{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:KLA6B6NDJKQDWJESJNHGIZK7CO","short_pith_number":"pith:KLA6B6ND","canonical_record":{"source":{"id":"2505.06599","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-10T11:10:48Z","cross_cats_sorted":[],"title_canon_sha256":"6f9e316944b63c1bd0a7d272b082c7488e66785b110795e4f095844067d1f7d1","abstract_canon_sha256":"fbca2a7ce3d52383665fad3f8e0184f1a1a9157bf0c07fe45deee52ba2f7e2f5"},"schema_version":"1.0"},"canonical_sha256":"52c1e0f9a34aa03b24924b4e64655f1391a7fe84c4f840cde8f3b9efa1f1b320","source":{"kind":"arxiv","id":"2505.06599","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.06599","created_at":"2026-07-05T11:01:12Z"},{"alias_kind":"arxiv_version","alias_value":"2505.06599v1","created_at":"2026-07-05T11:01:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.06599","created_at":"2026-07-05T11:01:12Z"},{"alias_kind":"pith_short_12","alias_value":"KLA6B6NDJKQD","created_at":"2026-07-05T11:01:12Z"},{"alias_kind":"pith_short_16","alias_value":"KLA6B6NDJKQDWJES","created_at":"2026-07-05T11:01:12Z"},{"alias_kind":"pith_short_8","alias_value":"KLA6B6ND","created_at":"2026-07-05T11:01:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:KLA6B6NDJKQDWJESJNHGIZK7CO","target":"record","payload":{"canonical_record":{"source":{"id":"2505.06599","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-10T11:10:48Z","cross_cats_sorted":[],"title_canon_sha256":"6f9e316944b63c1bd0a7d272b082c7488e66785b110795e4f095844067d1f7d1","abstract_canon_sha256":"fbca2a7ce3d52383665fad3f8e0184f1a1a9157bf0c07fe45deee52ba2f7e2f5"},"schema_version":"1.0"},"canonical_sha256":"52c1e0f9a34aa03b24924b4e64655f1391a7fe84c4f840cde8f3b9efa1f1b320","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:12.850115Z","signature_b64":"rwaahUrLC1sjrwIv4pq0r96lAq9bzMKN+Dky2DE4jQeojeysJhi2vxaEZ+a4rVNqRgmitMmrsbGmOrfdsnE1BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"52c1e0f9a34aa03b24924b4e64655f1391a7fe84c4f840cde8f3b9efa1f1b320","last_reissued_at":"2026-07-05T11:01:12.849604Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:12.849604Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.06599","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":"2026-07-05T11:01:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QT7mVrhs9Z9v8vrGo0RmjeAKler70lVQiM041ImtEUzmhLSdEuKM//8o2qQm0YeHCBq7OSiBwnVgQA/T/TEpDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T04:45:21.605548Z"},"content_sha256":"a154a05edb459c6b624ff6619816450bc197dd40a83953e59fc81a38d424ad5f","schema_version":"1.0","event_id":"sha256:a154a05edb459c6b624ff6619816450bc197dd40a83953e59fc81a38d424ad5f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:KLA6B6NDJKQDWJESJNHGIZK7CO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bridging the Gap: An Intermediate Language for Enhanced and Cost-Effective Grapheme-to-Phoneme Conversion with Homographs with Multiple Pronunciations Disambiguation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abbas Bertina, Elham Esmaeilnia, Hossein Biniazian, Mahdi Pirnia, Shahab Beirami, Soheil Shahi","submitted_at":"2025-05-10T11:10:48Z","abstract_excerpt":"Grapheme-to-phoneme (G2P) conversion for Persian presents unique challenges due to its complex phonological features, particularly homographs and Ezafe, which exist in formal and informal language contexts. This paper introduces an intermediate language specifically designed for Persian language processing that addresses these challenges through a multi-faceted approach. Our methodology combines two key components: Large Language Model (LLM) prompting techniques and a specialized sequence-to-sequence machine transliteration architecture. We developed and implemented a systematic approach for c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.06599","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/2505.06599/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":"2026-07-05T11:01:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BmnX+b8p7ZN6sn1ij/67ZCjp+aIps6pLz63sfrd8GgipEj4npSLNIfRX0veiZPCPdEf8ONiSiZnJah/AMxj4CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T04:45:21.606048Z"},"content_sha256":"8739150475be73db6044b81175495cc56086af672dfd9c503261594315b6a78b","schema_version":"1.0","event_id":"sha256:8739150475be73db6044b81175495cc56086af672dfd9c503261594315b6a78b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KLA6B6NDJKQDWJESJNHGIZK7CO/bundle.json","state_url":"https://pith.science/pith/KLA6B6NDJKQDWJESJNHGIZK7CO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KLA6B6NDJKQDWJESJNHGIZK7CO/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":"2026-08-19T04:45:21Z","links":{"resolver":"https://pith.science/pith/KLA6B6NDJKQDWJESJNHGIZK7CO","bundle":"https://pith.science/pith/KLA6B6NDJKQDWJESJNHGIZK7CO/bundle.json","state":"https://pith.science/pith/KLA6B6NDJKQDWJESJNHGIZK7CO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KLA6B6NDJKQDWJESJNHGIZK7CO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KLA6B6NDJKQDWJESJNHGIZK7CO","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":"fbca2a7ce3d52383665fad3f8e0184f1a1a9157bf0c07fe45deee52ba2f7e2f5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-10T11:10:48Z","title_canon_sha256":"6f9e316944b63c1bd0a7d272b082c7488e66785b110795e4f095844067d1f7d1"},"schema_version":"1.0","source":{"id":"2505.06599","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.06599","created_at":"2026-07-05T11:01:12Z"},{"alias_kind":"arxiv_version","alias_value":"2505.06599v1","created_at":"2026-07-05T11:01:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.06599","created_at":"2026-07-05T11:01:12Z"},{"alias_kind":"pith_short_12","alias_value":"KLA6B6NDJKQD","created_at":"2026-07-05T11:01:12Z"},{"alias_kind":"pith_short_16","alias_value":"KLA6B6NDJKQDWJES","created_at":"2026-07-05T11:01:12Z"},{"alias_kind":"pith_short_8","alias_value":"KLA6B6ND","created_at":"2026-07-05T11:01:12Z"}],"graph_snapshots":[{"event_id":"sha256:8739150475be73db6044b81175495cc56086af672dfd9c503261594315b6a78b","target":"graph","created_at":"2026-07-05T11:01:12Z","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/2505.06599/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Grapheme-to-phoneme (G2P) conversion for Persian presents unique challenges due to its complex phonological features, particularly homographs and Ezafe, which exist in formal and informal language contexts. This paper introduces an intermediate language specifically designed for Persian language processing that addresses these challenges through a multi-faceted approach. Our methodology combines two key components: Large Language Model (LLM) prompting techniques and a specialized sequence-to-sequence machine transliteration architecture. We developed and implemented a systematic approach for c","authors_text":"Abbas Bertina, Elham Esmaeilnia, Hossein Biniazian, Mahdi Pirnia, Shahab Beirami, Soheil Shahi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-10T11:10:48Z","title":"Bridging the Gap: An Intermediate Language for Enhanced and Cost-Effective Grapheme-to-Phoneme Conversion with Homographs with Multiple Pronunciations Disambiguation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.06599","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:a154a05edb459c6b624ff6619816450bc197dd40a83953e59fc81a38d424ad5f","target":"record","created_at":"2026-07-05T11:01:12Z","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":"fbca2a7ce3d52383665fad3f8e0184f1a1a9157bf0c07fe45deee52ba2f7e2f5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-10T11:10:48Z","title_canon_sha256":"6f9e316944b63c1bd0a7d272b082c7488e66785b110795e4f095844067d1f7d1"},"schema_version":"1.0","source":{"id":"2505.06599","kind":"arxiv","version":1}},"canonical_sha256":"52c1e0f9a34aa03b24924b4e64655f1391a7fe84c4f840cde8f3b9efa1f1b320","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"52c1e0f9a34aa03b24924b4e64655f1391a7fe84c4f840cde8f3b9efa1f1b320","first_computed_at":"2026-07-05T11:01:12.849604Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:01:12.849604Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rwaahUrLC1sjrwIv4pq0r96lAq9bzMKN+Dky2DE4jQeojeysJhi2vxaEZ+a4rVNqRgmitMmrsbGmOrfdsnE1BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:01:12.850115Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.06599","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a154a05edb459c6b624ff6619816450bc197dd40a83953e59fc81a38d424ad5f","sha256:8739150475be73db6044b81175495cc56086af672dfd9c503261594315b6a78b"],"state_sha256":"7cc1ddbb9cb98991c29e00dccc91fbc430092791b96ca15d3296ad5cc4f22c3d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f7xMf8nQbQbmlCrcf0bmXFQqe9VlHkSBuMUM9Sj/08grMumdSi3cpgxzeiUN+Z3trXNxmdBM9J2EZJwxmJy+CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T04:45:21.612461Z","bundle_sha256":"6f3a260244f66ade28058766f09938a1447a08c7310b79686d50f59b50696c12"}}