{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:Y6MSWVSQCQMMCLA3ODLAKDVZSX","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":"835859acd6b0b10b061ade69219e460d839f85aa2882e034c554afef379db7e2","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2025-05-31T22:51:36Z","title_canon_sha256":"c4196a2c07fc3cd81d00a3e60b1b57ef7b67948e812a0118d90b75742fa2e780"},"schema_version":"1.0","source":{"id":"2506.00736","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00736","created_at":"2026-07-05T11:13:39Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00736v1","created_at":"2026-07-05T11:13:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00736","created_at":"2026-07-05T11:13:39Z"},{"alias_kind":"pith_short_12","alias_value":"Y6MSWVSQCQMM","created_at":"2026-07-05T11:13:39Z"},{"alias_kind":"pith_short_16","alias_value":"Y6MSWVSQCQMMCLA3","created_at":"2026-07-05T11:13:39Z"},{"alias_kind":"pith_short_8","alias_value":"Y6MSWVSQ","created_at":"2026-07-05T11:13:39Z"}],"graph_snapshots":[{"event_id":"sha256:8aa0d64b6f22e138216f5e6b9c59e25e982921f27f20bec7bd907e4cabec15f5","target":"graph","created_at":"2026-07-05T11:13:39Z","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/2506.00736/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":["cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2025-05-31T22:51:36Z","title":"IMPACT: Iterative Mask-based Parallel Decoding for Text-to-Audio Generation with Diffusion Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00736","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":"sha256:76a18241e76e6995e060bed5966db74f4835f612a67b0ec7545e987fbd36e4e0","target":"record","created_at":"2026-07-05T11:13:39Z","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":"835859acd6b0b10b061ade69219e460d839f85aa2882e034c554afef379db7e2","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2025-05-31T22:51:36Z","title_canon_sha256":"c4196a2c07fc3cd81d00a3e60b1b57ef7b67948e812a0118d90b75742fa2e780"},"schema_version":"1.0","source":{"id":"2506.00736","kind":"arxiv","version":1}},"canonical_sha256":"c7992b56501418c12c1b70d6050eb995dce181cb19af24ab936659b875b34216","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c7992b56501418c12c1b70d6050eb995dce181cb19af24ab936659b875b34216","first_computed_at":"2026-07-05T11:13:39.637389Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:39.637389Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aPlwNJ16u8EqLRkg2TSQKn+ZLvs4XLGH5yeKHZixJEYb9cFeww0piVAT1Wlrt/aLOxo65v0ASMT2Gl6G2U1vBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:39.637972Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.00736","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:76a18241e76e6995e060bed5966db74f4835f612a67b0ec7545e987fbd36e4e0","sha256:8aa0d64b6f22e138216f5e6b9c59e25e982921f27f20bec7bd907e4cabec15f5"],"state_sha256":"e3a4aee02ce08319b21567571b9dfeeee95bfc39b491492f52e259926d339784"}