{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:Q4S55GU3AL527GNNDTOCCLOYH6","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":"df373188c5915df104462e0b6dab2174f07550bce8d6c9261989a1afa5a91784","cross_cats_sorted":["cs.AI","cs.MM","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-09-14T22:35:39Z","title_canon_sha256":"aa10cad7ada147cc1f251ce1148b87f245910b39516ed301d50371e7ca88aee5"},"schema_version":"1.0","source":{"id":"2309.08051","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.08051","created_at":"2026-07-05T07:30:37Z"},{"alias_kind":"arxiv_version","alias_value":"2309.08051v2","created_at":"2026-07-05T07:30:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.08051","created_at":"2026-07-05T07:30:37Z"},{"alias_kind":"pith_short_12","alias_value":"Q4S55GU3AL52","created_at":"2026-07-05T07:30:37Z"},{"alias_kind":"pith_short_16","alias_value":"Q4S55GU3AL527GNN","created_at":"2026-07-05T07:30:37Z"},{"alias_kind":"pith_short_8","alias_value":"Q4S55GU3","created_at":"2026-07-05T07:30:37Z"}],"graph_snapshots":[{"event_id":"sha256:5707e918b811483947a51011d3e66ae56b8ea7cdb4b8af689272b723e444f447","target":"graph","created_at":"2026-07-05T07:30:37Z","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/2309.08051/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite recent progress in text-to-audio (TTA) generation, we show that the state-of-the-art models, such as AudioLDM, trained on datasets with an imbalanced class distribution, such as AudioCaps, are biased in their generation performance. Specifically, they excel in generating common audio classes while underperforming in the rare ones, thus degrading the overall generation performance. We refer to this problem as long-tailed text-to-audio generation. To address this issue, we propose a simple retrieval-augmented approach for TTA models. Specifically, given an input text prompt, we first lev","authors_text":"Haohe Liu, Mark D. Plumbley, Qiushi Huang, Wenwu Wang, Xubo Liu, Yi Yuan","cross_cats":["cs.AI","cs.MM","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-09-14T22:35:39Z","title":"Retrieval-Augmented Text-to-Audio Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.08051","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:aa09e458f56b8f3ce453536f875c663873178f34d2905ff313e122cf2576a683","target":"record","created_at":"2026-07-05T07:30:37Z","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":"df373188c5915df104462e0b6dab2174f07550bce8d6c9261989a1afa5a91784","cross_cats_sorted":["cs.AI","cs.MM","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-09-14T22:35:39Z","title_canon_sha256":"aa10cad7ada147cc1f251ce1148b87f245910b39516ed301d50371e7ca88aee5"},"schema_version":"1.0","source":{"id":"2309.08051","kind":"arxiv","version":2}},"canonical_sha256":"8725de9a9b02fbaf99ad1cdc212dd83fbc2ba2dafa206372b9f519ee3956d1b0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8725de9a9b02fbaf99ad1cdc212dd83fbc2ba2dafa206372b9f519ee3956d1b0","first_computed_at":"2026-07-05T07:30:37.554573Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:30:37.554573Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hCwIQo7svRqhY8GXy90o/vyHZeFIOj7PUKNaBUwm8zVbaZOb/ofjtYyhkjF+Re+NyP6/5UFnjBDV0CKXJBSMAg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:30:37.555017Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.08051","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aa09e458f56b8f3ce453536f875c663873178f34d2905ff313e122cf2576a683","sha256:5707e918b811483947a51011d3e66ae56b8ea7cdb4b8af689272b723e444f447"],"state_sha256":"d52dfd370928a7990fb35a845936121e2612b36c9caaa58121b8336cb3638087"}