{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:5J4L5DECUU4JXRER4CWJCLY4HL","short_pith_number":"pith:5J4L5DEC","canonical_record":{"source":{"id":"2407.03892","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-07-04T12:35:32Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"3e1b9543c1f6b97cab1414c28b683840eb9fa6a08f3404718d1314712993b1ef","abstract_canon_sha256":"7721d945068f25f1a8f17d6077e3e2297d05a176083c49aa741481bc1b327ca0"},"schema_version":"1.0"},"canonical_sha256":"ea78be8c82a5389bc491e0ac912f1c3adbf9d4f00fa722bd1b172be544591686","source":{"kind":"arxiv","id":"2407.03892","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.03892","created_at":"2026-07-05T09:27:56Z"},{"alias_kind":"arxiv_version","alias_value":"2407.03892v1","created_at":"2026-07-05T09:27:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.03892","created_at":"2026-07-05T09:27:56Z"},{"alias_kind":"pith_short_12","alias_value":"5J4L5DECUU4J","created_at":"2026-07-05T09:27:56Z"},{"alias_kind":"pith_short_16","alias_value":"5J4L5DECUU4JXRER","created_at":"2026-07-05T09:27:56Z"},{"alias_kind":"pith_short_8","alias_value":"5J4L5DEC","created_at":"2026-07-05T09:27:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:5J4L5DECUU4JXRER4CWJCLY4HL","target":"record","payload":{"canonical_record":{"source":{"id":"2407.03892","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-07-04T12:35:32Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"3e1b9543c1f6b97cab1414c28b683840eb9fa6a08f3404718d1314712993b1ef","abstract_canon_sha256":"7721d945068f25f1a8f17d6077e3e2297d05a176083c49aa741481bc1b327ca0"},"schema_version":"1.0"},"canonical_sha256":"ea78be8c82a5389bc491e0ac912f1c3adbf9d4f00fa722bd1b172be544591686","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:27:56.619129Z","signature_b64":"fiYkw1cU6KmF7BB7MRo3YaZQCQRNMxVzSx4E5UOdBQ1Ixa3PXdQNZQky/NJEJlfWsu6+ia8TKci0ctl7hgkzDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea78be8c82a5389bc491e0ac912f1c3adbf9d4f00fa722bd1b172be544591686","last_reissued_at":"2026-07-05T09:27:56.618638Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:27:56.618638Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.03892","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":"2026-07-05T09:27:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uA/wm/4gYFEGR59Tg0PAZsSoWtQ46MP+JFV9maEbXqGevY9q8/mox/tk+BjjGQ9InVbHmhSjXpJ2hx37vejcBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T07:21:11.477212Z"},"content_sha256":"a59aa7a6d1902403e72cc7f23dfb0988dfa3108f671b42705db23b3d8fd12ee2","schema_version":"1.0","event_id":"sha256:a59aa7a6d1902403e72cc7f23dfb0988dfa3108f671b42705db23b3d8fd12ee2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:5J4L5DECUU4JXRER4CWJCLY4HL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the Effectiveness of Acoustic BPE in Decoder-Only TTS","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Bohan Li, Feiyu Shen, Kai Yu, Shuai Wang, Xie Chen, Yiwei Guo","submitted_at":"2024-07-04T12:35:32Z","abstract_excerpt":"Discretizing speech into tokens and generating them by a decoder-only model have been a promising direction for text-to-speech (TTS) and spoken language modeling (SLM). To shorten the sequence length of speech tokens, acoustic byte-pair encoding (BPE) has emerged in SLM that treats speech tokens from self-supervised semantic representations as characters to further compress the token sequence. But the gain in TTS has not been fully investigated, and the proper choice of acoustic BPE remains unclear. In this work, we conduct a comprehensive study on various settings of acoustic BPE to explore i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.03892","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/2407.03892/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":"2026-07-05T09:27:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ehq3dvqSIJqCDOTwRcVNuTyVFJv0PcHHarjrt6NSxhEKLkOGeP1tFSeytu2Ug3S0S82U/geyGFVNo1k/VduHDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T07:21:11.478572Z"},"content_sha256":"7822fadc99e8dddcb258441dc817bdcbd1bcaaf46c1d94f40cd83df8e5b4ac8d","schema_version":"1.0","event_id":"sha256:7822fadc99e8dddcb258441dc817bdcbd1bcaaf46c1d94f40cd83df8e5b4ac8d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5J4L5DECUU4JXRER4CWJCLY4HL/bundle.json","state_url":"https://