{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4QCMU5VRIZ4G3BR6YNG7SYWPWQ","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":"eb090ce5e79c79f77b2364c545b44d70d8658f15118bfe23095ca53f7bc98af8","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2026-05-29T07:58:54Z","title_canon_sha256":"9412f87a626f7f8f2e217c22d649a2e99c61997ce58292d28854063531aa364d"},"schema_version":"1.0","source":{"id":"2605.30965","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.30965","created_at":"2026-06-01T01:03:27Z"},{"alias_kind":"arxiv_version","alias_value":"2605.30965v1","created_at":"2026-06-01T01:03:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30965","created_at":"2026-06-01T01:03:27Z"},{"alias_kind":"pith_short_12","alias_value":"4QCMU5VRIZ4G","created_at":"2026-06-01T01:03:27Z"},{"alias_kind":"pith_short_16","alias_value":"4QCMU5VRIZ4G3BR6","created_at":"2026-06-01T01:03:27Z"},{"alias_kind":"pith_short_8","alias_value":"4QCMU5VR","created_at":"2026-06-01T01:03:27Z"}],"graph_snapshots":[{"event_id":"sha256:457df85cd0bb96f487d00cb4fed58c68c571e971e4e2499af122fc0eb81e18b5","target":"graph","created_at":"2026-06-01T01:03:27Z","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/2605.30965/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in text-guided audio generation have yielded promising results in diverse domains, including sound effects, speech, and music. However, jointly generating speech with environmental audio remains challenging due to the inherent disparities in their acoustic patterns and temporal dynamics. We propose ImmersiveTTS, an environment-aware text-to-speech (TTS) model that generates natural speech seamlessly integrated within environmental contexts by explicitly modeling cross-modal interactions. Our model builds on a multimodal diffusion transformer and fuses transcript-aligned spe","authors_text":"Jun-Hak Yun, Seong-Whan Lee, Seung-Bin Kim","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2026-05-29T07:58:54Z","title":"ImmersiveTTS: Environment-Aware Text-to-Speech with Multimodal Diffusion Transformer and Domain-Specific Representation Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30965","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:eef9ef6d883d9125d4a73b52d9a23af9132807c40f484ea11ec2a7726fbc31d0","target":"record","created_at":"2026-06-01T01:03:27Z","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":"eb090ce5e79c79f77b2364c545b44d70d8658f15118bfe23095ca53f7bc98af8","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2026-05-29T07:58:54Z","title_canon_sha256":"9412f87a626f7f8f2e217c22d649a2e99c61997ce58292d28854063531aa364d"},"schema_version":"1.0","source":{"id":"2605.30965","kind":"arxiv","version":1}},"canonical_sha256":"e404ca76b146786d863ec34df962cfb4148cbfad38ffebd45ea366fbadb04372","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e404ca76b146786d863ec34df962cfb4148cbfad38ffebd45ea366fbadb04372","first_computed_at":"2026-06-01T01:03:27.776984Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-01T01:03:27.776984Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"z3tfzavwDxq+5nMflEjQHLOjA2U1sccTHlggRh1X7D+jrirMY+Ibzgg5qRt6PSMjhcze4oGPBZW1SpifmZB8BA==","signature_status":"signed_v1","signed_at":"2026-06-01T01:03:27.777448Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.30965","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eef9ef6d883d9125d4a73b52d9a23af9132807c40f484ea11ec2a7726fbc31d0","sha256:457df85cd0bb96f487d00cb4fed58c68c571e971e4e2499af122fc0eb81e18b5"],"state_sha256":"290b2ccb2777ac4cd645aa3767a6d5cd5f852cf013f9f175272422aae546548a"}