{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:UAZ2Y4PWCOKXZXYWHO3BCNN2LT","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":"4e8ece6e3efed7306c51b92cb5da44c787ea4ea08f90f05a570495311f3b40d8","cross_cats_sorted":["cs.AI","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-05-27T07:15:35Z","title_canon_sha256":"d1c9de388c8281a3dae77f579f49b795fa89158c395df1470e7addbd0ad166fc"},"schema_version":"1.0","source":{"id":"2605.28063","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.28063","created_at":"2026-05-28T01:04:57Z"},{"alias_kind":"arxiv_version","alias_value":"2605.28063v1","created_at":"2026-05-28T01:04:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28063","created_at":"2026-05-28T01:04:57Z"},{"alias_kind":"pith_short_12","alias_value":"UAZ2Y4PWCOKX","created_at":"2026-05-28T01:04:57Z"},{"alias_kind":"pith_short_16","alias_value":"UAZ2Y4PWCOKXZXYW","created_at":"2026-05-28T01:04:57Z"},{"alias_kind":"pith_short_8","alias_value":"UAZ2Y4PW","created_at":"2026-05-28T01:04:57Z"}],"graph_snapshots":[{"event_id":"sha256:99b3337e3041bd3ed43d86bfb48d42c82d9555b9d4db9309cd5a80a17d6f07de","target":"graph","created_at":"2026-05-28T01:04:57Z","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/2605.28063/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Ruihua Song, Xihua Wang, Xin Cheng, Yijing Chen, Yuyue Wang","cross_cats":["cs.AI","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-05-27T07:15:35Z","title":"Unified Synthesis of Compositional Speech and Sound from Free-Form Text Prompts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28063","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:c260239cf6570899a4aff931f2af295268185aebceeee7e31c6ea5f53a8f3cd0","target":"record","created_at":"2026-05-28T01:04:57Z","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":"4e8ece6e3efed7306c51b92cb5da44c787ea4ea08f90f05a570495311f3b40d8","cross_cats_sorted":["cs.AI","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-05-27T07:15:35Z","title_canon_sha256":"d1c9de388c8281a3dae77f579f49b795fa89158c395df1470e7addbd0ad166fc"},"schema_version":"1.0","source":{"id":"2605.28063","kind":"arxiv","version":1}},"canonical_sha256":"a033ac71f613957cdf163bb61135ba5cca73e5e93b10beab8fbea3e263cb61ca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a033ac71f613957cdf163bb61135ba5cca73e5e93b10beab8fbea3e263cb61ca","first_computed_at":"2026-05-28T01:04:57.452686Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T01:04:57.452686Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"s42XU/tNzKYZrWxwBEUezxsM3VQdNKyOWnG0XknkqkZ4EpruRXSfvzHs6ztPvErVyHgi18iN+T4HtYNl9fmBBw==","signature_status":"signed_v1","signed_at":"2026-05-28T01:04:57.453111Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.28063","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c260239cf6570899a4aff931f2af295268185aebceeee7e31c6ea5f53a8f3cd0","sha256:99b3337e3041bd3ed43d86bfb48d42c82d9555b9d4db9309cd5a80a17d6f07de"],"state_sha256":"9b6a061cadd2e468243e56c32f04a10024746e57ac3015a5ece90d3ec8081650"}