{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UNL67X6J7NAZDPFGU22EIZYW2N","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":"98dfb285396438edd48d19b92177f62ee3ae2fac525b01c7f58720ece2be20cb","cross_cats_sorted":["cs.AI","cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-01-02T05:42:14Z","title_canon_sha256":"313dbd1a2379d08b5d7cc3ecdbda6184afec93e76678420aa44ffc741e88b5f1"},"schema_version":"1.0","source":{"id":"2401.01044","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.01044","created_at":"2026-07-05T07:29:33Z"},{"alias_kind":"arxiv_version","alias_value":"2401.01044v1","created_at":"2026-07-05T07:29:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.01044","created_at":"2026-07-05T07:29:33Z"},{"alias_kind":"pith_short_12","alias_value":"UNL67X6J7NAZ","created_at":"2026-07-05T07:29:33Z"},{"alias_kind":"pith_short_16","alias_value":"UNL67X6J7NAZDPFG","created_at":"2026-07-05T07:29:33Z"},{"alias_kind":"pith_short_8","alias_value":"UNL67X6J","created_at":"2026-07-05T07:29:33Z"}],"graph_snapshots":[{"event_id":"sha256:f1340df6f4bf366fd8839199125ed1fd4c5e95970417ee6f16fae6660e03c824","target":"graph","created_at":"2026-07-05T07:29:33Z","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/2401.01044/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in diffusion models and large language models (LLMs) have significantly propelled the field of AIGC. Text-to-Audio (TTA), a burgeoning AIGC application designed to generate audio from natural language prompts, is attracting increasing attention. However, existing TTA studies often struggle with generation quality and text-audio alignment, especially for complex textual inputs. Drawing inspiration from state-of-the-art Text-to-Image (T2I) diffusion models, we introduce Auffusion, a TTA system adapting T2I model frameworks to TTA task, by effectively leveraging their inherent","authors_text":"Jinlong Xue, Ya Li, Yayue Deng, Yingming Gao","cross_cats":["cs.AI","cs.CL","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-01-02T05:42:14Z","title":"Auffusion: Leveraging the Power of Diffusion and Large Language Models for Text-to-Audio Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.01044","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":"sha256:1f1ec47c2725fce24bacda23fd9667e08b4ef2da249156209ce394c495ed4868","target":"record","created_at":"2026-07-05T07:29:33Z","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":"98dfb285396438edd48d19b92177f62ee3ae2fac525b01c7f58720ece2be20cb","cross_cats_sorted":["cs.AI","cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-01-02T05:42:14Z","title_canon_sha256":"313dbd1a2379d08b5d7cc3ecdbda6184afec93e76678420aa44ffc741e88b5f1"},"schema_version":"1.0","source":{"id":"2401.01044","kind":"arxiv","version":1}},"canonical_sha256":"a357efdfc9fb4191bca6a6b4446716d37abafe83321a51a69a9ac88f5d708394","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a357efdfc9fb4191bca6a6b4446716d37abafe83321a51a69a9ac88f5d708394","first_computed_at":"2026-07-05T07:29:33.257394Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:29:33.257394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ecm5oMuwO7nWuYjOiok/by43R8eRCse8zVz4HJg6N5VUQQBetJt8nnORktNAJFM0CZs84CQDwM9j3+eKFg2vCA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:29:33.257796Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.01044","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1f1ec47c2725fce24bacda23fd9667e08b4ef2da249156209ce394c495ed4868","sha256:f1340df6f4bf366fd8839199125ed1fd4c5e95970417ee6f16fae6660e03c824"],"state_sha256":"6bcd0a5d4634ccd2afad19357a81d6c4e5f0c98380014558e5d38b66c24c9572"}