{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:3MY6FZPVRYAOIDJHNOT2LFMX2E","short_pith_number":"pith:3MY6FZPV","canonical_record":{"source":{"id":"2302.14523","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-28T12:33:12Z","cross_cats_sorted":[],"title_canon_sha256":"fdc550e042f8bcfe2cfc3e6e4caf33f21d9241a5be0aae6f06e6feb30fa83e26","abstract_canon_sha256":"bb98c5d9151a12a258d1147ad9053d1c0f78e97a1f9c84bd840a5f2a77fb248c"},"schema_version":"1.0"},"canonical_sha256":"db31e2e5f58e00e40d276ba7a59597d127ca6ed4378e81e067d947517236f37d","source":{"kind":"arxiv","id":"2302.14523","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.14523","created_at":"2026-07-05T05:46:46Z"},{"alias_kind":"arxiv_version","alias_value":"2302.14523v1","created_at":"2026-07-05T05:46:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.14523","created_at":"2026-07-05T05:46:46Z"},{"alias_kind":"pith_short_12","alias_value":"3MY6FZPVRYAO","created_at":"2026-07-05T05:46:46Z"},{"alias_kind":"pith_short_16","alias_value":"3MY6FZPVRYAOIDJH","created_at":"2026-07-05T05:46:46Z"},{"alias_kind":"pith_short_8","alias_value":"3MY6FZPV","created_at":"2026-07-05T05:46:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:3MY6FZPVRYAOIDJHNOT2LFMX2E","target":"record","payload":{"canonical_record":{"source":{"id":"2302.14523","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-28T12:33:12Z","cross_cats_sorted":[],"title_canon_sha256":"fdc550e042f8bcfe2cfc3e6e4caf33f21d9241a5be0aae6f06e6feb30fa83e26","abstract_canon_sha256":"bb98c5d9151a12a258d1147ad9053d1c0f78e97a1f9c84bd840a5f2a77fb248c"},"schema_version":"1.0"},"canonical_sha256":"db31e2e5f58e00e40d276ba7a59597d127ca6ed4378e81e067d947517236f37d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:46:46.207335Z","signature_b64":"DEB/AUBG2gMgiokpLZkRlad1npjZpcR8KOVBS728X2LLTvdEJZ+VYEXebS0rObthfmr8do6sTiqdf7GDFjfkAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db31e2e5f58e00e40d276ba7a59597d127ca6ed4378e81e067d947517236f37d","last_reissued_at":"2026-07-05T05:46:46.206974Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:46:46.206974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.14523","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":"2026-07-05T05:46:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"naonRpK7CSjKjUax472Z2qMAyRb6TJ2rRl+kNbBF5Aow1Xe+l8Qr5P61sxzclH7KNogRrFaSPnAPN4BKeiP/Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T09:24:08.051712Z"},"content_sha256":"51fbc5ebb5d06a4e97019e3a39c7e298cbb1eee0bb2b93c9ed398a117f7b72a8","schema_version":"1.0","event_id":"sha256:51fbc5ebb5d06a4e97019e3a39c7e298cbb1eee0bb2b93c9ed398a117f7b72a8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:3MY6FZPVRYAOIDJHNOT2LFMX2E","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Automatic Heteronym Resolution Pipeline Using RAD-TTS Aligners","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Evelina Bakhturina, Jocelyn Huang, Oktai Tatanov","submitted_at":"2023-02-28T12:33:12Z","abstract_excerpt":"Grapheme-to-phoneme (G2P) transduction is part of the standard text-to-speech (TTS) pipeline. However, G2P conversion is difficult for languages that contain heteronyms -- words that have one spelling but can be pronounced in multiple ways. G2P datasets with annotated heteronyms are limited in size and expensive to create, as human labeling remains the primary method for heteronym disambiguation. We propose a RAD-TTS Aligner-based pipeline to automatically disambiguate heteronyms in datasets that contain both audio with text transcripts. The best pronunciation can be chosen by generating all p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.14523","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/2302.14523/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":"2026-07-05T05:46:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3pQfHO4LMASTH2/hTx8Mr/SqHkE7eYJfPqR1cszFOtKHnoIkOybjhD/zyatFcvfKHzCwt0FPILZR+4vQszgtCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T09:24:08.052466Z"},"content_sha256":"0bb6f39affe4559148fd320b180ac08adedc20d9a231d18e480cc40587fcdf38","schema_version":"1.0","event_id":"sha256:0bb6f39affe4559148fd320b180ac08adedc20d9a231d18e480cc40587fcdf38"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3MY6FZPVRYAOIDJHNOT2LFMX2E/bundle.json","state_url":"https://pith