{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:TWKVZ3SQ33J62PK4V67YOZO4VR","short_pith_number":"pith:TWKVZ3SQ","canonical_record":{"source":{"id":"2505.12973","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-19T11:11:12Z","cross_cats_sorted":[],"title_canon_sha256":"5e0e1f6d87560e6ffbe45081686c93907d41ad3c357deba5b4c5ad3e9ab6d8bb","abstract_canon_sha256":"2958384cf4ac962dcdd644e32272ea4155579210d853845aa409f78ea5835d7b"},"schema_version":"1.0"},"canonical_sha256":"9d955cee50ded3ed3d5cafbf8765dcac59ab37c5631b99619c857cba1dfb0da7","source":{"kind":"arxiv","id":"2505.12973","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.12973","created_at":"2026-07-05T11:05:13Z"},{"alias_kind":"arxiv_version","alias_value":"2505.12973v1","created_at":"2026-07-05T11:05:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12973","created_at":"2026-07-05T11:05:13Z"},{"alias_kind":"pith_short_12","alias_value":"TWKVZ3SQ33J6","created_at":"2026-07-05T11:05:13Z"},{"alias_kind":"pith_short_16","alias_value":"TWKVZ3SQ33J62PK4","created_at":"2026-07-05T11:05:13Z"},{"alias_kind":"pith_short_8","alias_value":"TWKVZ3SQ","created_at":"2026-07-05T11:05:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:TWKVZ3SQ33J62PK4V67YOZO4VR","target":"record","payload":{"canonical_record":{"source":{"id":"2505.12973","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-19T11:11:12Z","cross_cats_sorted":[],"title_canon_sha256":"5e0e1f6d87560e6ffbe45081686c93907d41ad3c357deba5b4c5ad3e9ab6d8bb","abstract_canon_sha256":"2958384cf4ac962dcdd644e32272ea4155579210d853845aa409f78ea5835d7b"},"schema_version":"1.0"},"canonical_sha256":"9d955cee50ded3ed3d5cafbf8765dcac59ab37c5631b99619c857cba1dfb0da7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:13.117489Z","signature_b64":"CiKWQzkX2FHI7Va2XJnCrZTstFfKb1bWjchJNBiqAV81K4GL/yf6v84VSzdT+I3Z1NJtO0y2J2VKxCADdXMrCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d955cee50ded3ed3d5cafbf8765dcac59ab37c5631b99619c857cba1dfb0da7","last_reissued_at":"2026-07-05T11:05:13.116987Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:13.116987Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.12973","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":"2026-07-05T11:05:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pkj8PYiaOVd3PFBMuavtgC4whCPPkruQtgXsPdcfxKafaDK4QzV3qnoilspCEnHD9XAYnAAyDM5LvCNbgxFhCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T16:11:54.787443Z"},"content_sha256":"db062acfdc75f6c51faaa593ce442faf3863d62f6da41ef21f40e3a3022be86f","schema_version":"1.0","event_id":"sha256:db062acfdc75f6c51faaa593ce442faf3863d62f6da41ef21f40e3a3022be86f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:TWKVZ3SQ33J62PK4V67YOZO4VR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fast, Not Fancy: Rethinking G2P with Rich Data and Rule-Based Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hamid R. Rabiee, Mahta Fetrat Qharabagh, Zahra Dehghanian","submitted_at":"2025-05-19T11:11:12Z","abstract_excerpt":"Homograph disambiguation remains a significant challenge in grapheme-to-phoneme (G2P) conversion, especially for low-resource languages. This challenge is twofold: (1) creating balanced and comprehensive homograph datasets is labor-intensive and costly, and (2) specific disambiguation strategies introduce additional latency, making them unsuitable for real-time applications such as screen readers and other accessibility tools. In this paper, we address both issues. First, we propose a semi-automated pipeline for constructing homograph-focused datasets, introduce the HomoRich dataset generated "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12973","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/2505.12973/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":"2026-07-05T11:05:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cHA1vpFhUaIO5JTQ/t272+GISg2bNTKxcEGwmdrrAFX9cVYk5eR1dk9mEniXaIX0CX4f9GD9Pq9MX23cKYsjAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T16:11:54.788482Z"},"content_sha256":"80dff328ff6de5839b0d7249cbd5ab5590db782ba8a6b8fd311526d08cdd5640","schema_version":"1.0","event_id":"sha256:80dff328ff6de5839b0d7249cbd5ab5590db782ba8a6b8fd311526d08cdd5640"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TWKVZ3SQ33J62PK4V67YOZO4VR/bundle.json","state_url":"https://pith