{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3N6AN3BJHOPQRJWQO7DKKXZZFS","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":"5c99849b22c3fea62b22c877b8a838b84d14a74448ce4c3cba4d99ebbdcb7762","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-06-13T03:03:02Z","title_canon_sha256":"6fdeae108ec6b45d1673ea427ea657f0d5d36a458705bbd45f7593148362398d"},"schema_version":"1.0","source":{"id":"2406.08771","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.08771","created_at":"2026-07-05T08:32:13Z"},{"alias_kind":"arxiv_version","alias_value":"2406.08771v2","created_at":"2026-07-05T08:32:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.08771","created_at":"2026-07-05T08:32:13Z"},{"alias_kind":"pith_short_12","alias_value":"3N6AN3BJHOPQ","created_at":"2026-07-05T08:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"3N6AN3BJHOPQRJWQ","created_at":"2026-07-05T08:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"3N6AN3BJ","created_at":"2026-07-05T08:32:13Z"}],"graph_snapshots":[{"event_id":"sha256:8f5ebdfb772437ba18e13d3a3c3973ef21a245820e02b3a3306e414433b2a434","target":"graph","created_at":"2026-07-05T08:32:13Z","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/2406.08771/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sound Event Localization and Detection (SELD) involves detecting and localizing sound events using multichannel sound recordings. Previously proposed Event-Independent Network V2 (EINV2) has achieved outstanding performance on SELD. However, it still faces challenges in effectively extracting features across spectral, spatial, and temporal domains. This paper proposes a three-stage network structure named Multi-scale Feature Fusion (MFF) module to fully extract multi-scale features across spectral, spatial, and temporal domains. The MFF module utilizes parallel subnetworks architecture to gene","authors_text":"Da Mu, Haobo Yue, Zhicheng Zhang","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-06-13T03:03:02Z","title":"MFF-EINV2: Multi-scale Feature Fusion across Spectral-Spatial-Temporal Domains for Sound Event Localization and Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.08771","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":"sha256:8995bb14630775ff9c7486ddd0c3bc2b97f46ae908a0a84cfd3fd8293bc07da2","target":"record","created_at":"2026-07-05T08:32:13Z","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":"5c99849b22c3fea62b22c877b8a838b84d14a74448ce4c3cba4d99ebbdcb7762","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-06-13T03:03:02Z","title_canon_sha256":"6fdeae108ec6b45d1673ea427ea657f0d5d36a458705bbd45f7593148362398d"},"schema_version":"1.0","source":{"id":"2406.08771","kind":"arxiv","version":2}},"canonical_sha256":"db7c06ec293b9f08a6d077c6a55f392caddfffa2add8a0ce403005ad83dbcf53","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"db7c06ec293b9f08a6d077c6a55f392caddfffa2add8a0ce403005ad83dbcf53","first_computed_at":"2026-07-05T08:32:13.458273Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:32:13.458273Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BzMDZ70SEiAELws+rL/A0ZwpxYGeuVcmfhT9GmvBRvRORndeCZgqS70cSVNLnDY5jXErpNj+9wl1plDexVrKBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:32:13.458754Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.08771","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8995bb14630775ff9c7486ddd0c3bc2b97f46ae908a0a84cfd3fd8293bc07da2","sha256:8f5ebdfb772437ba18e13d3a3c3973ef21a245820e02b3a3306e414433b2a434"],"state_sha256":"1f651cd247cbde6e6f70c9b238f41562a4389639292212d00b9ea33bd848df6b"}