{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:5AI37DSN57ZA7RD75NOFBLOXX7","short_pith_number":"pith:5AI37DSN","canonical_record":{"source":{"id":"2307.16430","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-07-31T06:36:44Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"93b669890a860e448d9cbda294a752192a3531e555e023e83fa4cb85bd93f1f7","abstract_canon_sha256":"17b879bea0924300a4aa91e766b4191b38c09db581dfeed7415aedf88b6ba26b"},"schema_version":"1.0"},"canonical_sha256":"e811bf8e4deff20fc47feb5c50add7bfd0eb7ad5ec8daadda4f208ca5e9d5bc7","source":{"kind":"arxiv","id":"2307.16430","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.16430","created_at":"2026-07-05T06:36:03Z"},{"alias_kind":"arxiv_version","alias_value":"2307.16430v1","created_at":"2026-07-05T06:36:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.16430","created_at":"2026-07-05T06:36:03Z"},{"alias_kind":"pith_short_12","alias_value":"5AI37DSN57ZA","created_at":"2026-07-05T06:36:03Z"},{"alias_kind":"pith_short_16","alias_value":"5AI37DSN57ZA7RD7","created_at":"2026-07-05T06:36:03Z"},{"alias_kind":"pith_short_8","alias_value":"5AI37DSN","created_at":"2026-07-05T06:36:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:5AI37DSN57ZA7RD75NOFBLOXX7","target":"record","payload":{"canonical_record":{"source":{"id":"2307.16430","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-07-31T06:36:44Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"93b669890a860e448d9cbda294a752192a3531e555e023e83fa4cb85bd93f1f7","abstract_canon_sha256":"17b879bea0924300a4aa91e766b4191b38c09db581dfeed7415aedf88b6ba26b"},"schema_version":"1.0"},"canonical_sha256":"e811bf8e4deff20fc47feb5c50add7bfd0eb7ad5ec8daadda4f208ca5e9d5bc7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:36:03.615681Z","signature_b64":"uK88Bn8MlfMRWdoINfCIDaU+drLKJm0ac/nVEKdvG3M12EtrqLtBOoOyYfSpZEYPrR1imGr2yozZ7vcZAllMBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e811bf8e4deff20fc47feb5c50add7bfd0eb7ad5ec8daadda4f208ca5e9d5bc7","last_reissued_at":"2026-07-05T06:36:03.615151Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:36:03.615151Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.16430","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":"2026-07-05T06:36:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XyTqUMjvHbF6Mdi51O1KC/Xq1pcmYvmEKjj915rg723woQXZzZWGELjPRIZCtiqHb5hFF5mmzz8+IlVQU8E/CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T21:22:30.376736Z"},"content_sha256":"59b27f2b3c44319843ab1d8af301e67cc5cdb94c04da400a819d9d8419868282","schema_version":"1.0","event_id":"sha256:59b27f2b3c44319843ab1d8af301e67cc5cdb94c04da400a819d9d8419868282"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:5AI37DSN57ZA7RD75NOFBLOXX7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VITS2: Improving Quality and Efficiency of Single-Stage Text-to-Speech with Adversarial Learning and Architecture Design","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Beomjeong Kim, Dohee Kong, Jeongmin Kim, Jihoon Park, Jungil Kong, Sangjin Kim","submitted_at":"2023-07-31T06:36:44Z","abstract_excerpt":"Single-stage text-to-speech models have been actively studied recently, and their results have outperformed two-stage pipeline systems. Although the previous single-stage model has made great progress, there is room for improvement in terms of its intermittent unnaturalness, computational efficiency, and strong dependence on phoneme conversion. In this work, we introduce VITS2, a single-stage text-to-speech model that efficiently synthesizes a more natural speech by improving several aspects of the previous work. We propose improved structures and training mechanisms and present that the propo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.16430","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/2307.16430/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":"2026-07-05T06:36:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7ip25ZNFpUuH7dW272DRghs95RHYipsFsbepYkALKdXcCSwxvpG5uBuM7S9kosgR4QpBKTGhay0/OLtIKay3BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T21:22:30.377283Z"},"content_sha256":"68ed86abbe893816a3a69bc2301def020689631aac4e9b99ad1874fa0593668d","schema_version":"1.0","event_id":"sha256:68ed86abbe893816a3a69bc2301def020689631aac4e9b99ad1874fa0593668d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5AI37DSN57ZA7RD75NOFBLOXX7/bundle.json","state_url":"https://pith.science/pith/5AI37DSN57ZA7RD75NOFBLOXX7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5AI37DSN57ZA7RD75NOFBLOXX7/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":"2026-08-09T21:22:30Z","links":{"resolver":"https://pith.science/pith/5AI37DSN57ZA7RD75NOFBLOXX7","bundle":"https://pith.science/pith/5AI37DSN57ZA7RD75NOFBLOXX7/bundle.json","state":"https://pith.science/pith/5AI37DSN57ZA7RD75NOFBLOXX7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5AI37DSN57ZA7RD75NOFBLOXX7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5AI37DSN57ZA7RD75NOFBLOXX7","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":"17b879bea0924300a4aa91e766b4191b38c09db581dfeed7415aedf88b6ba26b","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-07-31T06:36:44Z","title_canon_sha256":"93b669890a860e448d9cbda294a752192a3531e555e023e83fa4cb85bd93f1f7"},"schema_version":"1.0","source":{"id":"2307.16430","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.16430","created_at":"2026-07-05T06:36:03Z"},{"alias_kind":"arxiv_version","alias_value":"2307.16430v1","created_at":"2026-07-05T06:36:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.16430","created_at":"2026-07-05T06:36:03Z"},{"alias_kind":"pith_short_12","alias_value":"5AI37DSN57ZA","created_at":"2026-07-05T06:36:03Z"},{"alias_kind":"pith_short_16","alias_value":"5AI37DSN57ZA7RD7","created_at":"2026-07-05T06:36:03Z"},{"alias_kind":"pith_short_8","alias_value":"5AI37DSN","created_at":"2026-07-05T06:36:03Z"}],"graph_snapshots":[{"event_id":"sha256:68ed86abbe893816a3a69bc2301def020689631aac4e9b99ad1874fa0593668d","target":"graph","created_at":"2026-07-05T06:36:03Z","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/2307.16430/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Single-stage text-to-speech models have been actively studied recently, and their results have outperformed two-stage pipeline systems. Although the previous single-stage model has made great progress, there is room for improvement in terms of its intermittent unnaturalness, computational efficiency, and strong dependence on phoneme conversion. In this work, we introduce VITS2, a single-stage text-to-speech model that efficiently synthesizes a more natural speech by improving several aspects of the previous work. We propose improved structures and training mechanisms and present that the propo","authors_text":"Beomjeong Kim, Dohee Kong, Jeongmin Kim, Jihoon Park, Jungil Kong, Sangjin Kim","cross_cats":["cs.LG","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-07-31T06:36:44Z","title":"VITS2: Improving Quality and Efficiency of Single-Stage Text-to-Speech with Adversarial Learning and Architecture Design"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.16430","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":"sha256:59b27f2b3c44319843ab1d8af301e67cc5cdb94c04da400a819d9d8419868282","target":"record","created_at":"2026-07-05T06:36:03Z","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":"17b879bea0924300a4aa91e766b4191b38c09db581dfeed7415aedf88b6ba26b","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-07-31T06:36:44Z","title_canon_sha256":"93b669890a860e448d9cbda294a752192a3531e555e023e83fa4cb85bd93f1f7"},"schema_version":"1.0","source":{"id":"2307.16430","kind":"arxiv","version":1}},"canonical_sha256":"e811bf8e4deff20fc47feb5c50add7bfd0eb7ad5ec8daadda4f208ca5e9d5bc7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e811bf8e4deff20fc47feb5c50add7bfd0eb7ad5ec8daadda4f208ca5e9d5bc7","first_computed_at":"2026-07-05T06:36:03.615151Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:36:03.615151Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uK88Bn8MlfMRWdoINfCIDaU+drLKJm0ac/nVEKdvG3M12EtrqLtBOoOyYfSpZEYPrR1imGr2yozZ7vcZAllMBg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:36:03.615681Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.16430","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:59b27f2b3c44319843ab1d8af301e67cc5cdb94c04da400a819d9d8419868282","sha256:68ed86abbe893816a3a69bc2301def020689631aac4e9b99ad1874fa0593668d"],"state_sha256":"b7bd9cc383316f2d9f16f7270bae1392cdb074a81c806a38373b2fd1ae39b2ca"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7f31dhk3qr7wYIiKoYQwDxIKYKyjGdLosYplVvzu8Ul00SEDMPhbHseegSFJIENQW5raQz2hbcX3qzCpPY5RDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T21:22:30.382611Z","bundle_sha256":"0dd60d535c341048d6ee96a447d79b04a1cf96f515a0f15c39b0746937c75d0b"}}