{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:2B36X3ALDWR4PGJFLFVQQQ3CVX","short_pith_number":"pith:2B36X3AL","canonical_record":{"source":{"id":"2406.04633","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-07T04:34:03Z","cross_cats_sorted":[],"title_canon_sha256":"0c55fdd897018d8f16894bcc0f547da00fe05b96b514976cbddec23dfc70d5d3","abstract_canon_sha256":"ca58a863311613259e2efaeae616fb77d3f2deb873ddd9d7a6cf140c3a662059"},"schema_version":"1.0"},"canonical_sha256":"d077ebec0b1da3c79925596b084362adc1606389835e7057e5ad14d7ef47724f","source":{"kind":"arxiv","id":"2406.04633","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.04633","created_at":"2026-07-05T08:28:46Z"},{"alias_kind":"arxiv_version","alias_value":"2406.04633v1","created_at":"2026-07-05T08:28:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04633","created_at":"2026-07-05T08:28:46Z"},{"alias_kind":"pith_short_12","alias_value":"2B36X3ALDWR4","created_at":"2026-07-05T08:28:46Z"},{"alias_kind":"pith_short_16","alias_value":"2B36X3ALDWR4PGJF","created_at":"2026-07-05T08:28:46Z"},{"alias_kind":"pith_short_8","alias_value":"2B36X3AL","created_at":"2026-07-05T08:28:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:2B36X3ALDWR4PGJFLFVQQQ3CVX","target":"record","payload":{"canonical_record":{"source":{"id":"2406.04633","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-07T04:34:03Z","cross_cats_sorted":[],"title_canon_sha256":"0c55fdd897018d8f16894bcc0f547da00fe05b96b514976cbddec23dfc70d5d3","abstract_canon_sha256":"ca58a863311613259e2efaeae616fb77d3f2deb873ddd9d7a6cf140c3a662059"},"schema_version":"1.0"},"canonical_sha256":"d077ebec0b1da3c79925596b084362adc1606389835e7057e5ad14d7ef47724f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:46.771803Z","signature_b64":"eLSDgWhI/BLoJSCvI7L/ASDkgGA7TKD9VbNhq68KHQELWB///QnuDCYazjKnxmCD5Qi8P1WEy+vrHJSVyAzfAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d077ebec0b1da3c79925596b084362adc1606389835e7057e5ad14d7ef47724f","last_reissued_at":"2026-07-05T08:28:46.771370Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:46.771370Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.04633","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":"2026-07-05T08:28:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tfspFHdm3UOwgfElyP3nBogkfqLeSMqsyb3o6pKATyb+pMeD2Q9YLz0LdBXlZFQdLoWXsmYfq+6lPNLW60IBDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T10:42:31.086728Z"},"content_sha256":"230679aa63d64f950149ad9ead07b3928925f850b347c7099f0db734929cf822","schema_version":"1.0","event_id":"sha256:230679aa63d64f950149ad9ead07b3928925f850b347c7099f0db734929cf822"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:2B36X3ALDWR4PGJFLFVQQQ3CVX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Boosting Diffusion Model for Spectrogram Up-sampling in Text-to-speech: An Empirical Study","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Chong Zhang, Sheng Zhao, Yang Zheng, Yanqing Liu","submitted_at":"2024-06-07T04:34:03Z","abstract_excerpt":"Scaling text-to-speech (TTS) with autoregressive language model (LM) to large-scale datasets by quantizing waveform into discrete speech tokens is making great progress to capture the diversity and expressiveness in human speech, but the speech reconstruction quality from discrete speech token is far from satisfaction depending on the compressed speech token compression ratio. Generative diffusion models trained with score-matching loss and continuous normalized flow trained with flow-matching loss have become prominent in generation of images as well as speech. LM based TTS systems usually qu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04633","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/2406.04633/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":"2026-07-05T08:28:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Wqc6WJvWaSQnsFmSoTWPsc1sClsOI8avcjgJocA1e6Mja9lx+0zI/MK61mcI2WdXOI33EK3XEVKFEQzR9Vy8Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T10:42:31.087208Z"},"content_sha256":"3da4df1d5692df64bf58cbc4d6714bc163afa3692c120269d18552b8158f659d","schema_version":"1.0","event_id":"sha256:3da4df1d5692df64bf58cbc4d6714bc163afa3692c120269d18552b8158f659d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2B36X3ALDWR4PGJFLFVQQQ3CVX/bundle.json","state_url":"https://pith.science