{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:UHQJVCXEXCQ4MX2HD7U6K32JHH","short_pith_number":"pith:UHQJVCXE","canonical_record":{"source":{"id":"2408.09027","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-08-16T21:48:53Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"999162c7afb725efaf51410b6c34e1a832eeddd838fe72cce43a17c6e6278d8b","abstract_canon_sha256":"4e2bab3585b2a709f9de8f83e9908c34d5752e97adf59b95a80dbd1de9065f3f"},"schema_version":"1.0"},"canonical_sha256":"a1e09a8ae4b8a1c65f471fe9e56f4939c72d5b857885ec13f389ae9d5609ed28","source":{"kind":"arxiv","id":"2408.09027","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.09027","created_at":"2026-07-05T09:50:04Z"},{"alias_kind":"arxiv_version","alias_value":"2408.09027v2","created_at":"2026-07-05T09:50:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.09027","created_at":"2026-07-05T09:50:04Z"},{"alias_kind":"pith_short_12","alias_value":"UHQJVCXEXCQ4","created_at":"2026-07-05T09:50:04Z"},{"alias_kind":"pith_short_16","alias_value":"UHQJVCXEXCQ4MX2H","created_at":"2026-07-05T09:50:04Z"},{"alias_kind":"pith_short_8","alias_value":"UHQJVCXE","created_at":"2026-07-05T09:50:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:UHQJVCXEXCQ4MX2HD7U6K32JHH","target":"record","payload":{"canonical_record":{"source":{"id":"2408.09027","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-08-16T21:48:53Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"999162c7afb725efaf51410b6c34e1a832eeddd838fe72cce43a17c6e6278d8b","abstract_canon_sha256":"4e2bab3585b2a709f9de8f83e9908c34d5752e97adf59b95a80dbd1de9065f3f"},"schema_version":"1.0"},"canonical_sha256":"a1e09a8ae4b8a1c65f471fe9e56f4939c72d5b857885ec13f389ae9d5609ed28","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:50:04.768679Z","signature_b64":"e8e7J+WmEy5XUyxqempv+OiYyAVywFN+MKZAtfryJNC4HuLfQRQ2b98jNnrGsgcNGp8FF6Q3vITkFhJHtq+GCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1e09a8ae4b8a1c65f471fe9e56f4939c72d5b857885ec13f389ae9d5609ed28","last_reissued_at":"2026-07-05T09:50:04.768139Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:50:04.768139Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.09027","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":"2026-07-05T09:50:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FHz5UrKR6RuJeqfeaQrHOvRJ2W6nk/IQlYcXDrRdgY+gTyxsqDnt17rC8g6XKh/mCLtxJ4839e7ecizGEMiSBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T14:14:54.226303Z"},"content_sha256":"78c9ac52adda2f17655532c2f419e298a2ea86b664391443d55f3c8ea60414f2","schema_version":"1.0","event_id":"sha256:78c9ac52adda2f17655532c2f419e298a2ea86b664391443d55f3c8ea60414f2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:UHQJVCXEXCQ4MX2HD7U6K32JHH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient Autoregressive Audio Modeling via Next-Scale Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Bhiksha Raj, Hao Chen, Jie Sun, Jinglu Wang, Kai Qiu, Marios Savvides, Xiang Li, Zhe Lin","submitted_at":"2024-08-16T21:48:53Z","abstract_excerpt":"Audio generation has achieved remarkable progress with the advance of sophisticated generative models, such as diffusion models (DMs) and autoregressive (AR) models. However, due to the naturally significant sequence length of audio, the efficiency of audio generation remains an essential issue to be addressed, especially for AR models that are incorporated in large language models (LLMs). In this paper, we analyze the token length of audio tokenization and propose a novel \\textbf{S}cale-level \\textbf{A}udio \\textbf{T}okenizer (SAT), with improved residual quantization. Based on SAT, a scale-l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.09027","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/2408.09027/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":"2026-07-05T09:50:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bFMjKkM5cFaj2KDj9lPOiX02fJHrEMaqN7gY7XrMVaVW3dVzFTOxXD4wWMsYPwB0yRqsCC0X16xxNrhw5xuHBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T14:14:54.226855Z"},"content_sha256":"5c368cf301cba3d7635bfb0e9e6583eb8eca8a3c61e9013afda4043d7420babd","schema_version":"1.0","event_id":"sha256:5c368cf301cba3d7635bfb0e9e6583eb8eca8a3c61e9013afda4043d7420babd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UHQJVCXEXCQ4MX2HD7U6K32JHH/bundle.json","state_url":"https://pith.science