{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:X6HEBTGJ2A53IU75N6NMDPM7UP","short_pith_number":"pith:X6HEBTGJ","canonical_record":{"source":{"id":"2410.13839","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-10-17T17:55:26Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"2800fe1f157b4e5c716e9d7cf1755e015d486728b38a8aa9615a3677b2bcc6f7","abstract_canon_sha256":"c5008b02bd6014e355e601e6c141e1cdbb8ef8fe20fefe8c08db2554710048bc"},"schema_version":"1.0"},"canonical_sha256":"bf8e40ccc9d03bb453fd6f9ac1bd9fa3e3015197a7d1656fb45b0032696d07c5","source":{"kind":"arxiv","id":"2410.13839","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.13839","created_at":"2026-07-05T09:22:06Z"},{"alias_kind":"arxiv_version","alias_value":"2410.13839v1","created_at":"2026-07-05T09:22:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.13839","created_at":"2026-07-05T09:22:06Z"},{"alias_kind":"pith_short_12","alias_value":"X6HEBTGJ2A53","created_at":"2026-07-05T09:22:06Z"},{"alias_kind":"pith_short_16","alias_value":"X6HEBTGJ2A53IU75","created_at":"2026-07-05T09:22:06Z"},{"alias_kind":"pith_short_8","alias_value":"X6HEBTGJ","created_at":"2026-07-05T09:22:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:X6HEBTGJ2A53IU75N6NMDPM7UP","target":"record","payload":{"canonical_record":{"source":{"id":"2410.13839","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-10-17T17:55:26Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"2800fe1f157b4e5c716e9d7cf1755e015d486728b38a8aa9615a3677b2bcc6f7","abstract_canon_sha256":"c5008b02bd6014e355e601e6c141e1cdbb8ef8fe20fefe8c08db2554710048bc"},"schema_version":"1.0"},"canonical_sha256":"bf8e40ccc9d03bb453fd6f9ac1bd9fa3e3015197a7d1656fb45b0032696d07c5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:22:06.361133Z","signature_b64":"kfvd0mOsyJnG6rWX0aYSGF9LXUAe8v/jkWsrFMmTd02ylPOPFwHfgiwacuuPrcF5E+yN1BTzngFJUn+PrCbEBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf8e40ccc9d03bb453fd6f9ac1bd9fa3e3015197a7d1656fb45b0032696d07c5","last_reissued_at":"2026-07-05T09:22:06.360559Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:22:06.360559Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.13839","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":"2026-07-05T09:22:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Kjqh9l9ENihwm4c+8zkNBbhXzyEsVEPVE0WDPkVrE/rweAyKvGXEFXKW8WkuEgGctot8T4N4dzQYltdxYdChCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T02:01:47.908808Z"},"content_sha256":"22e8dfa0663acba8ab3365c0b703e37da8a89be253b9267ba5cd7205a89a5981","schema_version":"1.0","event_id":"sha256:22e8dfa0663acba8ab3365c0b703e37da8a89be253b9267ba5cd7205a89a5981"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:X6HEBTGJ2A53IU75N6NMDPM7UP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Accelerating Codec-based Speech Synthesis with Multi-Token Prediction and Speculative Decoding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Jeongsoo Choi, Ji-Hoon Kim, JinSeok Park, Joon Son Chung, Shukjae Choi, Tan Dat Nguyen, Younglo Lee","submitted_at":"2024-10-17T17:55:26Z","abstract_excerpt":"The goal of this paper is to accelerate codec-based speech synthesis systems with minimum sacrifice to speech quality. We propose an enhanced inference method that allows for flexible trade-offs between speed and quality during inference without requiring additional training. Our core idea is to predict multiple tokens per inference step of the AR module using multiple prediction heads, resulting in a linear reduction in synthesis time as the number of heads increases. Furthermore, we introduce a novel speculative decoding technique that utilises a Viterbi-based algorithm to select the optimal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.13839","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/2410.13839/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":"2026-07-05T09:22:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TMp7mPGur6QXFIq+CzoM0UOepYhldh33WPRd+ud/1CAgXvcP76BjwZMOhPJXzXU5CAceT00Kd3hsAn+fPsRgBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T02:01:47.909313Z"},"content_sha256":"48a994b2ff86452d65a587806f568bbe4efc7881c571e1efc707524654417c5b","schema_version":"1.0","event_id":"sha256:48a994b2ff86452d65a587806f568bbe4efc7881c571e1efc707524654417c5b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/X6HEBTGJ2A53IU75N6NMDPM7UP/bundle.json","state_url":"https://pith