{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:U3GRAVILG3Y5MTXPZ7JCHZ3F3K","short_pith_number":"pith:U3GRAVIL","canonical_record":{"source":{"id":"2606.16417","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-15T08:55:28Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"7f87edd3dfe8c60b61c6985c6b47cdced20e5b0f509665cdbc7b40cdd30becf0","abstract_canon_sha256":"7005c476be098f5a2656cdea23f395e42ed9f3c26217ac44c94e0cbe1f81fe94"},"schema_version":"1.0"},"canonical_sha256":"a6cd10550b36f1d64eefcfd223e765dab2e9fa964dff899c71faa32f2d7737fa","source":{"kind":"arxiv","id":"2606.16417","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.16417","created_at":"2026-06-19T16:12:56Z"},{"alias_kind":"arxiv_version","alias_value":"2606.16417v2","created_at":"2026-06-19T16:12:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.16417","created_at":"2026-06-19T16:12:56Z"},{"alias_kind":"pith_short_12","alias_value":"U3GRAVILG3Y5","created_at":"2026-06-19T16:12:56Z"},{"alias_kind":"pith_short_16","alias_value":"U3GRAVILG3Y5MTXP","created_at":"2026-06-19T16:12:56Z"},{"alias_kind":"pith_short_8","alias_value":"U3GRAVIL","created_at":"2026-06-19T16:12:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:U3GRAVILG3Y5MTXPZ7JCHZ3F3K","target":"record","payload":{"canonical_record":{"source":{"id":"2606.16417","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-15T08:55:28Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"7f87edd3dfe8c60b61c6985c6b47cdced20e5b0f509665cdbc7b40cdd30becf0","abstract_canon_sha256":"7005c476be098f5a2656cdea23f395e42ed9f3c26217ac44c94e0cbe1f81fe94"},"schema_version":"1.0"},"canonical_sha256":"a6cd10550b36f1d64eefcfd223e765dab2e9fa964dff899c71faa32f2d7737fa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:12:56.418678Z","signature_b64":"x7yZtbh+EgCYyJ3kYyOETJ7/5vdtWW8OD243Qw/PygOwFnwqmeJWpgd8HOpevLQMrMi6SX2YbliXiuXfN/PzCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a6cd10550b36f1d64eefcfd223e765dab2e9fa964dff899c71faa32f2d7737fa","last_reissued_at":"2026-06-19T16:12:56.418287Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:12:56.418287Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.16417","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":"2026-06-19T16:12:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"COiu8VtT8Q3eLVX6mpDxxVm2g5tMNT6yi5wQV/9JHqUeIGQnvswulZl7nPoLmrW3+gfNvzooYUaY4S68Hf47DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T07:20:13.652534Z"},"content_sha256":"591b9f733c27a6487336348a5ddbbedf74cf9858aae6b88deef11e1490577c8a","schema_version":"1.0","event_id":"sha256:591b9f733c27a6487336348a5ddbbedf74cf9858aae6b88deef11e1490577c8a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:U3GRAVILG3Y5MTXPZ7JCHZ3F3K","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Joycent: Diffusion-based Accent TTS without Accented Phone Prediction","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Xintong Wang, Ye Wang","submitted_at":"2026-06-15T08:55:28Z","abstract_excerpt":"Accent text-to-speech (TTS) aims to synthesize speech with target accents. Existing accent TTS systems typically rely on a two-stage pipeline that first converts standard phone sequences into accented phone sequences and then synthesizes accented speech. However, such approaches suffer from error accumulation and require paired standard-accented phone sequence data, which is often limited in practice. Moreover, text-based accented phone representations are insufficient to model acoustic accent characteristics such as prosody and rhythm. In this work, we propose Joycent, a diffusion-based accen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.16417","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.16417/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":"2026-06-19T16:12:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bIJ+GbXvoUvdibMwjT5KIvtsFgkXVdCy2QgRYohCOIraDfjXIKUV238dhzWtObMdx1o03PY1l63VRl2OyAB8Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T07:20:13.652912Z"},"content_sha256":"21569d9963e4ec10a25923d1e65814d376a7a3f715a5e634b7ab58d1f8539602","schema_version":"1.0","event_id":"sha256:21569d9963e4ec10a25923d1e65814d376a7a3f715a5e634b7ab58d1f8539602"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/U3GRAVILG3Y5MTXPZ7JCHZ3F3K/bundle.json","state_url":"https://pith.science/