{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:OXAC2W3MH7L5I2H72WFU27MUTV","short_pith_number":"pith:OXAC2W3M","canonical_record":{"source":{"id":"2605.17846","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-05-18T04:40:31Z","cross_cats_sorted":[],"title_canon_sha256":"2f0d8071a23cd141ef2fa0bd62de4f21c635b6249c70126d943aeb7585a8ce47","abstract_canon_sha256":"40bb46b375683467d1e3199e2acd70dcba48aa4e773722c9f8d67ef6c45dde80"},"schema_version":"1.0"},"canonical_sha256":"75c02d5b6c3fd7d468ffd58b4d7d949d6773eca079b9a06945bf6adb4a1e97f5","source":{"kind":"arxiv","id":"2605.17846","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.17846","created_at":"2026-05-20T00:05:01Z"},{"alias_kind":"arxiv_version","alias_value":"2605.17846v1","created_at":"2026-05-20T00:05:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17846","created_at":"2026-05-20T00:05:01Z"},{"alias_kind":"pith_short_12","alias_value":"OXAC2W3MH7L5","created_at":"2026-05-20T00:05:01Z"},{"alias_kind":"pith_short_16","alias_value":"OXAC2W3MH7L5I2H7","created_at":"2026-05-20T00:05:01Z"},{"alias_kind":"pith_short_8","alias_value":"OXAC2W3M","created_at":"2026-05-20T00:05:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:OXAC2W3MH7L5I2H72WFU27MUTV","target":"record","payload":{"canonical_record":{"source":{"id":"2605.17846","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-05-18T04:40:31Z","cross_cats_sorted":[],"title_canon_sha256":"2f0d8071a23cd141ef2fa0bd62de4f21c635b6249c70126d943aeb7585a8ce47","abstract_canon_sha256":"40bb46b375683467d1e3199e2acd70dcba48aa4e773722c9f8d67ef6c45dde80"},"schema_version":"1.0"},"canonical_sha256":"75c02d5b6c3fd7d468ffd58b4d7d949d6773eca079b9a06945bf6adb4a1e97f5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:05:01.466182Z","signature_b64":"C7h9gU0qSiImD/FyKMvWJDYncRtBa3JiZZJoBwwB+NWxODKplkeZu3/+hoUduWOm9cIN+XPMtFj95L7ezzdIBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"75c02d5b6c3fd7d468ffd58b4d7d949d6773eca079b9a06945bf6adb4a1e97f5","last_reissued_at":"2026-05-20T00:05:01.465377Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:05:01.465377Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.17846","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":"2026-05-20T00:05:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rwg7xXrh0Qd05Rh6VlFvQyGrHGDCtXt0R7eM4qU8AgwtU4sE5ppvwexS9N45Vx8M2ilXiG9v1j3ZbuaEhL0cCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T10:01:51.855532Z"},"content_sha256":"c3ef464d0882e7ae1e7c5a0cf3cbc245f2d658366eb9f5d576a3dd5624650141","schema_version":"1.0","event_id":"sha256:c3ef464d0882e7ae1e7c5a0cf3cbc245f2d658366eb9f5d576a3dd5624650141"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:OXAC2W3MH7L5I2H72WFU27MUTV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"UrduSpeech: A 156-Hour Urdu Speech Corpus with 12-Dimension Paralinguistic Annotations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Attia Nafees ul Haq, Chunjiang He, Jingbin Hu, Lei Xie, Zeyu Zhu","submitted_at":"2026-05-18T04:40:31Z","abstract_excerpt":"Despite 230 million speakers, Urdu remains critically under-resourced in speech technology. We introduce UrduSpeech: a large high-fidelity Urdu corpus comprising 156 hours of audio with 12-dimension paralinguistic metadata, encompassing US-Std, US-CS, US-EngPk. To address Right-to-Left script constraints and frequent code-switching, we developed UrduSpeech, a LLM-driven pipeline to curate data across 12 diverse categories, including news, drama, and rare literary forms like Bait-Bazi. We also release a 9-hour US-Benchmark set, manually corrected by native annotators to serve as a standard. Hum"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17846","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/2605.17846/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":"2026-05-20T00:05:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xJQGSk658YUlxYEVO2/BYZ81NE0DjXFnm2J9n461BdiyPY78rToZksdVE1M1ftg7aVoHK/CHu4kw0zcwim5cAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T10:01:51.855912Z"},"content_sha256":"1bdd866d2fb7fd75b80a7b552b200bba80aaa7d914613422002ef1e72c661a83","schema_version":"1.0","event_id":"sha256:1bdd866d2fb7fd75b80a7b552b200bba80aaa7d914613422002ef1e72c661a83"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OXAC2W3MH7L5I2H72WFU27MUTV/bundle.json","state_url":"https://