{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:EJ7SFRV7JUGJGWBK7QHVGLL5TV","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":"2bf0867e78453ac8542b20728ef0af120a19656e51de37b2a6f33ee91f0625d7","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-13T19:57:42Z","title_canon_sha256":"12b873851caacc4cd5b1f7f7d663a7be1bea5eb08249940e9aed36a321fa5e14"},"schema_version":"1.0","source":{"id":"2506.12199","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.12199","created_at":"2026-07-05T11:21:23Z"},{"alias_kind":"arxiv_version","alias_value":"2506.12199v1","created_at":"2026-07-05T11:21:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.12199","created_at":"2026-07-05T11:21:23Z"},{"alias_kind":"pith_short_12","alias_value":"EJ7SFRV7JUGJ","created_at":"2026-07-05T11:21:23Z"},{"alias_kind":"pith_short_16","alias_value":"EJ7SFRV7JUGJGWBK","created_at":"2026-07-05T11:21:23Z"},{"alias_kind":"pith_short_8","alias_value":"EJ7SFRV7","created_at":"2026-07-05T11:21:23Z"}],"graph_snapshots":[{"event_id":"sha256:81bd701297207098e705a1b21960f319bc2376f1e2340ed1e52ce9887c84562f","target":"graph","created_at":"2026-07-05T11:21:23Z","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/2506.12199/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Spatial audio is essential for enhancing the immersiveness of audio-visual experiences, yet its production typically demands complex recording systems and specialized expertise. In this work, we address a novel problem of generating first-order ambisonics, a widely used spatial audio format, directly from silent videos. To support this task, we introduce YT-Ambigen, a dataset comprising 102K 5-second YouTube video clips paired with corresponding first-order ambisonics. We also propose new evaluation metrics to assess the spatial aspect of generated audio based on audio energy maps and saliency","authors_text":"Gunhee Kim, Heeseung Yun, Jaeyeon Kim","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-13T19:57:42Z","title":"ViSAGe: Video-to-Spatial Audio Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.12199","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:b6cf305ae471e983a8acc0cc7533bdf0609a5254932ba2f0cd198bcd45a71f5a","target":"record","created_at":"2026-07-05T11:21:23Z","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":"2bf0867e78453ac8542b20728ef0af120a19656e51de37b2a6f33ee91f0625d7","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-13T19:57:42Z","title_canon_sha256":"12b873851caacc4cd5b1f7f7d663a7be1bea5eb08249940e9aed36a321fa5e14"},"schema_version":"1.0","source":{"id":"2506.12199","kind":"arxiv","version":1}},"canonical_sha256":"227f22c6bf4d0c93582afc0f532d7d9d5b16bea089e4b3bb73160b3ae96a7cef","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"227f22c6bf4d0c93582afc0f532d7d9d5b16bea089e4b3bb73160b3ae96a7cef","first_computed_at":"2026-07-05T11:21:23.144164Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:21:23.144164Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nbpMFRAM1zh0mefOjahxE7RY9IMSYtmrjrB71sJLopAbRQO2hUBn6KRomlUHoYVqWbysEwKaeG3IKmxCXk/sCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:21:23.144685Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.12199","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b6cf305ae471e983a8acc0cc7533bdf0609a5254932ba2f0cd198bcd45a71f5a","sha256:81bd701297207098e705a1b21960f319bc2376f1e2340ed1e52ce9887c84562f"],"state_sha256":"5c46556a155e42a5fadb57b9bfae73b97fd811c1b9209a5d014cc0cb81b64ded"}