.science/pith/3MY6FZPVRYAOIDJHNOT2LFMX2E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3MY6FZPVRYAOIDJHNOT2LFMX2E/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":"2026-08-19T09:24:08Z","links":{"resolver":"https://pith.science/pith/3MY6FZPVRYAOIDJHNOT2LFMX2E","bundle":"https://pith.science/pith/3MY6FZPVRYAOIDJHNOT2LFMX2E/bundle.json","state":"https://pith.science/pith/3MY6FZPVRYAOIDJHNOT2LFMX2E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3MY6FZPVRYAOIDJHNOT2LFMX2E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:3MY6FZPVRYAOIDJHNOT2LFMX2E","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":"bb98c5d9151a12a258d1147ad9053d1c0f78e97a1f9c84bd840a5f2a77fb248c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-28T12:33:12Z","title_canon_sha256":"fdc550e042f8bcfe2cfc3e6e4caf33f21d9241a5be0aae6f06e6feb30fa83e26"},"schema_version":"1.0","source":{"id":"2302.14523","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.14523","created_at":"2026-07-05T05:46:46Z"},{"alias_kind":"arxiv_version","alias_value":"2302.14523v1","created_at":"2026-07-05T05:46:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.14523","created_at":"2026-07-05T05:46:46Z"},{"alias_kind":"pith_short_12","alias_value":"3MY6FZPVRYAO","created_at":"2026-07-05T05:46:46Z"},{"alias_kind":"pith_short_16","alias_value":"3MY6FZPVRYAOIDJH","created_at":"2026-07-05T05:46:46Z"},{"alias_kind":"pith_short_8","alias_value":"3MY6FZPV","created_at":"2026-07-05T05:46:46Z"}],"graph_snapshots":[{"event_id":"sha256:0bb6f39affe4559148fd320b180ac08adedc20d9a231d18e480cc40587fcdf38","target":"graph","created_at":"2026-07-05T05:46:46Z","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/2302.14523/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Grapheme-to-phoneme (G2P) transduction is part of the standard text-to-speech (TTS) pipeline. However, G2P conversion is difficult for languages that contain heteronyms -- words that have one spelling but can be pronounced in multiple ways. G2P datasets with annotated heteronyms are limited in size and expensive to create, as human labeling remains the primary method for heteronym disambiguation. We propose a RAD-TTS Aligner-based pipeline to automatically disambiguate heteronyms in datasets that contain both audio with text transcripts. The best pronunciation can be chosen by generating all p","authors_text":"Evelina Bakhturina, Jocelyn Huang, Oktai Tatanov","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-28T12:33:12Z","title":"Automatic Heteronym Resolution Pipeline Using RAD-TTS Aligners"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.14523","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":"sha256:51fbc5ebb5d06a4e97019e3a39c7e298cbb1eee0bb2b93c9ed398a117f7b72a8","target":"record","created_at":"2026-07-05T05:46:46Z","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":"bb98c5d9151a12a258d1147ad9053d1c0f78e97a1f9c84bd840a5f2a77fb248c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-28T12:33:12Z","title_canon_sha256":"fdc550e042f8bcfe2cfc3e6e4caf33f21d9241a5be0aae6f06e6feb30fa83e26"},"schema_version":"1.0","source":{"id":"2302.14523","kind":"arxiv","version":1}},"canonical_sha256":"db31e2e5f58e00e40d276ba7a59597d127ca6ed4378e81e067d947517236f37d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"db31e2e5f58e00e40d276ba7a59597d127ca6ed4378e81e067d947517236f37d","first_computed_at":"2026-07-05T05:46:46.206974Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:46:46.206974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DEB/AUBG2gMgiokpLZkRlad1npjZpcR8KOVBS728X2LLTvdEJZ+VYEXebS0rObthfmr8do6sTiqdf7GDFjfkAA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:46:46.207335Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.14523","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:51fbc5ebb5d06a4e97019e3a39c7e298cbb1eee0bb2b93c9ed398a117f7b72a8","sha256:0bb6f39affe4559148fd320b180ac08adedc20d9a231d18e480cc40587fcdf38"],"state_sha256":"fd683cc2f1cc5ba64f08c442cc111c2d604de21ff00d731710eec292eca2d392"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L7Pu8w0hBGehe0ErxzIHHHaY/PVh/PyraBqg/mqFzwx2hrMr5Gg0JzcJwNbB/on0iceTTc8skebtPBCirR4KDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T09:24:08.057605Z","bundle_sha256":"4352809dadc13eca9cc15b6405a3ddf3d5d2dcb5df0e8f410292f824a12ef54a"}}