{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:IVWIGR5WMFINVKKLQJWYDKN5VI","short_pith_number":"pith:IVWIGR5W","canonical_record":{"source":{"id":"2310.14580","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-10-23T05:38:41Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"1625ba54dcf9919490ab6f67cbe3873124d6323c4862d5f73af9dfbc1fed483f","abstract_canon_sha256":"0a97b571e730a5e54b8ac853951f8af819a83f8d1786765846b278ac360d6548"},"schema_version":"1.0"},"canonical_sha256":"456c8347b66150daa94b826d81a9bdaa239673375fe744069210e62502c40bc4","source":{"kind":"arxiv","id":"2310.14580","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.14580","created_at":"2026-07-05T07:33:21Z"},{"alias_kind":"arxiv_version","alias_value":"2310.14580v4","created_at":"2026-07-05T07:33:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.14580","created_at":"2026-07-05T07:33:21Z"},{"alias_kind":"pith_short_12","alias_value":"IVWIGR5WMFIN","created_at":"2026-07-05T07:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"IVWIGR5WMFINVKKL","created_at":"2026-07-05T07:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"IVWIGR5W","created_at":"2026-07-05T07:33:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:IVWIGR5WMFINVKKLQJWYDKN5VI","target":"record","payload":{"canonical_record":{"source":{"id":"2310.14580","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-10-23T05:38:41Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"1625ba54dcf9919490ab6f67cbe3873124d6323c4862d5f73af9dfbc1fed483f","abstract_canon_sha256":"0a97b571e730a5e54b8ac853951f8af819a83f8d1786765846b278ac360d6548"},"schema_version":"1.0"},"canonical_sha256":"456c8347b66150daa94b826d81a9bdaa239673375fe744069210e62502c40bc4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:33:21.108471Z","signature_b64":"loLmI+BNiStctVtg9lZAQXhttaE1aqYUDvJwOmbrjDUOq7roIVm70iPGfYYcz046efYjTcplOoSe6J0CI+qbAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"456c8347b66150daa94b826d81a9bdaa239673375fe744069210e62502c40bc4","last_reissued_at":"2026-07-05T07:33:21.108039Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:33:21.108039Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.14580","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:33:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Uu+bXP2vElKI3ppUNAyMAacbQVT/Iv+stqkC4ZVonqI4Ng6RNoqTNf+rDaMCmBYYjM+egIlZXLv6hIJluRS4CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T18:47:53.560690Z"},"content_sha256":"186fb45466cfa64525d4aa3ee78893cc70a220f29513ad0caf0a8d86ea5cbc20","schema_version":"1.0","event_id":"sha256:186fb45466cfa64525d4aa3ee78893cc70a220f29513ad0caf0a8d86ea5cbc20"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:IVWIGR5WMFINVKKLQJWYDKN5VI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Acoustic BPE for Speech Generation with Discrete Tokens","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Chenpeng Du, Feiyu Shen, Kai Yu, Xie Chen, Yiwei Guo","submitted_at":"2023-10-23T05:38:41Z","abstract_excerpt":"Discrete audio tokens derived from self-supervised learning models have gained widespread usage in speech generation. However, current practice of directly utilizing audio tokens poses challenges for sequence modeling due to the length of the token sequence. Additionally, this approach places the burden on the model to establish correlations between tokens, further complicating the modeling process. To address this issue, we propose acoustic BPE which encodes frequent audio token patterns by utilizing byte-pair encoding. Acoustic BPE effectively reduces the sequence length and leverages the pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.14580","kind":"arxiv","version":4},"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/2310.14580/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":"2026-07-05T07:33:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gRpcDwANtNUUGCPZafFRvE6FWJyplt7+Vri9YtdZlJakE3tzJzQl2HZR6OrIpkVRyngthFo6rARobJNsFcwuAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T18:47:53.561066Z"},"content_sha256":"711792581b96baa366dc9dd02b7a76afbefc5ddb2407e12b11915498eac2d7c1","schema_version":"1.0","event_id":"sha256:711792581b96baa366dc9dd02b7a76afbefc5ddb2407e12b11915498eac2d7c1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IVWIGR5WMFINVKKLQJWYDKN5VI/bundle.json","state_url":"https://pith.science/