{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EFDHBLNAQUPZNETU7SX4UATXBM","short_pith_number":"pith:EFDHBLNA","schema_version":"1.0","canonical_sha256":"214670ada0851f969274fcafca02770b3ad4685be41185b9bcceff7ed5e614ea","source":{"kind":"arxiv","id":"2605.03934","version":2},"attestation_state":"computed","paper":{"title":"Towards Open World Sound Event Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Sound event detection can now identify unknown events and learn from them incrementally.","cross_cats":["cs.AI"],"primary_cat":"cs.SD","authors_text":"L.H.Son, L.T.Minh, P.H.Hai","submitted_at":"2026-05-05T16:23:06Z","abstract_excerpt":"Sound Event Detection (SED) plays a vital role in audio understanding, with applications in surveillance, smart cities, healthcare, and multimedia indexing. However, conventional SED systems operate under a closed-world assumption, limiting their effectiveness in real-world environments where novel acoustic events frequently emerge. Inspired by the success of open-world learning in computer vision, we introduce the Open-World Sound Event Detection (OW-SED) paradigm, where models must detect known events, identify unseen ones, and incrementally learn from them. To tackle the unique challenges o"},"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":"2605.03934","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-05-05T16:23:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6f149b81fc5a6d242b0ac81dc04510d74ca87093a6d4f97a2ab0b6ec3a39c901","abstract_canon_sha256":"757aaff7ea77f4965a8071c8cc48dc1b695b62a03325b0616c489339a730d4a5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T02:04:41.626815Z","signature_b64":"C7sXyOiPXFsAd/E+2uNJsoduwtHr8274fNsm88/0TP5Cc8GyfNsNI0UF4NrwVYhL7aKVcuH0Sx6T3/O6zt3NAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"214670ada0851f969274fcafca02770b3ad4685be41185b9bcceff7ed5e614ea","last_reissued_at":"2026-05-22T02:04:41.626066Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T02:04:41.626066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Open World Sound Event Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Sound event detection can now identify unknown events and learn from them incrementally.","cross_cats":["cs.AI"],"primary_cat":"cs.SD","authors_text":"L.H.Son, L.T.Minh, P.H.Hai","submitted_at":"2026-05-05T16:23:06Z","abstract_excerpt":"Sound Event Detection (SED) plays a vital role in audio understanding, with applications in surveillance, smart cities, healthcare, and multimedia indexing. However, conventional SED systems operate under a closed-world assumption, limiting their effectiveness in real-world environments where novel acoustic events frequently emerge. Inspired by the success of open-world learning in computer vision, we introduce the Open-World Sound Event Detection (OW-SED) paradigm, where models must detect known events, identify unseen ones, and incrementally learn from them. To tackle the unique challenges o"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experimental results demonstrate that our method achieves marginally superior performance compared to existing leading techniques in closed-world settings and significantly improves over existing baselines in open-world scenarios.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the 1D Deformable architecture combined with feature disentanglement, one-to-many matching, and diversity loss can effectively handle overlapping and ambiguous events while enabling incremental learning of novel sounds.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Introduces OW-SED paradigm and WOOT transformer framework to detect known sounds, identify unseen events, and incrementally learn in open audio environments.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Sound event detection can now identify unknown events and learn from them incrementally.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"46f874015e0b76ac436e07f9c10044f8d0ac9bbdc684c7b1c431e516be898d9b"},"source":{"id":"2605.03934","kind":"arxiv","version":2},"verdict":{"id":"bbd5c6ef-b79d-432f-a1b7-86602e3d5bc9","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-07T12:34:44.363054Z","strongest_claim":"Experimental results demonstrate that our method achieves marginally superior performance compared to existing leading techniques in closed-world settings and significantly improves over existing baselines in open-world scenarios.","one_line_summary":"Introduces OW-SED paradigm and WOOT transformer framework to detect known sounds, identify unseen events, and incrementally learn in open audio environments.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the 1D Deformable architecture combined with feature disentanglement, one-to-many matching, and diversity loss can effectively handle overlapping and ambiguous events while enabling incremental learning of novel sounds.","pith_extraction_headline":"Sound event detection can now identify unknown events and learn from them incrementally."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.03934/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-20T12:40:53.397156Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-20T00:01:21.499481Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T14:55:03.873844Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"46514ca0a7f1fadfcbe29db25510a917fe9310f2f2872fed1b7cb99af34efd16"},"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":"2605.03934","created_at":"2026-05-22T02:04:41.626187+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.03934v2","created_at":"2026-05-22T02:04:41.626187+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.03934","created_at":"2026-05-22T02:04:41.626187+00:00"},{"alias_kind":"pith_short_12","alias_value":"EFDHBLNAQUPZ","created_at":"2026-05-22T02:04:41.626187+00:00"},{"alias_kind":"pith_short_16","alias_value":"EFDHBLNAQUPZNETU","created_at":"2026-05-22T02:04:41.626187+00:00"},{"alias_kind":"pith_short_8","alias_value":"EFDHBLNA","created_at":"2026-05-22T02:04:41.626187+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EFDHBLNAQUPZNETU7SX4UATXBM","json":"https://pith.science/pith/EFDHBLNAQUPZNETU7SX4UATXBM.json","graph_json":"https://pith.science/api/pith-number/EFDHBLNAQUPZNETU7SX4UATXBM/graph.json","events_json":"https://pith.science/api/pith-number/EFDHBLNAQUPZNETU7SX4UATXBM/events.json","paper":"https://pith.science/paper/EFDHBLNA"},"agent_actions":{"view_html":"https://pith.science/pith/EFDHBLNAQUPZNETU7SX4UATXBM","download_json":"https://pith.science/pith/EFDHBLNAQUPZNETU7SX4UATXBM.json","view_paper":"https://pith.science/paper/EFDHBLNA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.03934&json=true","fetch_graph":"https://pith.science/api/pith-number/EFDHBLNAQUPZNETU7SX4UATXBM/graph.json","fetch_events":"https://pith.science/api/pith-number/EFDHBLNAQUPZNETU7SX4UATXBM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EFDHBLNAQUPZNETU7SX4UATXBM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EFDHBLNAQUPZNETU7SX4UATXBM/action/storage_attestation","attest_author":"https://pith.science/pith/EFDHBLNAQUPZNETU7SX4UATXBM/action/author_attestation","sign_citation":"https://pith.science/pith/EFDHBLNAQUPZNETU7SX4UATXBM/action/citation_signature","submit_replication":"https://pith.science/pith/EFDHBLNAQUPZNETU7SX4UATXBM/action/replication_record"}},"created_at":"2026-05-22T02:04:41.626187+00:00","updated_at":"2026-05-22T02:04:41.626187+00:00"}