{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:EJ7SFRV7JUGJGWBK7QHVGLL5TV","short_pith_number":"pith:EJ7SFRV7","canonical_record":{"source":{"id":"2506.12199","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-13T19:57:42Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"12b873851caacc4cd5b1f7f7d663a7be1bea5eb08249940e9aed36a321fa5e14","abstract_canon_sha256":"2bf0867e78453ac8542b20728ef0af120a19656e51de37b2a6f33ee91f0625d7"},"schema_version":"1.0"},"canonical_sha256":"227f22c6bf4d0c93582afc0f532d7d9d5b16bea089e4b3bb73160b3ae96a7cef","source":{"kind":"arxiv","id":"2506.12199","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:EJ7SFRV7JUGJGWBK7QHVGLL5TV","target":"record","payload":{"canonical_record":{"source":{"id":"2506.12199","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-13T19:57:42Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"12b873851caacc4cd5b1f7f7d663a7be1bea5eb08249940e9aed36a321fa5e14","abstract_canon_sha256":"2bf0867e78453ac8542b20728ef0af120a19656e51de37b2a6f33ee91f0625d7"},"schema_version":"1.0"},"canonical_sha256":"227f22c6bf4d0c93582afc0f532d7d9d5b16bea089e4b3bb73160b3ae96a7cef","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:23.144685Z","signature_b64":"nbpMFRAM1zh0mefOjahxE7RY9IMSYtmrjrB71sJLopAbRQO2hUBn6KRomlUHoYVqWbysEwKaeG3IKmxCXk/sCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"227f22c6bf4d0c93582afc0f532d7d9d5b16bea089e4b3bb73160b3ae96a7cef","last_reissued_at":"2026-07-05T11:21:23.144164Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:23.144164Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.12199","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:21:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E6+l5nXzjpqWqg9EhH7457z3scQFzlDCttcuo+kxjRH8kgoa5A5ixnSpGVisGyHTC40i6JeqJau/pC1DPEMZBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T05:04:39.157724Z"},"content_sha256":"b6cf305ae471e983a8acc0cc7533bdf0609a5254932ba2f0cd198bcd45a71f5a","schema_version":"1.0","event_id":"sha256:b6cf305ae471e983a8acc0cc7533bdf0609a5254932ba2f0cd198bcd45a71f5a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:EJ7SFRV7JUGJGWBK7QHVGLL5TV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ViSAGe: Video-to-Spatial Audio Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Gunhee Kim, Heeseung Yun, Jaeyeon Kim","submitted_at":"2025-06-13T19:57:42Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.12199","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/2506.12199/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:21:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jZTVx8R7gCDq3Ddr4ZNaXtS2FRdb2IgdQojG4VySD8rI9ZC8i0os9vgv1HCdrINhYnJIc1xAU2bpwiatGHSNDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T05:04:39.158085Z"},"content_sha256":"81bd701297207098e705a1b21960f319bc2376f1e2340ed1e52ce9887c84562f","schema_version":"1.0","event_id":"sha256:81bd701297207098e705a1b21960f319bc2376f1e2340ed1e52ce9887c84562f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EJ7SFRV7JUGJGWBK7QHVGLL5TV/bundle.json","state_url":"https://pith.science/pith/EJ7SFRV7JUGJGWBK7QHVGLL5TV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EJ7SFRV7JUGJGWBK7QHVGLL5TV/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-06T05:04:39Z","links":{"resolver":"https://pith.science/pith/EJ7SFRV7JUGJGWBK7QHVGLL5TV","bundle":"https://pith.science/pith/EJ7SFRV7JUGJGWBK7QHVGLL5TV/bundle.json","state":"https://pith.science/pith/EJ7SFRV7JUGJGWBK7QHVGLL5TV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EJ7SFRV7JUGJGWBK7QHVGLL5TV/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZJ7GDhGtESHqPJa0sR73Y9a6plqK8FhROVzWxE8EAIYFYhbdWMwu/q2PzVy1ZXAdvend9Jy0sXqnhT3s20imBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T05:04:39.160002Z","bundle_sha256":"30562ba1d1b96d2c33ea6e6058a610816d3880ae619e9ea048e3b489e3de1c64"}}