Harf-Speech scores Arabic pronunciation at the phoneme level with 0.791 correlation to expert pathologists."}],"snapshot_sha256":"49c329ded3649b5fee6b73e115b2646794f663a6b46d5e5bef41489b010ec591"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"6af27d2f2e76041dab127244f663de9259ffb1c0df052de5b323f80f26e4802d"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.06191/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automated phoneme-level pronunciation assessment is vital for scalable speech therapy and language learning, yet validated tools for Arabic remain scarce. We present Harf-Speech, a modular system scoring Arabic pronunciation at the phoneme level on a clinical scale. It combines an MSA phonetizer, a fine-tuned speech-to-phoneme model, Levenshtein alignment, and a blended scorer using longest common subsequence and edit-distance metrics. We fine-tune three ASR architectures on Arabic phoneme data and benchmark them with zero-shot multimodal models; the best, OmniASR-CTC-1B-v2, achieves 8.92% pho","authors_text":"Abdulrhman Aljouie, Asif Azad, Ayah Othman Sindi, Bdour Alwuqaysi, Ehsan Hoque, MD Sadik Hossain Shanto, Mohammad Sadat Hossain, Sabri Boughorbel, Yahya Bokhari","cross_cats":["cs.AI","cs.CL","cs.SD"],"headline":"Harf-Speech scores Arabic pronunciation at the phoneme level with 0.791 correlation to expert pathologists.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-03-11T04:10:35Z","title":"Harf-Speech: A Clinically Aligned Framework for Arabic Phoneme-Level Speech Assessment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.06191","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-15T13:37:38.480667Z","id":"57a87f6b-1df2-4115-a99a-a41f29e8692d","model_set":{"reader":"grok-4.3"},"one_line_summary":"Harf-Speech delivers phoneme-level Arabic pronunciation scores that correlate 0.79 with certified speech-language pathologists on 40 utterances.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Harf-Speech scores Arabic pronunciation at the phoneme level with 0.791 correlation to expert pathologists.","strongest_claim":"Harf-Speech attains a Pearson correlation of 0.791 and ICC(2,1) of 0.659 with mean expert scores, outperforming existing end-to-end assessment frameworks.","weakest_assumption":"The 40 utterances scored by three pathologists are representative of the clinical population and that the blended LCS-plus-edit-distance metric faithfully captures the clinical judgment used by experts."}},"verdict_id":"57a87f6b-1df2-4115-a99a-a41f29e8692d"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:290e97ebfba37f4240f720557b9c50f64f34c37031ac82282ba1674c2f8ce628","target":"record","created_at":"2026-06-23T01:12:04Z","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":"a85077a7c51d43c1937f223da245ec11944ec938a12518197b1b027bcb8af9c6","cross_cats_sorted":["cs.AI","cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-03-11T04:10:35Z","title_canon_sha256":"7da72b745669f941c53f604c963e5f999c8fab871f1dab17223f411087c0e19e"},"schema_version":"1.0","source":{"id":"2604.06191","kind":"arxiv","version":2}},"canonical_sha256":"5c3ce87c9774300742eb050517e79599de7bbb2f40a420b492b19a049aedab0e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5c3ce87c9774300742eb050517e79599de7bbb2f40a420b492b19a049aedab0e","first_computed_at":"2026-06-23T01:12:04.509307Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T01:12:04.509307Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cC3Mum4NFv2WkZxGgEv5K1oOWaYNVhqcxmE+rLLkOetEEytDXr1auh1eBXBMqdYKyyYWNQ0NYq1+XTIi+Hz4Dw==","signature_status":"signed_v1","signed_at":"2026-06-23T01:12:04.509899Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.06191","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:290e97ebfba37f4240f720557b9c50f64f34c37031ac82282ba1674c2f8ce628","sha256:72a07568b7b1509e6cd357892513c207584108a802a6fea001d26af9d59e1f1f"],"state_sha256":"a4240ca3c0166340592842eff86f8a829c4a2aae7900dc4d356def9787e1201a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iog/R7vlfTx9Z3ZKYeZhfYiUlOZ3oFupKZSBtkSDwJkRlFulTAJRhu2Pv48yW/L1G5BzGCu0pPIKK6m3/SUKBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-27T20:17:22.029731Z","bundle_sha256":"e3a3c3a762f713dce66581134372860c913067c2a4b0fddf024bd398d00a6fcd"}}