{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:6CHWYJH3LSLF4HHGTP2RYQENAV","short_pith_number":"pith:6CHWYJH3","canonical_record":{"source":{"id":"2404.02781","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-04-03T14:52:20Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"ee29176b2a0c6f7d81764928581a018d18dc3b84f13eec3607e9e3dcde9eb18c","abstract_canon_sha256":"d8b16bdff5c457602d19d73fd045a885edb7942f1cfd0d4e4636dc647e1df2db"},"schema_version":"1.0"},"canonical_sha256":"f08f6c24fb5c965e1ce69bf51c408d0573094c92d6e9e4e5c4ec5515891e2e63","source":{"kind":"arxiv","id":"2404.02781","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.02781","created_at":"2026-07-05T08:04:01Z"},{"alias_kind":"arxiv_version","alias_value":"2404.02781v1","created_at":"2026-07-05T08:04:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.02781","created_at":"2026-07-05T08:04:01Z"},{"alias_kind":"pith_short_12","alias_value":"6CHWYJH3LSLF","created_at":"2026-07-05T08:04:01Z"},{"alias_kind":"pith_short_16","alias_value":"6CHWYJH3LSLF4HHG","created_at":"2026-07-05T08:04:01Z"},{"alias_kind":"pith_short_8","alias_value":"6CHWYJH3","created_at":"2026-07-05T08:04:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:6CHWYJH3LSLF4HHGTP2RYQENAV","target":"record","payload":{"canonical_record":{"source":{"id":"2404.02781","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-04-03T14:52:20Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"ee29176b2a0c6f7d81764928581a018d18dc3b84f13eec3607e9e3dcde9eb18c","abstract_canon_sha256":"d8b16bdff5c457602d19d73fd045a885edb7942f1cfd0d4e4636dc647e1df2db"},"schema_version":"1.0"},"canonical_sha256":"f08f6c24fb5c965e1ce69bf51c408d0573094c92d6e9e4e5c4ec5515891e2e63","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:04:01.129104Z","signature_b64":"yHRWSgdyof7u/2CFFytU5yPkYvWFlD9xL9viciY1rCR9VzfBXxbsmdOrfbfdA42n+qTBAVOBKLLqcjfSgjmVAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f08f6c24fb5c965e1ce69bf51c408d0573094c92d6e9e4e5c4ec5515891e2e63","last_reissued_at":"2026-07-05T08:04:01.128626Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:04:01.128626Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.02781","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":"2026-07-05T08:04:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HAOKJWJkRgL3cpClbdaAdouxDgMjeRR+eoRZ9Lc3W+Gu3cWOIXWUe3L6QZQJ8n+BThG8J9C0wHXaf4tzY0hfCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T07:13:02.250516Z"},"content_sha256":"4c4c9766ee56ed5870e4ee9f23a8f371d7917ba74163f83ea60c4eee22e7e0eb","schema_version":"1.0","event_id":"sha256:4c4c9766ee56ed5870e4ee9f23a8f371d7917ba74163f83ea60c4eee22e7e0eb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:6CHWYJH3LSLF4HHGTP2RYQENAV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CLaM-TTS: Improving Neural Codec Language Model for Zero-Shot Text-to-Speech","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Jaehyeon Kim, Jaewoong Cho, Keon Lee, Seungjun Chung","submitted_at":"2024-04-03T14:52:20Z","abstract_excerpt":"With the emergence of neural audio codecs, which encode multiple streams of discrete tokens from audio, large language models have recently gained attention as a promising approach for zero-shot Text-to-Speech (TTS) synthesis. Despite the ongoing rush towards scaling paradigms, audio tokenization ironically amplifies the scalability challenge, stemming from its long sequence length and the complexity of modelling the multiple sequences. To mitigate these issues, we present CLaM-TTS that employs a probabilistic residual vector quantization to (1) achieve superior compression in the token length"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.02781","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/2404.02781/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":"2026-07-05T08:04:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iFTtpxWdv5CH8dsEIEAezceAndbJdICutpb4adHmwiN2eJZfEENDvQSCrrdckucUV3GzrWFco2Z/lme19vaGBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T07:13:02.251030Z"},"content_sha256":"6fc0fc405d475ceb44467a73afcc4ebd86315f8358b30c9bbd98b134d3686335","schema_version":"1.0","event_id":"sha256:6fc0fc405d475ceb44467a73afcc4ebd86315f8358b30c9bbd98b134d3686335"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6CHWYJH3LSLF4HHGTP2RYQENAV/bundle.json","state_url":"https://pith