{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:BSWWT44OYU2HFSWEEJFC5RONN3","short_pith_number":"pith:BSWWT44O","schema_version":"1.0","canonical_sha256":"0cad69f38ec53472cac4224a2ec5cd6eee582826cd6c72f3883e706c51f59557","source":{"kind":"arxiv","id":"2106.10806","version":1},"attestation_state":"computed","paper":{"title":"Ensemble of ACCDOA- and EINV2-based Systems with D3Nets and Impulse Response Simulation for Sound Event Localization and Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Emiru Tsunoo, Kazuki Shimada, Masafumi Takahashi, Naoya Takahashi, Shusuke Takahashi, Yuichiro Koyama, Yuki Mitsufuji","submitted_at":"2021-06-21T01:52:45Z","abstract_excerpt":"This report describes our systems submitted to the DCASE2021 challenge task 3: sound event localization and detection (SELD) with directional interference. Our previous system based on activity-coupled Cartesian direction of arrival (ACCDOA) representation enables us to solve a SELD task with a single target. This ACCDOA-based system with efficient network architecture called RD3Net and data augmentation techniques outperformed state-of-the-art SELD systems in terms of localization and location-dependent detection. Using the ACCDOA-based system as a base, we perform model ensembles by averagin"},"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":"2106.10806","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-06-21T01:52:45Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"44f62605fc621a5c2e03ca648124a1a23b5877a80f11a2b90fa32868045a1270","abstract_canon_sha256":"4ac8b42b78a872843549b5ddc7aa7b20374fa9877c301e5538bd4a1dc2ea9c47"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:50:53.593752Z","signature_b64":"ucnbs2+Q0vKoXozlyUD/XMTdHX8GeK9nJzyhVPS5FEAOaXipoJHQ3X4y37Hke8kpVtV3cyGYntgfn8gO+424DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0cad69f38ec53472cac4224a2ec5cd6eee582826cd6c72f3883e706c51f59557","last_reissued_at":"2026-07-05T02:50:53.593366Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:50:53.593366Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ensemble of ACCDOA- and EINV2-based Systems with D3Nets and Impulse Response Simulation for Sound Event Localization and Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Emiru Tsunoo, Kazuki Shimada, Masafumi Takahashi, Naoya Takahashi, Shusuke Takahashi, Yuichiro Koyama, Yuki Mitsufuji","submitted_at":"2021-06-21T01:52:45Z","abstract_excerpt":"This report describes our systems submitted to the DCASE2021 challenge task 3: sound event localization and detection (SELD) with directional interference. Our previous system based on activity-coupled Cartesian direction of arrival (ACCDOA) representation enables us to solve a SELD task with a single target. This ACCDOA-based system with efficient network architecture called RD3Net and data augmentation techniques outperformed state-of-the-art SELD systems in terms of localization and location-dependent detection. Using the ACCDOA-based system as a base, we perform model ensembles by averagin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.10806","kind":"arxiv","version":1},"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/2106.10806/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":"2106.10806","created_at":"2026-07-05T02:50:53.593434+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.10806v1","created_at":"2026-07-05T02:50:53.593434+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.10806","created_at":"2026-07-05T02:50:53.593434+00:00"},{"alias_kind":"pith_short_12","alias_value":"BSWWT44OYU2H","created_at":"2026-07-05T02:50:53.593434+00:00"},{"alias_kind":"pith_short_16","alias_value":"BSWWT44OYU2HFSWE","created_at":"2026-07-05T02:50:53.593434+00:00"},{"alias_kind":"pith_short_8","alias_value":"BSWWT44O","created_at":"2026-07-05T02:50:53.593434+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.17247","citing_title":"DeepASA: An Object-Oriented Multi-Purpose Network for Auditory Scene Analysis","ref_index":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BSWWT44OYU2HFSWEEJFC5RONN3","json":"https://pith.science/pith/BSWWT44OYU2HFSWEEJFC5RONN3.json","graph_json":"https://pith.science/api/pith-number/BSWWT44OYU2HFSWEEJFC5RONN3/graph.json","events_json":"https://pith.science/api/pith-number/BSWWT44OYU2HFSWEEJFC5RONN3/events.json","paper":"https://pith.science/paper/BSWWT44O"},"agent_actions":{"view_html":"https://pith.science/pith/BSWWT44OYU2HFSWEEJFC5RONN3","download_json":"https://pith.science/pith/BSWWT44OYU2HFSWEEJFC5RONN3.json","view_paper":"https://pith.science/paper/BSWWT44O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.10806&json=true","fetch_graph":"https://pith.science/api/pith-number/BSWWT44OYU2HFSWEEJFC5RONN3/graph.json","fetch_events":"https://pith.science/api/pith-number/BSWWT44OYU2HFSWEEJFC5RONN3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BSWWT44OYU2HFSWEEJFC5RONN3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BSWWT44OYU2HFSWEEJFC5RONN3/action/storage_attestation","attest_author":"https://pith.science/pith/BSWWT44OYU2HFSWEEJFC5RONN3/action/author_attestation","sign_citation":"https://pith.science/pith/BSWWT44OYU2HFSWEEJFC5RONN3/action/citation_signature","submit_replication":"https://pith.science/pith/BSWWT44OYU2HFSWEEJFC5RONN3/action/replication_record"}},"created_at":"2026-07-05T02:50:53.593434+00:00","updated_at":"2026-07-05T02:50:53.593434+00:00"}