pith.science/pith/5J4L5DECUU4JXRER4CWJCLY4HL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5J4L5DECUU4JXRER4CWJCLY4HL/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":"2026-08-06T07:21:11Z","links":{"resolver":"https://pith.science/pith/5J4L5DECUU4JXRER4CWJCLY4HL","bundle":"https://pith.science/pith/5J4L5DECUU4JXRER4CWJCLY4HL/bundle.json","state":"https://pith.science/pith/5J4L5DECUU4JXRER4CWJCLY4HL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5J4L5DECUU4JXRER4CWJCLY4HL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5J4L5DECUU4JXRER4CWJCLY4HL","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":"7721d945068f25f1a8f17d6077e3e2297d05a176083c49aa741481bc1b327ca0","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-07-04T12:35:32Z","title_canon_sha256":"3e1b9543c1f6b97cab1414c28b683840eb9fa6a08f3404718d1314712993b1ef"},"schema_version":"1.0","source":{"id":"2407.03892","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.03892","created_at":"2026-07-05T09:27:56Z"},{"alias_kind":"arxiv_version","alias_value":"2407.03892v1","created_at":"2026-07-05T09:27:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.03892","created_at":"2026-07-05T09:27:56Z"},{"alias_kind":"pith_short_12","alias_value":"5J4L5DECUU4J","created_at":"2026-07-05T09:27:56Z"},{"alias_kind":"pith_short_16","alias_value":"5J4L5DECUU4JXRER","created_at":"2026-07-05T09:27:56Z"},{"alias_kind":"pith_short_8","alias_value":"5J4L5DEC","created_at":"2026-07-05T09:27:56Z"}],"graph_snapshots":[{"event_id":"sha256:7822fadc99e8dddcb258441dc817bdcbd1bcaaf46c1d94f40cd83df8e5b4ac8d","target":"graph","created_at":"2026-07-05T09:27:56Z","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/2407.03892/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Discretizing speech into tokens and generating them by a decoder-only model have been a promising direction for text-to-speech (TTS) and spoken language modeling (SLM). To shorten the sequence length of speech tokens, acoustic byte-pair encoding (BPE) has emerged in SLM that treats speech tokens from self-supervised semantic representations as characters to further compress the token sequence. But the gain in TTS has not been fully investigated, and the proper choice of acoustic BPE remains unclear. In this work, we conduct a comprehensive study on various settings of acoustic BPE to explore i","authors_text":"Bohan Li, Feiyu Shen, Kai Yu, Shuai Wang, Xie Chen, Yiwei Guo","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-07-04T12:35:32Z","title":"On the Effectiveness of Acoustic BPE in Decoder-Only TTS"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.03892","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:a59aa7a6d1902403e72cc7f23dfb0988dfa3108f671b42705db23b3d8fd12ee2","target":"record","created_at":"2026-07-05T09:27:56Z","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":"7721d945068f25f1a8f17d6077e3e2297d05a176083c49aa741481bc1b327ca0","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-07-04T12:35:32Z","title_canon_sha256":"3e1b9543c1f6b97cab1414c28b683840eb9fa6a08f3404718d1314712993b1ef"},"schema_version":"1.0","source":{"id":"2407.03892","kind":"arxiv","version":1}},"canonical_sha256":"ea78be8c82a5389bc491e0ac912f1c3adbf9d4f00fa722bd1b172be544591686","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ea78be8c82a5389bc491e0ac912f1c3adbf9d4f00fa722bd1b172be544591686","first_computed_at":"2026-07-05T09:27:56.618638Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:27:56.618638Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fiYkw1cU6KmF7BB7MRo3YaZQCQRNMxVzSx4E5UOdBQ1Ixa3PXdQNZQky/NJEJlfWsu6+ia8TKci0ctl7hgkzDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:27:56.619129Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.03892","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a59aa7a6d1902403e72cc7f23dfb0988dfa3108f671b42705db23b3d8fd12ee2","sha256:7822fadc99e8dddcb258441dc817bdcbd1bcaaf46c1d94f40cd83df8e5b4ac8d"],"state_sha256":"6cbdec042c3b507b6a680bce721434f66389633cfef26411dd1b1e41bf9862ce"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9VEnzAwbdbk5qi980YS1JmhfGwjQebkmtSTHFCGlAwsYPSE8ib6Wd1tfvR0TpvT6hFIcLH72WYZLwMjmLEq5Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T07:21:11.484394Z","bundle_sha256":"65243cfac98dbdbf7ac9a91f967416c5081e97176b7e12d0c725add1f2d5edf4"}}