{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RELS3FENLKPPHMOU6GUQXHDRDB","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":"773ecae485dbb8bec885e2e8af63e52af40481a1b72f34b017a4d93c98c1d2e3","cross_cats_sorted":["cs.CL","cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-12-26T21:13:12Z","title_canon_sha256":"f91896935609bcf6049c0d8916b7c8e177a45e5b804a3e7dc3156be15388c213"},"schema_version":"1.0","source":{"id":"2412.19351","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.19351","created_at":"2026-07-05T11:29:53Z"},{"alias_kind":"arxiv_version","alias_value":"2412.19351v2","created_at":"2026-07-05T11:29:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.19351","created_at":"2026-07-05T11:29:53Z"},{"alias_kind":"pith_short_12","alias_value":"RELS3FENLKPP","created_at":"2026-07-05T11:29:53Z"},{"alias_kind":"pith_short_16","alias_value":"RELS3FENLKPPHMOU","created_at":"2026-07-05T11:29:53Z"},{"alias_kind":"pith_short_8","alias_value":"RELS3FEN","created_at":"2026-07-05T11:29:53Z"}],"graph_snapshots":[{"event_id":"sha256:d9281a1122c7d909c663cf10af941ce80c293cd6b01dd75a9f7e19277273e015","target":"graph","created_at":"2026-07-05T11:29:53Z","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/2412.19351/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent years have seen significant progress in Text-To-Audio (TTA) synthesis, enabling users to enrich their creative workflows with synthetic audio generated from natural language prompts. Despite this progress, the effects of data, model architecture, training objective functions, and sampling strategies on target benchmarks are not well understood. With the purpose of providing a holistic understanding of the design space of TTA models, we set up a large-scale empirical experiment focused on diffusion and flow matching models. Our contributions include: 1) AF-Synthetic, a large dataset of h","authors_text":"Arushi Goel, Bryan Catanzaro, Rafael Valle, Sang-gil Lee, Sungwon Kim, Zhifeng Kong","cross_cats":["cs.CL","cs.LG","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-12-26T21:13:12Z","title":"ETTA: Elucidating the Design Space of Text-to-Audio Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.19351","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:d27ad6e423ada123caec4f205905cca09a7f17c4d1a4f7aa490695a040b4d82c","target":"record","created_at":"2026-07-05T11:29:53Z","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":"773ecae485dbb8bec885e2e8af63e52af40481a1b72f34b017a4d93c98c1d2e3","cross_cats_sorted":["cs.CL","cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-12-26T21:13:12Z","title_canon_sha256":"f91896935609bcf6049c0d8916b7c8e177a45e5b804a3e7dc3156be15388c213"},"schema_version":"1.0","source":{"id":"2412.19351","kind":"arxiv","version":2}},"canonical_sha256":"89172d948d5a9ef3b1d4f1a90b9c711849aabf9bfdf1e80d1f827009268c918f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"89172d948d5a9ef3b1d4f1a90b9c711849aabf9bfdf1e80d1f827009268c918f","first_computed_at":"2026-07-05T11:29:53.468914Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:29:53.468914Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ULMsioPnTSTe+ESpJleq3lFZCX5rz4+/tXZVBfhC7K92Rnn50mqbZ+/JIGD/MpQevDjAGQD7v9dHwpiYSPmRAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:29:53.469491Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.19351","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d27ad6e423ada123caec4f205905cca09a7f17c4d1a4f7aa490695a040b4d82c","sha256:d9281a1122c7d909c663cf10af941ce80c293cd6b01dd75a9f7e19277273e015"],"state_sha256":"2eaea537a279efdb6ac51a94cf13783e1d10c6d9450b92de9ad8c20d60a8c375"}