{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OXFALNBB5TZCXKG77ASUDFOLXS","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":"55a7881c2eec2033e67ae44ff30fc82db676ceb7e48744f64d15837517b754ca","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-30T06:57:00Z","title_canon_sha256":"e5eea4c153b6ba1d51efc1639d49e04c7baa8c533e65396cb7701889e5a2364b"},"schema_version":"1.0","source":{"id":"2407.20592","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.20592","created_at":"2026-07-05T09:49:08Z"},{"alias_kind":"arxiv_version","alias_value":"2407.20592v2","created_at":"2026-07-05T09:49:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.20592","created_at":"2026-07-05T09:49:08Z"},{"alias_kind":"pith_short_12","alias_value":"OXFALNBB5TZC","created_at":"2026-07-05T09:49:08Z"},{"alias_kind":"pith_short_16","alias_value":"OXFALNBB5TZCXKG7","created_at":"2026-07-05T09:49:08Z"},{"alias_kind":"pith_short_8","alias_value":"OXFALNBB","created_at":"2026-07-05T09:49:08Z"}],"graph_snapshots":[{"event_id":"sha256:a0223fa6a0b34c160a67e3a8a63f89c4826a4175d1ff9d9c44d8ff6fe81eff58","target":"graph","created_at":"2026-07-05T09:49:08Z","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/2407.20592/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce EgoSonics, a method to generate semantically meaningful and synchronized audio tracks conditioned on silent egocentric videos. Generating audio for silent egocentric videos could open new applications in virtual reality, assistive technologies, or for augmenting existing datasets. Existing work has been limited to domains like speech, music, or impact sounds and cannot capture the broad range of audio frequencies found in egocentric videos. EgoSonics addresses these limitations by building on the strengths of latent diffusion models for conditioned audio synthesis. We first encode","authors_text":"Aashish Rai, Srinath Sridhar","cross_cats":["cs.MM","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-30T06:57:00Z","title":"EgoSonics: Generating Synchronized Audio for Silent Egocentric Videos"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.20592","kind":"arxiv","version":2},"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":"sha256:5b6325360c364e0ab71a609bc2adb129c6011aa79de1baecf04d9dad275a71f5","target":"record","created_at":"2026-07-05T09:49:08Z","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":"55a7881c2eec2033e67ae44ff30fc82db676ceb7e48744f64d15837517b754ca","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-30T06:57:00Z","title_canon_sha256":"e5eea4c153b6ba1d51efc1639d49e04c7baa8c533e65396cb7701889e5a2364b"},"schema_version":"1.0","source":{"id":"2407.20592","kind":"arxiv","version":2}},"canonical_sha256":"75ca05b421ecf22ba8dff8254195cbbcab83beafd096c2f0bca365f17e3e4b1b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"75ca05b421ecf22ba8dff8254195cbbcab83beafd096c2f0bca365f17e3e4b1b","first_computed_at":"2026-07-05T09:49:08.533355Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:49:08.533355Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mLk7hEzwUl1LnZjSRpayWohcivxKvFdgiKj7l+lGQUN9e7WRhHvqJhw+M84LwKaEctEnuQbXkIG8IfkGek70CA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:49:08.533823Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.20592","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5b6325360c364e0ab71a609bc2adb129c6011aa79de1baecf04d9dad275a71f5","sha256:a0223fa6a0b34c160a67e3a8a63f89c4826a4175d1ff9d9c44d8ff6fe81eff58"],"state_sha256":"180e563509907ce26b18380ab9645e6e3f294fc5687d3d6e5d5a5c43606daca9"}