{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:Y6MSWVSQCQMMCLA3ODLAKDVZSX","short_pith_number":"pith:Y6MSWVSQ","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"},"canonical_sha256":"c7992b56501418c12c1b70d6050eb995dce181cb19af24ab936659b875b34216","source":{"kind":"arxiv","id":"2506.00736","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:Y6MSWVSQCQMMCLA3ODLAKDVZSX","target":"record","payload":{"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"},"canonical_sha256":"c7992b56501418c12c1b70d6050eb995dce181cb19af24ab936659b875b34216","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"},"source_kind":"arxiv","source_id":"2506.00736","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:13:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z9XjDejbfr96LJ9OyyRK69PlphA+YbGHBohAm+cZw6wDc7YYOEMt3DVTvdvhdoa2y7/jb4xk0zkVzZOJZqIBCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T08:13:17.483705Z"},"content_sha256":"76a18241e76e6995e060bed5966db74f4835f612a67b0ec7545e987fbd36e4e0","schema_version":"1.0","event_id":"sha256:76a18241e76e6995e060bed5966db74f4835f612a67b0ec7545e987fbd36e4e0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:Y6MSWVSQCQMMCLA3ODLAKDVZSX","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:13:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nBlyrHaqOiGpxJNbtVsKCAxZ4pevaStWMp8mj6UiqlSTHANsf83DDOPhQk6Kq4lmaoHXqAtxd3YNrQT1nsB3BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T08:13:17.484089Z"},"content_sha256":"8aa0d64b6f22e138216f5e6b9c59e25e982921f27f20bec7bd907e4cabec15f5","schema_version":"1.0","event_id":"sha256:8aa0d64b6f22e138216f5e6b9c59e25e982921f27f20bec7bd907e4cabec15f5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y6MSWVSQCQMMCLA3ODLAKDVZSX/bundle.json","state_url":"https://pith.science/pith/Y6MSWVSQCQMMCLA3ODLAKDVZSX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y6MSWVSQCQMMCLA3ODLAKDVZSX/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-06T08:13:17Z","links":{"resolver":"https://pith.science/pith/Y6MSWVSQCQMMCLA3ODLAKDVZSX","bundle":"https://pith.science/pith/Y6MSWVSQCQMMCLA3ODLAKDVZSX/bundle.json","state":"https://pith.science/pith/Y6MSWVSQCQMMCLA3ODLAKDVZSX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y6MSWVSQCQMMCLA3ODLAKDVZSX/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6YEKxWMUB8KlyRGPsPjynsYFPgfrU+KDOSPiKztGH1h5t/CvOHXQhkZDCkf+XVc442sWZ/KS00Him42oSJM5DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T08:13:17.486175Z","bundle_sha256":"bdc2d0f8f708d8582f13d07df8c0603c210546b821bbaa93c4aaf40e88be0b91"}}