{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:IVUYM7JYYCPSEM6627Z6BDJP45","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":"b10881e74834f623dfba853348e00d4003d034252237e9d235c0573dd1e86153","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-10T17:41:19Z","title_canon_sha256":"3fd9692c4ae48bb079eaa0b335d33623a74267d10d799c85482c6087280fcdda"},"schema_version":"1.0","source":{"id":"2308.05725","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.05725","created_at":"2026-07-05T06:40:04Z"},{"alias_kind":"arxiv_version","alias_value":"2308.05725v1","created_at":"2026-07-05T06:40:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.05725","created_at":"2026-07-05T06:40:04Z"},{"alias_kind":"pith_short_12","alias_value":"IVUYM7JYYCPS","created_at":"2026-07-05T06:40:04Z"},{"alias_kind":"pith_short_16","alias_value":"IVUYM7JYYCPSEM66","created_at":"2026-07-05T06:40:04Z"},{"alias_kind":"pith_short_8","alias_value":"IVUYM7JY","created_at":"2026-07-05T06:40:04Z"}],"graph_snapshots":[{"event_id":"sha256:3de87aceb2225f2ee0c111422090a0967c6e54e8b1bafd898385b951d03ad7f6","target":"graph","created_at":"2026-07-05T06:40:04Z","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/2308.05725/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent work has shown that it is possible to resynthesize high-quality speech based, not on text, but on low bitrate discrete units that have been learned in a self-supervised fashion and can therefore capture expressive aspects of speech that are hard to transcribe (prosody, voice styles, non-verbal vocalization). The adoption of these methods is still limited by the fact that most speech synthesis datasets are read, severely limiting spontaneity and expressivity. Here, we introduce Expresso, a high-quality expressive speech dataset for textless speech synthesis that includes both read speech","authors_text":"Antony D'Avirro, Bowen Shi, Emmanuel Dupoux, Felix Kreuk, Gabriel Synnaeve, Itai Gat, Jade Copet, Maryam Fazel-Zarani, Michael Hassid, Tal Remez, Tu Anh Nguyen, Wei-Ning Hsu, Yossi Adi","cross_cats":["cs.LG","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-10T17:41:19Z","title":"EXPRESSO: A Benchmark and Analysis of Discrete Expressive Speech Resynthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.05725","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:e86a38ae6c3fe39af78058bd67e0b4ab99cbca58d303403043ef0202cfc49216","target":"record","created_at":"2026-07-05T06:40:04Z","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":"b10881e74834f623dfba853348e00d4003d034252237e9d235c0573dd1e86153","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-10T17:41:19Z","title_canon_sha256":"3fd9692c4ae48bb079eaa0b335d33623a74267d10d799c85482c6087280fcdda"},"schema_version":"1.0","source":{"id":"2308.05725","kind":"arxiv","version":1}},"canonical_sha256":"4569867d38c09f2233ded7f3e08d2fe76acfaf21749cd3605e9dac9fa3a1e306","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4569867d38c09f2233ded7f3e08d2fe76acfaf21749cd3605e9dac9fa3a1e306","first_computed_at":"2026-07-05T06:40:04.294640Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:40:04.294640Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lvxYrwu/lyq+DhD15p5Iy/vdNkZwFfrhhNJnlCFmMCL4PUnlBc8F3xh6USNVbfk7bD1zf5LkWh8+rx5Yf0KECw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:40:04.295041Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.05725","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e86a38ae6c3fe39af78058bd67e0b4ab99cbca58d303403043ef0202cfc49216","sha256:3de87aceb2225f2ee0c111422090a0967c6e54e8b1bafd898385b951d03ad7f6"],"state_sha256":"4adf98145a485f3871b5daeef6fc17c8e0323727cccd3f0d6905a03437d80d87"}