{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6MMG7HCPPJ72NSMIDWVXOJVYLM","short_pith_number":"pith:6MMG7HCP","schema_version":"1.0","canonical_sha256":"f3186f9c4f7a7fa6c9881dab7726b85b0a222224ad20d727ae0074d1eda30d68","source":{"kind":"arxiv","id":"2407.03654","version":3},"attestation_state":"computed","paper":{"title":"DG-SED: Domain Generalization for Sound Event Detection with Heterogeneous Training Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Han Yin, Jisheng Bai, Rohan Kumar Das, Yang Xiao","submitted_at":"2024-07-04T05:50:40Z","abstract_excerpt":"This work explores domain generalization (DG) for sound event detection (SED), advancing adaptability to real-world scenarios. Our approach employs a mean-teacher framework with domain generalization named DG-SED to integrate heterogeneous training data while preserving the SED model performance across the datasets. Specifically, we first apply mixstyle to the frequency dimension to adapt the mel-spectrograms from different domains. Next, we use the adaptive residual normalization method to generalize features across multiple domains by applying instance normalization in the frequency dimensio"},"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":"2407.03654","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-07-04T05:50:40Z","cross_cats_sorted":[],"title_canon_sha256":"b3b746c638cd107ecbb6ab572411622569d1c9af76dabee1d4b20baa35a0e861","abstract_canon_sha256":"87626ace8aa2a203af5c3c8e842bc32d0dc3858e5b6a2ece46be1f5a4bc9631b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:59:05.998863Z","signature_b64":"zg++ZFuFh3QeK8jMzIQNSu1JtT571toplm528NBy+ckzsZRGFJWW8uHMNzx4wcJ5Eo2m6P3QYS3PItlhw1zpDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f3186f9c4f7a7fa6c9881dab7726b85b0a222224ad20d727ae0074d1eda30d68","last_reissued_at":"2026-07-05T11:59:05.998380Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:59:05.998380Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DG-SED: Domain Generalization for Sound Event Detection with Heterogeneous Training Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Han Yin, Jisheng Bai, Rohan Kumar Das, Yang Xiao","submitted_at":"2024-07-04T05:50:40Z","abstract_excerpt":"This work explores domain generalization (DG) for sound event detection (SED), advancing adaptability to real-world scenarios. Our approach employs a mean-teacher framework with domain generalization named DG-SED to integrate heterogeneous training data while preserving the SED model performance across the datasets. Specifically, we first apply mixstyle to the frequency dimension to adapt the mel-spectrograms from different domains. Next, we use the adaptive residual normalization method to generalize features across multiple domains by applying instance normalization in the frequency dimensio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.03654","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/2407.03654/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":"2407.03654","created_at":"2026-07-05T11:59:05.998439+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.03654v3","created_at":"2026-07-05T11:59:05.998439+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.03654","created_at":"2026-07-05T11:59:05.998439+00:00"},{"alias_kind":"pith_short_12","alias_value":"6MMG7HCPPJ72","created_at":"2026-07-05T11:59:05.998439+00:00"},{"alias_kind":"pith_short_16","alias_value":"6MMG7HCPPJ72NSMI","created_at":"2026-07-05T11:59:05.998439+00:00"},{"alias_kind":"pith_short_8","alias_value":"6MMG7HCP","created_at":"2026-07-05T11:59:05.998439+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.09606","citing_title":"Ensemble Confidence Calibration for Sound Event Detection in Open-environment","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6MMG7HCPPJ72NSMIDWVXOJVYLM","json":"https://pith.science/pith/6MMG7HCPPJ72NSMIDWVXOJVYLM.json","graph_json":"https://pith.science/api/pith-number/6MMG7HCPPJ72NSMIDWVXOJVYLM/graph.json","events_json":"https://pith.science/api/pith-number/6MMG7HCPPJ72NSMIDWVXOJVYLM/events.json","paper":"https://pith.science/paper/6MMG7HCP"},"agent_actions":{"view_html":"https://pith.science/pith/6MMG7HCPPJ72NSMIDWVXOJVYLM","download_json":"https://pith.science/pith/6MMG7HCPPJ72NSMIDWVXOJVYLM.json","view_paper":"https://pith.science/paper/6MMG7HCP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.03654&json=true","fetch_graph":"https://pith.science/api/pith-number/6MMG7HCPPJ72NSMIDWVXOJVYLM/graph.json","fetch_events":"https://pith.science/api/pith-number/6MMG7HCPPJ72NSMIDWVXOJVYLM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6MMG7HCPPJ72NSMIDWVXOJVYLM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6MMG7HCPPJ72NSMIDWVXOJVYLM/action/storage_attestation","attest_author":"https://pith.science/pith/6MMG7HCPPJ72NSMIDWVXOJVYLM/action/author_attestation","sign_citation":"https://pith.science/pith/6MMG7HCPPJ72NSMIDWVXOJVYLM/action/citation_signature","submit_replication":"https://pith.science/pith/6MMG7HCPPJ72NSMIDWVXOJVYLM/action/replication_record"}},"created_at":"2026-07-05T11:59:05.998439+00:00","updated_at":"2026-07-05T11:59:05.998439+00:00"}