/pith/2B36X3ALDWR4PGJFLFVQQQ3CVX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2B36X3ALDWR4PGJFLFVQQQ3CVX/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":"2026-08-08T10:42:31Z","links":{"resolver":"https://pith.science/pith/2B36X3ALDWR4PGJFLFVQQQ3CVX","bundle":"https://pith.science/pith/2B36X3ALDWR4PGJFLFVQQQ3CVX/bundle.json","state":"https://pith.science/pith/2B36X3ALDWR4PGJFLFVQQQ3CVX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2B36X3ALDWR4PGJFLFVQQQ3CVX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2B36X3ALDWR4PGJFLFVQQQ3CVX","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":"ca58a863311613259e2efaeae616fb77d3f2deb873ddd9d7a6cf140c3a662059","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-07T04:34:03Z","title_canon_sha256":"0c55fdd897018d8f16894bcc0f547da00fe05b96b514976cbddec23dfc70d5d3"},"schema_version":"1.0","source":{"id":"2406.04633","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.04633","created_at":"2026-07-05T08:28:46Z"},{"alias_kind":"arxiv_version","alias_value":"2406.04633v1","created_at":"2026-07-05T08:28:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04633","created_at":"2026-07-05T08:28:46Z"},{"alias_kind":"pith_short_12","alias_value":"2B36X3ALDWR4","created_at":"2026-07-05T08:28:46Z"},{"alias_kind":"pith_short_16","alias_value":"2B36X3ALDWR4PGJF","created_at":"2026-07-05T08:28:46Z"},{"alias_kind":"pith_short_8","alias_value":"2B36X3AL","created_at":"2026-07-05T08:28:46Z"}],"graph_snapshots":[{"event_id":"sha256:3da4df1d5692df64bf58cbc4d6714bc163afa3692c120269d18552b8158f659d","target":"graph","created_at":"2026-07-05T08:28:46Z","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/2406.04633/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Scaling text-to-speech (TTS) with autoregressive language model (LM) to large-scale datasets by quantizing waveform into discrete speech tokens is making great progress to capture the diversity and expressiveness in human speech, but the speech reconstruction quality from discrete speech token is far from satisfaction depending on the compressed speech token compression ratio. Generative diffusion models trained with score-matching loss and continuous normalized flow trained with flow-matching loss have become prominent in generation of images as well as speech. LM based TTS systems usually qu","authors_text":"Chong Zhang, Sheng Zhao, Yang Zheng, Yanqing Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-07T04:34:03Z","title":"Boosting Diffusion Model for Spectrogram Up-sampling in Text-to-speech: An Empirical Study"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04633","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":"sha256:230679aa63d64f950149ad9ead07b3928925f850b347c7099f0db734929cf822","target":"record","created_at":"2026-07-05T08:28:46Z","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":"ca58a863311613259e2efaeae616fb77d3f2deb873ddd9d7a6cf140c3a662059","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-07T04:34:03Z","title_canon_sha256":"0c55fdd897018d8f16894bcc0f547da00fe05b96b514976cbddec23dfc70d5d3"},"schema_version":"1.0","source":{"id":"2406.04633","kind":"arxiv","version":1}},"canonical_sha256":"d077ebec0b1da3c79925596b084362adc1606389835e7057e5ad14d7ef47724f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d077ebec0b1da3c79925596b084362adc1606389835e7057e5ad14d7ef47724f","first_computed_at":"2026-07-05T08:28:46.771370Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:28:46.771370Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eLSDgWhI/BLoJSCvI7L/ASDkgGA7TKD9VbNhq68KHQELWB///QnuDCYazjKnxmCD5Qi8P1WEy+vrHJSVyAzfAA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:28:46.771803Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.04633","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:230679aa63d64f950149ad9ead07b3928925f850b347c7099f0db734929cf822","sha256:3da4df1d5692df64bf58cbc4d6714bc163afa3692c120269d18552b8158f659d"],"state_sha256":"f795f10d2a74c1cc8e330fe5bc3949eadd1ee22f9449a0d135a6e2e29880ab1c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wUMFIz42ld2AY/OfKBZTcS/CG4Cdgs38cXFw7860W+sfx/Z0q5RMJ94SuYXnf41LNExFIXiozvzM0I0zx9fpAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T10:42:31.090515Z","bundle_sha256":"53221be134a8ac2bd50ccd1df9ebe6e5d369dcff114164f8ec13e25843dd0939"}}