{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:IJCIFOTYXQ3IJVRAPL7ANO6G2S","short_pith_number":"pith:IJCIFOTY","canonical_record":{"source":{"id":"2606.09234","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-08T09:07:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a8f1682541077c877446a1da9ea89211ab62b644f3e361ace89c332c5abafa92","abstract_canon_sha256":"3910ee088baec1cf69b0376606804658676851b239957d2d746c870ce4ef791d"},"schema_version":"1.0"},"canonical_sha256":"424482ba78bc3684d6207afe06bbc6d4b2e4aa4035f4d9296a9a45f7e30b46d8","source":{"kind":"arxiv","id":"2606.09234","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.09234","created_at":"2026-06-09T02:08:09Z"},{"alias_kind":"arxiv_version","alias_value":"2606.09234v1","created_at":"2026-06-09T02:08:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09234","created_at":"2026-06-09T02:08:09Z"},{"alias_kind":"pith_short_12","alias_value":"IJCIFOTYXQ3I","created_at":"2026-06-09T02:08:09Z"},{"alias_kind":"pith_short_16","alias_value":"IJCIFOTYXQ3IJVRA","created_at":"2026-06-09T02:08:09Z"},{"alias_kind":"pith_short_8","alias_value":"IJCIFOTY","created_at":"2026-06-09T02:08:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:IJCIFOTYXQ3IJVRAPL7ANO6G2S","target":"record","payload":{"canonical_record":{"source":{"id":"2606.09234","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-08T09:07:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a8f1682541077c877446a1da9ea89211ab62b644f3e361ace89c332c5abafa92","abstract_canon_sha256":"3910ee088baec1cf69b0376606804658676851b239957d2d746c870ce4ef791d"},"schema_version":"1.0"},"canonical_sha256":"424482ba78bc3684d6207afe06bbc6d4b2e4aa4035f4d9296a9a45f7e30b46d8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:08:09.064843Z","signature_b64":"1/MkaIZM4ZegqR2jchk9DaWaezV7tqv8/Egk09LRoWL3CN1EJZMQ7WRJYhuokb9FDaLFncB8m84qO0VBCbEJDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"424482ba78bc3684d6207afe06bbc6d4b2e4aa4035f4d9296a9a45f7e30b46d8","last_reissued_at":"2026-06-09T02:08:09.063783Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:08:09.063783Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.09234","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":"2026-06-09T02:08:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3Gj2ZY7hJZGOfNpAcnXeN3CaPfFaVYG+cGB0LfN54cqn+9trmwkR9UuY4bhL2wQp2YAmHRJjFMhR2oqMMqosCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T18:13:29.540644Z"},"content_sha256":"dc3d19a5cbc43388745a3f8a61521023c867f4fac32d82562a138b4cb34e364e","schema_version":"1.0","event_id":"sha256:dc3d19a5cbc43388745a3f8a61521023c867f4fac32d82562a138b4cb34e364e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:IJCIFOTYXQ3IJVRAPL7ANO6G2S","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"End-to-End Training for Discrete Token LLM based TTS System","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SD","authors_text":"Changfeng Gao, Jun Yuan, ShiDong Shang, Ye Bai, Yong Ren, Zhao You","submitted_at":"2026-06-08T09:07:23Z","abstract_excerpt":"Recent state-of-the-art (SOTA) text-to-speech (TTS) systems typically adopt a cascaded pipeline consisting of a speech tokenizer, an autoregressive large language model (LLM), and a diffusion based flow-matching (FM) model, with these components trained independently. In this paper, we propose a fully end-to-end (E2E) optimization framework that unifies the training of the speech tokenizer, LLM, FM model, and an additional reward model (RM). Specifically, we first jointly optimize the tokenizer using multi-task objectives derived from reconstruction for FM, next-token prediction for LLM, and m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09234","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/2606.09234/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":"2026-06-09T02:08:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yzciEu7MIM2RPPmgU+DP+DwTGX9279V5rc7W7Yslyl5L4Ow5Gu0QhNcQN1mMM9xKRtXlDOgJZ89u0bHVkoskBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T18:13:29.541020Z"},"content_sha256":"d3dded9112269801af5decbe543a078afd79f5933d3c48c3fed656bca1036b84","schema_version":"1.0","event_id":"sha256:d3dded9112269801af5decbe543a078afd79f5933d3c48c3fed656bca1036b84"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IJCIFOTYXQ3IJVRAPL7ANO6G2S/bundle.json","state_url":