{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:GDKRF7S2VI6CW26RE6OY7MTC7W","short_pith_number":"pith:GDKRF7S2","canonical_record":{"source":{"id":"2507.03912","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-07-05T05:56:49Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"3842611c973cbf7c264e7b59959f0cc785beced68257f16312c0a9cd1f3afa3e","abstract_canon_sha256":"27ef8ffb88e5fcddd174657aa819eecdcf20423445caaae219fa1f3a06f615a6"},"schema_version":"1.0"},"canonical_sha256":"30d512fe5aaa3c2b6bd1279d8fb262fd9d47dcd5d302b3a8f19523be4864ac60","source":{"kind":"arxiv","id":"2507.03912","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.03912","created_at":"2026-07-05T11:32:37Z"},{"alias_kind":"arxiv_version","alias_value":"2507.03912v1","created_at":"2026-07-05T11:32:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.03912","created_at":"2026-07-05T11:32:37Z"},{"alias_kind":"pith_short_12","alias_value":"GDKRF7S2VI6C","created_at":"2026-07-05T11:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"GDKRF7S2VI6CW26R","created_at":"2026-07-05T11:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"GDKRF7S2","created_at":"2026-07-05T11:32:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:GDKRF7S2VI6CW26RE6OY7MTC7W","target":"record","payload":{"canonical_record":{"source":{"id":"2507.03912","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-07-05T05:56:49Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"3842611c973cbf7c264e7b59959f0cc785beced68257f16312c0a9cd1f3afa3e","abstract_canon_sha256":"27ef8ffb88e5fcddd174657aa819eecdcf20423445caaae219fa1f3a06f615a6"},"schema_version":"1.0"},"canonical_sha256":"30d512fe5aaa3c2b6bd1279d8fb262fd9d47dcd5d302b3a8f19523be4864ac60","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:32:37.155934Z","signature_b64":"FuvuWd1TpLlYg1FpQ/QqEXY9J2Lq071rK+qfBdYuPZJfcI171dbvBEY43KQT/QqgfMOfjuDXBHN4lVuH/Y1BCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30d512fe5aaa3c2b6bd1279d8fb262fd9d47dcd5d302b3a8f19523be4864ac60","last_reissued_at":"2026-07-05T11:32:37.155405Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:32:37.155405Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.03912","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":"2026-07-05T11:32:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TABEaAtP8GkM4liQB7k8Vc+OOYd34ehsJKyF+YV3ZeNdYor2XKPLFXiIMT4c1m3TImGbcoGlnLHY075PNCvKBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T12:03:27.463807Z"},"content_sha256":"41e7a376f9ac9ef540c4d375823416c8c4ef9ade59f4869f5f9e82e884697b26","schema_version":"1.0","event_id":"sha256:41e7a376f9ac9ef540c4d375823416c8c4ef9ade59f4869f5f9e82e884697b26"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:GDKRF7S2VI6CW26RE6OY7MTC7W","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Prosody Labeling with Phoneme-BERT and Speech Foundation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Tomoki Koriyama","submitted_at":"2025-07-05T05:56:49Z","abstract_excerpt":"This paper proposes a model for automatic prosodic label annotation, where the predicted labels can be used for training a prosody-controllable text-to-speech model. The proposed model utilizes not only rich acoustic features extracted by a self-supervised-learning (SSL)-based model or a Whisper encoder, but also linguistic features obtained from phoneme-input pretrained linguistic foundation models such as PnG BERT and PL-BERT. The concatenation of acoustic and linguistic features is used to predict phoneme-level prosodic labels. In the experimental evaluation on Japanese prosodic labels, inc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.03912","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/2507.03912/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":"2026-07-05T11:32:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qzn4S83MPeUtVdN5go6uvpcyuCh0WPBSlzb7nK7fJE2HXJ2eLfrDbl6EaTzmmP1d8RokXW/VHStWfmRtwdCzCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T12:03:27.464399Z"},"content_sha256":"41685cd193818f33c3495ec2ab78dd909eed97371b32ada33520571140a03c98","schema_version":"1.0","event_id":"sha256:41685cd193818f33c3495ec2ab78dd909eed97371b32ada33520571140a03c98"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GDKRF7S2VI6CW26RE6OY7MTC7W/bundle.json","state_url":"https://pith.science