{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SCWQCGUSE2MEL4SUBONT56RWVT","short_pith_number":"pith:SCWQCGUS","schema_version":"1.0","canonical_sha256":"90ad011a92269845f2540b9b3efa36acc2d002a784985a91ac1c2f30f2e1bf28","source":{"kind":"arxiv","id":"2506.23986","version":2},"attestation_state":"computed","paper":{"title":"StreamFlow: Streaming Flow Matching with Block-wise Guided Attention Mask for Speech Token Decoding","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Dake Guo, He Wang, Jixun Yao, Lei Xie, Linhan Ma","submitted_at":"2025-06-30T15:50:08Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2506.23986","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-30T15:50:08Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"dba8c10228bab01ddb4108adb27614f72462665acc93f305675c116f804627fd","abstract_canon_sha256":"b65d24dacb27c95e9e225ad47294f30c0b2be9981588c5ddd86e3a7f1517ffd1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:30:04.261550Z","signature_b64":"fka0PhCTwhpmMzFlJ7V4rdzpc1gPsE1JMe5nlbVR55S1DelG6uN+/PydmqmeHYZaUEFiu79xFX+80Ye3v/PQDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90ad011a92269845f2540b9b3efa36acc2d002a784985a91ac1c2f30f2e1bf28","last_reissued_at":"2026-07-05T11:30:04.261077Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:30:04.261077Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"StreamFlow: Streaming Flow Matching with Block-wise Guided Attention Mask for Speech Token Decoding","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Dake Guo, He Wang, Jixun Yao, Lei Xie, Linhan Ma","submitted_at":"2025-06-30T15:50:08Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23986","kind":"arxiv","version":2},"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/2506.23986/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2506.23986","created_at":"2026-07-05T11:30:04.261134+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.23986v2","created_at":"2026-07-05T11:30:04.261134+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23986","created_at":"2026-07-05T11:30:04.261134+00:00"},{"alias_kind":"pith_short_12","alias_value":"SCWQCGUSE2ME","created_at":"2026-07-05T11:30:04.261134+00:00"},{"alias_kind":"pith_short_16","alias_value":"SCWQCGUSE2MEL4SU","created_at":"2026-07-05T11:30:04.261134+00:00"},{"alias_kind":"pith_short_8","alias_value":"SCWQCGUS","created_at":"2026-07-05T11:30:04.261134+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2601.15621","citing_title":"Qwen3-TTS Technical Report","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SCWQCGUSE2MEL4SUBONT56RWVT","json":"https://pith.science/pith/SCWQCGUSE2MEL4SUBONT56RWVT.json","graph_json":"https://pith.science/api/pith-number/SCWQCGUSE2MEL4SUBONT56RWVT/graph.json","events_json":"https://pith.science/api/pith-number/SCWQCGUSE2MEL4SUBONT56RWVT/events.json","paper":"https://pith.science/paper/SCWQCGUS"},"agent_actions":{"view_html":"https://pith.science/pith/SCWQCGUSE2MEL4SUBONT56RWVT","download_json":"https://pith.science/pith/SCWQCGUSE2MEL4SUBONT56RWVT.json","view_paper":"https://pith.science/paper/SCWQCGUS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.23986&json=true","fetch_graph":"https://pith.science/api/pith-number/SCWQCGUSE2MEL4SUBONT56RWVT/graph.json","fetch_events":"https://pith.science/api/pith-number/SCWQCGUSE2MEL4SUBONT56RWVT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SCWQCGUSE2MEL4SUBONT56RWVT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SCWQCGUSE2MEL4SUBONT56RWVT/action/storage_attestation","attest_author":"https://pith.science/pith/SCWQCGUSE2MEL4SUBONT56RWVT/action/author_attestation","sign_citation":"https://pith.science/pith/SCWQCGUSE2MEL4SUBONT56RWVT/action/citation_signature","submit_replication":"https://pith.science/pith/SCWQCGUSE2MEL4SUBONT56RWVT/action/replication_record"}},"created_at":"2026-07-05T11:30:04.261134+00:00","updated_at":"2026-07-05T11:30:04.261134+00:00"}