{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:HBWTXDCSTHLCX4QG6EAHX7S6LK","short_pith_number":"pith:HBWTXDCS","canonical_record":{"source":{"id":"2409.04016","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2024-09-06T04:06:50Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"4eaa4de689abf67bb3f9f1dd5e263c15deb27b0741456df4c114874c08580944","abstract_canon_sha256":"ad5333935124f61a9c61100533660bb612024fa51c14ebb9fa1aeec3b08de8c8"},"schema_version":"1.0"},"canonical_sha256":"386d3b8c5299d62bf206f1007bfe5e5a8e1cbfef0c077e15d53cf84eea095b07","source":{"kind":"arxiv","id":"2409.04016","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.04016","created_at":"2026-07-05T09:04:00Z"},{"alias_kind":"arxiv_version","alias_value":"2409.04016v1","created_at":"2026-07-05T09:04:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.04016","created_at":"2026-07-05T09:04:00Z"},{"alias_kind":"pith_short_12","alias_value":"HBWTXDCSTHLC","created_at":"2026-07-05T09:04:00Z"},{"alias_kind":"pith_short_16","alias_value":"HBWTXDCSTHLCX4QG","created_at":"2026-07-05T09:04:00Z"},{"alias_kind":"pith_short_8","alias_value":"HBWTXDCS","created_at":"2026-07-05T09:04:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:HBWTXDCSTHLCX4QG6EAHX7S6LK","target":"record","payload":{"canonical_record":{"source":{"id":"2409.04016","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2024-09-06T04:06:50Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"4eaa4de689abf67bb3f9f1dd5e263c15deb27b0741456df4c114874c08580944","abstract_canon_sha256":"ad5333935124f61a9c61100533660bb612024fa51c14ebb9fa1aeec3b08de8c8"},"schema_version":"1.0"},"canonical_sha256":"386d3b8c5299d62bf206f1007bfe5e5a8e1cbfef0c077e15d53cf84eea095b07","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:04:00.387555Z","signature_b64":"7iv3DmiCNMv5dk7XW42MUzYd4oWt/MfScUF6jxKPynARZn8Dbkz7K6sQma3W96m7rIbY3XzVBMDeA2ueTUnxAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"386d3b8c5299d62bf206f1007bfe5e5a8e1cbfef0c077e15d53cf84eea095b07","last_reissued_at":"2026-07-05T09:04:00.387191Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:04:00.387191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.04016","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":"2026-07-05T09:04:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A+A4EcuQeeJ/cZmQ1whxplbRaLHv4zYzJ9ySWCSFzmIIK6e6UjKxJW3NyVKD3gKJnBmkmWkVqDtgkHPX84jHCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T11:18:32.576188Z"},"content_sha256":"339b5cbd5ab453ab954e0343fb34fab48e6ba13ea0dbb7754889aae8b09e6e35","schema_version":"1.0","event_id":"sha256:339b5cbd5ab453ab954e0343fb34fab48e6ba13ea0dbb7754889aae8b09e6e35"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:HBWTXDCSTHLCX4QG6EAHX7S6LK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Investigating Neural Audio Codecs for Speech Language Model-Based Speech Generation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Canrun Li, Chung-Hsien Tsai, Dongmei Wang, Jiaqi Li, Jinyu Li, Junkun Chen, Long Zhou, Michael Zeng, Midia Yousefi, Sheng Zhao, Shujie Liu, Xiaofei Wang, Yanqing Liu, Yao Qian, Zhen Xiao, Zhizheng Wu","submitted_at":"2024-09-06T04:06:50Z","abstract_excerpt":"Neural audio codec tokens serve as the fundamental building blocks for speech language model (SLM)-based speech generation. However, there is no systematic understanding on how the codec system affects the speech generation performance of the SLM. In this work, we examine codec tokens within SLM framework for speech generation to provide insights for effective codec design. We retrain existing high-performing neural codec models on the same data set and loss functions to compare their performance in a uniform setting. We integrate codec tokens into two SLM systems: masked-based parallel speech"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.04016","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/2409.04016/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":"2026-07-05T09:04:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Lai21OYlF6Fb3nsuvAZtjETMXgAwYUoYNMTC/FNLlc+K/lfi/WmeMjvR5DAxPRLiYcle2aMwTR/5WtDwijWdDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T11:18:32.576786Z"},"content_sha256":"35619e4575d4d245b922f2921c42ccf7ae09d26a4bf26817f8ac778b7af2791c","schema_version":"1.0","event_id":"sha256:35619e4575d4d245b922f2921c42ccf7ae09d26a4bf26817f8ac778b7af2791c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HBWTXDCSTHLCX4QG6EAHX7S6LK/bundle.json","state_url":"https://