{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WCKI535EWJ3UJ4LOJB3O6H65OL","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":"c80ff2af58ce925b1a9ea78149bdfa8dafdf1530517555af20a460dcaa446cb5","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-01-29T06:05:23Z","title_canon_sha256":"97509a8d5f56e72504384084a70feb3d910f13c693b5f42570dedb5134f769a4"},"schema_version":"1.0","source":{"id":"2401.17129","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.17129","created_at":"2026-07-05T07:39:19Z"},{"alias_kind":"arxiv_version","alias_value":"2401.17129v1","created_at":"2026-07-05T07:39:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.17129","created_at":"2026-07-05T07:39:19Z"},{"alias_kind":"pith_short_12","alias_value":"WCKI535EWJ3U","created_at":"2026-07-05T07:39:19Z"},{"alias_kind":"pith_short_16","alias_value":"WCKI535EWJ3UJ4LO","created_at":"2026-07-05T07:39:19Z"},{"alias_kind":"pith_short_8","alias_value":"WCKI535E","created_at":"2026-07-05T07:39:19Z"}],"graph_snapshots":[{"event_id":"sha256:184cbc625077de88df9bd8d883a18852274bbf9ef403258da857a38db478248b","target":"graph","created_at":"2026-07-05T07:39:19Z","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/2401.17129/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This technical report details our work towards building an enhanced audio-visual sound event localization and detection (SELD) network. We build on top of the audio-only SELDnet23 model and adapt it to be audio-visual by merging both audio and video information prior to the gated recurrent unit (GRU) of the audio-only network. Our model leverages YOLO and DETIC object detectors. We also build a framework that implements audio-visual data augmentation and audio-visual synthetic data generation. We deliver an audio-visual SELDnet system that outperforms the existing audio-visual SELD baseline.","authors_text":"Adrian S. Roman, Baladithya Balamurugan, Rithik Pothuganti","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-01-29T06:05:23Z","title":"Enhanced Sound Event Localization and Detection in Real 360-degree audio-visual soundscapes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.17129","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":"sha256:27862a23f8c7cfa1431c176b0108197df6187da2063d376e3eb2d686812a6d7c","target":"record","created_at":"2026-07-05T07:39:19Z","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":"c80ff2af58ce925b1a9ea78149bdfa8dafdf1530517555af20a460dcaa446cb5","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-01-29T06:05:23Z","title_canon_sha256":"97509a8d5f56e72504384084a70feb3d910f13c693b5f42570dedb5134f769a4"},"schema_version":"1.0","source":{"id":"2401.17129","kind":"arxiv","version":1}},"canonical_sha256":"b0948eefa4b27744f16e4876ef1fdd72e67bdbf0d8f73c67afe552b5b9981985","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b0948eefa4b27744f16e4876ef1fdd72e67bdbf0d8f73c67afe552b5b9981985","first_computed_at":"2026-07-05T07:39:19.800931Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:39:19.800931Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"w6IYGICAUSnVzlE5PJiuPOoHzUsLkhIPYNvWixlD2jnl8JiIxke7ZJQZdCx8zc3jlP3SHCRXAvUQyrnrTViBAA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:39:19.801548Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.17129","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:27862a23f8c7cfa1431c176b0108197df6187da2063d376e3eb2d686812a6d7c","sha256:184cbc625077de88df9bd8d883a18852274bbf9ef403258da857a38db478248b"],"state_sha256":"8f7852e5e5407d7a3bcdf8128e0fb88fa577ed7fed447c267288d90a1a0989b4"}