{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:DBG5FU5Z7IA6ELRFXCGUDKM4PA","short_pith_number":"pith:DBG5FU5Z","canonical_record":{"source":{"id":"2406.17957","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-06-25T22:18:52Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"9c3442af7944ed77ccb89bfe846eb15c353243432391fa2e6e8afd2135486ca1","abstract_canon_sha256":"7ac3f2ebb47578d010abcd8f8dcf317eb9b6bacd9667460655d5449e6b80884e"},"schema_version":"1.0"},"canonical_sha256":"184dd2d3b9fa01e22e25b88d41a99c7832d29f57a89196285e4b975b7357708f","source":{"kind":"arxiv","id":"2406.17957","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.17957","created_at":"2026-07-05T08:36:52Z"},{"alias_kind":"arxiv_version","alias_value":"2406.17957v1","created_at":"2026-07-05T08:36:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.17957","created_at":"2026-07-05T08:36:52Z"},{"alias_kind":"pith_short_12","alias_value":"DBG5FU5Z7IA6","created_at":"2026-07-05T08:36:52Z"},{"alias_kind":"pith_short_16","alias_value":"DBG5FU5Z7IA6ELRF","created_at":"2026-07-05T08:36:52Z"},{"alias_kind":"pith_short_8","alias_value":"DBG5FU5Z","created_at":"2026-07-05T08:36:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:DBG5FU5Z7IA6ELRFXCGUDKM4PA","target":"record","payload":{"canonical_record":{"source":{"id":"2406.17957","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-06-25T22:18:52Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"9c3442af7944ed77ccb89bfe846eb15c353243432391fa2e6e8afd2135486ca1","abstract_canon_sha256":"7ac3f2ebb47578d010abcd8f8dcf317eb9b6bacd9667460655d5449e6b80884e"},"schema_version":"1.0"},"canonical_sha256":"184dd2d3b9fa01e22e25b88d41a99c7832d29f57a89196285e4b975b7357708f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:36:52.929125Z","signature_b64":"90/467aX8Rj2EgE6rDN5sjtYNE425UsHPg72zpL6x/m34s1UxGfgbXjWwPCe7dwzskkufFpWvZX+s3hezdATBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"184dd2d3b9fa01e22e25b88d41a99c7832d29f57a89196285e4b975b7357708f","last_reissued_at":"2026-07-05T08:36:52.928650Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:36:52.928650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.17957","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":"2026-07-05T08:36:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dS4mOrfU4IErrl6kyNbg0kWUZsBfoJ+ps44zNnEMdqPqnwFF2CIqhtqNfi+DIW2+WkXklNX4AoyGN2pM8FGUCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T20:14:30.553740Z"},"content_sha256":"41a99433dd5c5d0d523c12286c10ee164f65b60999c4019cd5ad475aa5b1d97e","schema_version":"1.0","event_id":"sha256:41a99433dd5c5d0d523c12286c10ee164f65b60999c4019cd5ad475aa5b1d97e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:DBG5FU5Z7IA6ELRFXCGUDKM4PA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Robustness of LLM-based Speech Synthesis by Learning Monotonic Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Boris Ginsburg, Jason Li, Paarth Neekhara, Rafael Valle, Rohan Badlani, Shehzeen Hussain, Subhankar Ghosh","submitted_at":"2024-06-25T22:18:52Z","abstract_excerpt":"Large Language Model (LLM) based text-to-speech (TTS) systems have demonstrated remarkable capabilities in handling large speech datasets and generating natural speech for new speakers. However, LLM-based TTS models are not robust as the generated output can contain repeating words, missing words and mis-aligned speech (referred to as hallucinations or attention errors), especially when the text contains multiple occurrences of the same token. We examine these challenges in an encoder-decoder transformer model and find that certain cross-attention heads in such models implicitly learn the text"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.17957","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/2406.17957/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":"2026-07-05T08:36:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CoE00LppW8zTSFBHb/8VPJQ+jiiyyKzculcnP9THBXu5iH6GAxtxZzBZhzZnFHUSMB0jQMa2Bzr712+QSNSmCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T20:14:30.554262Z"},"content_sha256":"f5e761708b7e309c70bcd30f145818d330a7f3590d097e040aa499eacae997c1","schema_version":"1.0","event_id":"sha256:f5e761708b7e309c70bcd30f145818d330a7f3590d097e040aa499eacae997c1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DBG5FU5Z7IA6ELRFXCGUDKM4PA/bundle.json","state_url":"https://pith.science/pith/DBG5FU5Z7IA6ELRFXCGUDKM4PA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DBG5FU5Z7IA6ELRFXCGUDKM4PA/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":"2026-08-05T20:14:30Z","links":{"resolver":"https://pith.science/pith/DBG5FU5Z7IA6ELRFXCGUDKM4PA","bundle":"https://pith.science/pith/DBG5FU5Z7IA6ELRFXCGUDKM4PA/bundle.json","state":"https://pith.science/pith/DBG5FU5Z7IA6ELRFXCGUDKM4PA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DBG5FU5Z7IA6ELRFXCGUDKM4PA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DBG5FU5Z7IA6ELRFXCGUDKM4PA","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":"7ac3f2ebb47578d010abcd8f8dcf317eb9b6bacd9667460655d5449e6b80884e","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-06-25T22:18:52Z","title_canon_sha256":"9c3442af7944ed77ccb89bfe846eb15c353243432391fa2e6e8afd2135486ca1"},"schema_version":"1.0","source":{"id":"2406.17957","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.17957","created_at":"2026-07-05T08:36:52Z"},{"alias_kind":"arxiv_version","alias_value":"2406.17957v1","created_at":"2026-07-05T08:36:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.17957","created_at":"2026-07-05T08:36:52Z"},{"alias_kind":"pith_short_12","alias_value":"DBG5FU5Z7IA6","created_at":"2026-07-05T08:36:52Z"},{"alias_kind":"pith_short_16","alias_value":"DBG5FU5Z7IA6ELRF","created_at":"2026-07-05T08:36:52Z"},{"alias_kind":"pith_short_8","alias_value":"DBG5FU5Z","created_at":"2026-07-05T08:36:52Z"}],"graph_snapshots":[{"event_id":"sha256:f5e761708b7e309c70bcd30f145818d330a7f3590d097e040aa499eacae997c1","target":"graph","created_at":"2026-07-05T08:36:52Z","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/2406.17957/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Model (LLM) based text-to-speech (TTS) systems have demonstrated remarkable capabilities in handling large speech datasets and generating natural speech for new speakers. However, LLM-based TTS models are not robust as the generated output can contain repeating words, missing words and mis-aligned speech (referred to as hallucinations or attention errors), especially when the text contains multiple occurrences of the same token. We examine these challenges in an encoder-decoder transformer model and find that certain cross-attention heads in such models implicitly learn the text","authors_text":"Boris Ginsburg, Jason Li, Paarth Neekhara, Rafael Valle, Rohan Badlani, Shehzeen Hussain, Subhankar Ghosh","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-06-25T22:18:52Z","title":"Improving Robustness of LLM-based Speech Synthesis by Learning Monotonic Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.17957","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":"sha256:41a99433dd5c5d0d523c12286c10ee164f65b60999c4019cd5ad475aa5b1d97e","target":"record","created_at":"2026-07-05T08:36:52Z","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":"7ac3f2ebb47578d010abcd8f8dcf317eb9b6bacd9667460655d5449e6b80884e","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-06-25T22:18:52Z","title_canon_sha256":"9c3442af7944ed77ccb89bfe846eb15c353243432391fa2e6e8afd2135486ca1"},"schema_version":"1.0","source":{"id":"2406.17957","kind":"arxiv","version":1}},"canonical_sha256":"184dd2d3b9fa01e22e25b88d41a99c7832d29f57a89196285e4b975b7357708f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"184dd2d3b9fa01e22e25b88d41a99c7832d29f57a89196285e4b975b7357708f","first_computed_at":"2026-07-05T08:36:52.928650Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:36:52.928650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"90/467aX8Rj2EgE6rDN5sjtYNE425UsHPg72zpL6x/m34s1UxGfgbXjWwPCe7dwzskkufFpWvZX+s3hezdATBw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:36:52.929125Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.17957","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:41a99433dd5c5d0d523c12286c10ee164f65b60999c4019cd5ad475aa5b1d97e","sha256:f5e761708b7e309c70bcd30f145818d330a7f3590d097e040aa499eacae997c1"],"state_sha256":"f7bd37f5dd9f7e5b01b7a2e64902d56f0857823b59fe7b906b48623ffee04fdc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2+JvE1ymnPBnT7S6hoeMVHX/vn/urDwvEcLoZAPt+F2mHAeGeYkO7o9HYhH/0MXBrJvS9GQnbeaCsoFpTrouAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T20:14:30.559712Z","bundle_sha256":"b4e4544e84b0c07e9e4d7f76dd5e7a4eabc7f7e81ec792af2141f5913dd9fd62"}}