{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FACVF5VYNCQHATCPYJ6VUA3PXN","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":"76e499b5bd26c5286c7b64a17a42161c922c360ae54a430dfddf15f105e95638","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-06-25T16:02:59Z","title_canon_sha256":"7080379a05ddd997719ea84faae63e5eefe87bdf9fbf8bdf21c74f32df1b211b"},"schema_version":"1.0","source":{"id":"2406.17672","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.17672","created_at":"2026-07-05T08:36:49Z"},{"alias_kind":"arxiv_version","alias_value":"2406.17672v2","created_at":"2026-07-05T08:36:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.17672","created_at":"2026-07-05T08:36:49Z"},{"alias_kind":"pith_short_12","alias_value":"FACVF5VYNCQH","created_at":"2026-07-05T08:36:49Z"},{"alias_kind":"pith_short_16","alias_value":"FACVF5VYNCQHATCP","created_at":"2026-07-05T08:36:49Z"},{"alias_kind":"pith_short_8","alias_value":"FACVF5VY","created_at":"2026-07-05T08:36:49Z"}],"graph_snapshots":[{"event_id":"sha256:5b789f02f5105610d637ed668e7afee6bad88c9121b74d863710cc9778f97b2d","target":"graph","created_at":"2026-07-05T08:36:49Z","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/2406.17672/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in generative models that iteratively synthesize audio clips sparked great success to text-to-audio synthesis (TTA), but with the cost of slow synthesis speed and heavy computation. Although there have been attempts to accelerate the iterative procedure, high-quality TTA systems remain inefficient due to hundreds of iterations required in the inference phase and large amount of model parameters. To address the challenges, we propose SpecMaskGIT, a light-weighted, efficient yet effective TTA model based on the masked generative modeling of spectrograms. First, SpecMaskGIT synthe","authors_text":"Akira Takahashi, Koichi Saito, Marco Comunit\\`a, Mengjie Zhao, Shiqi Yang, Shusuke Takahashi, Takashi Shibuya, Yukara Ikemiya, Yuki Mitsufuji, Zhi Zhong","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-06-25T16:02:59Z","title":"SpecMaskGIT: Masked Generative Modeling of Audio Spectrograms for Efficient Audio Synthesis and Beyond"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.17672","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:f1c9537cf9c7b210f7f6539d5f5791303761fa61e71c0bd33ce95ade3cfe8d6a","target":"record","created_at":"2026-07-05T08:36:49Z","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":"76e499b5bd26c5286c7b64a17a42161c922c360ae54a430dfddf15f105e95638","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-06-25T16:02:59Z","title_canon_sha256":"7080379a05ddd997719ea84faae63e5eefe87bdf9fbf8bdf21c74f32df1b211b"},"schema_version":"1.0","source":{"id":"2406.17672","kind":"arxiv","version":2}},"canonical_sha256":"280552f6b868a0704c4fc27d5a036fbb4486fa790eece1993f4ac55e58608682","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"280552f6b868a0704c4fc27d5a036fbb4486fa790eece1993f4ac55e58608682","first_computed_at":"2026-07-05T08:36:49.482974Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:36:49.482974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qX5UbML72pHCzvfl1gyOdm9WJLPELLEbxFAoG7F29xTsPSNnQ/Gz+xmBduiRJ4qAH7gH977sTCvCpl94QbFLAg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:36:49.483486Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.17672","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f1c9537cf9c7b210f7f6539d5f5791303761fa61e71c0bd33ce95ade3cfe8d6a","sha256:5b789f02f5105610d637ed668e7afee6bad88c9121b74d863710cc9778f97b2d"],"state_sha256":"ba5ff828b892e2e4a2ca8e21c44646c88b0fac865eddc3db9939313115cf8c3d"}