{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:IZURCTWC2VRFVLY6CURCUOIR5V","short_pith_number":"pith:IZURCTWC","canonical_record":{"source":{"id":"2502.04128","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2025-02-06T15:04:00Z","cross_cats_sorted":["cs.AI","cs.CL","cs.MM","cs.SD"],"title_canon_sha256":"321672531db2d8aa3f98788954de7c3d2f2d9655440203a04ffd99909c0b3d9c","abstract_canon_sha256":"f91318cc083f36c97b49659bad97ac6d65b6234f25f0ec937bcb4b3cc2b1d73f"},"schema_version":"1.0"},"canonical_sha256":"4669114ec2d5625aaf1e15222a3911ed510354f6b030b2da455374bda674e54b","source":{"kind":"arxiv","id":"2502.04128","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.04128","created_at":"2026-07-05T10:18:13Z"},{"alias_kind":"arxiv_version","alias_value":"2502.04128v2","created_at":"2026-07-05T10:18:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.04128","created_at":"2026-07-05T10:18:13Z"},{"alias_kind":"pith_short_12","alias_value":"IZURCTWC2VRF","created_at":"2026-07-05T10:18:13Z"},{"alias_kind":"pith_short_16","alias_value":"IZURCTWC2VRFVLY6","created_at":"2026-07-05T10:18:13Z"},{"alias_kind":"pith_short_8","alias_value":"IZURCTWC","created_at":"2026-07-05T10:18:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:IZURCTWC2VRFVLY6CURCUOIR5V","target":"record","payload":{"canonical_record":{"source":{"id":"2502.04128","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2025-02-06T15:04:00Z","cross_cats_sorted":["cs.AI","cs.CL","cs.MM","cs.SD"],"title_canon_sha256":"321672531db2d8aa3f98788954de7c3d2f2d9655440203a04ffd99909c0b3d9c","abstract_canon_sha256":"f91318cc083f36c97b49659bad97ac6d65b6234f25f0ec937bcb4b3cc2b1d73f"},"schema_version":"1.0"},"canonical_sha256":"4669114ec2d5625aaf1e15222a3911ed510354f6b030b2da455374bda674e54b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:18:13.177294Z","signature_b64":"HNvODzO0ET31GGogqphTP8cl8T8avPLNJcHA4Y6c38iN4uEbgo7AcTfGLVnvZsCiwBRUHK2Mwr6lCctboOHzAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4669114ec2d5625aaf1e15222a3911ed510354f6b030b2da455374bda674e54b","last_reissued_at":"2026-07-05T10:18:13.176802Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:18:13.176802Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.04128","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:18:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YPHHnETTnCCdJBIVspsdvYF8NYF2XZ2q0tqyV4objuAGFIlEOkM2zqaQNCM318UO/jumZQkqEy5FC645Ha5/Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-20T11:32:05.374927Z"},"content_sha256":"7f586b9a170b5c1ef9abfc8729c51d8d7b8f5a81f26c402c695694ea5a349aa9","schema_version":"1.0","event_id":"sha256:7f586b9a170b5c1ef9abfc8729c51d8d7b8f5a81f26c402c695694ea5a349aa9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:IZURCTWC2VRFVLY6CURCUOIR5V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Llasa: Scaling Train-Time and Inference-Time Compute for Llama-based Speech Synthesis","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.MM","cs.SD"],"primary_cat":"eess.AS","authors_text":"Chi-Min Chan, Haohe Liu, Hongzhan Lin, Jiahe Lei, Jianyi Chen, Lei Xie, Liumeng Xue, Qiuqiang Kong, Wei Xue, Xinfa Zhu, Xingjian Du, Xinsheng Wang, Xu Tan, Yike Guo, Yi Peng, Yizhu Jin, Yunlin Chen, Zhen Ye, Zheqi Dai, Zhifei Li","submitted_at":"2025-02-06T15:04:00Z","abstract_excerpt":"Recent advances in text-based large language models (LLMs), particularly in the GPT series and the o1 model, have demonstrated the effectiveness of scaling both training-time and inference-time compute. However, current state-of-the-art TTS systems leveraging LLMs are often multi-stage, requiring separate models (e.g., diffusion models after LLM), complicating the decision of whether to scale a particular model during training or testing. This work makes the following contributions: First, we explore the scaling of train-time and inference-time compute for speech synthesis. Second, we propose "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.04128","kind":"arxiv","version":2},"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/2502.04128/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":"2026-07-05T10:18:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RomHit6K+oct3SM2TfHvknChA5M6TklGm8edGjRV/ygVrIF9yWPFuKiI4ORK8q463WWAihQJEVjFP/HR54pbCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-20T11:32:05.375297Z"},"content_sha256":"518bb3b26291c972944cb94b35b160f63b63bc01853a7e125ddddd16c6f79dcf","schema_version":"1.0","event_id":"sha256:518bb3b26291c972944cb94b35b160f63b63bc01853a7e125ddddd16c6f79dcf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IZURCTWC2VRFVLY6CURCUOIR5V/bundle.json","state_url":"https://pith.science/pith/IZURCTWC2VRFVLY6CURCUOIR5V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IZURCTWC2VRFVLY6CURCUOIR5V/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":"2026-07-20T11:32:05Z","links":{"resolver":"https://pith.science/pith/IZURCTWC2VRFVLY6CURCUOIR5V","bundle":"https://pith.science/pith/IZURCTWC2VRFVLY6CURCUOIR5V/bundle.json","state":"https://pith.science/pith/IZURCTWC2VRFVLY6CURCUOIR5V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IZURCTWC2VRFVLY6CURCUOIR5V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IZURCTWC2VRFVLY6CURCUOIR5V","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":"f91318cc083f36c97b49659bad97ac6d65b6234f25f0ec937bcb4b3cc2b1d73f","cross_cats_sorted":["cs.AI","cs.CL","cs.MM","cs.SD"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2025-02-06T15:04:00Z","title_canon_sha256":"321672531db2d8aa3f98788954de7c3d2f2d9655440203a04ffd99909c0b3d9c"},"schema_version":"1.0","source":{"id":"2502.04128","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.04128","created_at":"2026-07-05T10:18:13Z"},{"alias_kind":"arxiv_version","alias_value":"2502.04128v2","created_at":"2026-07-05T10:18:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.04128","created_at":"2026-07-05T10:18:13Z"},{"alias_kind":"pith_short_12","alias_value":"IZURCTWC2VRF","created_at":"2026-07-05T10:18:13Z"},{"alias_kind":"pith_short_16","alias_value":"IZURCTWC2VRFVLY6","created_at":"2026-07-05T10:18:13Z"},{"alias_kind":"pith_short_8","alias_value":"IZURCTWC","created_at":"2026-07-05T10:18:13Z"}],"graph_snapshots":[{"event_id":"sha256:518bb3b26291c972944cb94b35b160f63b63bc01853a7e125ddddd16c6f79dcf","target":"graph","created_at":"2026-07-05T10:18:13Z","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/2502.04128/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in text-based large language models (LLMs), particularly in the GPT series and the o1 model, have demonstrated the effectiveness of scaling both training-time and inference-time compute. However, current state-of-the-art TTS systems leveraging LLMs are often multi-stage, requiring separate models (e.g., diffusion models after LLM), complicating the decision of whether to scale a particular model during training or testing. This work makes the following contributions: First, we explore the scaling of train-time and inference-time compute for speech synthesis. Second, we propose ","authors_text":"Chi-Min Chan, Haohe Liu, Hongzhan Lin, Jiahe Lei, Jianyi Chen, Lei Xie, Liumeng Xue, Qiuqiang Kong, Wei Xue, Xinfa Zhu, Xingjian Du, Xinsheng Wang, Xu Tan, Yike Guo, Yi Peng, Yizhu Jin, Yunlin Chen, Zhen Ye, Zheqi Dai, Zhifei Li","cross_cats":["cs.AI","cs.CL","cs.MM","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2025-02-06T15:04:00Z","title":"Llasa: Scaling Train-Time and Inference-Time Compute for Llama-based Speech Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.04128","kind":"arxiv","version":2},"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":"sha256:7f586b9a170b5c1ef9abfc8729c51d8d7b8f5a81f26c402c695694ea5a349aa9","target":"record","created_at":"2026-07-05T10:18:13Z","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":"f91318cc083f36c97b49659bad97ac6d65b6234f25f0ec937bcb4b3cc2b1d73f","cross_cats_sorted":["cs.AI","cs.CL","cs.MM","cs.SD"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2025-02-06T15:04:00Z","title_canon_sha256":"321672531db2d8aa3f98788954de7c3d2f2d9655440203a04ffd99909c0b3d9c"},"schema_version":"1.0","source":{"id":"2502.04128","kind":"arxiv","version":2}},"canonical_sha256":"4669114ec2d5625aaf1e15222a3911ed510354f6b030b2da455374bda674e54b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4669114ec2d5625aaf1e15222a3911ed510354f6b030b2da455374bda674e54b","first_computed_at":"2026-07-05T10:18:13.176802Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:18:13.176802Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HNvODzO0ET31GGogqphTP8cl8T8avPLNJcHA4Y6c38iN4uEbgo7AcTfGLVnvZsCiwBRUHK2Mwr6lCctboOHzAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:18:13.177294Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.04128","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7f586b9a170b5c1ef9abfc8729c51d8d7b8f5a81f26c402c695694ea5a349aa9","sha256:518bb3b26291c972944cb94b35b160f63b63bc01853a7e125ddddd16c6f79dcf"],"state_sha256":"3a551405d9737f3f7ebbfe1620c05dd3108a9637ca6e1cde3093b6d10255a4a9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SJHyWfYjDCS2IeFDzMfZj/yIEaTmshVj3qnQoqExz2OqE7eRCIsXzSuv6ZKQg8oyCOucqJvmNwVVcI4AsRbyCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-20T11:32:05.377777Z","bundle_sha256":"b7da4761c2d0681a105c7ccd667e945e5bfbdbeb6a3fd8c5175665bc54a74fb1"}}