{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:3GNDF5F755CYKIJ7232PC5BY2L","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":"947ed94526f242bc8b1a19300c4ef3ce1847cd6ef69e1656df147a73e92b5a1f","cross_cats_sorted":["cs.CV","cs.LG","cs.MM","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-05-30T23:53:12Z","title_canon_sha256":"b24ea9c41a8c7d7fbba4d9e2aa39c22730e5781c6f0a4c00589d6ed3a0eaf764"},"schema_version":"1.0","source":{"id":"2305.19458","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.19458","created_at":"2026-07-05T06:15:50Z"},{"alias_kind":"arxiv_version","alias_value":"2305.19458v1","created_at":"2026-07-05T06:15:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.19458","created_at":"2026-07-05T06:15:50Z"},{"alias_kind":"pith_short_12","alias_value":"3GNDF5F755CY","created_at":"2026-07-05T06:15:50Z"},{"alias_kind":"pith_short_16","alias_value":"3GNDF5F755CYKIJ7","created_at":"2026-07-05T06:15:50Z"},{"alias_kind":"pith_short_8","alias_value":"3GNDF5F7","created_at":"2026-07-05T06:15:50Z"}],"graph_snapshots":[{"event_id":"sha256:3cc751a6935d9156417c9b445fb941194e8a9a757ffa120f46a0d9fa99096573","target":"graph","created_at":"2026-07-05T06:15:50Z","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/2305.19458/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The ability to accurately recognize, localize and separate sound sources is fundamental to any audio-visual perception task. Historically, these abilities were tackled separately, with several methods developed independently for each task. However, given the interconnected nature of source localization, separation, and recognition, independent models are likely to yield suboptimal performance as they fail to capture the interdependence between these tasks. To address this problem, we propose a unified audio-visual learning framework (dubbed OneAVM) that integrates audio and visual cues for joi","authors_text":"Pedro Morgado, Shentong Mo","cross_cats":["cs.CV","cs.LG","cs.MM","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-05-30T23:53:12Z","title":"A Unified Audio-Visual Learning Framework for Localization, Separation, and Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.19458","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:e03f34a8a4ff0a1b3831168fd18a600ecb20c9d23473d0c2838e624d251004e1","target":"record","created_at":"2026-07-05T06:15:50Z","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":"947ed94526f242bc8b1a19300c4ef3ce1847cd6ef69e1656df147a73e92b5a1f","cross_cats_sorted":["cs.CV","cs.LG","cs.MM","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-05-30T23:53:12Z","title_canon_sha256":"b24ea9c41a8c7d7fbba4d9e2aa39c22730e5781c6f0a4c00589d6ed3a0eaf764"},"schema_version":"1.0","source":{"id":"2305.19458","kind":"arxiv","version":1}},"canonical_sha256":"d99a32f4bfef4585213fd6f4f17438d2c65841e775d468427322988bc3775a41","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d99a32f4bfef4585213fd6f4f17438d2c65841e775d468427322988bc3775a41","first_computed_at":"2026-07-05T06:15:50.425091Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:15:50.425091Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+pYwW3PhaAU1znAQ4q9rBn6TMqs1EKm9uimnIpeDsgErFDuWPX3d833VP3c+LnU4ZkoPmzktWSgYasZJU4jkDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:15:50.425482Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.19458","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e03f34a8a4ff0a1b3831168fd18a600ecb20c9d23473d0c2838e624d251004e1","sha256:3cc751a6935d9156417c9b445fb941194e8a9a757ffa120f46a0d9fa99096573"],"state_sha256":"c1e42c44b40e958d5d89f540d48cf80d031c2029e113f1aa0612fffd5930866f"}