.science/pith/6CHWYJH3LSLF4HHGTP2RYQENAV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6CHWYJH3LSLF4HHGTP2RYQENAV/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":"2026-08-06T07:13:02Z","links":{"resolver":"https://pith.science/pith/6CHWYJH3LSLF4HHGTP2RYQENAV","bundle":"https://pith.science/pith/6CHWYJH3LSLF4HHGTP2RYQENAV/bundle.json","state":"https://pith.science/pith/6CHWYJH3LSLF4HHGTP2RYQENAV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6CHWYJH3LSLF4HHGTP2RYQENAV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6CHWYJH3LSLF4HHGTP2RYQENAV","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":"d8b16bdff5c457602d19d73fd045a885edb7942f1cfd0d4e4636dc647e1df2db","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-04-03T14:52:20Z","title_canon_sha256":"ee29176b2a0c6f7d81764928581a018d18dc3b84f13eec3607e9e3dcde9eb18c"},"schema_version":"1.0","source":{"id":"2404.02781","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.02781","created_at":"2026-07-05T08:04:01Z"},{"alias_kind":"arxiv_version","alias_value":"2404.02781v1","created_at":"2026-07-05T08:04:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.02781","created_at":"2026-07-05T08:04:01Z"},{"alias_kind":"pith_short_12","alias_value":"6CHWYJH3LSLF","created_at":"2026-07-05T08:04:01Z"},{"alias_kind":"pith_short_16","alias_value":"6CHWYJH3LSLF4HHG","created_at":"2026-07-05T08:04:01Z"},{"alias_kind":"pith_short_8","alias_value":"6CHWYJH3","created_at":"2026-07-05T08:04:01Z"}],"graph_snapshots":[{"event_id":"sha256:6fc0fc405d475ceb44467a73afcc4ebd86315f8358b30c9bbd98b134d3686335","target":"graph","created_at":"2026-07-05T08:04:01Z","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/2404.02781/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the emergence of neural audio codecs, which encode multiple streams of discrete tokens from audio, large language models have recently gained attention as a promising approach for zero-shot Text-to-Speech (TTS) synthesis. Despite the ongoing rush towards scaling paradigms, audio tokenization ironically amplifies the scalability challenge, stemming from its long sequence length and the complexity of modelling the multiple sequences. To mitigate these issues, we present CLaM-TTS that employs a probabilistic residual vector quantization to (1) achieve superior compression in the token length","authors_text":"Jaehyeon Kim, Jaewoong Cho, Keon Lee, Seungjun Chung","cross_cats":["cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-04-03T14:52:20Z","title":"CLaM-TTS: Improving Neural Codec Language Model for Zero-Shot Text-to-Speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.02781","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":"sha256:4c4c9766ee56ed5870e4ee9f23a8f371d7917ba74163f83ea60c4eee22e7e0eb","target":"record","created_at":"2026-07-05T08:04:01Z","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":"d8b16bdff5c457602d19d73fd045a885edb7942f1cfd0d4e4636dc647e1df2db","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-04-03T14:52:20Z","title_canon_sha256":"ee29176b2a0c6f7d81764928581a018d18dc3b84f13eec3607e9e3dcde9eb18c"},"schema_version":"1.0","source":{"id":"2404.02781","kind":"arxiv","version":1}},"canonical_sha256":"f08f6c24fb5c965e1ce69bf51c408d0573094c92d6e9e4e5c4ec5515891e2e63","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f08f6c24fb5c965e1ce69bf51c408d0573094c92d6e9e4e5c4ec5515891e2e63","first_computed_at":"2026-07-05T08:04:01.128626Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:04:01.128626Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yHRWSgdyof7u/2CFFytU5yPkYvWFlD9xL9viciY1rCR9VzfBXxbsmdOrfbfdA42n+qTBAVOBKLLqcjfSgjmVAg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:04:01.129104Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.02781","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4c4c9766ee56ed5870e4ee9f23a8f371d7917ba74163f83ea60c4eee22e7e0eb","sha256:6fc0fc405d475ceb44467a73afcc4ebd86315f8358b30c9bbd98b134d3686335"],"state_sha256":"155ad714b84fcea16fc3fad5eb8d9da01b29c28b1eb049e16965496b360872de"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7v+WtSwEByv5SPYoEYtByewYKYp2VpQaa2H7FA07kvvyJ12ZCldXIvYLYtpcN8AW2PxUmwifLP5yjtAz6W2mDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T07:13:02.259889Z","bundle_sha256":"ed4115b329ab81f80361250d14416d2f768ba19bf04666bd1804f25afd1c4136"}}