{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:S2JZSEFS3NV3VMWVGLFNSFI3BL","short_pith_number":"pith:S2JZSEFS","canonical_record":{"source":{"id":"1801.00409","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-01-01T07:54:09Z","cross_cats_sorted":[],"title_canon_sha256":"e5710d64fb6c329c1b555582f49256db1d16fa1f75746cfcf3ab9785daf5bc4a","abstract_canon_sha256":"46783ba6f9c0c8e313c18c677e94f59b9e3e91148901086067dfc018bf0a27fb"},"schema_version":"1.0"},"canonical_sha256":"96939910b2db6bbab2d532cad9151b0ad3e8e132e6fa54707b75979003093bed","source":{"kind":"arxiv","id":"1801.00409","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.00409","created_at":"2026-05-18T00:22:02Z"},{"alias_kind":"arxiv_version","alias_value":"1801.00409v2","created_at":"2026-05-18T00:22:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.00409","created_at":"2026-05-18T00:22:02Z"},{"alias_kind":"pith_short_12","alias_value":"S2JZSEFS3NV3","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"S2JZSEFS3NV3VMWV","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"S2JZSEFS","created_at":"2026-05-18T12:32:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:S2JZSEFS3NV3VMWVGLFNSFI3BL","target":"record","payload":{"canonical_record":{"source":{"id":"1801.00409","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-01-01T07:54:09Z","cross_cats_sorted":[],"title_canon_sha256":"e5710d64fb6c329c1b555582f49256db1d16fa1f75746cfcf3ab9785daf5bc4a","abstract_canon_sha256":"46783ba6f9c0c8e313c18c677e94f59b9e3e91148901086067dfc018bf0a27fb"},"schema_version":"1.0"},"canonical_sha256":"96939910b2db6bbab2d532cad9151b0ad3e8e132e6fa54707b75979003093bed","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:02.413388Z","signature_b64":"QA40VtFvH9WHKHcqJh5mmF1Nzt2HuG9pLqHa3EXwEI4zMGNlgzFnU8OR2D8xADwH3Pp8K+r1F/azPCFFZ3AWAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"96939910b2db6bbab2d532cad9151b0ad3e8e132e6fa54707b75979003093bed","last_reissued_at":"2026-05-18T00:22:02.412772Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:02.412772Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1801.00409","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":"2026-05-18T00:22:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uEylrPlChali3Oq3aRGleYDOw0Ew8rdU0PkGrBlHksXN9zePv21PpsSXZ6lS7rMUNFV1utoDUnuxqFBIgB+YBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T05:00:38.581947Z"},"content_sha256":"55fd40ac20a5fae2b65be1c0a5278c0cc7298c9134398f96a334c783cb8257e6","schema_version":"1.0","event_id":"sha256:55fd40ac20a5fae2b65be1c0a5278c0cc7298c9134398f96a334c783cb8257e6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:S2JZSEFS3NV3VMWVGLFNSFI3BL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PronouncUR: An Urdu Pronunciation Lexicon Generator","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Agha Ali Raza, Awais Athar, Haris Bin Zia","submitted_at":"2018-01-01T07:54:09Z","abstract_excerpt":"State-of-the-art speech recognition systems rely heavily on three basic components: an acoustic model, a pronunciation lexicon and a language model. To build these components, a researcher needs linguistic as well as technical expertise, which is a barrier in low-resource domains. Techniques to construct these three components without having expert domain knowledge are in great demand. Urdu, despite having millions of speakers all over the world, is a low-resource language in terms of standard publically available linguistic resources. In this paper, we present a grapheme-to-phoneme conversion"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.00409","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2026-05-18T00:22:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7SVv7oXnoQhiYDJ4XZBqk6ivpI80WYU8+SauQoK8i5pew2NsvF8zZJndqXA7HiEVFQ05BtKJcO7nsxO3Vrl/AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T05:00:38.582277Z"},"content_sha256":"5900e7980c89c015b281d82d19a8fd86057604086ceef603f1da5cbc0c0f3fd2","schema_version":"1.0","event_id":"sha256:5900e7980c89c015b281d82d19a8fd86057604086ceef603f1da5cbc0c0f3fd2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/S2JZSEFS3NV3VMWVGLFNSFI3BL/bundle.json","state_url":"https://pith.science/pith/S2JZSEFS3NV3VMWVGLFNSFI3BL