pith.science/pith/HBWTXDCSTHLCX4QG6EAHX7S6LK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HBWTXDCSTHLCX4QG6EAHX7S6LK/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":"2026-08-04T11:18:32Z","links":{"resolver":"https://pith.science/pith/HBWTXDCSTHLCX4QG6EAHX7S6LK","bundle":"https://pith.science/pith/HBWTXDCSTHLCX4QG6EAHX7S6LK/bundle.json","state":"https://pith.science/pith/HBWTXDCSTHLCX4QG6EAHX7S6LK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HBWTXDCSTHLCX4QG6EAHX7S6LK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HBWTXDCSTHLCX4QG6EAHX7S6LK","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":"ad5333935124f61a9c61100533660bb612024fa51c14ebb9fa1aeec3b08de8c8","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2024-09-06T04:06:50Z","title_canon_sha256":"4eaa4de689abf67bb3f9f1dd5e263c15deb27b0741456df4c114874c08580944"},"schema_version":"1.0","source":{"id":"2409.04016","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.04016","created_at":"2026-07-05T09:04:00Z"},{"alias_kind":"arxiv_version","alias_value":"2409.04016v1","created_at":"2026-07-05T09:04:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.04016","created_at":"2026-07-05T09:04:00Z"},{"alias_kind":"pith_short_12","alias_value":"HBWTXDCSTHLC","created_at":"2026-07-05T09:04:00Z"},{"alias_kind":"pith_short_16","alias_value":"HBWTXDCSTHLCX4QG","created_at":"2026-07-05T09:04:00Z"},{"alias_kind":"pith_short_8","alias_value":"HBWTXDCS","created_at":"2026-07-05T09:04:00Z"}],"graph_snapshots":[{"event_id":"sha256:35619e4575d4d245b922f2921c42ccf7ae09d26a4bf26817f8ac778b7af2791c","target":"graph","created_at":"2026-07-05T09:04:00Z","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/2409.04016/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Neural audio codec tokens serve as the fundamental building blocks for speech language model (SLM)-based speech generation. However, there is no systematic understanding on how the codec system affects the speech generation performance of the SLM. In this work, we examine codec tokens within SLM framework for speech generation to provide insights for effective codec design. We retrain existing high-performing neural codec models on the same data set and loss functions to compare their performance in a uniform setting. We integrate codec tokens into two SLM systems: masked-based parallel speech","authors_text":"Canrun Li, Chung-Hsien Tsai, Dongmei Wang, Jiaqi Li, Jinyu Li, Junkun Chen, Long Zhou, Michael Zeng, Midia Yousefi, Sheng Zhao, Shujie Liu, Xiaofei Wang, Yanqing Liu, Yao Qian, Zhen Xiao, Zhizheng Wu","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2024-09-06T04:06:50Z","title":"Investigating Neural Audio Codecs for Speech Language Model-Based Speech Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.04016","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":"sha256:339b5cbd5ab453ab954e0343fb34fab48e6ba13ea0dbb7754889aae8b09e6e35","target":"record","created_at":"2026-07-05T09:04:00Z","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":"ad5333935124f61a9c61100533660bb612024fa51c14ebb9fa1aeec3b08de8c8","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2024-09-06T04:06:50Z","title_canon_sha256":"4eaa4de689abf67bb3f9f1dd5e263c15deb27b0741456df4c114874c08580944"},"schema_version":"1.0","source":{"id":"2409.04016","kind":"arxiv","version":1}},"canonical_sha256":"386d3b8c5299d62bf206f1007bfe5e5a8e1cbfef0c077e15d53cf84eea095b07","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"386d3b8c5299d62bf206f1007bfe5e5a8e1cbfef0c077e15d53cf84eea095b07","first_computed_at":"2026-07-05T09:04:00.387191Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:04:00.387191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7iv3DmiCNMv5dk7XW42MUzYd4oWt/MfScUF6jxKPynARZn8Dbkz7K6sQma3W96m7rIbY3XzVBMDeA2ueTUnxAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:04:00.387555Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.04016","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:339b5cbd5ab453ab954e0343fb34fab48e6ba13ea0dbb7754889aae8b09e6e35","sha256:35619e4575d4d245b922f2921c42ccf7ae09d26a4bf26817f8ac778b7af2791c"],"state_sha256":"1831d3cb4702227ae88af1e8220f321faa89efe5cddaa0b3f7ae1bc685367d55"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uONLAE94CZGdxrm05i0V+W7xi4PzcKrLDJpCIsTrQ/FBjCfm8nSoPXGXGG/m9c7tJBq/Mx9+/gWeqB6i2uDQCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T11:18:32.617363Z","bundle_sha256":"b7088cb7a0266a53dba605538c77123801f0d62a7682b32a35d431a2b7e21070"}}