{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CANZ6TIL6H4IFOF73KSAZ5V64J","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":"0b762cb355402ded53a7e02d4e7ed3c99c8a315f59b3432e536093bb94a018dc","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-06-19T04:34:53Z","title_canon_sha256":"cc2a64d0b34da1819afc3f405f9991c4fcd148063f397cf916e8172e9c96b1c7"},"schema_version":"1.0","source":{"id":"2506.16020","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.16020","created_at":"2026-07-05T11:24:28Z"},{"alias_kind":"arxiv_version","alias_value":"2506.16020v1","created_at":"2026-07-05T11:24:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.16020","created_at":"2026-07-05T11:24:28Z"},{"alias_kind":"pith_short_12","alias_value":"CANZ6TIL6H4I","created_at":"2026-07-05T11:24:28Z"},{"alias_kind":"pith_short_16","alias_value":"CANZ6TIL6H4IFOF7","created_at":"2026-07-05T11:24:28Z"},{"alias_kind":"pith_short_8","alias_value":"CANZ6TIL","created_at":"2026-07-05T11:24:28Z"}],"graph_snapshots":[{"event_id":"sha256:344ec2432641aea542f297f4753513c82f43cd1a7b0702cf7bf600ecffcc716a","target":"graph","created_at":"2026-07-05T11:24:28Z","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/2506.16020/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"To explore the potential advantages of utilizing spatial cues from images for generating stereo singing voices with room reverberation, we introduce VS-Singer, a vision-guided model designed to produce stereo singing voices with room reverberation from scene images. VS-Singer comprises three modules: firstly, a modal interaction network integrates spatial features into text encoding to create a linguistic representation enriched with spatial information. Secondly, the decoder employs a consistency Schr\\\"odinger bridge to facilitate one-step sample generation. Moreover, we utilize the SFE modul","authors_text":"Hao Huang, Jichen Yang, Kai Wang, Liang He, Ying Hu, Zijing Zhao","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-06-19T04:34:53Z","title":"VS-Singer: Vision-Guided Stereo Singing Voice Synthesis with Consistency Schr\\\"odinger Bridge"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.16020","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":"sha256:28f0b7b9fc88363296ce03b8ecc86c4e16264077002a734015653b57ae6fe332","target":"record","created_at":"2026-07-05T11:24:28Z","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":"0b762cb355402ded53a7e02d4e7ed3c99c8a315f59b3432e536093bb94a018dc","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-06-19T04:34:53Z","title_canon_sha256":"cc2a64d0b34da1819afc3f405f9991c4fcd148063f397cf916e8172e9c96b1c7"},"schema_version":"1.0","source":{"id":"2506.16020","kind":"arxiv","version":1}},"canonical_sha256":"101b9f4d0bf1f882b8bfdaa40cf6bee27f91e05f5a01de474a96b6b27c121508","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"101b9f4d0bf1f882b8bfdaa40cf6bee27f91e05f5a01de474a96b6b27c121508","first_computed_at":"2026-07-05T11:24:28.328814Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:24:28.328814Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0tZLOVez4TPK5FJXhAYz86tfTVUvnqyXcSZarzF8gsSTfZfHJN5BME7nRvxO5JmsaUCN1AtmLa277Atn252LCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:24:28.329414Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.16020","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:28f0b7b9fc88363296ce03b8ecc86c4e16264077002a734015653b57ae6fe332","sha256:344ec2432641aea542f297f4753513c82f43cd1a7b0702cf7bf600ecffcc716a"],"state_sha256":"1fa20f90bb7353151df9ef2fdf7cbadefbdba5591c2c0a4b3ee8005d13d34b37"}