{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:MXDAUGNGXA4S7ZJPKKZEKKTSRZ","short_pith_number":"pith:MXDAUGNG","canonical_record":{"source":{"id":"2401.00246","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-30T14:20:04Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"6d99643f6393868c939e1bc235e85d390d5a3f2230490673d60e0f15a32f7d7a","abstract_canon_sha256":"1665e88f4b95394b8b1e9d9b33d988d028d4cef0509068ead0bc6eda417c82b1"},"schema_version":"1.0"},"canonical_sha256":"65c60a19a6b8392fe52f52b2452a728e458a58c6c5dfb114a052ea7f1e1f9d78","source":{"kind":"arxiv","id":"2401.00246","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.00246","created_at":"2026-07-05T07:29:02Z"},{"alias_kind":"arxiv_version","alias_value":"2401.00246v1","created_at":"2026-07-05T07:29:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.00246","created_at":"2026-07-05T07:29:02Z"},{"alias_kind":"pith_short_12","alias_value":"MXDAUGNGXA4S","created_at":"2026-07-05T07:29:02Z"},{"alias_kind":"pith_short_16","alias_value":"MXDAUGNGXA4S7ZJP","created_at":"2026-07-05T07:29:02Z"},{"alias_kind":"pith_short_8","alias_value":"MXDAUGNG","created_at":"2026-07-05T07:29:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:MXDAUGNGXA4S7ZJPKKZEKKTSRZ","target":"record","payload":{"canonical_record":{"source":{"id":"2401.00246","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-30T14:20:04Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"6d99643f6393868c939e1bc235e85d390d5a3f2230490673d60e0f15a32f7d7a","abstract_canon_sha256":"1665e88f4b95394b8b1e9d9b33d988d028d4cef0509068ead0bc6eda417c82b1"},"schema_version":"1.0"},"canonical_sha256":"65c60a19a6b8392fe52f52b2452a728e458a58c6c5dfb114a052ea7f1e1f9d78","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:29:02.757051Z","signature_b64":"z9zBRNlcL6AVScaI6TeROv+3XceKmlEmS/qXEDFM4JZj4OlL//ILTgt0rc5nHIJ9TgD+n9Fzb52vsVk72VKHAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65c60a19a6b8392fe52f52b2452a728e458a58c6c5dfb114a052ea7f1e1f9d78","last_reissued_at":"2026-07-05T07:29:02.756380Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:29:02.756380Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.00246","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":"2026-07-05T07:29:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R/Zzb7v5xgbpyoadt2xhY+SnbK9GJZD1+h70fnv22hFUvVFV2/tZGdSVXhvS/sScLAu8rDKi9zr+TeEmMk16AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:57:39.944033Z"},"content_sha256":"9ba387066e9f830029d1fa728e2e755cf0f2afeea3db296f20fb076f0b92ee9e","schema_version":"1.0","event_id":"sha256:9ba387066e9f830029d1fa728e2e755cf0f2afeea3db296f20fb076f0b92ee9e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:MXDAUGNGXA4S7ZJPKKZEKKTSRZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Boosting Large Language Model for Speech Synthesis: An Empirical Study","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Furu Wei, Hongkun Hao, Jinyu Li, Long Zhou, Rui Wang, Shujie Hu, Shujie Liu","submitted_at":"2023-12-30T14:20:04Z","abstract_excerpt":"Large language models (LLMs) have made significant advancements in natural language processing and are concurrently extending the language ability to other modalities, such as speech and vision. Nevertheless, most of the previous work focuses on prompting LLMs with perception abilities like auditory comprehension, and the effective approach for augmenting LLMs with speech synthesis capabilities remains ambiguous. In this paper, we conduct a comprehensive empirical exploration of boosting LLMs with the ability to generate speech, by combining pre-trained LLM LLaMA/OPT and text-to-speech synthes"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.00246","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/2401.00246/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":"2026-07-05T07:29:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qh/2lpBG8HNoyEouThBJMcOxdIb402th7+7CPzl87luXe2Mr0J0GHC887vpCRBNO/xhXxfqYZ4UCQU5YbRX7AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:57:39.944531Z"},"content_sha256":"dec049e8bd74b88388bae1cfb620e5d318de9b9b97ec72f09e100b730ad47731","schema_version":"1.0","event_id":"sha256:dec049e8bd74b88388bae1cfb620e5d318de9b9b97ec72f09e100b730ad47731"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MXDAUGNGXA4S7ZJPKKZEKKTSRZ/bundle.json","state_url":