pith/U3GRAVILG3Y5MTXPZ7JCHZ3F3K/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/U3GRAVILG3Y5MTXPZ7JCHZ3F3K/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":"2026-07-04T07:20:13Z","links":{"resolver":"https://pith.science/pith/U3GRAVILG3Y5MTXPZ7JCHZ3F3K","bundle":"https://pith.science/pith/U3GRAVILG3Y5MTXPZ7JCHZ3F3K/bundle.json","state":"https://pith.science/pith/U3GRAVILG3Y5MTXPZ7JCHZ3F3K/state.json","well_known_bundle":"https://pith.science/.well-known/pith/U3GRAVILG3Y5MTXPZ7JCHZ3F3K/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:U3GRAVILG3Y5MTXPZ7JCHZ3F3K","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":"7005c476be098f5a2656cdea23f395e42ed9f3c26217ac44c94e0cbe1f81fe94","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-15T08:55:28Z","title_canon_sha256":"7f87edd3dfe8c60b61c6985c6b47cdced20e5b0f509665cdbc7b40cdd30becf0"},"schema_version":"1.0","source":{"id":"2606.16417","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.16417","created_at":"2026-06-19T16:12:56Z"},{"alias_kind":"arxiv_version","alias_value":"2606.16417v2","created_at":"2026-06-19T16:12:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.16417","created_at":"2026-06-19T16:12:56Z"},{"alias_kind":"pith_short_12","alias_value":"U3GRAVILG3Y5","created_at":"2026-06-19T16:12:56Z"},{"alias_kind":"pith_short_16","alias_value":"U3GRAVILG3Y5MTXP","created_at":"2026-06-19T16:12:56Z"},{"alias_kind":"pith_short_8","alias_value":"U3GRAVIL","created_at":"2026-06-19T16:12:56Z"}],"graph_snapshots":[{"event_id":"sha256:21569d9963e4ec10a25923d1e65814d376a7a3f715a5e634b7ab58d1f8539602","target":"graph","created_at":"2026-06-19T16:12:56Z","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/2606.16417/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Accent text-to-speech (TTS) aims to synthesize speech with target accents. Existing accent TTS systems typically rely on a two-stage pipeline that first converts standard phone sequences into accented phone sequences and then synthesizes accented speech. However, such approaches suffer from error accumulation and require paired standard-accented phone sequence data, which is often limited in practice. Moreover, text-based accented phone representations are insufficient to model acoustic accent characteristics such as prosody and rhythm. In this work, we propose Joycent, a diffusion-based accen","authors_text":"Xintong Wang, Ye Wang","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-15T08:55:28Z","title":"Joycent: Diffusion-based Accent TTS without Accented Phone Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.16417","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":"sha256:591b9f733c27a6487336348a5ddbbedf74cf9858aae6b88deef11e1490577c8a","target":"record","created_at":"2026-06-19T16:12:56Z","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":"7005c476be098f5a2656cdea23f395e42ed9f3c26217ac44c94e0cbe1f81fe94","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-15T08:55:28Z","title_canon_sha256":"7f87edd3dfe8c60b61c6985c6b47cdced20e5b0f509665cdbc7b40cdd30becf0"},"schema_version":"1.0","source":{"id":"2606.16417","kind":"arxiv","version":2}},"canonical_sha256":"a6cd10550b36f1d64eefcfd223e765dab2e9fa964dff899c71faa32f2d7737fa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a6cd10550b36f1d64eefcfd223e765dab2e9fa964dff899c71faa32f2d7737fa","first_computed_at":"2026-06-19T16:12:56.418287Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:12:56.418287Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"x7yZtbh+EgCYyJ3kYyOETJ7/5vdtWW8OD243Qw/PygOwFnwqmeJWpgd8HOpevLQMrMi6SX2YbliXiuXfN/PzCA==","signature_status":"signed_v1","signed_at":"2026-06-19T16:12:56.418678Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.16417","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:591b9f733c27a6487336348a5ddbbedf74cf9858aae6b88deef11e1490577c8a","sha256:21569d9963e4ec10a25923d1e65814d376a7a3f715a5e634b7ab58d1f8539602"],"state_sha256":"44bb1c276b5371827774cdb4b74a3bc234f28efac490260d6b6de913a6a457d0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8tq3UkXETGaieLRbdIHcqVxGtzuiK8rKYbef0ZxqjWDEd2X5kzN0nKyq4xyg0ro12rnXqHbX0/0zInLOCBedCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-04T07:20:13.660017Z","bundle_sha256":"46b2b490b21df7864f2b24e64b715dd94baba486ab1f515d4297af2719486ba5"}}