pith.science/pith/OXAC2W3MH7L5I2H72WFU27MUTV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OXAC2W3MH7L5I2H72WFU27MUTV/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":"2026-06-05T10:01:51Z","links":{"resolver":"https://pith.science/pith/OXAC2W3MH7L5I2H72WFU27MUTV","bundle":"https://pith.science/pith/OXAC2W3MH7L5I2H72WFU27MUTV/bundle.json","state":"https://pith.science/pith/OXAC2W3MH7L5I2H72WFU27MUTV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OXAC2W3MH7L5I2H72WFU27MUTV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OXAC2W3MH7L5I2H72WFU27MUTV","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":"40bb46b375683467d1e3199e2acd70dcba48aa4e773722c9f8d67ef6c45dde80","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-05-18T04:40:31Z","title_canon_sha256":"2f0d8071a23cd141ef2fa0bd62de4f21c635b6249c70126d943aeb7585a8ce47"},"schema_version":"1.0","source":{"id":"2605.17846","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.17846","created_at":"2026-05-20T00:05:01Z"},{"alias_kind":"arxiv_version","alias_value":"2605.17846v1","created_at":"2026-05-20T00:05:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17846","created_at":"2026-05-20T00:05:01Z"},{"alias_kind":"pith_short_12","alias_value":"OXAC2W3MH7L5","created_at":"2026-05-20T00:05:01Z"},{"alias_kind":"pith_short_16","alias_value":"OXAC2W3MH7L5I2H7","created_at":"2026-05-20T00:05:01Z"},{"alias_kind":"pith_short_8","alias_value":"OXAC2W3M","created_at":"2026-05-20T00:05:01Z"}],"graph_snapshots":[{"event_id":"sha256:1bdd866d2fb7fd75b80a7b552b200bba80aaa7d914613422002ef1e72c661a83","target":"graph","created_at":"2026-05-20T00:05:01Z","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/2605.17846/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite 230 million speakers, Urdu remains critically under-resourced in speech technology. We introduce UrduSpeech: a large high-fidelity Urdu corpus comprising 156 hours of audio with 12-dimension paralinguistic metadata, encompassing US-Std, US-CS, US-EngPk. To address Right-to-Left script constraints and frequent code-switching, we developed UrduSpeech, a LLM-driven pipeline to curate data across 12 diverse categories, including news, drama, and rare literary forms like Bait-Bazi. We also release a 9-hour US-Benchmark set, manually corrected by native annotators to serve as a standard. Hum","authors_text":"Attia Nafees ul Haq, Chunjiang He, Jingbin Hu, Lei Xie, Zeyu Zhu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-05-18T04:40:31Z","title":"UrduSpeech: A 156-Hour Urdu Speech Corpus with 12-Dimension Paralinguistic Annotations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17846","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:c3ef464d0882e7ae1e7c5a0cf3cbc245f2d658366eb9f5d576a3dd5624650141","target":"record","created_at":"2026-05-20T00:05:01Z","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":"40bb46b375683467d1e3199e2acd70dcba48aa4e773722c9f8d67ef6c45dde80","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-05-18T04:40:31Z","title_canon_sha256":"2f0d8071a23cd141ef2fa0bd62de4f21c635b6249c70126d943aeb7585a8ce47"},"schema_version":"1.0","source":{"id":"2605.17846","kind":"arxiv","version":1}},"canonical_sha256":"75c02d5b6c3fd7d468ffd58b4d7d949d6773eca079b9a06945bf6adb4a1e97f5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"75c02d5b6c3fd7d468ffd58b4d7d949d6773eca079b9a06945bf6adb4a1e97f5","first_computed_at":"2026-05-20T00:05:01.465377Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:05:01.465377Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"C7h9gU0qSiImD/FyKMvWJDYncRtBa3JiZZJoBwwB+NWxODKplkeZu3/+hoUduWOm9cIN+XPMtFj95L7ezzdIBw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:05:01.466182Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.17846","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c3ef464d0882e7ae1e7c5a0cf3cbc245f2d658366eb9f5d576a3dd5624650141","sha256:1bdd866d2fb7fd75b80a7b552b200bba80aaa7d914613422002ef1e72c661a83"],"state_sha256":"93238f6ccad37b2df930c93bbc76638ddba5a1ba8e7e08ff66aa6eb87d9cd8cf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gyanrh6cGtbDoz5lv22hpMy1lvFCHatRNMV0PD0T/HYNU8WZ2UtCqx+6MN6d8rKcFqSnInKQQpySuuxnYZfXCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T10:01:51.858194Z","bundle_sha256":"9a945dc950756d60b9e8f77e8cf6ae1a1b62b273612c078d149aba6c7e49e840"}}