/pith/GDKRF7S2VI6CW26RE6OY7MTC7W/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GDKRF7S2VI6CW26RE6OY7MTC7W/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":"2026-08-16T12:03:27Z","links":{"resolver":"https://pith.science/pith/GDKRF7S2VI6CW26RE6OY7MTC7W","bundle":"https://pith.science/pith/GDKRF7S2VI6CW26RE6OY7MTC7W/bundle.json","state":"https://pith.science/pith/GDKRF7S2VI6CW26RE6OY7MTC7W/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GDKRF7S2VI6CW26RE6OY7MTC7W/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GDKRF7S2VI6CW26RE6OY7MTC7W","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":"27ef8ffb88e5fcddd174657aa819eecdcf20423445caaae219fa1f3a06f615a6","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-07-05T05:56:49Z","title_canon_sha256":"3842611c973cbf7c264e7b59959f0cc785beced68257f16312c0a9cd1f3afa3e"},"schema_version":"1.0","source":{"id":"2507.03912","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.03912","created_at":"2026-07-05T11:32:37Z"},{"alias_kind":"arxiv_version","alias_value":"2507.03912v1","created_at":"2026-07-05T11:32:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.03912","created_at":"2026-07-05T11:32:37Z"},{"alias_kind":"pith_short_12","alias_value":"GDKRF7S2VI6C","created_at":"2026-07-05T11:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"GDKRF7S2VI6CW26R","created_at":"2026-07-05T11:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"GDKRF7S2","created_at":"2026-07-05T11:32:37Z"}],"graph_snapshots":[{"event_id":"sha256:41685cd193818f33c3495ec2ab78dd909eed97371b32ada33520571140a03c98","target":"graph","created_at":"2026-07-05T11:32:37Z","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/2507.03912/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper proposes a model for automatic prosodic label annotation, where the predicted labels can be used for training a prosody-controllable text-to-speech model. The proposed model utilizes not only rich acoustic features extracted by a self-supervised-learning (SSL)-based model or a Whisper encoder, but also linguistic features obtained from phoneme-input pretrained linguistic foundation models such as PnG BERT and PL-BERT. The concatenation of acoustic and linguistic features is used to predict phoneme-level prosodic labels. In the experimental evaluation on Japanese prosodic labels, inc","authors_text":"Tomoki Koriyama","cross_cats":["cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-07-05T05:56:49Z","title":"Prosody Labeling with Phoneme-BERT and Speech Foundation Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.03912","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":"sha256:41e7a376f9ac9ef540c4d375823416c8c4ef9ade59f4869f5f9e82e884697b26","target":"record","created_at":"2026-07-05T11:32:37Z","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":"27ef8ffb88e5fcddd174657aa819eecdcf20423445caaae219fa1f3a06f615a6","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-07-05T05:56:49Z","title_canon_sha256":"3842611c973cbf7c264e7b59959f0cc785beced68257f16312c0a9cd1f3afa3e"},"schema_version":"1.0","source":{"id":"2507.03912","kind":"arxiv","version":1}},"canonical_sha256":"30d512fe5aaa3c2b6bd1279d8fb262fd9d47dcd5d302b3a8f19523be4864ac60","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"30d512fe5aaa3c2b6bd1279d8fb262fd9d47dcd5d302b3a8f19523be4864ac60","first_computed_at":"2026-07-05T11:32:37.155405Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:32:37.155405Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FuvuWd1TpLlYg1FpQ/QqEXY9J2Lq071rK+qfBdYuPZJfcI171dbvBEY43KQT/QqgfMOfjuDXBHN4lVuH/Y1BCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:32:37.155934Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.03912","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:41e7a376f9ac9ef540c4d375823416c8c4ef9ade59f4869f5f9e82e884697b26","sha256:41685cd193818f33c3495ec2ab78dd909eed97371b32ada33520571140a03c98"],"state_sha256":"d6b1112390211cfce29b487541e04134c071ca275704d3ea17a372e3f14a140a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9nQLFk23ORobMgUL1iqpdQaTam7XrLVqbWXd0eYj/7RCWbOazDVZHN5M8pT49FGoBjjl/91eAPQFuIXyyswBCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T12:03:27.469683Z","bundle_sha256":"22caaf51e46445d95db9cc364fcb275d86eee6ce3cd8625de69cf0d40db09f78"}}