{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5RHHK5P3D2P6DODYUHRYRCNTGR","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":"44875c8da23c696b545b31cf495c5c0a3e8cdc0050bd8bda5b7cd17be3710478","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.MM","submitted_at":"2025-02-11T13:24:38Z","title_canon_sha256":"761cb2ee34aa748a88bff4654c1fc4a4b11aa2587ca64aafe85297f2ef6e9055"},"schema_version":"1.0","source":{"id":"2502.07538","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.07538","created_at":"2026-07-05T10:13:48Z"},{"alias_kind":"arxiv_version","alias_value":"2502.07538v2","created_at":"2026-07-05T10:13:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.07538","created_at":"2026-07-05T10:13:48Z"},{"alias_kind":"pith_short_12","alias_value":"5RHHK5P3D2P6","created_at":"2026-07-05T10:13:48Z"},{"alias_kind":"pith_short_16","alias_value":"5RHHK5P3D2P6DODY","created_at":"2026-07-05T10:13:48Z"},{"alias_kind":"pith_short_8","alias_value":"5RHHK5P3","created_at":"2026-07-05T10:13:48Z"}],"graph_snapshots":[{"event_id":"sha256:c13190c166b698c7bf05799db07f8611336d9adcb344bf6dc45101352e5957a1","target":"graph","created_at":"2026-07-05T10:13:48Z","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/2502.07538/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In multimedia applications such as films and video games, spatial audio techniques are widely employed to enhance user experiences by simulating 3D sound: transforming mono audio into binaural formats. However, this process is often complex and labor-intensive for sound designers, requiring precise synchronization of audio with the spatial positions of visual components. To address these challenges, we propose a visual-based spatial audio generation system - an automated system that integrates face detection YOLOv8 for object detection, monocular depth estimation, and spatial audio techniques.","authors_text":"Joshua Reiss, Ogulcan Gurelli, Xiaojing Liu, Yan Wang","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.MM","submitted_at":"2025-02-11T13:24:38Z","title":"Visual-based spatial audio generation system for multi-speaker environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.07538","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:b67102fe1b02e193b755e931382354134b636de903c43376d7b886fdac438c88","target":"record","created_at":"2026-07-05T10:13:48Z","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":"44875c8da23c696b545b31cf495c5c0a3e8cdc0050bd8bda5b7cd17be3710478","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.MM","submitted_at":"2025-02-11T13:24:38Z","title_canon_sha256":"761cb2ee34aa748a88bff4654c1fc4a4b11aa2587ca64aafe85297f2ef6e9055"},"schema_version":"1.0","source":{"id":"2502.07538","kind":"arxiv","version":2}},"canonical_sha256":"ec4e7575fb1e9fe1b878a1e38889b3344d4f2d78a94400a7932ce030052b2278","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ec4e7575fb1e9fe1b878a1e38889b3344d4f2d78a94400a7932ce030052b2278","first_computed_at":"2026-07-05T10:13:48.315839Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:13:48.315839Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xNBCHriN1ZsLsiMXx2NH9zJIcEacqTuvE2uX5OKSQ1CSw8TQiMJsSCX7RiVAOxOX+O0I6Onzv1VreRwdvuBcDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:13:48.316445Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.07538","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b67102fe1b02e193b755e931382354134b636de903c43376d7b886fdac438c88","sha256:c13190c166b698c7bf05799db07f8611336d9adcb344bf6dc45101352e5957a1"],"state_sha256":"5f902f722c0a1579c230f1c6d5d13bb6ad43be741fa167759a4861f12876e4fc"}