{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UJPATLNC52NS72BCG74PXDZWF3","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":"008548dcfac6c8828925e8b745fdd86df57858672b7d2cd789e3faf71c732e35","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2024-07-18T16:51:15Z","title_canon_sha256":"cc13997ab39a57cdf57e687ceb06bf6a74ab509290e6660cbcb864c1b4c569b3"},"schema_version":"1.0","source":{"id":"2407.13676","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.13676","created_at":"2026-07-05T08:45:42Z"},{"alias_kind":"arxiv_version","alias_value":"2407.13676v1","created_at":"2026-07-05T08:45:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.13676","created_at":"2026-07-05T08:45:42Z"},{"alias_kind":"pith_short_12","alias_value":"UJPATLNC52NS","created_at":"2026-07-05T08:45:42Z"},{"alias_kind":"pith_short_16","alias_value":"UJPATLNC52NS72BC","created_at":"2026-07-05T08:45:42Z"},{"alias_kind":"pith_short_8","alias_value":"UJPATLNC","created_at":"2026-07-05T08:45:42Z"}],"graph_snapshots":[{"event_id":"sha256:041e766d5fbf1072a5afc5a111bf5c424d9e689d1d598044c8c62d4a04d1dfe1","target":"graph","created_at":"2026-07-05T08:45:42Z","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/2407.13676/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent studies on learning-based sound source localization have mainly focused on the localization performance perspective. However, prior work and existing benchmarks overlook a crucial aspect: cross-modal interaction, which is essential for interactive sound source localization. Cross-modal interaction is vital for understanding semantically matched or mismatched audio-visual events, such as silent objects or off-screen sounds. In this paper, we first comprehensively examine the cross-modal interaction of existing methods, benchmarks, evaluation metrics, and cross-modal understanding tasks. ","authors_text":"Arda Senocak, Hanspeter Pfister, Hyeonggon Ryu, Joon Son Chung, Junsik Kim, Tae-Hyun Oh","cross_cats":["cs.CV","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2024-07-18T16:51:15Z","title":"Aligning Sight and Sound: Advanced Sound Source Localization Through Audio-Visual Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.13676","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:c798e3e03eccca0eee309e39e3bdb3aedb88c6fb10d7724b92a4e7bca20b8394","target":"record","created_at":"2026-07-05T08:45:42Z","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":"008548dcfac6c8828925e8b745fdd86df57858672b7d2cd789e3faf71c732e35","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2024-07-18T16:51:15Z","title_canon_sha256":"cc13997ab39a57cdf57e687ceb06bf6a74ab509290e6660cbcb864c1b4c569b3"},"schema_version":"1.0","source":{"id":"2407.13676","kind":"arxiv","version":1}},"canonical_sha256":"a25e09ada2ee9b2fe82237f8fb8f362ec62f1b4e853521d13d530701f7dc8b36","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a25e09ada2ee9b2fe82237f8fb8f362ec62f1b4e853521d13d530701f7dc8b36","first_computed_at":"2026-07-05T08:45:42.225029Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:45:42.225029Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jDlbSiphcImG6Rg2RYoRoBlAf1kGZ2cN+3kRiIhw4vidZl+jNjL7wjivgA6XhSc7Y0gXJHY6jWgA797Dkjp6DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:45:42.225415Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.13676","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c798e3e03eccca0eee309e39e3bdb3aedb88c6fb10d7724b92a4e7bca20b8394","sha256:041e766d5fbf1072a5afc5a111bf5c424d9e689d1d598044c8c62d4a04d1dfe1"],"state_sha256":"683327dbfd1d52f69143ece13b6b2e9ea993cfe42e3536f7c3d8a0d22827d449"}