{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UAZ2Y4PWCOKXZXYWHO3BCNN2LT","short_pith_number":"pith:UAZ2Y4PW","schema_version":"1.0","canonical_sha256":"a033ac71f613957cdf163bb61135ba5cca73e5e93b10beab8fbea3e263cb61ca","source":{"kind":"arxiv","id":"2605.28063","version":1},"attestation_state":"computed","paper":{"title":"Unified Synthesis of Compositional Speech and Sound from Free-Form Text Prompts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.SD","authors_text":"Ruihua Song, Xihua Wang, Xin Cheng, Yijing Chen, Yuyue Wang","submitted_at":"2026-05-27T07:15:35Z","abstract_excerpt":"Audio generation has made significant progress, yet synthesizing unified audio where speech and sounds are naturally composited remains a challenge. Current methods either rely on disjoint pipelines, which fail to capture fine-grained interactions, or require structured inputs and external text rewriting, which limits the flexibility of free-form text prompts. In this paper, we introduce a new task: Free-Form-Text-Prompt-to-Unified-Audio generation, which aims to directly synthesize unified audio containing speech, sound, and their composites from unconstrained natural language. To address thi"},"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":"2605.28063","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-05-27T07:15:35Z","cross_cats_sorted":["cs.AI","cs.MM"],"title_canon_sha256":"d1c9de388c8281a3dae77f579f49b795fa89158c395df1470e7addbd0ad166fc","abstract_canon_sha256":"4e8ece6e3efed7306c51b92cb5da44c787ea4ea08f90f05a570495311f3b40d8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:04:57.453111Z","signature_b64":"s42XU/tNzKYZrWxwBEUezxsM3VQdNKyOWnG0XknkqkZ4EpruRXSfvzHs6ztPvErVyHgi18iN+T4HtYNl9fmBBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a033ac71f613957cdf163bb61135ba5cca73e5e93b10beab8fbea3e263cb61ca","last_reissued_at":"2026-05-28T01:04:57.452686Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:04:57.452686Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unified Synthesis of Compositional Speech and Sound from Free-Form Text Prompts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.SD","authors_text":"Ruihua Song, Xihua Wang, Xin Cheng, Yijing Chen, Yuyue Wang","submitted_at":"2026-05-27T07:15:35Z","abstract_excerpt":"Audio generation has made significant progress, yet synthesizing unified audio where speech and sounds are naturally composited remains a challenge. Current methods either rely on disjoint pipelines, which fail to capture fine-grained interactions, or require structured inputs and external text rewriting, which limits the flexibility of free-form text prompts. In this paper, we introduce a new task: Free-Form-Text-Prompt-to-Unified-Audio generation, which aims to directly synthesize unified audio containing speech, sound, and their composites from unconstrained natural language. To address thi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28063","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/2605.28063/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":"2605.28063","created_at":"2026-05-28T01:04:57.452746+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.28063v1","created_at":"2026-05-28T01:04:57.452746+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28063","created_at":"2026-05-28T01:04:57.452746+00:00"},{"alias_kind":"pith_short_12","alias_value":"UAZ2Y4PWCOKX","created_at":"2026-05-28T01:04:57.452746+00:00"},{"alias_kind":"pith_short_16","alias_value":"UAZ2Y4PWCOKXZXYW","created_at":"2026-05-28T01:04:57.452746+00:00"},{"alias_kind":"pith_short_8","alias_value":"UAZ2Y4PW","created_at":"2026-05-28T01:04:57.452746+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UAZ2Y4PWCOKXZXYWHO3BCNN2LT","json":"https://pith.science/pith/UAZ2Y4PWCOKXZXYWHO3BCNN2LT.json","graph_json":"https://pith.science/api/pith-number/UAZ2Y4PWCOKXZXYWHO3BCNN2LT/graph.json","events_json":"https://pith.science/api/pith-number/UAZ2Y4PWCOKXZXYWHO3BCNN2LT/events.json","paper":"https://pith.science/paper/UAZ2Y4PW"},"agent_actions":{"view_html":"https://pith.science/pith/UAZ2Y4PWCOKXZXYWHO3BCNN2LT","download_json":"https://pith.science/pith/UAZ2Y4PWCOKXZXYWHO3BCNN2LT.json","view_paper":"https://pith.science/paper/UAZ2Y4PW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.28063&json=true","fetch_graph":"https://pith.science/api/pith-number/UAZ2Y4PWCOKXZXYWHO3BCNN2LT/graph.json","fetch_events":"https://pith.science/api/pith-number/UAZ2Y4PWCOKXZXYWHO3BCNN2LT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UAZ2Y4PWCOKXZXYWHO3BCNN2LT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UAZ2Y4PWCOKXZXYWHO3BCNN2LT/action/storage_attestation","attest_author":"https://pith.science/pith/UAZ2Y4PWCOKXZXYWHO3BCNN2LT/action/author_attestation","sign_citation":"https://pith.science/pith/UAZ2Y4PWCOKXZXYWHO3BCNN2LT/action/citation_signature","submit_replication":"https://pith.science/pith/UAZ2Y4PWCOKXZXYWHO3BCNN2LT/action/replication_record"}},"created_at":"2026-05-28T01:04:57.452746+00:00","updated_at":"2026-05-28T01:04:57.452746+00:00"}