{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:KLWND6XXZRFU4E2P3VDWXMSSWD","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":"85034e20421a21c1b3d00824da9ad995b5d50099b4aaae6bc82dc9012f64ebe2","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-10-05T12:56:23Z","title_canon_sha256":"e810843965bda61a4f27b4f9fd6aa01ff18f2777e14d452c876ed40fbd60b73a"},"schema_version":"1.0","source":{"id":"2110.02011","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.02011","created_at":"2026-07-05T03:31:03Z"},{"alias_kind":"arxiv_version","alias_value":"2110.02011v3","created_at":"2026-07-05T03:31:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.02011","created_at":"2026-07-05T03:31:03Z"},{"alias_kind":"pith_short_12","alias_value":"KLWND6XXZRFU","created_at":"2026-07-05T03:31:03Z"},{"alias_kind":"pith_short_16","alias_value":"KLWND6XXZRFU4E2P","created_at":"2026-07-05T03:31:03Z"},{"alias_kind":"pith_short_8","alias_value":"KLWND6XX","created_at":"2026-07-05T03:31:03Z"}],"graph_snapshots":[{"event_id":"sha256:fbf632f2bbb24d5bf8962ed6adb8d72a7e3929b33f690bd65867f5df28710f02","target":"graph","created_at":"2026-07-05T03:31:03Z","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/2110.02011/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sound event detection (SED) has gained increasing attention with its wide application in surveillance, video indexing, etc. Existing models in SED mainly generate frame-level prediction, converting it into a sequence multi-label classification problem. A critical issue with the frame-based model is that it pursues the best frame-level prediction rather than the best event-level prediction. Besides, it needs post-processing and cannot be trained in an end-to-end way. This paper firstly presents the one-dimensional Detection Transformer (1D-DETR), inspired by Detection Transformer for image obje","authors_text":"Hong Liu, Kazushige Ouchi, Long Yan, Rui Tao, Xiangdong Wang, Yueliang Qian, Zhirong Ye","cross_cats":["cs.LG","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-10-05T12:56:23Z","title":"Sound Event Detection Transformer: An Event-based End-to-End Model for Sound Event Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.02011","kind":"arxiv","version":3},"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":"sha256:446eeca6f639a329ee90481e581d61a0313aaf5542da73ad5a6d006ce2934deb","target":"record","created_at":"2026-07-05T03:31:03Z","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":"85034e20421a21c1b3d00824da9ad995b5d50099b4aaae6bc82dc9012f64ebe2","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-10-05T12:56:23Z","title_canon_sha256":"e810843965bda61a4f27b4f9fd6aa01ff18f2777e14d452c876ed40fbd60b73a"},"schema_version":"1.0","source":{"id":"2110.02011","kind":"arxiv","version":3}},"canonical_sha256":"52ecd1faf7cc4b4e134fdd476bb252b0fe0aac7416731e4d577152e515dfbe11","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"52ecd1faf7cc4b4e134fdd476bb252b0fe0aac7416731e4d577152e515dfbe11","first_computed_at":"2026-07-05T03:31:03.941193Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:31:03.941193Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6KiA1XoVEd5xhQBad0Y55OpI3tgHmQTSq6fle9Lct1xrHGnr1lhi8/jOXLTDwWfZ7KJ8sxdoLovwj3TCexh3AA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:31:03.941706Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.02011","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:446eeca6f639a329ee90481e581d61a0313aaf5542da73ad5a6d006ce2934deb","sha256:fbf632f2bbb24d5bf8962ed6adb8d72a7e3929b33f690bd65867f5df28710f02"],"state_sha256":"710797c6f4c6c8a554b66c33106f1a3bc96a0b133cabf18a297cc77b9bce8736"}