"https://pith.science/pith/IJCIFOTYXQ3IJVRAPL7ANO6G2S/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IJCIFOTYXQ3IJVRAPL7ANO6G2S/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":"2026-07-03T18:13:29Z","links":{"resolver":"https://pith.science/pith/IJCIFOTYXQ3IJVRAPL7ANO6G2S","bundle":"https://pith.science/pith/IJCIFOTYXQ3IJVRAPL7ANO6G2S/bundle.json","state":"https://pith.science/pith/IJCIFOTYXQ3IJVRAPL7ANO6G2S/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IJCIFOTYXQ3IJVRAPL7ANO6G2S/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:IJCIFOTYXQ3IJVRAPL7ANO6G2S","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":"3910ee088baec1cf69b0376606804658676851b239957d2d746c870ce4ef791d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-08T09:07:23Z","title_canon_sha256":"a8f1682541077c877446a1da9ea89211ab62b644f3e361ace89c332c5abafa92"},"schema_version":"1.0","source":{"id":"2606.09234","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.09234","created_at":"2026-06-09T02:08:09Z"},{"alias_kind":"arxiv_version","alias_value":"2606.09234v1","created_at":"2026-06-09T02:08:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09234","created_at":"2026-06-09T02:08:09Z"},{"alias_kind":"pith_short_12","alias_value":"IJCIFOTYXQ3I","created_at":"2026-06-09T02:08:09Z"},{"alias_kind":"pith_short_16","alias_value":"IJCIFOTYXQ3IJVRA","created_at":"2026-06-09T02:08:09Z"},{"alias_kind":"pith_short_8","alias_value":"IJCIFOTY","created_at":"2026-06-09T02:08:09Z"}],"graph_snapshots":[{"event_id":"sha256:d3dded9112269801af5decbe543a078afd79f5933d3c48c3fed656bca1036b84","target":"graph","created_at":"2026-06-09T02:08:09Z","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/2606.09234/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent state-of-the-art (SOTA) text-to-speech (TTS) systems typically adopt a cascaded pipeline consisting of a speech tokenizer, an autoregressive large language model (LLM), and a diffusion based flow-matching (FM) model, with these components trained independently. In this paper, we propose a fully end-to-end (E2E) optimization framework that unifies the training of the speech tokenizer, LLM, FM model, and an additional reward model (RM). Specifically, we first jointly optimize the tokenizer using multi-task objectives derived from reconstruction for FM, next-token prediction for LLM, and m","authors_text":"Changfeng Gao, Jun Yuan, ShiDong Shang, Ye Bai, Yong Ren, Zhao You","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-08T09:07:23Z","title":"End-to-End Training for Discrete Token LLM based TTS System"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09234","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:dc3d19a5cbc43388745a3f8a61521023c867f4fac32d82562a138b4cb34e364e","target":"record","created_at":"2026-06-09T02:08:09Z","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":"3910ee088baec1cf69b0376606804658676851b239957d2d746c870ce4ef791d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-08T09:07:23Z","title_canon_sha256":"a8f1682541077c877446a1da9ea89211ab62b644f3e361ace89c332c5abafa92"},"schema_version":"1.0","source":{"id":"2606.09234","kind":"arxiv","version":1}},"canonical_sha256":"424482ba78bc3684d6207afe06bbc6d4b2e4aa4035f4d9296a9a45f7e30b46d8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"424482ba78bc3684d6207afe06bbc6d4b2e4aa4035f4d9296a9a45f7e30b46d8","first_computed_at":"2026-06-09T02:08:09.063783Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T02:08:09.063783Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1/MkaIZM4ZegqR2jchk9DaWaezV7tqv8/Egk09LRoWL3CN1EJZMQ7WRJYhuokb9FDaLFncB8m84qO0VBCbEJDw==","signature_status":"signed_v1","signed_at":"2026-06-09T02:08:09.064843Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.09234","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dc3d19a5cbc43388745a3f8a61521023c867f4fac32d82562a138b4cb34e364e","sha256:d3dded9112269801af5decbe543a078afd79f5933d3c48c3fed656bca1036b84"],"state_sha256":"9f2a6693ed31a0c8a0f4c4c0d9426565d8f66bd7474012324a44131fde0c4ffd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YSVMvC1bCoM/aNWMd7BYdF2qBsCDhoSGiCp2GVQP+QNbspYtIL1a9JR19jxrn1Vqrs0jyC8Z0ppXcumlT1JCAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-03T18:13:29.543084Z","bundle_sha256":"4344126e5aec8c11861fc2a92bb1fc77af8d4cab5ea69742a21405cef820ac78"}}