{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SCWQCGUSE2MEL4SUBONT56RWVT","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":"b65d24dacb27c95e9e225ad47294f30c0b2be9981588c5ddd86e3a7f1517ffd1","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-30T15:50:08Z","title_canon_sha256":"dba8c10228bab01ddb4108adb27614f72462665acc93f305675c116f804627fd"},"schema_version":"1.0","source":{"id":"2506.23986","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.23986","created_at":"2026-07-05T11:30:04Z"},{"alias_kind":"arxiv_version","alias_value":"2506.23986v2","created_at":"2026-07-05T11:30:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23986","created_at":"2026-07-05T11:30:04Z"},{"alias_kind":"pith_short_12","alias_value":"SCWQCGUSE2ME","created_at":"2026-07-05T11:30:04Z"},{"alias_kind":"pith_short_16","alias_value":"SCWQCGUSE2MEL4SU","created_at":"2026-07-05T11:30:04Z"},{"alias_kind":"pith_short_8","alias_value":"SCWQCGUS","created_at":"2026-07-05T11:30:04Z"}],"graph_snapshots":[{"event_id":"sha256:a270b83ef258a6c830d66e9e00ba63b899fdc25492ecd0f5d6353d4948717711","target":"graph","created_at":"2026-07-05T11:30:04Z","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/2506.23986/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in discrete token-based speech generation have highlighted the importance of token-to-waveform generation for audio quality, particularly in real-time interactions. Traditional frameworks integrating semantic tokens with flow matching (FM) struggle with streaming capabilities due to their reliance on a global receptive field. Additionally, directly implementing token-by-token streaming speech generation often results in degraded audio quality. To address these challenges, we propose StreamFlow, a novel neural architecture that facilitates streaming flow matching with diffus","authors_text":"Dake Guo, He Wang, Jixun Yao, Lei Xie, Linhan Ma","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-30T15:50:08Z","title":"StreamFlow: Streaming Flow Matching with Block-wise Guided Attention Mask for Speech Token Decoding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23986","kind":"arxiv","version":2},"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:a0bbfc1c77fd201852b83a560087afa013e1ad716fdf16fc9117e2bbdce1caf8","target":"record","created_at":"2026-07-05T11:30:04Z","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":"b65d24dacb27c95e9e225ad47294f30c0b2be9981588c5ddd86e3a7f1517ffd1","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-30T15:50:08Z","title_canon_sha256":"dba8c10228bab01ddb4108adb27614f72462665acc93f305675c116f804627fd"},"schema_version":"1.0","source":{"id":"2506.23986","kind":"arxiv","version":2}},"canonical_sha256":"90ad011a92269845f2540b9b3efa36acc2d002a784985a91ac1c2f30f2e1bf28","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"90ad011a92269845f2540b9b3efa36acc2d002a784985a91ac1c2f30f2e1bf28","first_computed_at":"2026-07-05T11:30:04.261077Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:30:04.261077Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fka0PhCTwhpmMzFlJ7V4rdzpc1gPsE1JMe5nlbVR55S1DelG6uN+/PydmqmeHYZaUEFiu79xFX+80Ye3v/PQDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:30:04.261550Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.23986","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a0bbfc1c77fd201852b83a560087afa013e1ad716fdf16fc9117e2bbdce1caf8","sha256:a270b83ef258a6c830d66e9e00ba63b899fdc25492ecd0f5d6353d4948717711"],"state_sha256":"19ca417f7c01bd202fa469fca55f83c92d7e22f23b85a1196f16e79acf5f10ec"}