"https://pith.science/pith/MXDAUGNGXA4S7ZJPKKZEKKTSRZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MXDAUGNGXA4S7ZJPKKZEKKTSRZ/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":"2026-08-08T13:57:39Z","links":{"resolver":"https://pith.science/pith/MXDAUGNGXA4S7ZJPKKZEKKTSRZ","bundle":"https://pith.science/pith/MXDAUGNGXA4S7ZJPKKZEKKTSRZ/bundle.json","state":"https://pith.science/pith/MXDAUGNGXA4S7ZJPKKZEKKTSRZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MXDAUGNGXA4S7ZJPKKZEKKTSRZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:MXDAUGNGXA4S7ZJPKKZEKKTSRZ","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":"1665e88f4b95394b8b1e9d9b33d988d028d4cef0509068ead0bc6eda417c82b1","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-30T14:20:04Z","title_canon_sha256":"6d99643f6393868c939e1bc235e85d390d5a3f2230490673d60e0f15a32f7d7a"},"schema_version":"1.0","source":{"id":"2401.00246","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.00246","created_at":"2026-07-05T07:29:02Z"},{"alias_kind":"arxiv_version","alias_value":"2401.00246v1","created_at":"2026-07-05T07:29:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.00246","created_at":"2026-07-05T07:29:02Z"},{"alias_kind":"pith_short_12","alias_value":"MXDAUGNGXA4S","created_at":"2026-07-05T07:29:02Z"},{"alias_kind":"pith_short_16","alias_value":"MXDAUGNGXA4S7ZJP","created_at":"2026-07-05T07:29:02Z"},{"alias_kind":"pith_short_8","alias_value":"MXDAUGNG","created_at":"2026-07-05T07:29:02Z"}],"graph_snapshots":[{"event_id":"sha256:dec049e8bd74b88388bae1cfb620e5d318de9b9b97ec72f09e100b730ad47731","target":"graph","created_at":"2026-07-05T07:29:02Z","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/2401.00246/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have made significant advancements in natural language processing and are concurrently extending the language ability to other modalities, such as speech and vision. Nevertheless, most of the previous work focuses on prompting LLMs with perception abilities like auditory comprehension, and the effective approach for augmenting LLMs with speech synthesis capabilities remains ambiguous. In this paper, we conduct a comprehensive empirical exploration of boosting LLMs with the ability to generate speech, by combining pre-trained LLM LLaMA/OPT and text-to-speech synthes","authors_text":"Furu Wei, Hongkun Hao, Jinyu Li, Long Zhou, Rui Wang, Shujie Hu, Shujie Liu","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-30T14:20:04Z","title":"Boosting Large Language Model for Speech Synthesis: An Empirical Study"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.00246","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":"sha256:9ba387066e9f830029d1fa728e2e755cf0f2afeea3db296f20fb076f0b92ee9e","target":"record","created_at":"2026-07-05T07:29:02Z","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":"1665e88f4b95394b8b1e9d9b33d988d028d4cef0509068ead0bc6eda417c82b1","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-30T14:20:04Z","title_canon_sha256":"6d99643f6393868c939e1bc235e85d390d5a3f2230490673d60e0f15a32f7d7a"},"schema_version":"1.0","source":{"id":"2401.00246","kind":"arxiv","version":1}},"canonical_sha256":"65c60a19a6b8392fe52f52b2452a728e458a58c6c5dfb114a052ea7f1e1f9d78","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"65c60a19a6b8392fe52f52b2452a728e458a58c6c5dfb114a052ea7f1e1f9d78","first_computed_at":"2026-07-05T07:29:02.756380Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:29:02.756380Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"z9zBRNlcL6AVScaI6TeROv+3XceKmlEmS/qXEDFM4JZj4OlL//ILTgt0rc5nHIJ9TgD+n9Fzb52vsVk72VKHAA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:29:02.757051Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.00246","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9ba387066e9f830029d1fa728e2e755cf0f2afeea3db296f20fb076f0b92ee9e","sha256:dec049e8bd74b88388bae1cfb620e5d318de9b9b97ec72f09e100b730ad47731"],"state_sha256":"b3d0e4ee09b17627cac5e6b206b197f6f92891e158bb67bdeb675d967d9dd918"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xserufNiCppyhXvDnnGPFJQa8lylFJwBgfqeL02o3ZkBrCCoSIVr3+sY2/td+c9edDs6DLpjqe+9C2tioYlSAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T13:57:39.950611Z","bundle_sha256":"b813029f6b8027a1ec527b70761a8e75116cbfabeb9b62ac0deb0c85665639a2"}}