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/S2JZSEFS3NV3VMWVGLFNSFI3BL/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":"2026-06-12T05:00:38Z","links":{"resolver":"https://pith.science/pith/S2JZSEFS3NV3VMWVGLFNSFI3BL","bundle":"https://pith.science/pith/S2JZSEFS3NV3VMWVGLFNSFI3BL/bundle.json","state":"https://pith.science/pith/S2JZSEFS3NV3VMWVGLFNSFI3BL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/S2JZSEFS3NV3VMWVGLFNSFI3BL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:S2JZSEFS3NV3VMWVGLFNSFI3BL","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":"46783ba6f9c0c8e313c18c677e94f59b9e3e91148901086067dfc018bf0a27fb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-01-01T07:54:09Z","title_canon_sha256":"e5710d64fb6c329c1b555582f49256db1d16fa1f75746cfcf3ab9785daf5bc4a"},"schema_version":"1.0","source":{"id":"1801.00409","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.00409","created_at":"2026-05-18T00:22:02Z"},{"alias_kind":"arxiv_version","alias_value":"1801.00409v2","created_at":"2026-05-18T00:22:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.00409","created_at":"2026-05-18T00:22:02Z"},{"alias_kind":"pith_short_12","alias_value":"S2JZSEFS3NV3","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"S2JZSEFS3NV3VMWV","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"S2JZSEFS","created_at":"2026-05-18T12:32:50Z"}],"graph_snapshots":[{"event_id":"sha256:5900e7980c89c015b281d82d19a8fd86057604086ceef603f1da5cbc0c0f3fd2","target":"graph","created_at":"2026-05-18T00:22:02Z","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"},"paper":{"abstract_excerpt":"State-of-the-art speech recognition systems rely heavily on three basic components: an acoustic model, a pronunciation lexicon and a language model. To build these components, a researcher needs linguistic as well as technical expertise, which is a barrier in low-resource domains. Techniques to construct these three components without having expert domain knowledge are in great demand. Urdu, despite having millions of speakers all over the world, is a low-resource language in terms of standard publically available linguistic resources. In this paper, we present a grapheme-to-phoneme conversion","authors_text":"Agha Ali Raza, Awais Athar, Haris Bin Zia","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-01-01T07:54:09Z","title":"PronouncUR: An Urdu Pronunciation Lexicon Generator"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.00409","kind":"arxiv","version":2},"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":"sha256:55fd40ac20a5fae2b65be1c0a5278c0cc7298c9134398f96a334c783cb8257e6","target":"record","created_at":"2026-05-18T00:22:02Z","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":"46783ba6f9c0c8e313c18c677e94f59b9e3e91148901086067dfc018bf0a27fb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-01-01T07:54:09Z","title_canon_sha256":"e5710d64fb6c329c1b555582f49256db1d16fa1f75746cfcf3ab9785daf5bc4a"},"schema_version":"1.0","source":{"id":"1801.00409","kind":"arxiv","version":2}},"canonical_sha256":"96939910b2db6bbab2d532cad9151b0ad3e8e132e6fa54707b75979003093bed","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"96939910b2db6bbab2d532cad9151b0ad3e8e132e6fa54707b75979003093bed","first_computed_at":"2026-05-18T00:22:02.412772Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:22:02.412772Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QA40VtFvH9WHKHcqJh5mmF1Nzt2HuG9pLqHa3EXwEI4zMGNlgzFnU8OR2D8xADwH3Pp8K+r1F/azPCFFZ3AWAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:22:02.413388Z","signed_message":"canonical_sha256_bytes"},"source_id":"1801.00409","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:55fd40ac20a5fae2b65be1c0a5278c0cc7298c9134398f96a334c783cb8257e6","sha256:5900e7980c89c015b281d82d19a8fd86057604086ceef603f1da5cbc0c0f3fd2"],"state_sha256":"6278e7aa60d4df76bbe97275d8256e2819a2f9696f8fda11932aa6bd1103bfd6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4yZ8RFVoxX1+loKpJMt+P9PigmiCug2ViUBU+EikPTOkTr8QMk9xr4kIQpDD98PhG6w23RUM3UtmnqcXURqQDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-12T05:00:38.584205Z","bundle_sha256":"a73b99bca268064dd81a08c4500f868223888cbef4c23913534ac2ee4f479137"}}