pith/IVWIGR5WMFINVKKLQJWYDKN5VI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IVWIGR5WMFINVKKLQJWYDKN5VI/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":"2026-07-17T18:47:53Z","links":{"resolver":"https://pith.science/pith/IVWIGR5WMFINVKKLQJWYDKN5VI","bundle":"https://pith.science/pith/IVWIGR5WMFINVKKLQJWYDKN5VI/bundle.json","state":"https://pith.science/pith/IVWIGR5WMFINVKKLQJWYDKN5VI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IVWIGR5WMFINVKKLQJWYDKN5VI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:IVWIGR5WMFINVKKLQJWYDKN5VI","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":"0a97b571e730a5e54b8ac853951f8af819a83f8d1786765846b278ac360d6548","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-10-23T05:38:41Z","title_canon_sha256":"1625ba54dcf9919490ab6f67cbe3873124d6323c4862d5f73af9dfbc1fed483f"},"schema_version":"1.0","source":{"id":"2310.14580","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.14580","created_at":"2026-07-05T07:33:21Z"},{"alias_kind":"arxiv_version","alias_value":"2310.14580v4","created_at":"2026-07-05T07:33:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.14580","created_at":"2026-07-05T07:33:21Z"},{"alias_kind":"pith_short_12","alias_value":"IVWIGR5WMFIN","created_at":"2026-07-05T07:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"IVWIGR5WMFINVKKL","created_at":"2026-07-05T07:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"IVWIGR5W","created_at":"2026-07-05T07:33:21Z"}],"graph_snapshots":[{"event_id":"sha256:711792581b96baa366dc9dd02b7a76afbefc5ddb2407e12b11915498eac2d7c1","target":"graph","created_at":"2026-07-05T07:33:21Z","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/2310.14580/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Discrete audio tokens derived from self-supervised learning models have gained widespread usage in speech generation. However, current practice of directly utilizing audio tokens poses challenges for sequence modeling due to the length of the token sequence. Additionally, this approach places the burden on the model to establish correlations between tokens, further complicating the modeling process. To address this issue, we propose acoustic BPE which encodes frequent audio token patterns by utilizing byte-pair encoding. Acoustic BPE effectively reduces the sequence length and leverages the pr","authors_text":"Chenpeng Du, Feiyu Shen, Kai Yu, Xie Chen, Yiwei Guo","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-10-23T05:38:41Z","title":"Acoustic BPE for Speech Generation with Discrete Tokens"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.14580","kind":"arxiv","version":4},"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":"sha256:186fb45466cfa64525d4aa3ee78893cc70a220f29513ad0caf0a8d86ea5cbc20","target":"record","created_at":"2026-07-05T07:33:21Z","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":"0a97b571e730a5e54b8ac853951f8af819a83f8d1786765846b278ac360d6548","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-10-23T05:38:41Z","title_canon_sha256":"1625ba54dcf9919490ab6f67cbe3873124d6323c4862d5f73af9dfbc1fed483f"},"schema_version":"1.0","source":{"id":"2310.14580","kind":"arxiv","version":4}},"canonical_sha256":"456c8347b66150daa94b826d81a9bdaa239673375fe744069210e62502c40bc4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"456c8347b66150daa94b826d81a9bdaa239673375fe744069210e62502c40bc4","first_computed_at":"2026-07-05T07:33:21.108039Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:33:21.108039Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"loLmI+BNiStctVtg9lZAQXhttaE1aqYUDvJwOmbrjDUOq7roIVm70iPGfYYcz046efYjTcplOoSe6J0CI+qbAw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:33:21.108471Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.14580","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:186fb45466cfa64525d4aa3ee78893cc70a220f29513ad0caf0a8d86ea5cbc20","sha256:711792581b96baa366dc9dd02b7a76afbefc5ddb2407e12b11915498eac2d7c1"],"state_sha256":"d6e245346786caf5c8bb12d4a98d29c489db6dcf4966c2552b5f5b3416253e6b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t3m9WLGwUVxjR65Bh612h5QrseGV2xiGj0eY1AQCxE0kGhojiIrthDBBDKu43Bf8MtL9KRY1cQaOEqnm1Pd7BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-17T18:47:53.563289Z","bundle_sha256":"97064e95819e5a76940eea346fc5492b98be0c1e645e7b44c8427fb98f3d7b9b"}}