{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OSOJ7YRGWP7PX3L2T7LX2YU42S","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":"2975704c73e0ae19d18318df1f143bfd296fe14027e096a5c5dfd993df161b45","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-08-16T11:33:16Z","title_canon_sha256":"5f46214a4b7f4aa3d6ac19fdd213d7ccffb55fec6dddb1660cfa7bf0a8b0f4a1"},"schema_version":"1.0","source":{"id":"2408.08673","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.08673","created_at":"2026-07-05T08:56:24Z"},{"alias_kind":"arxiv_version","alias_value":"2408.08673v2","created_at":"2026-07-05T08:56:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.08673","created_at":"2026-07-05T08:56:24Z"},{"alias_kind":"pith_short_12","alias_value":"OSOJ7YRGWP7P","created_at":"2026-07-05T08:56:24Z"},{"alias_kind":"pith_short_16","alias_value":"OSOJ7YRGWP7PX3L2","created_at":"2026-07-05T08:56:24Z"},{"alias_kind":"pith_short_8","alias_value":"OSOJ7YRG","created_at":"2026-07-05T08:56:24Z"}],"graph_snapshots":[{"event_id":"sha256:a6b531a86e2d72023e751b65a53d94e8a2b102de63c25d29409db069c4e2f3c6","target":"graph","created_at":"2026-07-05T08:56:24Z","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/2408.08673/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sound event detection (SED) methods that leverage a large pre-trained Transformer encoder network have shown promising performance in recent DCASE challenges. However, they still rely on an RNN-based context network to model temporal dependencies, largely due to the scarcity of labeled data. In this work, we propose a pure Transformer-based SED model with masked-reconstruction based pre-training, termed MAT-SED. Specifically, a Transformer with relative positional encoding is first designed as the context network, pre-trained by the masked-reconstruction task on all available target data in a ","authors_text":"Haoyu Song, Ian McLoughlin, Kang Li, Pengfei Cai, Yan Song","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-08-16T11:33:16Z","title":"MAT-SED: A Masked Audio Transformer with Masked-Reconstruction Based Pre-training for Sound Event Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.08673","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":"sha256:40af767cd08d711f5a7fa4f5e50f703ec1eebf33fb5d35cb0d4e8ed46b92ba1d","target":"record","created_at":"2026-07-05T08:56:24Z","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":"2975704c73e0ae19d18318df1f143bfd296fe14027e096a5c5dfd993df161b45","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-08-16T11:33:16Z","title_canon_sha256":"5f46214a4b7f4aa3d6ac19fdd213d7ccffb55fec6dddb1660cfa7bf0a8b0f4a1"},"schema_version":"1.0","source":{"id":"2408.08673","kind":"arxiv","version":2}},"canonical_sha256":"749c9fe226b3fefbed7a9fd77d629cd4b4726b8122b88cb2b239be2427389ac0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"749c9fe226b3fefbed7a9fd77d629cd4b4726b8122b88cb2b239be2427389ac0","first_computed_at":"2026-07-05T08:56:24.824027Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:56:24.824027Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"u4Jk+Pg/UaaNFpd9/2Wm/9sDbqSjnNqRaHCYq59FrUsx1AgObhG8ofx38csIykkE7otV9pN2g2j9j6y2bEGLAg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:56:24.824473Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.08673","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:40af767cd08d711f5a7fa4f5e50f703ec1eebf33fb5d35cb0d4e8ed46b92ba1d","sha256:a6b531a86e2d72023e751b65a53d94e8a2b102de63c25d29409db069c4e2f3c6"],"state_sha256":"e33216c61640e27ed95a72e8f6e45f5b8c70d7918b3b85e8682699bff56cd250"}