{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:U7L3BSXXMV4GEKXRN6QIRPC2X4","short_pith_number":"pith:U7L3BSXX","canonical_record":{"source":{"id":"2406.02328","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-06-04T13:58:28Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"65fd0276d6a7fabf1f71c9e5d49a81be3a78349068a8da06e5ceb7c0e5f9afd0","abstract_canon_sha256":"7e89847727a766e6a0d85415f3e29bec46a5ce884fc49f294d36761153b396e5"},"schema_version":"1.0"},"canonical_sha256":"a7d7b0caf76578622af16fa088bc5abf014bd47a02c0f07f728d633cdfda91c0","source":{"kind":"arxiv","id":"2406.02328","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.02328","created_at":"2026-07-05T08:31:52Z"},{"alias_kind":"arxiv_version","alias_value":"2406.02328v3","created_at":"2026-07-05T08:31:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02328","created_at":"2026-07-05T08:31:52Z"},{"alias_kind":"pith_short_12","alias_value":"U7L3BSXXMV4G","created_at":"2026-07-05T08:31:52Z"},{"alias_kind":"pith_short_16","alias_value":"U7L3BSXXMV4GEKXR","created_at":"2026-07-05T08:31:52Z"},{"alias_kind":"pith_short_8","alias_value":"U7L3BSXX","created_at":"2026-07-05T08:31:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:U7L3BSXXMV4GEKXRN6QIRPC2X4","target":"record","payload":{"canonical_record":{"source":{"id":"2406.02328","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-06-04T13:58:28Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"65fd0276d6a7fabf1f71c9e5d49a81be3a78349068a8da06e5ceb7c0e5f9afd0","abstract_canon_sha256":"7e89847727a766e6a0d85415f3e29bec46a5ce884fc49f294d36761153b396e5"},"schema_version":"1.0"},"canonical_sha256":"a7d7b0caf76578622af16fa088bc5abf014bd47a02c0f07f728d633cdfda91c0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:31:52.136290Z","signature_b64":"QPnbqSMtVzmsKfwVrOgGt/cpADnc0sssI9TYh2kWNz+aNg2NWq4aY+N7svIeDQmoA6+JWl9NDvRmK8f5lRkQAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7d7b0caf76578622af16fa088bc5abf014bd47a02c0f07f728d633cdfda91c0","last_reissued_at":"2026-07-05T08:31:52.135796Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:31:52.135796Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.02328","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:31:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/943QSopAGn/LvjjhMwXq7OPK1ePXrE4PkGDEIuENom/nyi2wC9sAbPLpxT95TXnLMjQ2vjOKdo5HmPQy7s8Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:09:23.718863Z"},"content_sha256":"80234401788f9eb6595fa37fb53a125bef95d17b4796135352f751d78d9df7e7","schema_version":"1.0","event_id":"sha256:80234401788f9eb6595fa37fb53a125bef95d17b4796135352f751d78d9df7e7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:U7L3BSXXMV4GEKXRN6QIRPC2X4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SimpleSpeech: Towards Simple and Efficient Text-to-Speech with Scalar Latent Transformer Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Dingdong Wang, Dongchao Yang, Haohan Guo, Helen Meng, Xixin Wu, Xueyuan Chen","submitted_at":"2024-06-04T13:58:28Z","abstract_excerpt":"In this study, we propose a simple and efficient Non-Autoregressive (NAR) text-to-speech (TTS) system based on diffusion, named SimpleSpeech. Its simpleness shows in three aspects: (1) It can be trained on the speech-only dataset, without any alignment information; (2) It directly takes plain text as input and generates speech through an NAR way; (3) It tries to model speech in a finite and compact latent space, which alleviates the modeling difficulty of diffusion. More specifically, we propose a novel speech codec model (SQ-Codec) with scalar quantization, SQ-Codec effectively maps the compl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02328","kind":"arxiv","version":3},"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/2406.02328/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":"2026-07-05T08:31:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GBB+ZBYNQLDeAVn3z6h3OSbRjsiMS8PLFaaecODJkxmG+q4uSkDJpzNeAuCrmc78fgTWDhqvlgL1CPO7s37fBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:09:23.719362Z"},"content_sha256":"87025d3ffcf1b8d8bb47ea89d5b428f91d1a705c027be256e629e287ea31ddbf","schema_version":"1.0","event_id":"sha256:87025d3ffcf1b8d8bb47ea89d5b428f91d1a705c027be256e629e287ea31ddbf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/U7L3BSXXMV4GEKXRN6QIRPC2X4/bundle.json","state_url":"https://pith.science/pith/U7L3BSXXMV4GEKXRN6QIRPC2X4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/U7L3BSXXMV4GEKXRN6QIRPC2X4/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":"2026-08-08T22:09:23Z","links":{"resolver":"https://pith.science/pith/U7L3BSXXMV4GEKXRN6QIRPC2X4","bundle":"https://pith.science/pith/U7L3BSXXMV4GEKXRN6QIRPC2X4/bundle.json","state":"https://pith.science/pith/U7L3BSXXMV4GEKXRN6QIRPC2X4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/U7L3BSXXMV4GEKXRN6QIRPC2X4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:U7L3BSXXMV4GEKXRN6QIRPC2X4","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":"7e89847727a766e6a0d85415f3e29bec46a5ce884fc49f294d36761153b396e5","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-06-04T13:58:28Z","title_canon_sha256":"65fd0276d6a7fabf1f71c9e5d49a81be3a78349068a8da06e5ceb7c0e5f9afd0"},"schema_version":"1.0","source":{"id":"2406.02328","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.02328","created_at":"2026-07-05T08:31:52Z"},{"alias_kind":"arxiv_version","alias_value":"2406.02328v3","created_at":"2026-07-05T08:31:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02328","created_at":"2026-07-05T08:31:52Z"},{"alias_kind":"pith_short_12","alias_value":"U7L3BSXXMV4G","created_at":"2026-07-05T08:31:52Z"},{"alias_kind":"pith_short_16","alias_value":"U7L3BSXXMV4GEKXR","created_at":"2026-07-05T08:31:52Z"},{"alias_kind":"pith_short_8","alias_value":"U7L3BSXX","created_at":"2026-07-05T08:31:52Z"}],"graph_snapshots":[{"event_id":"sha256:87025d3ffcf1b8d8bb47ea89d5b428f91d1a705c027be256e629e287ea31ddbf","target":"graph","created_at":"2026-07-05T08:31:52Z","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/2406.02328/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this study, we propose a simple and efficient Non-Autoregressive (NAR) text-to-speech (TTS) system based on diffusion, named SimpleSpeech. Its simpleness shows in three aspects: (1) It can be trained on the speech-only dataset, without any alignment information; (2) It directly takes plain text as input and generates speech through an NAR way; (3) It tries to model speech in a finite and compact latent space, which alleviates the modeling difficulty of diffusion. More specifically, we propose a novel speech codec model (SQ-Codec) with scalar quantization, SQ-Codec effectively maps the compl","authors_text":"Dingdong Wang, Dongchao Yang, Haohan Guo, Helen Meng, Xixin Wu, Xueyuan Chen","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-06-04T13:58:28Z","title":"SimpleSpeech: Towards Simple and Efficient Text-to-Speech with Scalar Latent Transformer Diffusion Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02328","kind":"arxiv","version":3},"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":"sha256:80234401788f9eb6595fa37fb53a125bef95d17b4796135352f751d78d9df7e7","target":"record","created_at":"2026-07-05T08:31:52Z","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":"7e89847727a766e6a0d85415f3e29bec46a5ce884fc49f294d36761153b396e5","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-06-04T13:58:28Z","title_canon_sha256":"65fd0276d6a7fabf1f71c9e5d49a81be3a78349068a8da06e5ceb7c0e5f9afd0"},"schema_version":"1.0","source":{"id":"2406.02328","kind":"arxiv","version":3}},"canonical_sha256":"a7d7b0caf76578622af16fa088bc5abf014bd47a02c0f07f728d633cdfda91c0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a7d7b0caf76578622af16fa088bc5abf014bd47a02c0f07f728d633cdfda91c0","first_computed_at":"2026-07-05T08:31:52.135796Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:31:52.135796Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QPnbqSMtVzmsKfwVrOgGt/cpADnc0sssI9TYh2kWNz+aNg2NWq4aY+N7svIeDQmoA6+JWl9NDvRmK8f5lRkQAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:31:52.136290Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.02328","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:80234401788f9eb6595fa37fb53a125bef95d17b4796135352f751d78d9df7e7","sha256:87025d3ffcf1b8d8bb47ea89d5b428f91d1a705c027be256e629e287ea31ddbf"],"state_sha256":"88b35264a729a68e1464ac90d3b3d8eee4c78bfdddfc5c634d36929982b6925f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JgZmiDLDuc3wd4xXPODc0IfYPN61Nn0NbxkQIRWN2rtVSECKoIVzPyfqCX8GabbuyQ3unMoE64pBG9FiYSy7CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T22:09:23.724366Z","bundle_sha256":"25e466e5f50a55ead5589e3fd59c99d993518fde4e401ec84ecfcda595127720"}}