{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CMNEBIVH4KZAKG75VE75CPIRO5","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":"715068f9159b8243edd6cad071cbe3ea3fca6719ac7dff08d9310336c529b573","cross_cats_sorted":["cs.AI","cs.LG","eess.AS","eess.SP"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-02-05T12:36:21Z","title_canon_sha256":"b78d0f8361b7e5a01051d4d30533094faebf0c08d5d6b481c216c0a4461412ae"},"schema_version":"1.0","source":{"id":"2502.03128","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.03128","created_at":"2026-07-05T10:10:00Z"},{"alias_kind":"arxiv_version","alias_value":"2502.03128v1","created_at":"2026-07-05T10:10:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.03128","created_at":"2026-07-05T10:10:00Z"},{"alias_kind":"pith_short_12","alias_value":"CMNEBIVH4KZA","created_at":"2026-07-05T10:10:00Z"},{"alias_kind":"pith_short_16","alias_value":"CMNEBIVH4KZAKG75","created_at":"2026-07-05T10:10:00Z"},{"alias_kind":"pith_short_8","alias_value":"CMNEBIVH","created_at":"2026-07-05T10:10:00Z"}],"graph_snapshots":[{"event_id":"sha256:b0b6b1beac33aff843dbcdecae41f942cb18b22892794e49adc052ee8a13839e","target":"graph","created_at":"2026-07-05T10:10:00Z","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/2502.03128/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce Metis, a foundation model for unified speech generation. Unlike previous task-specific or multi-task models, Metis follows a pre-training and fine-tuning paradigm. It is pre-trained on large-scale unlabeled speech data using masked generative modeling and then fine-tuned to adapt to diverse speech generation tasks. Specifically, 1) Metis utilizes two discrete speech representations: SSL tokens derived from speech self-supervised learning (SSL) features, and acoustic tokens directly quantized from waveforms. 2) Metis performs masked generative pre-training on SSL tokens, utilizing ","authors_text":"Huan Liao, Jiachen Zheng, Junan Zhang, Xueyao Zhang, Yuancheng Wang, Zhizheng Wu","cross_cats":["cs.AI","cs.LG","eess.AS","eess.SP"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-02-05T12:36:21Z","title":"Metis: A Foundation Speech Generation Model with Masked Generative Pre-training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.03128","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:f91f0b95779c026e01fb590f48577b55fda6e291cb17bb3b488b09e058f3f245","target":"record","created_at":"2026-07-05T10:10:00Z","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":"715068f9159b8243edd6cad071cbe3ea3fca6719ac7dff08d9310336c529b573","cross_cats_sorted":["cs.AI","cs.LG","eess.AS","eess.SP"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-02-05T12:36:21Z","title_canon_sha256":"b78d0f8361b7e5a01051d4d30533094faebf0c08d5d6b481c216c0a4461412ae"},"schema_version":"1.0","source":{"id":"2502.03128","kind":"arxiv","version":1}},"canonical_sha256":"131a40a2a7e2b2051bfda93fd13d1177549cde90ff3a1d6ad776ffc8929581dd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"131a40a2a7e2b2051bfda93fd13d1177549cde90ff3a1d6ad776ffc8929581dd","first_computed_at":"2026-07-05T10:10:00.178650Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:10:00.178650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kIuKsei7WewauJNuo5fD9lnlkEwakwQM3lBu0MPOx8QLnIcxVy5sSmMC086VgIhuj0/H3GhCCDa1Si/J81+CBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:10:00.179129Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.03128","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f91f0b95779c026e01fb590f48577b55fda6e291cb17bb3b488b09e058f3f245","sha256:b0b6b1beac33aff843dbcdecae41f942cb18b22892794e49adc052ee8a13839e"],"state_sha256":"e95254f802387c27798111577ef537d3a27c75958108caa1ac77e90b19940024"}