/pith/UHQJVCXEXCQ4MX2HD7U6K32JHH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UHQJVCXEXCQ4MX2HD7U6K32JHH/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":"2026-08-08T14:14:54Z","links":{"resolver":"https://pith.science/pith/UHQJVCXEXCQ4MX2HD7U6K32JHH","bundle":"https://pith.science/pith/UHQJVCXEXCQ4MX2HD7U6K32JHH/bundle.json","state":"https://pith.science/pith/UHQJVCXEXCQ4MX2HD7U6K32JHH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UHQJVCXEXCQ4MX2HD7U6K32JHH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UHQJVCXEXCQ4MX2HD7U6K32JHH","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":"4e2bab3585b2a709f9de8f83e9908c34d5752e97adf59b95a80dbd1de9065f3f","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-08-16T21:48:53Z","title_canon_sha256":"999162c7afb725efaf51410b6c34e1a832eeddd838fe72cce43a17c6e6278d8b"},"schema_version":"1.0","source":{"id":"2408.09027","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.09027","created_at":"2026-07-05T09:50:04Z"},{"alias_kind":"arxiv_version","alias_value":"2408.09027v2","created_at":"2026-07-05T09:50:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.09027","created_at":"2026-07-05T09:50:04Z"},{"alias_kind":"pith_short_12","alias_value":"UHQJVCXEXCQ4","created_at":"2026-07-05T09:50:04Z"},{"alias_kind":"pith_short_16","alias_value":"UHQJVCXEXCQ4MX2H","created_at":"2026-07-05T09:50:04Z"},{"alias_kind":"pith_short_8","alias_value":"UHQJVCXE","created_at":"2026-07-05T09:50:04Z"}],"graph_snapshots":[{"event_id":"sha256:5c368cf301cba3d7635bfb0e9e6583eb8eca8a3c61e9013afda4043d7420babd","target":"graph","created_at":"2026-07-05T09:50:04Z","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/2408.09027/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio generation has achieved remarkable progress with the advance of sophisticated generative models, such as diffusion models (DMs) and autoregressive (AR) models. However, due to the naturally significant sequence length of audio, the efficiency of audio generation remains an essential issue to be addressed, especially for AR models that are incorporated in large language models (LLMs). In this paper, we analyze the token length of audio tokenization and propose a novel \\textbf{S}cale-level \\textbf{A}udio \\textbf{T}okenizer (SAT), with improved residual quantization. Based on SAT, a scale-l","authors_text":"Bhiksha Raj, Hao Chen, Jie Sun, Jinglu Wang, Kai Qiu, Marios Savvides, Xiang Li, Zhe Lin","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-08-16T21:48:53Z","title":"Efficient Autoregressive Audio Modeling via Next-Scale Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.09027","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":"sha256:78c9ac52adda2f17655532c2f419e298a2ea86b664391443d55f3c8ea60414f2","target":"record","created_at":"2026-07-05T09:50:04Z","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":"4e2bab3585b2a709f9de8f83e9908c34d5752e97adf59b95a80dbd1de9065f3f","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-08-16T21:48:53Z","title_canon_sha256":"999162c7afb725efaf51410b6c34e1a832eeddd838fe72cce43a17c6e6278d8b"},"schema_version":"1.0","source":{"id":"2408.09027","kind":"arxiv","version":2}},"canonical_sha256":"a1e09a8ae4b8a1c65f471fe9e56f4939c72d5b857885ec13f389ae9d5609ed28","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a1e09a8ae4b8a1c65f471fe9e56f4939c72d5b857885ec13f389ae9d5609ed28","first_computed_at":"2026-07-05T09:50:04.768139Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:50:04.768139Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"e8e7J+WmEy5XUyxqempv+OiYyAVywFN+MKZAtfryJNC4HuLfQRQ2b98jNnrGsgcNGp8FF6Q3vITkFhJHtq+GCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:50:04.768679Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.09027","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:78c9ac52adda2f17655532c2f419e298a2ea86b664391443d55f3c8ea60414f2","sha256:5c368cf301cba3d7635bfb0e9e6583eb8eca8a3c61e9013afda4043d7420babd"],"state_sha256":"6f90a9e5d569d112c113dffbeb3fe408e9c6dd55d1360b6b70c3cd1e99b9892b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"08L201WxPLrVOwfnLgaKeIpQsk522D84bm/p2kf4a3SEoExd2hdmfFSkgqOzDBggbtByyDmn8f0YXFxJJ4nKCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T14:14:54.232602Z","bundle_sha256":"e132ecf07059a1336c1e8c4e174687953ae82f0a933d8a93ca87615e8426424b"}}