{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UNL67X6J7NAZDPFGU22EIZYW2N","short_pith_number":"pith:UNL67X6J","schema_version":"1.0","canonical_sha256":"a357efdfc9fb4191bca6a6b4446716d37abafe83321a51a69a9ac88f5d708394","source":{"kind":"arxiv","id":"2401.01044","version":1},"attestation_state":"computed","paper":{"title":"Auffusion: Leveraging the Power of Diffusion and Large Language Models for Text-to-Audio Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Jinlong Xue, Ya Li, Yayue Deng, Yingming Gao","submitted_at":"2024-01-02T05:42:14Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2401.01044","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-01-02T05:42:14Z","cross_cats_sorted":["cs.AI","cs.CL","eess.AS"],"title_canon_sha256":"313dbd1a2379d08b5d7cc3ecdbda6184afec93e76678420aa44ffc741e88b5f1","abstract_canon_sha256":"98dfb285396438edd48d19b92177f62ee3ae2fac525b01c7f58720ece2be20cb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:29:33.257796Z","signature_b64":"Ecm5oMuwO7nWuYjOiok/by43R8eRCse8zVz4HJg6N5VUQQBetJt8nnORktNAJFM0CZs84CQDwM9j3+eKFg2vCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a357efdfc9fb4191bca6a6b4446716d37abafe83321a51a69a9ac88f5d708394","last_reissued_at":"2026-07-05T07:29:33.257394Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:29:33.257394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Auffusion: Leveraging the Power of Diffusion and Large Language Models for Text-to-Audio Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Jinlong Xue, Ya Li, Yayue Deng, Yingming Gao","submitted_at":"2024-01-02T05:42:14Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.01044","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/2401.01044/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2401.01044","created_at":"2026-07-05T07:29:33.257447+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.01044v1","created_at":"2026-07-05T07:29:33.257447+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.01044","created_at":"2026-07-05T07:29:33.257447+00:00"},{"alias_kind":"pith_short_12","alias_value":"UNL67X6J7NAZ","created_at":"2026-07-05T07:29:33.257447+00:00"},{"alias_kind":"pith_short_16","alias_value":"UNL67X6J7NAZDPFG","created_at":"2026-07-05T07:29:33.257447+00:00"},{"alias_kind":"pith_short_8","alias_value":"UNL67X6J","created_at":"2026-07-05T07:29:33.257447+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05196","citing_title":"Unified Audio Intelligence Without Regressing on Text Intelligence","ref_index":85,"is_internal_anchor":true},{"citing_arxiv_id":"2604.14707","citing_title":"Geo2Sound: A Scalable Geo-Aligned Framework for Soundscape Generation from Satellite Imagery","ref_index":71,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UNL67X6J7NAZDPFGU22EIZYW2N","json":"https://pith.science/pith/UNL67X6J7NAZDPFGU22EIZYW2N.json","graph_json":"https://pith.science/api/pith-number/UNL67X6J7NAZDPFGU22EIZYW2N/graph.json","events_json":"https://pith.science/api/pith-number/UNL67X6J7NAZDPFGU22EIZYW2N/events.json","paper":"https://pith.science/paper/UNL67X6J"},"agent_actions":{"view_html":"https://pith.science/pith/UNL67X6J7NAZDPFGU22EIZYW2N","download_json":"https://pith.science/pith/UNL67X6J7NAZDPFGU22EIZYW2N.json","view_paper":"https://pith.science/paper/UNL67X6J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.01044&json=true","fetch_graph":"https://pith.science/api/pith-number/UNL67X6J7NAZDPFGU22EIZYW2N/graph.json","fetch_events":"https://pith.science/api/pith-number/UNL67X6J7NAZDPFGU22EIZYW2N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UNL67X6J7NAZDPFGU22EIZYW2N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UNL67X6J7NAZDPFGU22EIZYW2N/action/storage_attestation","attest_author":"https://pith.science/pith/UNL67X6J7NAZDPFGU22EIZYW2N/action/author_attestation","sign_citation":"https://pith.science/pith/UNL67X6J7NAZDPFGU22EIZYW2N/action/citation_signature","submit_replication":"https://pith.science/pith/UNL67X6J7NAZDPFGU22EIZYW2N/action/replication_record"}},"created_at":"2026-07-05T07:29:33.257447+00:00","updated_at":"2026-07-05T07:29:33.257447+00:00"}