.science/pith/TWKVZ3SQ33J62PK4V67YOZO4VR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TWKVZ3SQ33J62PK4V67YOZO4VR/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":"2026-08-18T16:11:54Z","links":{"resolver":"https://pith.science/pith/TWKVZ3SQ33J62PK4V67YOZO4VR","bundle":"https://pith.science/pith/TWKVZ3SQ33J62PK4V67YOZO4VR/bundle.json","state":"https://pith.science/pith/TWKVZ3SQ33J62PK4V67YOZO4VR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TWKVZ3SQ33J62PK4V67YOZO4VR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TWKVZ3SQ33J62PK4V67YOZO4VR","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":"2958384cf4ac962dcdd644e32272ea4155579210d853845aa409f78ea5835d7b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-19T11:11:12Z","title_canon_sha256":"5e0e1f6d87560e6ffbe45081686c93907d41ad3c357deba5b4c5ad3e9ab6d8bb"},"schema_version":"1.0","source":{"id":"2505.12973","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.12973","created_at":"2026-07-05T11:05:13Z"},{"alias_kind":"arxiv_version","alias_value":"2505.12973v1","created_at":"2026-07-05T11:05:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12973","created_at":"2026-07-05T11:05:13Z"},{"alias_kind":"pith_short_12","alias_value":"TWKVZ3SQ33J6","created_at":"2026-07-05T11:05:13Z"},{"alias_kind":"pith_short_16","alias_value":"TWKVZ3SQ33J62PK4","created_at":"2026-07-05T11:05:13Z"},{"alias_kind":"pith_short_8","alias_value":"TWKVZ3SQ","created_at":"2026-07-05T11:05:13Z"}],"graph_snapshots":[{"event_id":"sha256:80dff328ff6de5839b0d7249cbd5ab5590db782ba8a6b8fd311526d08cdd5640","target":"graph","created_at":"2026-07-05T11:05:13Z","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/2505.12973/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Homograph disambiguation remains a significant challenge in grapheme-to-phoneme (G2P) conversion, especially for low-resource languages. This challenge is twofold: (1) creating balanced and comprehensive homograph datasets is labor-intensive and costly, and (2) specific disambiguation strategies introduce additional latency, making them unsuitable for real-time applications such as screen readers and other accessibility tools. In this paper, we address both issues. First, we propose a semi-automated pipeline for constructing homograph-focused datasets, introduce the HomoRich dataset generated ","authors_text":"Hamid R. Rabiee, Mahta Fetrat Qharabagh, Zahra Dehghanian","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-19T11:11:12Z","title":"Fast, Not Fancy: Rethinking G2P with Rich Data and Rule-Based Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12973","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:db062acfdc75f6c51faaa593ce442faf3863d62f6da41ef21f40e3a3022be86f","target":"record","created_at":"2026-07-05T11:05:13Z","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":"2958384cf4ac962dcdd644e32272ea4155579210d853845aa409f78ea5835d7b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-19T11:11:12Z","title_canon_sha256":"5e0e1f6d87560e6ffbe45081686c93907d41ad3c357deba5b4c5ad3e9ab6d8bb"},"schema_version":"1.0","source":{"id":"2505.12973","kind":"arxiv","version":1}},"canonical_sha256":"9d955cee50ded3ed3d5cafbf8765dcac59ab37c5631b99619c857cba1dfb0da7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9d955cee50ded3ed3d5cafbf8765dcac59ab37c5631b99619c857cba1dfb0da7","first_computed_at":"2026-07-05T11:05:13.116987Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:05:13.116987Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CiKWQzkX2FHI7Va2XJnCrZTstFfKb1bWjchJNBiqAV81K4GL/yf6v84VSzdT+I3Z1NJtO0y2J2VKxCADdXMrCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:05:13.117489Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.12973","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:db062acfdc75f6c51faaa593ce442faf3863d62f6da41ef21f40e3a3022be86f","sha256:80dff328ff6de5839b0d7249cbd5ab5590db782ba8a6b8fd311526d08cdd5640"],"state_sha256":"2011477a9ad7f30cbf4fdd777a5fa65434d4c4deef96728100e0e01783b22273"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SifIDX+iW6lqnSoC+dCHl7SeZV7LtNps693SbO2X6dYZtfXUht6mLOILZGmUtNzR0R4s3Xdgri0g6f51jgBpDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T16:11:54.793384Z","bundle_sha256":"7202fd33434bf650bd53ce08bc9262ee73cf175216f3530d5fb07d880b85d3bb"}}