{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:4MIIFTEIOKWABOMHS5IIOLFBP7","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":"21341a3e244d0f26c1163a5b7f550b519045f212342ff82acfb57a8e71d6aeea","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-07-07T15:45:42Z","title_canon_sha256":"cca3a7af2254b19f1b8a5a13fe6e6e34943412ee98358360b0045fab7cc891d8"},"schema_version":"1.0","source":{"id":"2107.03312","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.03312","created_at":"2026-07-05T02:56:02Z"},{"alias_kind":"arxiv_version","alias_value":"2107.03312v1","created_at":"2026-07-05T02:56:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.03312","created_at":"2026-07-05T02:56:02Z"},{"alias_kind":"pith_short_12","alias_value":"4MIIFTEIOKWA","created_at":"2026-07-05T02:56:02Z"},{"alias_kind":"pith_short_16","alias_value":"4MIIFTEIOKWABOMH","created_at":"2026-07-05T02:56:02Z"},{"alias_kind":"pith_short_8","alias_value":"4MIIFTEI","created_at":"2026-07-05T02:56:02Z"}],"graph_snapshots":[{"event_id":"sha256:7ccbcef80d44d8a7eff43912e77dc8cbadf12aa041aa546725ed8c6980eb315a","target":"graph","created_at":"2026-07-05T02:56:02Z","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/2107.03312/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present SoundStream, a novel neural audio codec that can efficiently compress speech, music and general audio at bitrates normally targeted by speech-tailored codecs. SoundStream relies on a model architecture composed by a fully convolutional encoder/decoder network and a residual vector quantizer, which are trained jointly end-to-end. Training leverages recent advances in text-to-speech and speech enhancement, which combine adversarial and reconstruction losses to allow the generation of high-quality audio content from quantized embeddings. By training with structured dropout applied to q","authors_text":"Ahmed Omran, Alejandro Luebs, Jan Skoglund, Marco Tagliasacchi, Neil Zeghidour","cross_cats":["cs.LG","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-07-07T15:45:42Z","title":"SoundStream: An End-to-End Neural Audio Codec"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.03312","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":"sha256:720b7db89764266098cf6dc4eef768b82a6a1540f3cf6b76048b3a37ba0b496a","target":"record","created_at":"2026-07-05T02:56:02Z","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":"21341a3e244d0f26c1163a5b7f550b519045f212342ff82acfb57a8e71d6aeea","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-07-07T15:45:42Z","title_canon_sha256":"cca3a7af2254b19f1b8a5a13fe6e6e34943412ee98358360b0045fab7cc891d8"},"schema_version":"1.0","source":{"id":"2107.03312","kind":"arxiv","version":1}},"canonical_sha256":"e31082cc8872ac00b9879750872ca17fc90e056f74a348bfcb408c713f3d7179","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e31082cc8872ac00b9879750872ca17fc90e056f74a348bfcb408c713f3d7179","first_computed_at":"2026-07-05T02:56:02.656632Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:56:02.656632Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"X6TZmq9vpRWzOmuLGthhkPw6dZtllT1Mlb2+iXo72FJM0jsjm4FEBTR6CJ4IbtEtzIY/SdVg7ofi2xeivtE+Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:56:02.657063Z","signed_message":"canonical_sha256_bytes"},"source_id":"2107.03312","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:720b7db89764266098cf6dc4eef768b82a6a1540f3cf6b76048b3a37ba0b496a","sha256:7ccbcef80d44d8a7eff43912e77dc8cbadf12aa041aa546725ed8c6980eb315a"],"state_sha256":"f2569f46a726d5eac18713cf6038f333a44c44397fc06d07bb18023bfd09a6c0"}