{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Y6MSWVSQCQMMCLA3ODLAKDVZSX","short_pith_number":"pith:Y6MSWVSQ","schema_version":"1.0","canonical_sha256":"c7992b56501418c12c1b70d6050eb995dce181cb19af24ab936659b875b34216","source":{"kind":"arxiv","id":"2506.00736","version":1},"attestation_state":"computed","paper":{"title":"IMPACT: Iterative Mask-based Parallel Decoding for Text-to-Audio Generation with Diffusion Modeling","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Bo-Ru Lu, Byeonggeun Kim, Chao Wang, Chieh-Chi Kao, Hung-yi Lee, Huy Phan, Kuan-Po Huang, Qingming Tang, Sashank Macha, Shalini Ghosh, Shu-wen Yang","submitted_at":"2025-05-31T22:51:36Z","abstract_excerpt":"Text-to-audio generation synthesizes realistic sounds or music given a natural language prompt. Diffusion-based frameworks, including the Tango and the AudioLDM series, represent the state-of-the-art in text-to-audio generation. Despite achieving high audio fidelity, they incur significant inference latency due to the slow diffusion sampling process. MAGNET, a mask-based model operating on discrete tokens, addresses slow inference through iterative mask-based parallel decoding. However, its audio quality still lags behind that of diffusion-based models. In this work, we introduce IMPACT, a tex"},"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":"2506.00736","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2025-05-31T22:51:36Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"c4196a2c07fc3cd81d00a3e60b1b57ef7b67948e812a0118d90b75742fa2e780","abstract_canon_sha256":"835859acd6b0b10b061ade69219e460d839f85aa2882e034c554afef379db7e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:39.637972Z","signature_b64":"aPlwNJ16u8EqLRkg2TSQKn+ZLvs4XLGH5yeKHZixJEYb9cFeww0piVAT1Wlrt/aLOxo65v0ASMT2Gl6G2U1vBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7992b56501418c12c1b70d6050eb995dce181cb19af24ab936659b875b34216","last_reissued_at":"2026-07-05T11:13:39.637389Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:39.637389Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"IMPACT: Iterative Mask-based Parallel Decoding for Text-to-Audio Generation with Diffusion Modeling","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Bo-Ru Lu, Byeonggeun Kim, Chao Wang, Chieh-Chi Kao, Hung-yi Lee, Huy Phan, Kuan-Po Huang, Qingming Tang, Sashank Macha, Shalini Ghosh, Shu-wen Yang","submitted_at":"2025-05-31T22:51:36Z","abstract_excerpt":"Text-to-audio generation synthesizes realistic sounds or music given a natural language prompt. Diffusion-based frameworks, including the Tango and the AudioLDM series, represent the state-of-the-art in text-to-audio generation. Despite achieving high audio fidelity, they incur significant inference latency due to the slow diffusion sampling process. MAGNET, a mask-based model operating on discrete tokens, addresses slow inference through iterative mask-based parallel decoding. However, its audio quality still lags behind that of diffusion-based models. In this work, we introduce IMPACT, a tex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00736","kind":"arxiv","version":1},"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/2506.00736/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":"2506.00736","created_at":"2026-07-05T11:13:39.637569+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.00736v1","created_at":"2026-07-05T11:13:39.637569+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00736","created_at":"2026-07-05T11:13:39.637569+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y6MSWVSQCQMM","created_at":"2026-07-05T11:13:39.637569+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y6MSWVSQCQMMCLA3","created_at":"2026-07-05T11:13:39.637569+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y6MSWVSQ","created_at":"2026-07-05T11:13:39.637569+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.30940","citing_title":"Towards Streaming Synchronized Spatial Audio Generation via Autoregressive Diffusion Transformer","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2603.13419","citing_title":"Diffusion Models Memorize in Training -- and Generalize in Inference","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y6MSWVSQCQMMCLA3ODLAKDVZSX","json":"https://pith.science/pith/Y6MSWVSQCQMMCLA3ODLAKDVZSX.json","graph_json":"https://pith.science/api/pith-number/Y6MSWVSQCQMMCLA3ODLAKDVZSX/graph.json","events_json":"https://pith.science/api/pith-number/Y6MSWVSQCQMMCLA3ODLAKDVZSX/events.json","paper":"https://pith.science/paper/Y6MSWVSQ"},"agent_actions":{"view_html":"https://pith.science/pith/Y6MSWVSQCQMMCLA3ODLAKDVZSX","download_json":"https://pith.science/pith/Y6MSWVSQCQMMCLA3ODLAKDVZSX.json","view_paper":"https://pith.science/paper/Y6MSWVSQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.00736&json=true","fetch_graph":"https://pith.science/api/pith-number/Y6MSWVSQCQMMCLA3ODLAKDVZSX/graph.json","fetch_events":"https://pith.science/api/pith-number/Y6MSWVSQCQMMCLA3ODLAKDVZSX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y6MSWVSQCQMMCLA3ODLAKDVZSX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y6MSWVSQCQMMCLA3ODLAKDVZSX/action/storage_attestation","attest_author":"https://pith.science/pith/Y6MSWVSQCQMMCLA3ODLAKDVZSX/action/author_attestation","sign_citation":"https://pith.science/pith/Y6MSWVSQCQMMCLA3ODLAKDVZSX/action/citation_signature","submit_replication":"https://pith.science/pith/Y6MSWVSQCQMMCLA3ODLAKDVZSX/action/replication_record"}},"created_at":"2026-07-05T11:13:39.637569+00:00","updated_at":"2026-07-05T11:13:39.637569+00:00"}