{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:KLWND6XXZRFU4E2P3VDWXMSSWD","short_pith_number":"pith:KLWND6XX","schema_version":"1.0","canonical_sha256":"52ecd1faf7cc4b4e134fdd476bb252b0fe0aac7416731e4d577152e515dfbe11","source":{"kind":"arxiv","id":"2110.02011","version":3},"attestation_state":"computed","paper":{"title":"Sound Event Detection Transformer: An Event-based End-to-End Model for Sound Event Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Hong Liu, Kazushige Ouchi, Long Yan, Rui Tao, Xiangdong Wang, Yueliang Qian, Zhirong Ye","submitted_at":"2021-10-05T12:56:23Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2110.02011","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-10-05T12:56:23Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"e810843965bda61a4f27b4f9fd6aa01ff18f2777e14d452c876ed40fbd60b73a","abstract_canon_sha256":"85034e20421a21c1b3d00824da9ad995b5d50099b4aaae6bc82dc9012f64ebe2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:31:03.941706Z","signature_b64":"6KiA1XoVEd5xhQBad0Y55OpI3tgHmQTSq6fle9Lct1xrHGnr1lhi8/jOXLTDwWfZ7KJ8sxdoLovwj3TCexh3AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"52ecd1faf7cc4b4e134fdd476bb252b0fe0aac7416731e4d577152e515dfbe11","last_reissued_at":"2026-07-05T03:31:03.941193Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:31:03.941193Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sound Event Detection Transformer: An Event-based End-to-End Model for Sound Event Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Hong Liu, Kazushige Ouchi, Long Yan, Rui Tao, Xiangdong Wang, Yueliang Qian, Zhirong Ye","submitted_at":"2021-10-05T12:56:23Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.02011","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2110.02011/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2110.02011","created_at":"2026-07-05T03:31:03.941255+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.02011v3","created_at":"2026-07-05T03:31:03.941255+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.02011","created_at":"2026-07-05T03:31:03.941255+00:00"},{"alias_kind":"pith_short_12","alias_value":"KLWND6XXZRFU","created_at":"2026-07-05T03:31:03.941255+00:00"},{"alias_kind":"pith_short_16","alias_value":"KLWND6XXZRFU4E2P","created_at":"2026-07-05T03:31:03.941255+00:00"},{"alias_kind":"pith_short_8","alias_value":"KLWND6XX","created_at":"2026-07-05T03:31:03.941255+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17775","citing_title":"A Neuromorphic Trigger for Efficient Audio Event Detection","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03934","citing_title":"Towards Open World Sound Event Detection","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03934","citing_title":"Towards Open World Sound Event Detection","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KLWND6XXZRFU4E2P3VDWXMSSWD","json":"https://pith.science/pith/KLWND6XXZRFU4E2P3VDWXMSSWD.json","graph_json":"https://pith.science/api/pith-number/KLWND6XXZRFU4E2P3VDWXMSSWD/graph.json","events_json":"https://pith.science/api/pith-number/KLWND6XXZRFU4E2P3VDWXMSSWD/events.json","paper":"https://pith.science/paper/KLWND6XX"},"agent_actions":{"view_html":"https://pith.science/pith/KLWND6XXZRFU4E2P3VDWXMSSWD","download_json":"https://pith.science/pith/KLWND6XXZRFU4E2P3VDWXMSSWD.json","view_paper":"https://pith.science/paper/KLWND6XX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.02011&json=true","fetch_graph":"https://pith.science/api/pith-number/KLWND6XXZRFU4E2P3VDWXMSSWD/graph.json","fetch_events":"https://pith.science/api/pith-number/KLWND6XXZRFU4E2P3VDWXMSSWD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KLWND6XXZRFU4E2P3VDWXMSSWD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KLWND6XXZRFU4E2P3VDWXMSSWD/action/storage_attestation","attest_author":"https://pith.science/pith/KLWND6XXZRFU4E2P3VDWXMSSWD/action/author_attestation","sign_citation":"https://pith.science/pith/KLWND6XXZRFU4E2P3VDWXMSSWD/action/citation_signature","submit_replication":"https://pith.science/pith/KLWND6XXZRFU4E2P3VDWXMSSWD/action/replication_record"}},"created_at":"2026-07-05T03:31:03.941255+00:00","updated_at":"2026-07-05T03:31:03.941255+00:00"}