.science/pith/X6HEBTGJ2A53IU75N6NMDPM7UP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/X6HEBTGJ2A53IU75N6NMDPM7UP/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":"2026-08-18T02:01:47Z","links":{"resolver":"https://pith.science/pith/X6HEBTGJ2A53IU75N6NMDPM7UP","bundle":"https://pith.science/pith/X6HEBTGJ2A53IU75N6NMDPM7UP/bundle.json","state":"https://pith.science/pith/X6HEBTGJ2A53IU75N6NMDPM7UP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/X6HEBTGJ2A53IU75N6NMDPM7UP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:X6HEBTGJ2A53IU75N6NMDPM7UP","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":"c5008b02bd6014e355e601e6c141e1cdbb8ef8fe20fefe8c08db2554710048bc","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-10-17T17:55:26Z","title_canon_sha256":"2800fe1f157b4e5c716e9d7cf1755e015d486728b38a8aa9615a3677b2bcc6f7"},"schema_version":"1.0","source":{"id":"2410.13839","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.13839","created_at":"2026-07-05T09:22:06Z"},{"alias_kind":"arxiv_version","alias_value":"2410.13839v1","created_at":"2026-07-05T09:22:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.13839","created_at":"2026-07-05T09:22:06Z"},{"alias_kind":"pith_short_12","alias_value":"X6HEBTGJ2A53","created_at":"2026-07-05T09:22:06Z"},{"alias_kind":"pith_short_16","alias_value":"X6HEBTGJ2A53IU75","created_at":"2026-07-05T09:22:06Z"},{"alias_kind":"pith_short_8","alias_value":"X6HEBTGJ","created_at":"2026-07-05T09:22:06Z"}],"graph_snapshots":[{"event_id":"sha256:48a994b2ff86452d65a587806f568bbe4efc7881c571e1efc707524654417c5b","target":"graph","created_at":"2026-07-05T09:22:06Z","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/2410.13839/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The goal of this paper is to accelerate codec-based speech synthesis systems with minimum sacrifice to speech quality. We propose an enhanced inference method that allows for flexible trade-offs between speed and quality during inference without requiring additional training. Our core idea is to predict multiple tokens per inference step of the AR module using multiple prediction heads, resulting in a linear reduction in synthesis time as the number of heads increases. Furthermore, we introduce a novel speculative decoding technique that utilises a Viterbi-based algorithm to select the optimal","authors_text":"Jeongsoo Choi, Ji-Hoon Kim, JinSeok Park, Joon Son Chung, Shukjae Choi, Tan Dat Nguyen, Younglo Lee","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-10-17T17:55:26Z","title":"Accelerating Codec-based Speech Synthesis with Multi-Token Prediction and Speculative Decoding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.13839","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":"sha256:22e8dfa0663acba8ab3365c0b703e37da8a89be253b9267ba5cd7205a89a5981","target":"record","created_at":"2026-07-05T09:22:06Z","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":"c5008b02bd6014e355e601e6c141e1cdbb8ef8fe20fefe8c08db2554710048bc","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-10-17T17:55:26Z","title_canon_sha256":"2800fe1f157b4e5c716e9d7cf1755e015d486728b38a8aa9615a3677b2bcc6f7"},"schema_version":"1.0","source":{"id":"2410.13839","kind":"arxiv","version":1}},"canonical_sha256":"bf8e40ccc9d03bb453fd6f9ac1bd9fa3e3015197a7d1656fb45b0032696d07c5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bf8e40ccc9d03bb453fd6f9ac1bd9fa3e3015197a7d1656fb45b0032696d07c5","first_computed_at":"2026-07-05T09:22:06.360559Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:22:06.360559Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kfvd0mOsyJnG6rWX0aYSGF9LXUAe8v/jkWsrFMmTd02ylPOPFwHfgiwacuuPrcF5E+yN1BTzngFJUn+PrCbEBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:22:06.361133Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.13839","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:22e8dfa0663acba8ab3365c0b703e37da8a89be253b9267ba5cd7205a89a5981","sha256:48a994b2ff86452d65a587806f568bbe4efc7881c571e1efc707524654417c5b"],"state_sha256":"21c5969a9185b7196dee0bd99f49d7988cc0035144a35f4ef892de0ce0fe134d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+naUz2Nbrp0anDStO5wQY/eW/ddCHA1bK2JyWatTJsuGPaBuzZWQynkDiBJwiGDNnN8y1zpx/3mTpzpie6EyCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T02:01:47.914808Z","bundle_sha256":"da0345451f6956e6896045edb7e4b72fc3787ade68ea4b69466c1eb8c487d2d4"}}